Communication method and communication device

Abstract

Provided are a communication method and a communication device. The communication method comprises: a first device directly predicting a first event on the basis of a first model, wherein the first event comprises an event used for indicating a radio link failure and / or a measurement event.

Description

Communication method and communication device TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and more particularly, to a communication method and a communication device. BACKGROUND

[0002] With the development of communication technology, the communication system introduces a model-based prediction technology. Therefore, in the communication system, how to realize accurate prediction based on the model is a problem to be solved.

[0003] SUMMARY

[0004] The present application provides a communication method and a communication device. The various aspects involved in the present application are introduced below.

[0005] In a first aspect, a communication method is provided, comprising: directly predicting, by a first device, a first event according to a first model, the first event comprising an event for indicating a radio link failure and / or a measurement event.

[0006] In a second aspect, a communication device is provided, the communication device being a first device, the first device comprising: a prediction module configured to directly predict a first event according to a first model, the first event comprising an event for indicating a radio link failure and / or a measurement event.

[0007] In a third aspect, a communication device is provided, comprising a transceiver, a memory and a processor, the memory being configured to store a program, the processor being configured to invoke the program in the memory and control the transceiver to receive or send a signal, so that the communication device performs the method of the first aspect.

[0008] In a fourth aspect, an apparatus is provided, comprising a processor configured to invoke a program from a memory, so that the apparatus performs the method of the first aspect.

[0009] In a fifth aspect, a chip is provided, comprising a processor configured to invoke a program from a memory, so that a device installed with the chip performs the method of the first aspect.

[0010] In a sixth aspect, a computer-readable storage medium is provided, having a program stored thereon, the program causing a computer to perform the method of the first aspect.

[0011] In a seventh aspect, a computer program product is provided, characterized in that it comprises a program, the program causing a computer to perform the method of the first aspect.

[0012] In an eighth aspect, a computer program is provided, the computer program causing a computer to perform the method of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0013] FIG. 1 is an example diagram of a system architecture of a wireless communication system to which embodiments of the present application can be applied.

[0014] FIG. 2 is an example diagram of a wireless link measurement procedure.

[0015] FIG. 3 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0016] FIG. 4 is an example diagram of an implementation of a prediction window according to an embodiment of the present application.

[0017] FIG. 5 is a schematic structural diagram of a communication device according to an embodiment of the present application.

[0018] FIG. 6 is a schematic diagram of an apparatus to which embodiments of the present application can be applied. DETAILED DESCRIPTION

[0019] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0020] Communication system

[0021] FIG. 1 is an example diagram of a system architecture of a wireless communication system 100 to which embodiments of the present application can be applied. The wireless communication system 100 can include a network device 110 and a terminal device 120. The network device 110 can be a device that communicates with the terminal device 120. The network device 110 can provide network coverage for a specific geographic area and can communicate with the terminal device 120 located within the coverage area. The terminal device 120 can access a network (such as a wireless network) through the network device 110. Optionally, the wireless communication system 100 can also include a network controller, a mobile management entity, and other network entities, which are not limited by embodiments of the present application.

[0022] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: 5G system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided by the present application can also be applied to future communication systems, such as the sixth generation mobile communication system, such as satellite communication system, etc.

[0023] The terminal device in the embodiments of the present application can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile terminal (MT), a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user apparatus. The terminal device in the embodiments of the present application can refer to a device providing voice and / or data connectivity for a user, and can be used to connect people, things and machines, such as handheld devices with wireless connection function, vehicle-mounted devices, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer (Pad), a notebook computer, a palm computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. Optionally, the terminal device can be used to act as a base station. For example, the terminal device can act as a scheduling entity, which provides sidelink signals between terminal devices in vehicle to everything (V2X) or device to device (D2D), etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and the smart home device communicate with each other without relaying the communication signals through the base station.

[0024] The network device in the embodiments of the present application can be a device for communicating with a terminal device. The network device may, for example, be an access network device or a radio access network device. For example, the network device can be a base station. The base station can broadly cover various names in the following or be replaced by the names in the following: Node B (Node B), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof.

[0025] Radio link failure (RLF)

[0026] A terminal device in a radio resource control (RRC) connected state (RRC_CONNECTED) continuously monitors the downlink radio link quality of a serving cell during movement. The network device determines the synchronization and out-of-sync state of the channel according to the signal quality of the synchronization signal / physical broadcast channel (PBCH) block (SSB) or channel state information reference signal (CSI-RS) of the terminal device. As shown in FIG. 2, during the wireless problem detection stage, when the block error rate (BLER) of N310 (a constant value configured by the network device) consecutive physical downlink control channels (PDCCHs) is greater than 10%, it can be considered that the terminal device has gone out of sync with the network device. At this time, the terminal device can start the T310 timer. Before the T310 timer expires, if the BLER of N311 (a constant value configured by the network device) consecutive PDCCHs is less than 2%, it can be considered that the terminal device has re-synchronized with the network device. At this time, the running of the T310 timer can be stopped, and it is considered that the wireless link of the terminal device is restored. Otherwise, if the T310 timer expires, it means that the wireless link of the terminal device has failed. In the case of wireless link failure, the terminal device triggers a connection re-establishment procedure.

[0027] RLF prediction in artificial intelligence (AI) / machine learning (ML) for mobility project

[0028] RLF prediction is one of the three use cases in the current AI / ML for mobility project. Currently, the protocol defines two RLF prediction methods: direct prediction and indirect prediction.

[0029] Direct prediction is to directly predict whether RLF will occur in the future based on historical measurement data (such as signal to interference plus noise ratio (SINR)) or some other auxiliary parameters.

[0030] Indirect prediction is to first predict the future measurement value based on historical measurement data or some other auxiliary parameters. Then, based on the predicted measurement value, it is determined whether a RLF will occur through the traditional RLF decision mechanism. For example, the SINR in the next 3s can be predicted based on the SINR in the past 2s; then, the predicted SINR is used to determine whether a RLF will occur in the next 3s through the decision method introduced above.

[0031] The following consensus was reached at the 2#127 meeting of the radio access network (RAN) 2: For the direct prediction method, the model output is the probability of RLF occurring within a time window. When the probability is greater than a threshold, it can be assumed that a RLF will occur. Then, the prediction result of the model can be compared with the actual RLF situation to determine the accuracy of the model prediction. At the same time, the meeting also defined the key performance indicators (KPIs) for measuring direct RLF prediction, including: missed RLF detection, false RLF detection, and F1 score.

[0032] Measurement event prediction

[0033] Measurement event prediction is one of the three use cases in the current AI / ML mobility project. Currently, the protocol defines two measurement event prediction methods: direct prediction and indirect prediction. Direct prediction is to directly predict whether a measurement event (such as A3 event) will occur in the future based on historical measurement data (such as reference signal receiving power (RSRP)).

[0034] Indirect prediction is to first predict the future measurement value based on historical measurement data, and then determine whether a measurement event will occur based on the predicted measurement value through the traditional handover mechanism. For example, the RSRP in the next 3s can be predicted based on the RSRP in the past 2s; then, the predicted RSRP can be used to determine whether an A3 event will occur in the next 3s through the traditional measurement event decision method.

[0035] The current protocol describes the direct RLF prediction very generally, and does not expand on the specific implementation of the RLF prediction. For example, although the protocol defines the output of the direct RLF as the probability of RLF occurring within a time window, it does not define the specific setting method of the time window. For another example, although the protocol defines the KPIs of the direct RLF prediction to include missed RLF detection and false RLF detection, it lacks corresponding descriptions on the specific determination method of such KPIs.

[0036] For the direct prediction technology of the measurement event, there are similar problems as the RLF direct prediction. For example, the current protocol discussion only describes that the direct prediction of the measurement event can be performed, but does not discuss the method and performance evaluation method of the direct prediction.

[0037] In view of the above problems, the embodiments of the present application are described in detail below in combination with FIG. 3.

[0038] FIG. 3 is a schematic flowchart of a communication method provided by an embodiment of the present application. The method of FIG. 3 can be performed by a first device. The first device can be a terminal device or a network device.

[0039] Referring to FIG. 3, in step S310, the first device directly predicts a first event according to a first model. The first model mentioned here can be an AI / ML model. If the first device is a terminal device (the first model is deployed in the terminal device), the terminal device can directly predict the first event according to the measurement value by using the first model. If the first device is a network device (the first model is deployed in the network device), the network device can first receive the measurement value from the terminal device, and then directly predict the first event by using the first model based on the measurement value sent by the terminal device.

[0040] The embodiments of the present application do not specifically limit the type of the first event, which can be any type of event that supports direct prediction. In some implementation manners, the first event includes a radio link failure event. Accordingly, step S310 can be expressed as: the first device directly predicts the radio link failure according to the first model. In addition to the radio link failure event, the first event can also be other events related to radio link measurement. It should be understood that the radio link measurement mentioned here can refer to the radio link measurement of a serving cell, or the radio link measurement of a non-serving cell.

[0041] In other implementation manners, the first event includes a measurement event (such as an A3 event, or other types of related events of cell switching). Accordingly, step S310 can be expressed as: the first device directly predicts the measurement event according to the first model.

[0042] The output (or prediction result) of the first model is not specifically limited in the embodiments of the present application. In some implementations, the output of the first model can be a prediction result corresponding to a time window. For the convenience of description, the time window is referred to as a first time window hereinafter. The first time window can also be referred to as a prediction window (PW).

[0043] Further, in some implementations, the output of the first model can indicate a probability of occurrence of the first event in the first time window. For example, if the probability of occurrence of the first event in the first time window is greater than (or greater than or equal to) a first threshold, it can be inferred that the first event will occur in the first time window. The first threshold can be sent by the second device to the first device. For example, the first device is a terminal device, and the second device is a network device, the network device can send the first threshold to the terminal device through a message or signaling. For example, the first threshold can be included in a model identification message sent by the network device to the terminal device. For another example, the first threshold can also be included in RRC signaling.

[0044] In some implementations, the first model makes a prediction based on measurement values in a certain time window. For the convenience of distinction, the time window is referred to as a second time window hereinafter. The second time window can also be referred to as an observation window (OW) sometimes. For example, the first model can predict the probability of occurrence of the first event in the first time window based on measurement values in the second time window. The measurement values in the second time window can be real measurement values or measurement values output by other models. The measurement values can be measurement values capable of measuring signal quality. For example, the measurement values can include SINR and / or RSRP and / or RSRQ.

[0045] According to the first model, the occurrence of the first event (such as RLF or a measurement event) can be directly predicted in advance, so that proactive measures can be taken to avoid the occurrence of RLF or to prepare for handover in advance.

[0046] The definition of the first time window is not specifically limited in the embodiments of the present application. Several possible definition methods of the first time window are given below.

[0047] In some implementations, the first time window slides with the sliding of the second time window.

[0048] In some implementations, the first time window slides with the sliding of the second time window, and the first time window is continuous with the second time window in the time domain (or the first time window is consecutive to the second time window).

[0049] The left side of FIG. 4 shows one possible definition of the first time window. In this definition, the PW (first time window) slides and is consecutive to the OW. As can be seen from the left side of FIG. 4, as time goes on, the OW slides gradually, and the PW slides with the sliding of the OW. Thus, the model can constantly determine whether a first event occurs within the PW after the current time.

[0050] In some implementations, the first time window slides with the sliding of the second time window, and there is a fixed time interval between the first time window and the second time window.

[0051] The middle of FIG. 4 shows another possible definition of the first time window. In this definition, the PW slides and is a certain distance away from the OW. As can be seen from the middle of FIG. 4, as time goes on, the OW slides gradually, and the PW slides with the sliding of the OW, but the OW and the PW are not adjacent, and there is a time interval between them during which there is neither a real measurement value nor a prediction value.

[0052] In some implementations, the position of the first time window remains unchanged during the sliding of the second time window within a first time range. The first time range mentioned here can be determined based on pre-defined information, configuration information of the network device, or implementation of the terminal device.

[0053] The right side of FIG. 4 shows yet another possible definition of the first time window. In this definition, the PW is fixed and is a certain distance away from the OW. As time goes on, the OW slides gradually, but the PW is fixed during the sliding of the OW. At the initial time, the OW and the PW are not adjacent, and there is a time interval between them during which there is neither a real measurement value nor a prediction value. As the OW slides, the OW gradually approaches the PW and can even be adjacent to the PW.

[0054] The multiple definitions mentioned above can be used in combination. For example, the first device can first use the definition shown in the middle of FIG. 4 to make a prediction. Assuming that the first device predicts that an RLF or a measurement event will occur between t5-t7 at t1, to ensure the accuracy of the prediction result, the first device can use the definition shown in the right side of FIG. 4 to fix the PW at t5-t7. Then, the first device can continue to slide the OW, so as to continuously predict whether an RLF or a measurement event will occur within t5-t7 by using the measurement values at different times.

[0055] In some implementations, the position of the first time window is determined based on an input parameter of the first model. For example, the input parameter can indicate a time interval between the second time window and the first time window. The distance between the first time window and the second time window can be variable at different time instants. For example, the probability of RLF / measurement event occurring at t5-t7 is given at t1, the probability of RLF / measurement event occurring at t6-t8 is given at t2, and the probability of RLF / measurement event occurring at t4-t6 is given at t3.

[0056] In some implementations, the first time window is determined in a plurality of candidate manners (e.g., the three manners shown in FIG. 4, and the manner based on the input parameter of the model mentioned above). The first device can indicate the manner of determining the first time window from the plurality of candidate manners according to the first information sent by the second device. Taking the first device as a terminal device and the second device as a network device as an example, the first information can be downlink control information (DCI), a media access control control element (MAC CE), or RRC signaling.

[0057] In some implementations, the first device can send second information to the second device. The second information can be used to indicate that the first device supports (or does not support) the plurality of candidate manners. The second information can be, for example, capability information of the first device. For example, the first model is deployed at the terminal device side, and the terminal device supports the plurality of candidate manners. The terminal device can report its capability to the network device through the second information, and the network device can use the first information to indicate which of the plurality of candidate manners is used by the terminal device.

[0058] The manner of measuring the performance (e.g., the prediction performance) of the first model is not specifically limited in the embodiments of the present application. The performance of the first model can be determined based on one or more of the first to sixth indicators mentioned below. The indicators are described in detail below.

[0059] In some implementations, the performance of the first model can be determined based on a first indicator. The first indicator can be an indicator related to true prediction. The true prediction mentioned herein can also be referred to as true detection. The true prediction can be defined, for example, as that the first model predicts a probability of occurrence of the first event (e.g., RLF or measurement event) in the first time window to be greater than (or greater than or equal to) the first threshold, and the first event actually occurs in the first time window. The first indicator can be determined based on a number of times of true prediction by the first model. For example, the first indicator can indicate the number of times of true prediction by the first model. For another example, the first indicator can indicate a true prediction rate (e.g., a ratio of the number of times of true prediction to a total number of predictions) of the first model.

[0060] In some implementations, the performance of the first model can be determined based on a second indicator. The second indicator can be an indicator related to missed detection. The missed detection mentioned herein can be defined, for example, as that the first event (e.g., RLF or measurement event) actually occurs at the first time, but the first time does not fall into the first type of time window. The first type of time window mentioned herein is the first time window in which the first model predicts a probability of occurrence of the first event to be greater than the first threshold. That is, a certain first event actually occurs, but the first model does not predict it. The second indicator can be determined based on a number of times of missed detection by the first model. For example, the second indicator can indicate the number of times of missed detection by the first model. For another example, the second indicator can indicate a missed detection rate (e.g., a ratio of the number of times of missed detection to a total number of predictions) of the first model.

[0061] In some implementations, the performance of the first model can be determined based on a third indicator. The third indicator can be an indicator related to false detection. The false detection mentioned herein can be defined, for example, as that the first model predicts a probability of occurrence of the first event (e.g., RLF or measurement event) in the first time window to be greater than the first threshold, but the first event does not occur in the first time window. The third indicator can be determined based on a number of times of false detection by the first model. For example, the third indicator can indicate the number of times of false detection by the first model. For another example, the third indicator can indicate a false detection rate (e.g., a ratio of the number of times of false detection to a total number of predictions) of the first model.

[0062] In some implementations, the performance of the first model can be determined based on a fourth indicator. The fourth indicator can be a precision of the first model. The fourth indicator can be determined based on the first indicator and the second indicator. For example, the fourth indicator can be equal to: the number of times of true prediction / (the number of times of true prediction + the number of times of missed detection).

[0063] In some implementations, the performance of the first model can be determined based on a fifth metric. The fifth metric can be a recall of the first model. The fifth metric can be determined based on the first metric and the third metric. For example, the fifth metric can be equal to: the number of true predictions / (the number of true predictions + the number of false positives).

[0064] In some implementations, the performance of the first model can be determined based on a sixth metric. The sixth metric can be an Fbeta score (or F score) of the first model. As an example, the value of beta can be 1, in which case the sixth metric can refer to an Fl score of the first model. The sixth metric (e.g., Fbeta score or Fl score) can be determined based on the fourth metric and the fifth metric. For example, the sixth metric can be equal to: 2 * the fourth metric * the fifth metric / (the fourth metric + the fifth metric) = 2 * the number of true predictions / (2 * the number of true predictions + the number of false positives + the number of false negatives).

[0065] In some implementations, the performance of the first model can be determined based on one or more of the following: the first metric is less than or equal to a second threshold, the second metric is greater than or equal to a third threshold, the third metric is greater than or equal to a fourth threshold, the fourth metric is less than or equal to a fifth threshold, the fifth metric is less than or equal to a sixth threshold, and the sixth metric is less than or equal to a seventh threshold.

[0066] One or more of the second threshold to the seventh threshold described above can be sent by the second device to the first device. For example, the first device is a terminal device and the second device is a network device, the network device can send one or more of the second threshold to the seventh threshold to the terminal device through some message or signaling. The threshold can be included in a model identification message or in RRC signaling.

[0067] In some implementations, if the performance of the first model does not satisfy a first condition, the first model is deactivated, switched or not enabled, the first condition can be determined based on one or more of the first metric to the sixth metric. For example, the first condition can include that one or more of the first metric to the sixth metric of the first model satisfies a corresponding threshold requirement. If the first condition is not satisfied, it means that the performance of the first model is not good, and the first model needs to be deactivated, switched or not enabled. The not enabled first model mentioned here refers to that in some cases, the network device or the terminal device can first monitor the model performance, and determine whether to enable the model for prediction based on the performance.

[0068] As an example, the terminal device can first start a first model. Then, the terminal device can count one or more of the false detection rate, the missed detection rate, and the F1 score of the first model in a period of time, and if these indicators meet the requirements, the first model can be enabled. If these indicators do not meet the requirements, the terminal device can switch to another model or no longer use any AI / ML model.

[0069] As another example, the terminal device has run a first model. In a period of time, the terminal device continuously performs model monitoring to determine whether the first model is still applicable (or whether it needs to be deactivated). The terminal device can count one or more of the false detection rate, the missed detection rate, and the F1 score of the first model, and if these indicators do not meet the requirements, the terminal device can deactivate the first model. If these indicators meet the requirements, the terminal device can continue to use the first model.

[0070] By accurately defining the performance measurement method of the first model, the performance of the first model can be continuously monitored during the running of the first model. Then, model management (such as model switching and model deactivation) can be performed according to the monitoring result, the running efficiency of the model is guaranteed, the service interruption time is reduced, and the user experience is improved.

[0071] The method embodiments of the present application are described in detail above in combination with FIGS. 1 to 4, and the device embodiments of the present application are described in detail below in combination with FIGS. 5 to 6. It should be understood that the description of the method embodiments corresponds to the description of the device embodiments, and therefore, the parts not described in detail can be referred to the foregoing method embodiments.

[0072] FIG. 5 is a structural schematic diagram of a communication device provided by an embodiment of the present application. The communication device 500 shown in FIG. 5 can be the first device mentioned above. The communication device 500 includes a prediction module 510. The prediction module 510 is configured to directly predict a first event according to a first model, the first event including an event indicating a radio link failure and / or a measurement event.

[0073] In some implementations, the first model is used to indicate a probability of occurrence of the first event within a first time window.

[0074] In some implementations, the first model predicts the probability of occurrence of the first event within the first time window based on a measurement value within a second time window.

[0075] In some implementations, the first time window slides with the sliding of the second time window.

[0076] In some implementations, the first time window and the second time window are continuous in the time domain.

[0077] In some embodiments, the first time window and the second time window have a fixed time interval.

[0078] In some embodiments, the position of the first time window remains unchanged during the sliding of the second time window in the first time range.

[0079] In some embodiments, the position of the first time window is determined based on an input parameter of the first model.

[0080] In some embodiments, the manner of determining the first time window comprises a plurality of candidate manners, and the communication device 500 further comprises a communication module configured to receive first information sent by the second device, the first information being used to indicate the manner of determining the first time window from the plurality of candidate manners.

[0081] In some embodiments, the communication module is further configured to send second information to the second device, the second information being used to indicate whether the first device supports the plurality of candidate manners.

[0082] In some embodiments, the performance of the first model is determined based on one or more of the following indicators of the first model: a first indicator related to a true prediction, the true prediction being used to indicate that the first model predicts that the first event occurs in the first time window with a probability greater than a first threshold, and the first event actually occurs in the first time window; a second indicator related to a missed detection, the missed detection being used to indicate that the first event actually occurs at a first time, but the first time does not fall into a first type of time window, the first type of time window being a first time window in which the first model predicts that the first event occurs with a probability greater than the first threshold; a third indicator related to a false detection, the false detection being used to indicate that the first model predicts that the first event occurs in the first time window with a probability greater than the first threshold, but the first event does not occur in the first time window; a fourth indicator, the fourth indicator being a precision of the first model, and the precision being determined based on the first indicator and the second indicator; a fifth indicator, the fifth indicator being a recall of the first model, and the recall being determined based on the first indicator and the third indicator; and a sixth indicator, the sixth indicator being an Fbeta score of the first model, and the Fbeta score being determined based on the fourth indicator and the fifth indicator.

[0083] In some implementations, the performance of the first model is determined based on one or more of the following: the first indicator is less than or equal to a second threshold, where the first indicator is determined based on a number of times the true prediction; the second indicator is greater than or equal to a third threshold, where the second indicator is determined based on a number of times the missed detection; the third indicator is greater than or equal to a fourth threshold, where the third indicator is determined based on a number of times the false detection; the fourth indicator is less than or equal to a fifth threshold; the fifth indicator is less than or equal to a sixth threshold; and the sixth indicator is less than or equal to a seventh threshold.

[0084] In some implementations, if the performance of the first model does not satisfy a first condition, the first model is deactivated, switched or not enabled, where the first condition is determined based on one or more of the first indicator to the sixth indicator.

[0085] FIG. 6 is a schematic structural diagram of a communication apparatus to which embodiments of the present application can be applied. The dashed line in FIG. 6 indicates that the unit or module is optional. The apparatus 600 can be used to implement the methods described in the above method embodiments. The apparatus 600 can be a chip, a terminal device or a network device.

[0086] The apparatus 600 can include one or more processors 610. The processor 610 can support the apparatus 600 to implement the methods described in the foregoing method embodiments. The processor 610 can be a general purpose processor or a dedicated processor. For example, the processor can be a central processing unit (CPU). Alternatively, the processor can also be other general purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0087] The apparatus 600 can also include one or more memories 620. The memory 620 stores programs, which can be executed by the processor 610, so that the processor 610 performs the methods described in the foregoing method embodiments. The memory 620 can be independent of the processor 610 or integrated in the processor 610.

[0088] The apparatus 600 can further include a transceiver 630. The processor 610 can communicate with other devices or chips through the transceiver 630. For example, the processor 610 can perform data transceiving with other devices or chips through the transceiver 630.

[0089] The embodiment of the present application further provides a computer readable storage medium for storing a program. The computer readable storage medium can be applied to the communication device provided by the embodiment of the present application, and the program causes the computer to execute the method performed by the communication device in the various embodiments of the present application.

[0090] The embodiment of the present application further provides a computer program product. The computer program product includes a program. The computer program product can be applied to the communication device provided by the embodiment of the present application, and the program causes the computer to execute the method performed by the communication device in the various embodiments of the present application.

[0091] The embodiment of the present application further provides a computer program. The computer program can be applied to the communication device provided by the embodiment of the present application, and the computer program causes the computer to execute the method performed by the communication device in the various embodiments of the present application.

[0092] It should be understood that the terms "system" and "network" can be used interchangeably in the present application. In addition, the terms used in the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. The terms "first", "second", "third", and "fourth" and the like in the specification and claims of the present application and the drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0093] In the embodiments of the present application, the "indication" mentioned can be direct indication, or indirect indication, or can be a representation of having a correlation relationship. For example, A indicates B, which can mean that B can be obtained by A, for example, B can be obtained by A; or it can mean that A indirectly indicates B, for example, A indicates C, and B can be obtained by C; or it can mean that A and B have a correlation relationship.

[0094] In the embodiments of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0095] In the embodiments of the present application, the term "corresponding" can mean that there is a direct or indirect corresponding relationship between the two, or it can mean that there is a correlation relationship between the two, or it can mean the relationship of indication and being indicated, configuration and being configured, etc.

[0096] In the embodiments of the present application, the "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables or other manners that can be used to indicate relevant information in devices (for example, including terminal devices and network devices), and the specific implementation manners are not limited in the present application. For example, the predefinition can refer to the definition in a protocol.

[0097] In the embodiments of the present application, the "protocol" can refer to a standard protocol in the communication field, for example, can include the LTE protocol, the NR protocol and the related protocol applied to the future communication system, and the present application is not limited to this.

[0098] In the embodiments of the present application, the term "and / or" is only used to describe the association relationship of the associated objects, that is, there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0099] In various embodiments of the present application, the size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0100] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. For example, the device embodiments described above are only schematic, and for example, the division of the units is only a logical function division, and there can be another division way in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0101] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiments of the present application.

[0102] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0103] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented 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, all or part of the processes or functions described in the embodiments of the present application are generated. 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 one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server, data center and the like integrated with one or more available media sets. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, digital video disc (DVD)) or semiconductor media (for example, solid state disk (SSD)) and the like.

[0104] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: Comprise: The first device directly predicts a first event according to a first model, the first event comprising an event indicating a radio link failure and / or a measurement event.

2. The method of claim 1, wherein, The first model is used to indicate a probability of the first event occurring within a first time window.

3. The method of claim 2, wherein, The first model predicts the probability of the first event occurring within the first time window based on measurement values within a second time window.

4. The method of claim 3, wherein, The first time window slides with the sliding of the second time window.

5. The method according to claim 3 or 4, characterized in that, The first time window is continuous with the second time window in the time domain.

6. The method according to claim 3 or 4, characterized in that, There is a fixed time interval between the first time window and the second time window.

7. The method of claim 3, wherein, The position of the first time window remains unchanged in the process of sliding the second time window within a first time range.

8. The method of claim 3, wherein, The position of the first time window is determined based on an input parameter of the first model.

9. The method according to any one of claims 2 to 8, characterized in that, The determination manner of the first time window comprises a plurality of candidate manners, and the method further comprises: The first device receives first information sent by a second device, the first information being used to indicate the determination manner of the first time window from the plurality of candidate manners.

10. The method of claim 9, wherein, The method further comprises: The first device sends second information to the second device, the second information being used to indicate whether the first device supports the plurality of candidate manners.

11. The method according to any one of claims 1 to 10, characterized in that, The performance of the first model is determined based on one or more of the following indicators of the first model: A first indicator related to a true prediction, the true prediction being used to indicate that the first model predicts that the probability of the first event occurring within the first time window is greater than a first threshold, and the first event actually occurs within the first time window; A second indicator related to a missed detection, the missed detection being used to indicate that the first event actually occurs at a first time, but the first time does not fall within a first type of time window, the first type of time window being a first time window in which the first model predicts that the probability of the first event occurring is greater than the first threshold; A third indicator related to a false detection, the false detection being used to indicate that the first model predicts that the probability of the first event occurring within the first time window is greater than the first threshold, but the first event does not occur within the first time window; A fourth indicator, the fourth indicator being a precision rate of the first model, and the precision rate being determined based on the first indicator and the second indicator; A fifth indicator, the fifth indicator being a recall rate of the first model, and the recall rate being determined based on the first indicator and the third indicator; A sixth indicator, the sixth indicator being an Fbeta score of the first model, and the Fbeta score being determined based on the fourth indicator and the fifth indicator.

12. The method of claim 11, wherein, The performance of the first model is determined based on one or more of the following: The first indicator is less than or equal to a second threshold, wherein the first indicator is determined based on the number of true predictions; The second indicator is greater than or equal to a third threshold, wherein the second indicator is determined based on the number of missed detections; The third indicator is greater than or equal to a fourth threshold, wherein the third indicator is determined based on the number of false detections; The fourth indicator is less than or equal to a fifth threshold; The fifth indicator is less than or equal to a sixth threshold; The sixth indicator is less than or equal to a seventh threshold.

13. The method according to claim 11 or 12, characterized in that, If performance of the first model does not satisfy a first condition, the first model is deactivated, switched or not enabled, the first condition being determined based on one or more of the first indicator to the sixth indicator.

14. A communication device, characterized by The communication device is a first device, and the first device includes: a prediction module configured to directly predict a first event according to a first model, the first event including an event indicating a radio link failure and / or a measurement event. The first model is used to indicate a probability of the first event occurring within a first time window.

15. The communication device of claim 14, wherein, The first model predicts the probability of the first event occurring within the first time window based on a measurement value within a second time window.

16. The communication device of claim 15, wherein, The first time window slides with a slide of the second time window.

17. The communication device of claim 16, wherein, The first time window is continuous with the second time window in a time domain.

18. The communication device of claim 16 or 17, wherein, The first time window and the second time window have a fixed time interval.

19. The communication device of claim 16 or 17, wherein, During a sliding of the second time window within a first time range, a position of the first time window remains unchanged.

20. The communication device of claim 16, wherein, The position of the first time window is determined based on an input parameter of the first model.

21. The communication device of claim 16, wherein, The first time window is determined in a plurality of candidate manners, and the communication device further includes:

22. The communication device of any of claims 15-21, wherein, a communication module configured to receive first information sent by a second device, the first information being used to indicate a determination manner of the first time window from the plurality of candidate manners. The communication module is further configured to send second information to the second device, the second information being used to indicate whether the first device supports the plurality of candidate manners.

23. The communication device of claim 22, wherein, Performance of the first model is determined based on one or more of the following indicators of the first model:

24. The communication device of any of claims 14-23, wherein, a first indicator related to a true prediction, the true prediction being used to indicate that the first model predicts a probability of the first event occurring within the first time window to be greater than a first threshold, and the first event actually occurs within the first time window; a second indicator related to a missed detection, the missed detection being used to indicate that the first event actually occurs at a first time, but the first time does not fall into a first type of time window, the first type of time window being a first time window in which the first model predicts a probability of the first event occurring to be greater than the first threshold; a third indicator related to a false detection, the false detection being used to indicate that the first model predicts a probability of the first event occurring within the first time window to be greater than the first threshold, but the first event does not occur within the first time window; a fourth indicator, the fourth indicator being a precision of the first model, and the precision being determined based on the first indicator and the second indicator; a fifth indicator, the fifth indicator being a recall of the first model, and the recall being determined based on the first indicator and the third indicator; a sixth indicator, the sixth indicator being an Fbeta score of the first model, and the Fbeta score being determined based on the fourth indicator and the fifth indicator. Performance of the first model is determined based on one or more of the following:

25. The communication device of claim 24, wherein, the first indicator is less than or equal to a second threshold, wherein the first indicator is determined based on a number of the true predictions. ​ the second indicator is greater than or equal to a third threshold, wherein the second indicator is determined based on the number of missed detections; the third indicator is greater than or equal to a fourth threshold, wherein the third indicator is determined based on the number of false detections; the fourth indicator is less than or equal to a fifth threshold; the fifth indicator is less than or equal to a sixth threshold; the sixth indicator is less than or equal to a seventh threshold.

26. The communication device of claim 24 or 25, wherein, deactivating, switching or not enabling the first model if the performance of the first model does not satisfy a first condition, the first condition being determined based on one or more of the first indicator to the sixth indicator.

27. A communications device, characterized by A communication device comprising a transceiver, a memory and a processor, the memory being configured to store a program, the processor being configured to invoke the program in the memory and control the transceiver to receive or transmit signals, so as to enable the communication device to perform the method according to any one of claims 1 to 13.

28. An apparatus comprising: A processor configured to invoke a program in a memory, so as to enable the apparatus to perform the method according to any one of claims 1 to 13.

29. A chip, characterized by A processor configured to invoke a program in a memory, so as to enable the apparatus to perform the method according to any one of claims 1 to 13.

30. A computer-readable storage medium, characterized in that, A computer program product having stored thereon a program which causes a computer to perform the method according to any one of claims 1 to 13.

31. A computer program product, characterised in that, A computer program product having stored thereon a program which causes a computer to perform the method according to any one of claims 1 to 13.

32. A computer program, characterized in that, A computer program product having stored thereon a program which causes a computer to perform the method according to any one of claims 1 to 13.

Images