Wireless communication method, terminal device and network device

Abstract

The embodiment of the invention provides a wireless communication method, terminal equipment and network equipment, and the method comprises the steps: obtaining the performances of M historical signals through the detection of the M historical signals; based on the performance of the M historical signals, predicting the performance of the N target signals and / or K target signals of which the performance meets a preset condition in the N target signals by using a target prediction model; wherein M and N are positive integers, and K is smaller than or equal to N. According to the wireless communication method provided by the embodiment of the invention, the signaling overhead and time delay caused by acquiring the performance of the N target signals and / or acquiring K target signals of which the performance meets the prediction condition in the N target signals are reduced.

Description

Wireless communication method, terminal device, and network device Technical Field

[0001] The embodiments of the present application relate to the field of communications, and more specifically, to a wireless communication method, a terminal device, and a network device. Background Art

[0002] In the related art, during the beam failure recovery (BFR) process, the terminal device determines the beam failure event (Beam Failure Event) by measuring the performance of the beam failure detection reference signal (Beam Failure Detection Reference Signal, BFD RS), and discovers the new beam by measuring the performance of the new beam identification reference signal (New Beam Identification Reference Signal, NBI RS). However, the configuration of BFD RS and NBI RS inevitably causes additional signaling overhead, which in turn leads to excessively high costs in the BFR process. In addition, since BFD RS and NBI RS are periodic reference signals, their own periodicity will cause the performance measurement of BFD RS and NBI RS to be periodic, thereby increasing the BFR delay.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide a wireless communication method, terminal device and network device, which reduce the signaling overhead and delay caused by the performance of obtaining N target signals and / or obtaining K target signals among N target signals whose performance meets the prediction conditions.

[0005] In a first aspect, an embodiment of the present application provides a wireless communication method, including:

[0006] Acquire performance of the M historical signals by detecting the M historical signals;

[0007] Based on the performance of the M historical signals, using a target prediction model to predict the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition;

[0008] Wherein, M and N are both positive integers, and K≤N.

[0009] In a second aspect, an embodiment of the present application provides a wireless communication method, including:

[0010] Receive a beam failure recovery request (BFRQ) sent by a terminal device;

[0011] The BFRQ includes identifiers of K target signals and information indicating time units of beam failure events corresponding to the K target signals.

[0012] In a third aspect, an embodiment of the present application provides a wireless communication method, including:

[0013] Performance of receiving M historical signals sent by the terminal device;

[0014] Based on the performance of the M historical signals, using a target prediction model to predict the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition;

[0015] Wherein, M and N are both positive integers, and K≤N.

[0016] In a fourth aspect, an embodiment of the present application provides a wireless communication method, including:

[0017] receiving instruction information sent by the network device;

[0018] The indication information includes identifiers of K target signals and information for indicating time units in which beam failure events corresponding to the K target signals occur.

[0019] In a fifth aspect, the present application provides a terminal device for executing the method in the first aspect, the fourth aspect, or their respective implementations. Specifically, the terminal device includes a functional module for executing the method in the first aspect, the fourth aspect, or their respective implementations.

[0020] In one implementation, the terminal device may include a processing unit configured to execute functions related to information processing. For example, the processing unit may be a processor.

[0021] In one implementation, the terminal device may include a transmitting unit and / or a receiving unit. The transmitting unit is configured to perform functions related to transmission, and the receiving unit is configured to perform functions related to reception. For example, the transmitting unit may be a transmitter, and the receiving unit may be a receiver. For another example, if the terminal device is a communication chip, the transmitting unit may be an input circuit or interface of the communication chip, and the transmitting unit may be an output circuit or interface of the communication chip.

[0022] In a sixth aspect, the present application provides a network device for executing the method in the second aspect, the third aspect, or their respective implementations. Specifically, the network device includes a functional module for executing the method in the second aspect, the third aspect, or their respective implementations.

[0023] In one implementation, the network device may include a processing unit configured to execute functions related to information processing. For example, the processing unit may be a processor.

[0024] In one implementation, the network device may include a transmitting unit and / or a receiving unit. The transmitting unit is configured to perform functions related to transmission, and the receiving unit is configured to perform functions related to reception. For example, the transmitting unit may be a transmitter, and the receiving unit may be a receiver. For another example, if the network device is a communication chip, the receiving unit may be an input circuit or interface of the communication chip, and the transmitting unit may be an output circuit or interface of the communication chip.

[0025] In a seventh aspect, an embodiment of the present application provides a terminal device, comprising a transceiver, a processor, and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory, so that the processor and the transceiver perform the method of the first aspect, the fourth aspect, or any implementation thereof.

[0026] In one implementation, there are one or more processors and one or more memories.

[0027] In one implementation, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

[0028] In one implementation, the transceiver includes a transmitter (transmitter) and a receiver (receiver).

[0029] In an eighth aspect, the present application provides a network device comprising a transceiver, a processor, and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory, so that the processor and the transceiver perform the method of the second aspect, the third aspect, or any implementation thereof.

[0030] In one implementation, there are one or more processors and one or more memories.

[0031] In one implementation, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

[0032] In one implementation, the transceiver includes a transmitter (transmitter) and a receiver (receiver).

[0033] In a ninth aspect, the present application provides a chip for implementing the method of any one of the first to fourth aspects or their respective implementations. Specifically, the chip includes: a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes the method of any one of the first to fourth aspects or their respective implementations.

[0034] In a tenth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program enables a computer to execute the method of any one of the above-mentioned first to fourth aspects or its various implementations.

[0035] In an eleventh aspect, the present application provides a computer program product comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method of any one of the above-mentioned first to fourth aspects or any of their implementations.

[0036] In a twelfth aspect, the present application provides a computer program which, when executed on a computer, enables the computer to execute the method in any one of the above-mentioned first to fourth aspects or in each of its implementations.

[0037] In the embodiment of the present application, by introducing a target prediction model and predicting the performance of N target signals and / or K target signals among the N target signals whose performance meets preset conditions based on the performance of M historical signals, compared with the method in which the network device configures a reference signal specifically for measuring the performance of the target signal for the terminal device, the network device avoids configuring a reference signal specifically for measuring the performance of the target signal for the terminal device, which not only reduces the signaling overhead caused by obtaining the performance of the N target signals and / or the K target signals, but also reduces the delay caused by obtaining the performance of the N target signals and / or the K target signals. In short, the solution provided by the embodiment of the present application can reduce the signaling overhead and delay caused by obtaining the performance of N target signals and / or obtaining K target signals among the N target signals whose performance meets the prediction conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.

[0039] FIG2 is a schematic diagram of a neuron structure provided in an embodiment of the present application.

[0040] FIG3 is an example of the structure of a neural network provided in an embodiment of the present application.

[0041] FIG4 is a schematic diagram of a convolutional neural network provided in an embodiment of the present application.

[0042] FIG5 is a schematic diagram of an LSTM unit provided in an embodiment of the present application.

[0043] FIG6 is a schematic diagram of using two independent prediction models to train and infer K optimal signals and the performance of the K optimal signals provided in an embodiment of the present application.

[0044] FIG7 is a schematic diagram of the input and output relationship of the prediction model 1 provided in an embodiment of the present application.

[0045] FIG8 is a schematic diagram of the input and output relationship of the prediction model 2 provided in an embodiment of the present application.

[0046] FIG9 is a schematic flow chart of the BFR process provided in an embodiment of the present application.

[0047] FIG10 is a schematic flowchart of a wireless communication method provided in an embodiment of the present application.

[0048] FIG11 is a schematic diagram of the relationship between the historical signal and the target signal provided in an embodiment of the present application.

[0049] FIG12 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the spatial domain, as provided in an embodiment of the present application.

[0050] FIG13 is a schematic diagram of signal prediction or signal performance prediction in the time domain provided by an embodiment of the present application.

[0051] FIG14 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the time domain, as provided in an embodiment of the present application.

[0052] FIG15 is a schematic diagram of signal prediction or signal performance prediction in the time domain and spatial domain provided by an embodiment of the present application.

[0053] FIG16 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the time domain and the spatial domain, as provided in an embodiment of the present application.

[0054] FIG17 is a schematic diagram showing the relationship between the performance prediction of the BFD RS and the NBI RS prediction provided in an embodiment of the present application.

[0055] Figure 18 is another schematic flowchart of the wireless communication method provided in an embodiment of the present application.

[0056] Figure 19 is another schematic flowchart of the wireless communication method provided in an embodiment of the present application.

[0057] Figure 20 is another schematic flowchart of the wireless communication method provided in an embodiment of the present application.

[0058] Figure 21 is a schematic block diagram of a terminal device provided in an embodiment of the present application.

[0059] Figure 22 is a schematic block diagram of a network device provided in an embodiment of the present application.

[0060] Figure 23 is another schematic block diagram of the network device provided in an embodiment of the present application.

[0061] Figure 24 is another schematic block diagram of the terminal device provided in an embodiment of the present application.

[0062] Figure 25 is a schematic block diagram of a communication device provided in an embodiment of the present application.

[0063] Figure 26 is a schematic block diagram of the chip provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] 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.

[0065] It should be noted that the terms "predefined" or "preset" involved in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). This application does not limit its specific implementation method. For example, the preset may refer to a definition in a protocol. Optionally, the "protocol" may refer to a standard protocol in the field of communications, such as an LTE protocol, an NR protocol, and related protocols used in future communication systems, which is not specifically limited in this application.

[0066] In addition, the term "indication" can be a direct indication, an indirect indication, or an indication of an associated relationship. For example, A indicates B, which 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 associated relationship between A and B. The term "correspondence" can mean that there is a direct or indirect correspondence between the two, or it can mean that there is an associated relationship between the two, or it can mean a relationship between indication and being indicated, configuration and being configured, etc. In addition, the description "at the time of..." involved in the embodiments of the present application can be interpreted as "if" or "if" or "when..." or "in response to". Similarly, depending on the context, the phrase "if it is determined" or "if (the stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to the determination" or "when (the stated condition or event) is detected" or "in response to detecting (the stated condition or event)". The term "predefined" or "predefined rules" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and this application does not limit its specific implementation method. For example, predefined can refer to what is defined in the protocol. It should also be understood that in the embodiment of the present application, the "protocol" may refer to a standard protocol in the field of communications, for example, it may include LTE protocol, NR protocol and related protocols used in future communication systems, and this application does not limit this. In addition, in the embodiment of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. Specifically, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0067] FIG1 is an example of a system framework of an embodiment of the present application.

[0068] As shown in Figure 1, a communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0069] It should be understood that the embodiments of the present application are only illustrative of the communication system 100, but the embodiments of the present application are not limited thereto. That is, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Internet of Things (IoT) system, Narrow Band Internet of Things (NB-IoT) system, enhanced Machine-Type Communications (eMTC) system, 5G communication system (also known as New Radio (NR) communication system), or future communication systems.

[0070] In the communication system 100 shown in Figure 1, the network device 120 may be an access network device that communicates with the terminal device 110. The access network device may provide communication coverage for a specific geographical area and may communicate with the terminal device 110 (eg, UE) located within the coverage area.

[0071] The network device 120 may be an evolved Node B (eNB or eNodeB) in a Long Term Evolution (LTE) system, or a Next Generation Radio Access Network (NG RAN) device, or a base station (gNB) in an NR system, or a wireless controller in a Cloud Radio Access Network (CRAN), or the network device 120 may be a relay station, an access point, an in-vehicle device, a wearable device, a hub, a switch, a bridge, a router, or a network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0072] The terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wireless connection.

[0073] For example, the terminal device 110 may refer to an access terminal, user equipment (UE), a subscriber unit, a subscriber station, a mobile station, a mobile station, 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. An access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolution network, etc.

[0074] The terminal device 110 can be used for device-to-device (D2D) communication.

[0075] The wireless communication system 100 may further include a core network device 130 for communicating with the base station. The core network device 130 may be a 5G core network (5G Core, 5GC) device, such as an Access and Mobility Management Function (AMF), an Authentication Server Function (AUSF), a User Plane Function (UPF), or a Session Management Function (SMF). Optionally, the core network device 130 may also be an Evolved Packet Core (EPC) device of an LTE network, such as a Session Management Function + Core Packet Gateway (SMF+PGW-C) device. It should be understood that SMF+PGW-C can simultaneously implement the functions that can be implemented by SMF and PGW-C. During the network evolution process, the above-mentioned core network device may also be called other names, or a new network entity may be formed by dividing the functions of the core network, which is not limited in the embodiments of the present application.

[0076] The functional units in the communication system 100 may also establish connections and implement communication via next generation (NG) network interfaces.

[0077] For example, the terminal device establishes an air interface connection with the access network device through the NR interface for transmitting user plane data and control plane signaling; the terminal device can establish a control plane signaling connection with the AMF through the NG interface 1 (referred to as N1); the access network device, such as the next generation wireless access base station (gNB), can establish a user plane data connection with the UPF through the NG interface 3 (referred to as N3); the access network device can establish a control plane signaling connection with the AMF through the NG interface 2 (referred to as N2); the UPF can establish a control plane signaling connection with the SMF through the NG interface 4 (referred to as N4); the UPF can exchange user plane data with the data network through the NG interface 6 (referred to as N6); the AMF can establish a control plane signaling connection with the SMF through the NG interface 11 (referred to as N11); the SMF can establish a control plane signaling connection with the PCF through the NG interface 7 (referred to as N7).

[0078] Figure 1 exemplarily shows a base station, a core network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple base station devices and each base station may include other numbers of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0079] It should be understood that in the embodiments of the present application, any device with communication functionality in the network / system may be referred to as a communication device. Taking the communication system 100 shown in FIG1 as an example, the communication device may include a network device 120 and a terminal device 110 with communication functionality. The network device 120 and the terminal device 110 may be the devices described above and will not be described in detail here. The communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0080] 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.

[0081] In order to facilitate a better understanding of the embodiments of the present application, the relevant contents of the present application are explained.

[0082] 1. Neural Network (NN).

[0083] The NN model is a computational model consisting of multiple interconnected neuron nodes, where the connections between nodes represent the weighted values ​​from input signals to output signals, called weights. Each node performs weighted summation (SUM) on different input signals and outputs them through a specific activation function (f).

[0084] FIG2 is a schematic diagram of a neuron structure provided in an embodiment of the present application.

[0085] As shown in Figure 2, a1, a2, ..., an represent input signals, w1, w2, ..., wn represent weights, f represents the activation function, and t represents the output. That is, the node performs a weighted sum of a1, a2, ..., an according to w1, w2, ..., wn, and outputs t using a specific activation function (f).

[0086] FIG3 is an example of the structure of a neural network provided in an embodiment of the present application.

[0087] As shown in Figure 3, a neural network consists of an input layer, a hidden layer, and an output layer. By using different connections, weights, and activation functions among multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. When each upper-level node is connected to all of its lower-level nodes, the NN is a fully connected neural network, also known as a deep neural network (DNN). This NN can be used to predict signals or signal properties in the spatial domain.

[0088] FIG4 is a schematic diagram of a convolutional neural network provided in an embodiment of the present application.

[0089] As shown in Figure 4, the basic structure of a convolutional neural network (CNN) consists of an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer. Each neuron in the convolutional kernel of a convolutional layer is locally connected to its input. The introduction of a pooling layer extracts the local maximum or average features of a particular layer, effectively reducing network parameters and exploiting local features, enabling the CNN to converge quickly and achieve excellent performance.

[0090] A recurrent neural network (RNN) is a type of neural network that models sequential data and has achieved remarkable success in natural language processing applications such as machine translation and speech recognition. Specifically, the network memorizes information from past moments and uses it to calculate current outputs. This means that nodes in the hidden layers are no longer disconnected but connected, and hidden layer inputs include not only the input layer but also the output of the previous hidden layer. Common RNN structures include long short-term memory (LSTM) and gated recurrent unit (GRU).

[0091] FIG5 is a schematic diagram of an LSTM unit provided in an embodiment of the present application.

[0092] As shown in Figure 5, the basic LSTM cell structure includes an activation function (tanh), an input gate (the first σ from left to right), a forget gate (the second σ from left to right), and an output gate (the third σ from left to right). When information enters the LSTM cell, its usefulness is determined based on the rules. Only information that meets the algorithm's requirements is retained, while information that does not meet the requirements is forgotten through the forget gate. Unlike RNNs, which only consider the most recent state, LSTMs determine which states should be retained and which should be forgotten, addressing the shortcomings of traditional RNNs in long-term memory.

[0093] 2. NN training.

[0094] A NN can be trained and obtained through the processes of data set construction, training, verification and testing. The embodiments of the present application assume that the NN has been trained in advance in an offline or online manner. It should be noted that offline training and online training are not mutually exclusive. First, the NW can obtain a static training result through offline training, which can be referred to as offline training here. During the use of the NN by the NW or UE, as the UE further measures and / or reports, the NN can continue to collect more data and perform real-time online training to optimize the parameters of the NN to achieve better inference and prediction results.

[0095] The following uses the prediction of spatial domain signals and their performance as an example to illustrate how to train a DNN using supervised (label-based) learning. With a labeled dataset, classic algorithms such as backpropagation (including gradient descent) can be used to find the final model parameters.

[0096] FIG6 is a schematic diagram of using two independent prediction models to train and infer K optimal signals and the performance of the K optimal signals provided in an embodiment of the present application.

[0097] As shown in Figure 6, two independent prediction models can be used to perform inference. Specifically, the two prediction models use the same input but have different outputs: prediction model 1 outputs the indexes of the K best signals, while prediction model 2 outputs the performance of the K best signals.

[0098] For example, the data set used for training may include the following parts:

[0099] Input: Prediction Model 1 and Prediction Model 2 use the same input, namely, the measured performance of M historical signals, such as the Layer 1 Reference Signal Receiving Power (L1-RSRP). The M historical signals can be input in a certain order.

[0100] Label: For prediction model 1, its label is the index of the K best signals measured in the entire set; for prediction model 2, its label is the performance of the K best signals measured in the entire set.

[0101] Output: For prediction model 1, the indexes of the K best signals are output; for prediction model 2, the performance of the K best signals is output.

[0102] It should be noted that if prediction model 1 outputs K optimal signals, then the prediction model 1 can infer situations where there are less than K optimal signals, but cannot handle situations where there are more than K optimal signals. This is because the prediction model 1 has not been trained and its model parameters cannot support it.

[0103] FIG7 is a schematic diagram of the input and output relationship of the prediction model 1 provided in an embodiment of the present application.

[0104] As shown in Figure 7, a set of M historical signal measurements (a subset of the full set) serves as the input for prediction model 1. The output is the indices of the K best signals, i.e., the K best signals with the highest performance. The labels used by prediction model 1 are the indices of the K best signals measured in the full set (e.g., with the highest L1-RSRP).

[0105] FIG8 is a schematic diagram of the input and output relationship of the prediction model 2 provided in an embodiment of the present application.

[0106] As shown in Figure 8, prediction model 2 shares the same input as prediction model 1. Unlike prediction model 1, the output of prediction model 2 is the performance of the K best signals. The labels are the performance of the K best signals measured in the entire set.

[0107] 3. Beam failure recovery (BFR).

[0108] During the evolution of the 3GPP standard, beam recovery mechanisms in different scenarios were supported. Specifically, the first version of the New Radio (NR) (i.e., Rel.15) supported the beam failure recovery mechanism for the primary cell (PCell) or primary secondary cell (PSCell); Rel.16 supported the beam recovery mechanism for the secondary cell (SCell). Rel.17 supports the TRP-specific beam failure recovery mechanism. In order to better understand the beam recovery mechanism.

[0109] The BFR process of PCell or PSCell is described below by taking the BFR process of PCell or PSCell as an example.

[0110] FIG9 is a schematic flow chart of the BFR process provided in an embodiment of the present application.

[0111] As shown in Figure 9, the BFR process may include:

[0112] In step S210 , the user equipment (UE) performs beam failure detection (BFD) based on a beam failure detection reference signal (BFD RS) and new beam identification (NBI) based on a new beam identification reference signal (NBI RS).

[0113] S220, reporting of beam failure.

[0114] Exemplarily, the UE reports a beam failure request (Beam Failure ReQuest, BFRQ) to the network (NW). When a beam failure event occurs in the serving cell, the UE can use uplink resources to carry the BFR Media Access Control (MAC) control element (CE) to inform the NW of the beam failure. The MAC CE should include the serving cell identifier (ID) of the beam failure and a new beam suitable for physical downlink control channel (PDCCH) transmission (selected from NBI RS). The uplink resources can come from the PUCCH-Scheduling Request (SR) sent by the UE, or they can be uplink physical uplink shared channel (PUSCH) resources used for other purposes. In addition, the BFR MAC CE can also be carried in message 3 (Msg.3) or message A (Msg.A) of random access.

[0115] S230, beam failure recovery response.

[0116] For example, the NW sends a Beam Failure Request Response (BFRR) to the UE. After receiving the BFRQ from the UE, if the NW agrees with the UE's beam failure recovery request, it needs to give the UE a confirmation. This confirmation is achieved through downlink control information (DCI). The DCI contains the same Hybrid Automatic Repeat Request (HARQ) process ID as the previously scheduled PUSCH (carrying BFR MAC CE) and the inverted New Data Indicator (NDI) field.

[0117] S240: 28 symbols after the UE receives the BFRR, the UE's PDCCH and PUCCH beams automatically return to the new beams.

[0118] It should be understood that FIG9 is merely an example of the present application and should not be construed as a limitation to the present application.

[0119] For example, the BFR process involved in the embodiment of the present application can be primary cell beam failure recovery or secondary cell beam failure recovery.

[0120] It is worth noting that the above-mentioned BFR process relies on periodic Channel State Information Reference Signal (CSI-RS) and / or Synchronization Signal / PBCH Block (SSB) as BFD RS to detect beam failure events (Beam Failure Events), and periodic CSI-RS and / or SSB as NBI RS to find a suitable new beam (reported to the NW via BFRQ only when beam failure occurs). BFD RS and NBI RS are both periodic downlink reference signals. In one case, the NW explicitly configures the radio resource control (RRC) to the UE, or the UE determines the downlink (DL) reference signal (RS) contained in the transmission configuration indication (TCI) state of the control resource set (CORESET) where the physical downlink control channel (PDCCH) is located. The TCI state is also called beam indication information. This imposes a certain amount of downlink reference signal overhead on the NR system, leading to excessively high costs in the BFR process. Furthermore, due to the inherent characteristics of periodic reference signals, the time delay required to complete multiple periodic measurements also results in excessive BFR latency.

[0121] In view of this, the present application introduces a prediction model based on artificial intelligence (AI) and / or machine learning (ML) (hereinafter referred to as the target prediction model) to predict signal performance and / or predict signals that meet the prediction conditions, thereby reducing the overhead and delay caused by reference signal measurement in the time domain and / or spatial domain. In addition, if the beam failure event can be predicted in advance, the occurrence of the beam failure event can be avoided in advance through the mechanism of spatial filter adjustment, thereby improving the overall experience of the UE.

[0122] AI refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive field within computer science that seeks to understand the essence of intelligence and create new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making. It should be understood that AI technology is an interdisciplinary discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0123] ML is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0124] The following describes the wireless communication method provided in an embodiment of the present application when the target prediction model is deployed on the terminal device side.

[0125] FIG10 is a schematic flow chart of a wireless communication method 310 provided in an embodiment of the present application. The wireless communication method 310 may be executed by a terminal device, for example, the terminal device shown in FIG1 .

[0126] As shown in FIG10 , the wireless communication method 310 may include:

[0127] S311, the terminal device obtains performance of the M historical signals by detecting the M historical signals;

[0128] S312, the terminal device uses a target prediction model to predict the performance of N target signals and / or K target signals whose performance meets preset conditions among the N target signals based on the performance of the M historical signals;

[0129] Wherein, M and N are both positive integers, and K≤N.

[0130] In the embodiment of the present application, by introducing a target prediction model and predicting the performance of N target signals and / or K target signals among the N target signals whose performance meets preset conditions based on the performance of M historical signals, compared with the method in which the network device configures a reference signal specifically for measuring the performance of the target signal for the terminal device, the network device avoids configuring a reference signal specifically for measuring the performance of the target signal for the terminal device, which not only reduces the signaling overhead caused by obtaining the performance of the N target signals and / or the K target signals, but also reduces the delay caused by obtaining the performance of the N target signals and / or the K target signals. In short, the solution provided by the embodiment of the present application can reduce the signaling overhead and delay caused by obtaining the performance of N target signals and / or obtaining K target signals among the N target signals whose performance meets the prediction conditions.

[0131] Exemplarily, when the target prediction model is used to predict K target signals, it can be specifically used to predict the indexes of the K target signals.

[0132] Exemplarily, the target prediction model can be trained in the manner of training prediction model 1. For example, when the target prediction model is used to predict K target signals whose performance meets preset conditions among N target signals, it can be trained in the manner of training prediction model 1.

[0133] Exemplarily, the target prediction model can be trained in the manner described above for training prediction model 2. For example, when the target prediction model is used to predict the performance of N target signals, it can be trained in the manner described above for training prediction model 2. For another example, when the target prediction model is used to predict K target signals among N target signals whose performance meets preset conditions and the performance of the K target signals, it can be trained in the manner described above for training prediction model 2.

[0134] In some embodiments, the historical signal includes a reference signal and / or a physical channel.

[0135] Exemplarily, the historical signal may be an uplink channel or an uplink signal. The uplink channel may include a physical random access channel (PRACH), a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), etc. The uplink reference signal may include an uplink demodulation reference signal (DMRS), a sounding reference signal (SRS), a phase tracking reference signal (PT-RS), etc. Among them, the uplink DMRS can be used for demodulation of the uplink channel, the SRS can be used for measurement of the uplink channel, uplink time-frequency synchronization or phase tracking, and the PT-RS can also be used for measurement of the uplink channel, uplink time-frequency synchronization or phase tracking.

[0136] Exemplarily, the historical signal may be a downlink channel or a downlink signal. The downlink channel may include a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a paging control channel (PCCH), a paging channel (PCH), a primary common control physical channel (P-CCPCH), etc. The downlink reference signal may include a downlink demodulation reference signal (DMRS), wherein the downlink DMRS may be used for demodulation of the downlink channel.

[0137] It should be understood that the embodiments of the present application may include uplink physical channels or uplink reference signals with the same name but different functions as those described above, or may include uplink physical channels or uplink reference signals with different names but the same functions as those described above, and the present application does not limit this. In addition, it should be understood that the terms "downlink" and "uplink" involved in the present application are used to indicate the transmission direction of a signal or data, where "downlink" is used to indicate that the transmission direction of a signal or data is a first direction from a site to a user equipment in a cell, and "uplink" is used to indicate that the transmission direction of a signal or data is a second direction from a user equipment in a cell to a site. For example, "downlink signal" indicates that the transmission direction of the signal is the first direction.

[0138] In addition, in other alternative embodiments, the terms "historical signal" and "target signal" involved in this application can be equivalently replaced by "beam (pair)", which means "beam" or "beam pair". Specifically, "beam" refers to the transmit beam on the downlink NW side, and "beam pair" refers to a pair of downlink transmit beams (NW side) and receive beams (UE side). "Beam" can also be called a spatial filter. For example, the transmit beam can be called a spatial domain transmission filter (Spatial domain transmission filter or Spatial domain filter for transmission), or the receive beam can be called a spatial domain reception filter (Spatial domain reception filter or Spatial domain filter for reception). Prediction can also be equivalently replaced by inference or other terms with the same or similar meanings.

[0139] Exemplarily, the performance of the N target signals and / or the K target signals among the N target signals whose performance meets preset conditions can be used for beam failure recovery (BFR). For example, the performance of the N target signals and / or the K target signals can be used for beam failure detection (BFD) and new beam identification (NBI) in BFR. For BFD, the performance of the N target signals and / or the K target signals can be used to predict the performance of the BFD RS, and then predict whether a beam failure event occurs. For NBI, the performance of the N target signals and / or the K target signals can be used to predict an NBI RS that meets preset conditions, that is, a new beam that can be used for beam recovery.

[0140] It is worth noting that the prediction of the performance of the BFD RS and the prediction of the NBI RS that meets the preset conditions can be predicted by the same prediction model or by two independent prediction models, which is not specifically limited in the embodiments of the present application.

[0141] As a specific example, the target prediction model involved in this application can be trained with two sets of parameters, one set of which can be used to predict the performance of the BFD RS, and the other set of which can be used to predict the NBI RS that meets preset conditions. As another specific example, the target prediction model involved in this application can be used only for predicting the performance of the BFD RS. In addition, a prediction model independent of the target prediction model and used to predict the NBI RS that meets preset conditions can be trained. As yet another example, the target prediction model involved in this application can be used only for predicting the NBI RS that meets preset conditions. In addition, a prediction model independent of the target prediction model and used to predict the performance of the BFD RS can be trained.

[0142] Of course, in other alternative embodiments, the performance of the N target signals and / or the K target signals may also be used in other scenarios, and this application does not make specific limitations on this.

[0143] In some embodiments, the reference signal includes a cell-specific (Cell-Specific) reference signal and / or a terminal device-specific (UE-specific) reference signal.

[0144] Exemplarily, a cell-specific reference signal is specific to a cell and needs to consider the coverage of the cell. For example, a cell-specific reference signal may be a reference signal that relatively evenly covers the cell. For a terminal device-specific reference signal, only the coverage of the terminal device needs to be considered. For example, the terminal device-specific reference signal may be a reference signal that can cover the terminal device.

[0145] In some embodiments, the M historical signals and the N target signals are spatially correlated signals.

[0146] Exemplarily, the M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein the M spatial filters are a subset of the N spatial filters; or, the M spatial filters and the N spatial filters are partially different; or, the M spatial filters and the N spatial filters are mutually different. In other words, there is a correlation in the spatial domain between the M spatial filters corresponding to the M historical signals and the N spatial filters corresponding to the N target signals.

[0147] In some embodiments, the M historical signals and the N target signals are identical signals in the spatial domain.

[0148] Exemplarily, the M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein the M spatial filters are the same as the N spatial filters.

[0149] Of course, in other alternative embodiments, the M historical signals and the N target signals may also be distinguished from other perspectives, and this application does not specifically limit this. As an example, the M historical signals are a subset of the N target signals. For example, the signal type of the M historical signals is a subset of the signal type of the N target signals. As another example, the M historical signals and the N target signals are partially different. For example, the signal type of the M historical signals and the signal type of the N target signals are partially different. As yet another example, the M historical signals and the N target signals are different from each other. For example, the signal type of the M historical signals and the signal type of the N target signals are different from each other.

[0150] In some embodiments, the preset condition may be determined based on application scenarios of the K target signals.

[0151] Exemplarily, if the K target signals are used for NBD, the preset condition may be less than or equal to a preset threshold.

[0152] Exemplarily, if the K target signals are used for NBI, the preset condition may be greater than or equal to a preset threshold.

[0153] In some embodiments, the S312 may include:

[0154] The terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the spatial domain based on the performance of the M historical signals.

[0155] Exemplarily, if the M historical signals and the N target signals are signals associated in the spatial domain, the terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the spatial domain based on the performance of the M historical signals.

[0156] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals at a first moment, then:

[0157] The performance of the N target signals includes: the performance of the N target signals at the first moment;

[0158] The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

[0159] Exemplarily, the terminal device may use the target prediction model to predict the performance of the N target signals at the first moment based on the performance of the M historical signals at the first moment; or, the terminal device may use the target prediction model to predict the target signal among the N target signals whose performance meets the preset conditions at the first moment based on the performance of the M historical signals at the first moment.

[0160] It is worth noting that the terminal device's prediction in the spatial domain based on the M historical signals is primarily based on the fact that the M historical signals and the N target signals are spatially correlated signals, for example, the M spatial filters and the N spatial filters have a certain correlation. For example, if the spatial filter directions of the M historical signals are close to the spatial filter directions of the N target signals, then if the performance of the M historical signals is good, the performance of the N target signals is also often good, and vice versa.

[0161] FIG11 is a schematic diagram of the relationship between the historical signal and the target signal provided in an embodiment of the present application.

[0162] As shown in Figure 11, it is assumed that the reference signals sent by the network device include cell-specific reference signals and terminal device-specific reference signals. The cell-specific reference signals can be reference signal 1, reference signal 3, and reference signal 5, wherein reference signal 3 is a reference signal covering the terminal device. The terminal device-specific reference signals can be reference signal 2 and reference signal 6, that is, reference signal 2 and reference signal 6 can both cover the terminal device. In this case, the M historical signals involved in this application may include reference signal 3 among the cell-specific reference signals that can cover the terminal device, and may also include reference signal 2 or reference signal 6 that is specific to the terminal device. Assuming that reference signal 4 is the target signal, it means that the historical signal and the target signal are signals that are associated in the spatial domain. At this time, the terminal device can use the target prediction model to predict the performance of reference signal 4 or predict that reference signal 4 is a signal that meets the preset conditions based on the performance of reference signal 3, reference signal 2, and reference signal 6.

[0163] FIG12 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the spatial domain, as provided in an embodiment of the present application.

[0164] As shown in Figure 12, the target prediction model includes an input layer, a hidden layer, and an output layer. Through different connection methods, weights, and activation functions of multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. When each upper-level node is connected to all of its lower-level nodes, the target prediction model is a DNN. This target prediction model can be used to predict signals or signal performance in the spatial domain. Specifically, during the prediction process, the input of the target prediction model is the performance of historical signals 1 to M, and the output of the target prediction model is the performance of target signal 1 to N. Similarly, during the training process, the input of the target prediction model is the performance of historical signals 1 to M, and the output of the target prediction model is the performance of target signal 1 to N. Furthermore, the labels used in the target prediction model are the measured performance of target signals 1 to N. Based on this, the terminal device can train the target prediction model based on the predicted performance of target signals 1 to N and the measured performance of target signals 1 to N.

[0165] Of course, FIG12 is merely an example of the present application and should not be construed as a limitation to the present application.

[0166] For example, in other alternative embodiments, the target prediction model may be used to predict K target signals among N target signals whose performance meets the prediction conditions.

[0167] Specifically, during the prediction process, the input of the target prediction model is the performance of historical signal 1 to the performance of historical signal M, and the output of the target prediction model is the index of target signal 1 to the index of target signal K that meets the preset conditions. Similarly, during the training process, the input of the target prediction model is the performance of historical signal 1 to the performance of historical signal M, and the output of the target prediction model is the index of target signal 1 to the index of target signal K. Furthermore, the labels used in the target prediction model are the measured index of target signal 1 to the index of target signal K. Based on this, the terminal device can train the target prediction model based on the predicted index of target signal 1 to the index of target signal K and the measured index of target signal 1 to the index of target signal K.

[0168] In some embodiments, the S312 may include:

[0169] The terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the time domain based on the performance of the M historical signals.

[0170] Exemplarily, if the M historical signals and the N target signals are the same signals in the spatial domain, the terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the time domain based on the performance of the M historical signals.

[0171] In some embodiments, if the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then:

[0172] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0173] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0174] The F time units are located after the E time units, and E and F are both positive integers.

[0175] Exemplarily, the terminal device may use the target prediction model to predict the performance of the N target signals in each of the F time units based on the performance of the N target signals in each of the E time units.

[0176] For example, the terminal device can use the target prediction model to predict the performance of the first target signal among the N target signals in each of the E time units, based on the performance of the first target signal in each of the F time units.

[0177] Exemplarily, the terminal device can use the target prediction model to predict the target signal among the N target signals whose performance meets the preset conditions in each of the F time units based on the performance of the N target signals in each of the E time units.

[0178] For example, the terminal device can use the target prediction model to predict whether the second target signal among the N target signals is a target signal whose performance meets the preset conditions in each of the F time units based on the performance of the second target signal in the N time units.

[0179] Exemplarily, the performance of the N target signals in each of the E time units may be sorted according to the index order of the N target signals. For example, the performance of the N target signals in each of the E time units may be sorted in descending order or in ascending order according to the index of the N target signals.

[0180] Of course, in other alternative embodiments, for each of the E time units, the input of the target prediction model may be the correspondence between N performances and the indexes of the N target signals. For example, the input of the target prediction model may be the indexes of the M target signals and the performance of each of the N target signals.

[0181] Exemplarily, the time unit includes but is not limited to: time slot, symbol, frame, subframe, etc.

[0182] Exemplarily, the time unit includes milliseconds or seconds, etc.

[0183] Exemplarily, the E time units are E consecutive time units.

[0184] Exemplarily, the F time units are F consecutive time units.

[0185] Exemplarily, the E time units and the F time units are continuous or have a gap.

[0186] Exemplarily, the E time units are time units within a measurement period of the target signal.

[0187] Exemplarily, the F time units are time units within a prediction period of the target signal.

[0188] FIG13 is a schematic diagram of signal prediction or signal performance prediction in the time domain provided by an embodiment of the present application.

[0189] As shown in Figure 13, assuming that the E time units are the measurement period of the target signal, the terminal device first measures the performance of the target signal within the measurement period of the target signal to obtain the performance of each time unit within the measurement period of the target signal. Then, based on the performance of each time unit within the measurement period of the target signal, the terminal device predicts the performance of the target signal in each time unit within the prediction period of the target signal. Furthermore, the terminal device can also determine whether the performance of the target signal predicted in the time unit within the prediction period of the target signal has dropped below a certain threshold based on the performance of the target signal in each time unit within the prediction period of the target signal.

[0190] FIG14 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the time domain, as provided in an embodiment of the present application.

[0191] As shown in FIG14 , taking the example of a terminal device that can use the target prediction model to predict the performance of the N target signals in each of F time units based on the performance of the N target signals in each of E time units, the target prediction model includes E cascaded LSTM units, and the input of each LSTM unit is the performance of the N target signals measured in one time unit. Assuming that the E time units in the time domain include the E-1th time unit, the E-2th time unit, ..., the 1st time unit, and the 0th time unit, the input of the first of the E LSTM units is the performance of the N target signals measured in the E-1th time unit, the input of the second LSTM unit is the performance of the N target signals measured in the E-2th time unit, and so on. The input of the second-to-last LSTM unit is the performance of the N target signals measured in the 1st time unit, and the input of the last LSTM unit is the performance of the N target signals measured in the 0th time unit. The performance of the N target signals in each of the E time units may be sorted according to the index order of the N target signals. Based on this, the output of the last LSTM unit is the performance of the N target signals in each of the F time units.

[0192] Of course, FIG14 is merely an example of the present application and should not be construed as a limitation to the present application.

[0193] For example, in other alternative embodiments, the target prediction model may be used to predict K target signals among N target signals whose performance meets the prediction conditions.

[0194] In some embodiments, the S312 may include:

[0195] The terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain based on the performance of the M historical signals.

[0196] Exemplarily, if the M historical signals and the N target signals are correlated signals in the spatial domain, the terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals in the spatial domain and time domain based on the performance of the M historical signals.

[0197] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals in each of E time units, then:

[0198] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0199] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0200] The F time units are located after the E time units, and E and F are both positive integers.

[0201] Exemplarily, the terminal device may use the target prediction model to predict the performance of the N target signals in each of the F time units based on the performance of the M historical signals in each of the E time units.

[0202] For example, the terminal device can use the target prediction model to predict the performance of the first historical signal in the M historical signals in each of the E time units, based on the performance of the first historical signal in each of the F time units.

[0203] Exemplarily, the terminal device can use the target prediction model to predict the target signal whose performance meets the preset conditions among the N target signals in each of the F time units based on the performance of the M historical signals in each of the E time units.

[0204] For example, the terminal device can use the target prediction model to predict whether the second historical signal among the M historical signals is a target signal whose performance meets the preset conditions in each of the F time units based on the performance of the second historical signal in the M historical signals in each of the E time units.

[0205] Exemplarily, the performance of the M historical signals in each of the E time units may be sorted according to the index order of the M historical signals. For example, the performance of the M historical signals in each of the E time units may be sorted in descending or ascending order according to the index of the M historical signals.

[0206] Of course, in other alternative embodiments, for each of the E time units, the input of the target prediction model may be the correspondence between the performance of the M historical signals and the indexes of the M historical signals. For example, the input of the target prediction model may be the indexes of the M historical signals and the performance of each target signal in the N historical signals.

[0207] It is worth noting that the main basis for the terminal device to make predictions in the spatial domain and the spatial domain based on the M historical signals is that the M historical signals and the N target signals are correlated signals in the spatial domain, for example, the M spatial filters and the N spatial filters have a certain correlation. For example, if the spatial filter directions of the M historical signals are close to the spatial filter directions of the N target signals, then if the performance of the M historical signals is good, the performance of the N target signals will often be good for a certain period of time in the future, and vice versa.

[0208] Exemplarily, the time unit includes but is not limited to: time slot, symbol, frame, subframe, etc.

[0209] Exemplarily, the time unit includes milliseconds or seconds, etc.

[0210] Exemplarily, the E time units are E consecutive time units.

[0211] Exemplarily, the F time units are F consecutive time units.

[0212] Exemplarily, the E time units and the F time units are continuous or have a gap.

[0213] Exemplarily, the E time units are time units within a measurement period of the target signal.

[0214] Exemplarily, the F time units are time units within a prediction period of the target signal.

[0215] In some embodiments, the terminal device may predict the performance of the N target signals in each of the F time units in the following two ways:

[0216] Method 1:

[0217] The terminal device uses the first sub-model in the target prediction model to predict the performance of the N target signals in each of the E time units based on the performance of the M historical signals in each of the E time units; and uses the second sub-model in the target prediction model to predict the performance of the N target signals in each of the F time units based on the performance of the N target signals in each of the E time units.

[0218] Method 2:

[0219] The terminal device uses the second sub-model in the target prediction model to predict the performance of the M historical signals in each of the F time units based on the performance of the M historical signals in each of the E time units; and uses the first sub-model in the target prediction model to predict the performance of the N target signals in each of the F time units based on the performance of the M historical signals in each of the F time units.

[0220] Exemplarily, the first sub-model may be E DNNs corresponding to the E time units.

[0221] Exemplarily, the second sub-model may be E LSTM units corresponding to the E time units and cascaded.

[0222] Exemplarily, the E DNNs and the E LSTM units are connected in a one-to-one correspondence.

[0223] Exemplarily, for the method 1, the performance of the M historical signals in each of the E time units is the input of one of the E DNNs.

[0224] Exemplarily, for mode 2, the performance of the M historical signals in each of the E time units is the input of one LSTM unit among the E LSTM units.

[0225] Of course, in other alternative embodiments, the first sub-model and the second sub-model may also be implemented through other models or networks, and this application does not make specific limitations on this.

[0226] FIG15 is a schematic diagram of signal prediction or signal performance prediction in the time domain and spatial domain provided by an embodiment of the present application.

[0227] As shown in Figure 15, assuming that the E time units are the measurement period of the historical signal, the terminal device first measures the performance of the historical signal within the measurement period of the historical signal to obtain the performance of each time unit within the measurement period of the historical signal. Then, based on the performance of each time unit within the measurement period of the historical signal, the terminal device predicts the performance of the target signal in each time unit within the prediction period of the target signal. Furthermore, the terminal device can also determine whether the performance of the target signal predicted in the time unit within the prediction period of the target signal has dropped below a certain threshold based on the performance of the target signal in each time unit within the prediction period of the target signal.

[0228] FIG16 is a schematic diagram of the structure of a target prediction model that can perform signal prediction or signal performance prediction in the time domain and the spatial domain, as provided in an embodiment of the present application.

[0229] As shown in Figure 16, taking the example that the terminal device can use the target prediction model to predict the performance of the N target signals in each of F time units based on the performance of the M historical signals in each of E time units, the target prediction model includes E cascaded LSTM units and E DNNs, each LSTM unit is connected to a DNN, wherein the input of each LSTM unit is the output of the connected RNN, and the input of each RNN is the performance of the M historical signals measured in one time unit. Assuming that the E time units in the time domain include the E-1th time unit, the E-2th time unit, ..., the 1st time unit, and the 0th time unit, the input of the first E LSTM units is: the output of the DNN connected to it using the performance of the M historical signals measured at the E-1th time unit as input, the input of the second LSTM unit is: the output of the DNN connected to it using the performance of the M historical signals measured at the E-2th time unit as input, and so on. The input of the second-to-last LSTM unit is: the output of the DNN connected to it using the performance of the M historical signals measured at the 1st time unit as input, and the input of the last LSTM unit is: the output of the DNN connected to it using the performance of the M historical signals measured at the 0th time unit as input. The performance of the M historical signals in each of the E time units can be sorted according to the index order of the M historical signals. Based on this, the output of the last LSTM unit is the performance of the N target signals in each of the F time units.

[0230] Of course, FIG16 is merely an example of the present application and should not be construed as a limitation to the present application.

[0231] For example, in other alternative embodiments, the target prediction model may be used to predict K target signals among N target signals whose performance meets the prediction conditions.

[0232] In some embodiments, the target signal is a BFD RS or a PDCCH.

[0233] In this embodiment, the target signal is designed to be BFD RS or PDCCH, which is equivalent to performing beam failure detection in the beam failure recovery mechanism based on AI / ML. That is, the trained target prediction model can be used to directly predict the performance of BFD RS or PDCCH in the time domain and / or space domain. On the one hand, the signaling overhead and delay caused by the UE determining the PDCCH performance based on the measured BFD RS performance can be reduced. On the other hand, the performance of the BFD RS or PDCCH predicted in the time domain (or time domain and space domain) can predict the beam failure event in advance, thereby avoiding the occurrence of the beam failure event to a certain extent.

[0234] For example, the performance of the PDCCH can be judged by the quality of other channels. For example, for the downlink PDSCH, the UE can infer the PDCCH BLER based on factors such as the PDSCH decoding success rate or SINR, which reflect signal performance; or the NW can infer the PDCCH BLER based on factors such as the uplink PUCCH and / or PUSCH decoding success rate or SINR, which reflect signal performance.

[0235] Exemplarily, the input of the target prediction model can be the performance of other channels such as PDSCH / PUCCH / PUSCH or the performance of signal CSI-RS / SSB / SRS, and the output is PDCCH BLER. The labels used in the training of the target prediction model are the performance of other channels when PDCCH beam failure occurs, such as the error probability or SINR of PDSCH or the error probability or SINR of PUCCH / PUSCH. In other words, as long as there is enough data to learn this correlation, the target prediction model can learn the relationship between channels implicit in the system, thereby completing the inference of PDCCH BLER without BFD RS measurement, and then realizing beam failure prediction.

[0236] In some embodiments, the method 310 may further include:

[0237] The terminal device determines whether a beam failure event occurs based on the performance of the N target signals and the value of K.

[0238] Exemplarily, the N target signals are N BFD RSs.

[0239] Exemplarily, the N target signals are N PDCCHs.

[0240] In some embodiments, if the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, the terminal device determines that a beam failure event has occurred; otherwise, the terminal device determines that no beam failure event has occurred.

[0241] Exemplarily, the N target signals are N BFD RSs. If the number of target signals in the N BFD RSs whose performance is less than or equal to a first preset threshold is not 0, or the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, the terminal device determines that a beam failure event has occurred; otherwise, the terminal device determines that no beam failure event has occurred.

[0242] Exemplarily, the N target signals are N PDCCHs. If the number of target signals in the N PDCCHs whose performance is less than or equal to a first preset threshold is not 0, or the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, the terminal device determines that a beam failure event has occurred; otherwise, the terminal device determines that no beam failure event has occurred.

[0243] Exemplarily, the performance of the target signal includes a BLER of the target signal. A larger BLER of the target signal indicates a smaller performance of the target signal, or in other words, a smaller BLER of the target signal indicates a greater performance of the target signal.

[0244] It is worth noting that when the performance of the target signal includes the BLER of the target signal, the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, which can be equivalently replaced by: the number of target signals among the N target signals whose BLER is greater than or equal to the first preset threshold is not 0; similarly, when the preset condition is less than or equal to the first preset threshold, the value of K is not 0, which can be equivalently replaced by: when the preset condition is that the BLER is greater than or equal to the first preset threshold, the value of K is not 0.

[0245] For example, assuming that the first preset threshold is 10%, in a specific example, the N target signals are N BFD RSs, and the BLERs of the N BFD RSs can be considered as the BLERs of the PDCCHs corresponding to the N BFD RSs. If the BLERs of the PDCCHs corresponding to the N BFD RSs are higher than 10%, it means that the BLERs of the PDCCHs corresponding to the N BFD RSs will have a significant negative impact on the detection of the PDCCHs. In this case, the UE can consider it as a beam failure event. In another specific example, the N target signals are N PDCCHs. If the BLERs of the N PDCCHs are higher than 10%, it means that the BLERs of the N PDCCHs will have a significant negative impact on the detection of the PDCCHs. In this case, the UE can consider it as a beam failure event.

[0246] Exemplarily, the performance of the target signal includes the layer 1 reference signal receiving power (Layer 1 Reference Signal Receiving Power, L1-RSRP) of the target signal, the layer 1 signal to interference plus noise ratio (Layer 1 Signal to Interference plus Noise Ratio, L1-SINR) or the layer 1 reference signal receiving quality (Layer 1 Reference Signal Receiving Quality, L1-RSRQ). The larger the L1-RSRP, L1-SINR or L1-RSRQ of the target signal, the greater the performance of the target signal, or in other words, the smaller the L1-RSRP, L1-SINR or L1-RSRQ of the target signal, the lower the performance of the target signal.

[0247] It is worth noting that when the performance of the target signal includes L1-RSRP, L1-SINR or L1-RSRQ of the target signal, the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, which can be equivalently replaced by: the number of target signals among the N target signals whose L1-RSRP, L1-SINR or L1-RSRQ is less than or equal to the first preset threshold is not 0; similarly, when the preset condition is less than or equal to the first preset threshold, the value of K is not 0, which can be equivalently replaced by: when the preset condition is that L1-RSRP, L1-SINR or L1-RSRQ is less than or equal to the first preset threshold, the value of K is not 0.

[0248] In some embodiments, the N target signals are N NBI RSs.

[0249] In this embodiment, the target signal is designed as NBI RS, which is equivalent to performing NBI in the beam failure recovery mechanism based on AI / ML. That is, the trained target prediction model can be used to directly predict the performance of NBI RS in the time domain and / or spatial domain. On the one hand, the signaling overhead and delay caused by the UE performing NBI based on the measured NBI RS performance can be reduced. On the other hand, the performance of the NBI RS predicted in the time domain (or time domain and spatial domain) can predict the beam failure event in advance, thereby avoiding the occurrence of the beam failure event to a certain extent.

[0250] In some embodiments, the S312 may include:

[0251] If a beam failure event occurs, the terminal device uses the target prediction model to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

[0252] Exemplarily, the N target signals are N NBI RSs. If a beam failure event occurs, the terminal device uses the target prediction model to predict the performance of the N NBI RSs and / or the K target signals among the N NBI RSs that meet the prediction conditions based on the performance of the M historical signals.

[0253] Taking into account the characteristics of prediction in the time domain on the timeline, when the target prediction model predicts that no beam failure event is predicted in the next E unit time, or when it is determined through BFD RS detection that the beam failure event will not be triggered, the UE can omit a certain degree of NBI RS measurement or prediction of NBI RS. Therefore, the frequency of NBI RS prediction can be reduced through the linkage between BFD RS prediction and NBI RS prediction, thereby reducing the energy consumption of the terminal device.

[0254] FIG17 is a schematic diagram showing the relationship between the performance prediction of the BFD RS and the NBI RS prediction provided in an embodiment of the present application.

[0255] As shown in Figure 17, the terminal device can measure the BFD RS and NBI RS separately during their measurement periods and predict the BFD RS performance during the prediction period based on the BFD RS measurement performance during the measurement period. If the BFD RS performance during a certain time unit within the prediction period indicates that a beam failure event has not occurred, the subsequent NBI RS measurement or prediction can be canceled.

[0256] In some embodiments, the method 310 may further include:

[0257] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

[0258] Exemplarily, the N target signals are N NBI RSs. If the number of target signals in the N NBI RSs whose performance is greater than or equal to a third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of P NBI RSs and / or the K target signals in the P NBI RSs whose performance meets the preset conditions; wherein the N NBI RSs are a subset of the P NBI RSs.

[0259] In other words, when the prediction result of the target prediction model shows that there is no suitable NBI RS among the N NBI RSs, the target prediction model can expand the search range and predict a suitable NBI RS from P NBI RSs to complete the subsequent process in beam failure recovery.

[0260] In some embodiments, the N target signals are RSs configured by the network device.

[0261] Exemplarily, the N target signals are RSs configured by the network device through radio resource control (RRC) signaling, media access control (MAC) control element (CE) or downlink control information (DCI).

[0262] Exemplarily, the N target signals are reference signals included in a transmission configuration indication (TCI) state of a control resource set (CORESET) where a PDCCH used by the terminal device is located.

[0263] In some embodiments, the P target signals include all target signals corresponding to the target frequency band.

[0264] Exemplarily, the N target signals are RSs configured by the network device through radio resource control (RRC) signaling, media access control (MAC) control element (CE) or downlink control information (DCI).

[0265] Exemplarily, the target frequency band is a frequency band used by the terminal device.

[0266] In some embodiments, the method 310 may further include:

[0267] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, a beam failure recovery request BFRQ is sent to the network device; wherein the BFRQ includes the identifiers of the K target signals.

[0268] Exemplarily, the N target signals are N NBI RSs. The terminal device can find a suitable NBI RS by predicting the performance of the NBI RS and report it to the network device, or the terminal device can directly predict a suitable NBI RS using the target prediction model and report the predicted NBI RS to the network device. If the number of target signals in the N target signals whose performance is greater than or equal to the third preset threshold is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, a MAC CE carrying the BFRQ is sent to the network device.

[0269] Exemplarily, the BFRQ includes identifiers of the K target signals and an identifier (ID) of a serving cell where beam failure occurs.

[0270] Specifically, after a beam failure event occurs in the UE's serving cell, the UE can use uplink resources to carry a BFR media access control (MAC) control element (CE) to inform the NW of the beam failure. The MAC CE may include the serving cell identifier (ID) of the beam failure and an NBI RS suitable for transmission via the physical downlink control channel (PDCCH) (selected from the NBI RS set configured by the network device for the terminal device). The uplink resources may come from a PUCCH-scheduling request (SR) sent by the UE, or may be an uplink physical uplink shared channel (PUSCH) resource used for other purposes. In addition, the BFR MAC CE may also be carried in a random access message 3 (Msg.3) or message A (Msg.A).

[0271] Exemplarily, the identifiers of the K target signals may be signals among the N target signals mentioned above.

[0272] Exemplarily, the identifiers of the K target signals may be signals among the P target signals mentioned above.

[0273] Exemplarily, the identifiers of the K target signals may be indexes of the K target signals.

[0274] In some embodiments, the method 310 may further include:

[0275] After sending the BFRR for Q time units, the terminal device receives the BFRR sent by the network device.

[0276] Exemplarily, the BFRR is used to confirm that the network device has received the target signal reported by the terminal device.

[0277] Specifically, when the NW receives the BFRQ sent by the UE, if it agrees with the UE's beam failure recovery request, it needs to give the UE a confirmation (i.e., the BFRR). The BFRR is implemented through downlink control information (DCI), which contains the same Hybrid Automatic Repeat Request (HARQ) process ID as the previously scheduled PUSCH (carrying BFR MAC CE) and the inverted New Data Indicator (NDI) field.

[0278] In some embodiments, the method 310 may further include:

[0279] After receiving Q time units of the BFRR, the terminal device uses the spatial domain filters corresponding to the K target signals to transmit data; where Q is a positive integer.

[0280] Exemplarily, the Q time units are time units of 28 symbols or other lengths.

[0281] In some embodiments, the BFRQ further includes information indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

[0282] Exemplarily, if the target prediction model is a prediction performed in the time domain, or the target prediction model is a prediction performed in the time domain and the spatial domain, the BFRQ also includes information for indicating the time unit in which the beam failure event occurs corresponding to the K target signals.

[0283] Exemplarily, one or more target signals among the K target signals correspond to a time unit in which a beam failure event occurs.

[0284] Exemplarily, the information for indicating the time unit where the beam failure event occurs corresponding to the K target signals may be: information for indicating the position of the time unit where the beam failure event occurs corresponding to the K target signals in the F time units mentioned above, information for indicating the position of the time unit where the beam failure event occurs corresponding to the K target signals in the measurement period of the target signal mentioned above, or information for indicating the position of the time unit where the beam failure event occurs corresponding to the K target signals in the prediction period of the target signal mentioned above.

[0285] In some embodiments, the method 310 may further include:

[0286] At a later moment between the second moment and the third moment, the terminal device uses the spatial domain filter corresponding to the first target signal among the K target signals to perform data transmission;

[0287] The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0288] Exemplarily, the third moment is the starting moment, ending moment, middle moment or other reference moment of the time unit in which the beam failure event occurs corresponding to the first target signal.

[0289] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: Layer 1 Reference Signal Receiving Power (L1-RSRP), Layer 1 Signal to Interference plus Noise Ratio (L1-SINR), Layer 1 Reference Signal Receiving Quality (L1-RSRQ), and block error rate (BLER).

[0290] Exemplarily, when the target signal is NBD RS or PDCCH, the performance of the target signal is BLER.

[0291] Exemplarily, when the target signal is NBI RS, the performance of the target signal is L1-RSRP, L1-SINR or L1-RSRQ.

[0292] In some embodiments, the method 310 may further include:

[0293] The terminal device sends the capability information of the terminal device to the network device;

[0294] The capability information includes at least one of the following:

[0295] Information indicating whether the target prediction model is supported;

[0296] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0297] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0298] Information of the target prediction model.

[0299] Exemplarily, the information of the target prediction model may include type information supported by the target prediction model, description information of the target prediction model, prediction capability of the target prediction model, etc. Optionally, the type information includes DNN, LSTM or other model types. Optionally, the description information includes the number of output parameters, the number of layers and the number of output parameters of the target prediction model. Optionally, the prediction capability includes the type of the target signal that the target prediction model can predict, whether the target prediction model can support the performance prediction of the N target signals, or whether the target prediction model supports the prediction of K target signals that meet the preset conditions, etc.

[0300] In some embodiments, the method 310 may further include:

[0301] The terminal device receives configuration information sent by the network device, where the configuration information is used to configure the terminal device to use the target prediction model.

[0302] Exemplarily, if the terminal device supports the target prediction model, after the terminal device sends the capability information of the terminal device to the network device, the terminal device receives the configuration information sent by the network device. After receiving the configuration information, the terminal device uses the target prediction model to predict signal performance or signal.

[0303] Exemplarily, the configuration information may also include trained parameters of the target prediction model.

[0304] Exemplarily, the configuration information may further include information for indicating whether the target prediction model performs prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. Of course, the configuration information may also not include information for indicating whether the target prediction model performs prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. In this case, the terminal device may determine whether to perform prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. This embodiment of the present application does not specifically limit this.

[0305] Exemplarily, the configuration information is carried by the network device through RRC signaling, MAC CE or DCI.

[0306] In the above, in combination with Figures 10 to 17, the wireless communication method provided according to the embodiment of the present application when the target prediction model is deployed on the terminal device side is described in detail from the perspective of the terminal device. Below, in combination with Figure 18, the wireless communication method provided according to the embodiment of the present application is described from the perspective of the network device.

[0307] Figure 18 is a schematic flow chart of a wireless communication method 320 provided in an embodiment of the present application. The wireless communication method 320 can be interactively executed by a terminal device and a network device. The terminal device shown in Figure 18 can be the terminal device shown in Figure 1, and the network device shown in Figure 18 can be the access network device shown in Figure 1.

[0308] As shown in FIG. 18 , the method 320 may include:

[0309] S321, the network device receives a beam failure recovery request BFRQ sent by the terminal device;

[0310] The BFRQ includes identifiers of K target signals and information indicating time units of beam failure events corresponding to the K target signals.

[0311] Exemplarily, the BFRQ includes identifiers of the K target signals and an identifier (ID) of a serving cell where beam failure occurs.

[0312] Specifically, after a beam failure event occurs in the UE's serving cell, the UE can use uplink resources to carry a BFR media access control (MAC) control element (CE) to inform the NW of the beam failure. The MAC CE may include the serving cell identifier (ID) of the beam failure and an NBI RS suitable for transmission via the physical downlink control channel (PDCCH) (selected from the NBI RS set configured by the network device for the terminal device). The uplink resources may come from a PUCCH-scheduling request (SR) sent by the UE, or may be an uplink physical uplink shared channel (PUSCH) resource used for other purposes. In addition, the BFR MAC CE may also be carried in a random access message 3 (Msg.3) or message A (Msg.A).

[0313] Exemplarily, the identifiers of the K target signals may be signals among the N target signals mentioned above.

[0314] Exemplarily, the identifiers of the K target signals may be signals among the P target signals mentioned above.

[0315] Exemplarily, the identifiers of the K target signals may be indexes of the K target signals.

[0316] In some embodiments, the method 320 may further include:

[0317] After sending the BFRR for Q time units, the network device sends the BFRR to the terminal device.

[0318] Exemplarily, the BFRR is used to confirm that the network device has received the target signal reported by the terminal device.

[0319] Specifically, when the NW receives the BFRQ sent by the UE, if it agrees with the UE's beam failure recovery request, it needs to give the UE a confirmation (i.e., the BFRR). The BFRR is implemented through downlink control information (DCI), which contains the same hybrid automatic repeat request (HARQ) process ID as the previously scheduled PUSCH (carrying BFR MAC CE) and the inverted new data indication (NDI) field.

[0320] In some embodiments, the method 320 may further include:

[0321] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0322] The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0323] Exemplarily, the third moment is the starting moment, ending moment, middle moment or other reference moment of the time unit in which the beam failure event occurs corresponding to the first target signal.

[0324] In some embodiments, the method 320 may further include:

[0325] Receiving capability information sent by the terminal device;

[0326] The capability information includes at least one of the following:

[0327] Information indicating whether the target prediction model is supported;

[0328] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0329] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0330] Information of the target prediction model.

[0331] Exemplarily, the information of the target prediction model may include type information supported by the target prediction model, description information of the target prediction model, prediction capability of the target prediction model, etc. Optionally, the type information includes DNN, LSTM or other model types. Optionally, the description information includes the number of output parameters, the number of layers and the number of output parameters of the target prediction model. Optionally, the prediction capability includes the type of the target signal that the target prediction model can predict, whether the target prediction model can support the performance prediction of the N target signals, or whether the target prediction model supports the prediction of K target signals that meet the preset conditions, etc.

[0332] In some embodiments, the method 320 may further include:

[0333] Configuration information is sent to the terminal device, where the configuration information is used to configure the terminal device to use the target prediction model.

[0334] Exemplarily, when the network device determines that the terminal device supports the target prediction model based on the received capability information, the network device may send the configuration information to the terminal device. After receiving the configuration information, the terminal device uses the target prediction model to predict signal performance or signal.

[0335] Exemplarily, the configuration information may also include trained parameters of the target prediction model.

[0336] Exemplarily, the configuration information may further include information for indicating whether the target prediction model performs prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. Of course, the configuration information may also not include information for indicating whether the target prediction model performs prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. In this case, the terminal device may determine whether to perform prediction in the time domain, in the spatial domain, or in the spatiotemporal domain. This embodiment of the present application does not specifically limit this.

[0337] Exemplarily, the configuration information is carried by the network device through RRC signaling, MAC CE or DCI.

[0338] It should be understood that the steps in the wireless communication method 320 may refer to the corresponding steps in the wireless communication method 310, and for the sake of brevity, they are not repeated here.

[0339] The following describes the wireless communication method provided in an embodiment of the present application when the target prediction model is deployed on the network device side.

[0340] It should be noted that no matter whether the target prediction model is deployed on the terminal device side or on the network device side, its specific implementation method for predicting the performance of N target signals and / or the K target signals among the N target signals whose performance meets the preset conditions is not affected. The main difference is that if the target prediction model is deployed on the network device side, the terminal device needs to report the performance of the M historical signals obtained by measurement to the network device, so that the network device uses the performance of the M historical signals reported by the terminal device as input and uses the target prediction model to predict the performance of the N target signals and / or the K target signals among the N target signals whose performance meets the preset conditions. In view of this, the specific implementation method of the network device using the target prediction model to perform signal performance prediction and / or signal prediction can refer to the relevant content of the terminal device using the target prediction model to perform signal performance prediction and / or signal prediction. In order to avoid repetition, it will not be described in detail below.

[0341] FIG19 is a schematic flow chart of a wireless communication method 410 provided in an embodiment of the present application. The wireless communication method 410 may be executed by a terminal device, for example, the terminal device shown in FIG1 .

[0342] As shown in FIG. 19 , the wireless communication method 410 may include:

[0343] S411, receiving performance of M historical signals sent by the terminal device;

[0344] S412, based on the performance of the M historical signals, using a target prediction model to predict the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition;

[0345] Wherein, M and N are both positive integers, and K≤N.

[0346] Exemplarily, the network device may receive the performance of M historical signals reported by the terminal device through MAC CE or UCI.

[0347] In some embodiments, the S412 may include:

[0348] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain.

[0349] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals at a first moment, then:

[0350] The performance of the N target signals includes: the performance of the N target signals at the first moment;

[0351] The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

[0352] In some embodiments, the S412 may include:

[0353] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the time domain.

[0354] In some embodiments, if the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then:

[0355] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0356] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0357] The F time units are located after the E time units, and E and F are both positive integers.

[0358] In some embodiments, the S412 may include:

[0359] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain.

[0360] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals in each of E time units, then:

[0361] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0362] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0363] The F time units are located after the E time units, and E and F are both positive integers.

[0364] In some embodiments, based on the performance of the M historical signals in each of the E time units, the target prediction model may be used to predict the performance of the N target signals in each of the F time units in the following manner, including:

[0365] Based on the performance of the M historical signals in each of the E time units, using the first sub-model in the target prediction model, predict the performance of the N target signals in each of the E time units; and based on the performance of the N target signals in each of the E time units, using the second sub-model in the target prediction model, predict the performance of the N target signals in each of the F time units;

[0366] or,

[0367] Based on the performance of the M historical signals in each of the E time units, the second sub-model in the target prediction model is used to predict the performance of the M historical signals in each of the F time units; and based on the performance of the M historical signals in each of the F time units, the first sub-model in the target prediction model is used to predict the performance of the N target signals in each of the F time units.

[0368] In some embodiments, the M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein the M spatial filters are a subset of the N spatial filters; or, the M spatial filters and the N spatial filters are partially different; or, the M spatial filters and the N spatial filters are different from each other.

[0369] In some embodiments, the historical signal includes a reference signal and / or a physical channel.

[0370] In some embodiments, the reference signal includes a cell-specific reference signal and / or a terminal device-specific reference signal.

[0371] In some embodiments, the target signal is a beam failure detection reference signal BFD RS or a physical downlink control channel PDCCH.

[0372] In some embodiments, the method 410 may further include:

[0373] Based on the performance of the N target signals and the value of K, it is determined whether a beam failure event occurs.

[0374] In some embodiments, if the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, it is determined that a beam failure event has occurred; otherwise, it is determined that no beam failure event has occurred.

[0375] In some embodiments, the N target signals are N new beam finding reference signals NBI RS.

[0376] In some embodiments, the S412 may include:

[0377] If a beam failure event occurs, the target prediction model is used to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

[0378] In some embodiments, the method 410 may further include:

[0379] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

[0380] In some embodiments, the N target signals are RSs configured by a network device to the terminal device.

[0381] In some embodiments, the P target signals include all target signals corresponding to the target frequency band.

[0382] In some embodiments, the method 410 may further include:

[0383] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, an indication message is sent to the terminal device, and the indication message includes the identifiers of the K target signals.

[0384] It is worth noting that when the target prediction model is deployed on the terminal device side, if the target signal is BFD RS or NBI RS, the terminal device predicts BFD RS or NBI RS. At this time, after predicting the appropriate NBI RS, it is necessary to report the predicted appropriate NBI RS to the network device through BFRQ. After receiving the BFRQ, the network device feeds back BFRR to the terminal device to complete beam failure recovery or avoid sending beam failure events.

[0385] However, when the target prediction model is deployed on the network device side, if the target signal is BFD RS or NBI RS, the terminal device predicts BFD RS or NBI RS. Under this setting, the terminal device no longer needs to report BFRQ, that is, when the target prediction model predicts (infers) a beam failure event, the appropriate NBI RS predicted by the network device can be indicated to the terminal device through indication information, thereby completing beam failure recovery or avoiding sending a beam failure event. For example, the network device can send the indication information to the terminal device via MAC or MAC+DCI.

[0386] In some embodiments, the method 410 may further include:

[0387] After sending Q time units of the indication information, using the spatial domain filters corresponding to the K target signals for data transmission;

[0388] Wherein, Q is a positive integer.

[0389] In some embodiments, the indication information further includes information for indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

[0390] In some embodiments, the method 410 may further include:

[0391] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0392] The second moment is the moment of sending the indication information, and the third moment is determined according to the time unit of the occurrence of the beam failure event corresponding to the first target signal.

[0393] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

[0394] In some embodiments, the method 410 may further include:

[0395] Receiving capability information sent by the terminal device;

[0396] The capability information includes at least one of the following:

[0397] Information indicating whether the target prediction model is supported;

[0398] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0399] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0400] Information of the target prediction model.

[0401] In the above, combined with Figure 19, the wireless communication method provided according to the embodiment of the present application when the target prediction model is deployed on the network device side is described in detail from the perspective of the terminal device. Below, combined with Figure 20, the wireless communication method provided according to the embodiment of the present application is described from the perspective of the terminal device.

[0402] Figure 20 is a schematic flow chart of a wireless communication method 420 provided in an embodiment of the present application. The wireless communication method 320 can be interactively executed by a terminal device and a network device. The terminal device shown in Figure 20 can be the terminal device shown in Figure 1, and the network device shown in Figure 20 can be the access network device shown in Figure 1.

[0403] As shown in FIG. 20 , the method 420 may include:

[0404] S421, receiving instruction information sent by the network device;

[0405] The indication information includes identifiers of K target signals and information for indicating time units in which beam failure events corresponding to the K target signals occur.

[0406] In some embodiments, the method 420 may further include:

[0407] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0408] The second moment is the moment when the terminal device receives the indication information, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0409] In some embodiments, the method 420 may further include:

[0410] Sending capability information of the terminal device to the network device;

[0411] The capability information includes at least one of the following:

[0412] Information indicating whether the target prediction model is supported;

[0413] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0414] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0415] Information of the target prediction model.

[0416] In some embodiments, the method 420 may further include:

[0417] A capability of sending M historical signals to the network device.

[0418] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

[0419] It should be understood that the steps in the wireless communication method 420 may refer to the corresponding steps in the wireless communication method 410, and for the sake of brevity, they are not repeated here.

[0420] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, a variety of simple modifications can be made to the technical solution of the present application, and these simple modifications all fall within the scope of protection of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner unless there is any contradiction. In order to avoid unnecessary repetition, the present application will not further explain various possible combinations. For another example, the various different embodiments of the present application can also be arbitrarily combined, and as long as they do not violate the ideas of the present application, they should also be regarded as the contents disclosed in the present application.

[0421] It should also be understood that in the various method embodiments of the present application, the size of the sequence 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. In addition, in the embodiments of the present application, the terms "downlink" and "uplink" are used to indicate the transmission direction of the signal or data, wherein "downlink" is used to indicate that the transmission direction of the signal or data is the first direction sent from the site to the user equipment of the cell, and "uplink" is used to indicate that the transmission direction of the signal or data is the second direction sent from the user equipment of the cell to the site. For example, "downlink signal" indicates that the transmission direction of the signal is the first direction. In addition, in the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. Specifically, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0422] The above describes in detail the method embodiment of the present application in conjunction with Figures 1 to 20, and the following describes in detail the device embodiment of the present application in conjunction with Figures 21 to 26.

[0423] FIG21 is a schematic block diagram of a terminal device 510 according to an embodiment of the present application.

[0424] As shown in FIG21 , the terminal device 510 may include:

[0425] An acquiring unit 511 is configured to acquire performance of the M historical signals by detecting the M historical signals;

[0426] A prediction unit 512 is configured to predict, based on the performance of the M historical signals, the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition using a target prediction model;

[0427] Wherein, M and N are both positive integers, and K≤N.

[0428] In some embodiments, the prediction unit 512 is specifically configured to:

[0429] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain.

[0430] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals at a first moment, then:

[0431] The performance of the N target signals includes: the performance of the N target signals at the first moment;

[0432] The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

[0433] In some embodiments, the prediction unit 512 is specifically configured to:

[0434] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the time domain.

[0435] In some embodiments, if the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then:

[0436] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0437] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0438] The F time units are located after the E time units, and E and F are both positive integers.

[0439] In some embodiments, the prediction unit 512 is specifically configured to:

[0440] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain.

[0441] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals in each of E time units, then:

[0442] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0443] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0444] The F time units are located after the E time units, and E and F are both positive integers.

[0445] In some embodiments, the prediction unit 512 is specifically configured to:

[0446] Based on the performance of the M historical signals in each of the E time units, using the first sub-model in the target prediction model, predict the performance of the N target signals in each of the E time units; and based on the performance of the N target signals in each of the E time units, using the second sub-model in the target prediction model, predict the performance of the N target signals in each of the F time units;

[0447] or,

[0448] Based on the performance of the M historical signals in each of the E time units, the second sub-model in the target prediction model is used to predict the performance of the M historical signals in each of the F time units; and based on the performance of the M historical signals in each of the F time units, the first sub-model in the target prediction model is used to predict the performance of the N target signals in each of the F time units.

[0449] In some embodiments, the M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein the M spatial filters are a subset of the N spatial filters; or, the M spatial filters and the N spatial filters are partially different; or, the M spatial filters and the N spatial filters are different from each other.

[0450] In some embodiments, the target signal is a beam failure detection reference signal BFD RS or a physical downlink control channel PDCCH.

[0451] In some embodiments, the prediction unit 512 is further configured to:

[0452] Based on the performance of the N target signals and the value of K, it is determined whether a beam failure event occurs.

[0453] In some embodiments, the prediction unit 512 is specifically configured to:

[0454] If the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, it is determined that a beam failure event has occurred; otherwise, it is determined that no beam failure event has occurred.

[0455] In some embodiments, the N target signals are N new beam finding reference signals NBI RS.

[0456] In some embodiments, the prediction unit 512 is specifically configured to:

[0457] If a beam failure event occurs, the target prediction model is used to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

[0458] In some embodiments, the prediction unit 512 is further configured to:

[0459] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

[0460] In some embodiments, the N target signals are RSs configured by the network device.

[0461] In some embodiments, the P target signals include all target signals corresponding to the target frequency band.

[0462] In some embodiments, the prediction unit 512 is further configured to:

[0463] If the number of target signals whose performance is greater than or equal to the third preset threshold among the N target signals is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, sending a beam failure recovery request BFRQ to the network device;

[0464] The BFRQ includes identifiers of the K target signals.

[0465] In some embodiments, the prediction unit 512 is further configured to:

[0466] After receiving the Q time units of the BFRR, using the spatial domain filters corresponding to the K target signals for data transmission;

[0467] Wherein, Q is a positive integer.

[0468] In some embodiments, the BFRQ further includes information indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

[0469] In some embodiments, the prediction unit 512 is further configured to:

[0470] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0471] The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0472] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

[0473] In some embodiments, the prediction unit 512 is further configured to:

[0474] Sending capability information of the terminal device to the network device;

[0475] The capability information includes at least one of the following:

[0476] Information indicating whether the target prediction model is supported;

[0477] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0478] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0479] Information of the target prediction model.

[0480] In some embodiments, the prediction unit 512 is further configured to:

[0481] Receive configuration information sent by a network device, where the configuration information is used to configure the terminal device to use the target prediction model.

[0482] It should be understood that the apparatus embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. Specifically, the terminal device 510 shown in Figure 21 may correspond to the corresponding subject in the method 310 of the embodiment of the present application, and the aforementioned and other operations and / or functions of each unit in the terminal device 510 are respectively for implementing the corresponding processes in the method 310 provided in the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0483] FIG22 is a schematic block diagram of a network device 520 according to an embodiment of the present application.

[0484] As shown in FIG. 22 , the network device 520 may include:

[0485] The receiving unit 521 is configured to receive a beam failure recovery request BFRQ sent by a terminal device;

[0486] The BFRQ includes identifiers of K target signals and information indicating time units of beam failure events corresponding to the K target signals.

[0487] In some embodiments, the receiving unit 521 is further configured to:

[0488] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0489] The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0490] In some embodiments, the receiving unit 521 is further configured to:

[0491] Receiving capability information sent by the terminal device;

[0492] The capability information includes at least one of the following:

[0493] Information indicating whether the target prediction model is supported;

[0494] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0495] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0496] Information of the target prediction model.

[0497] In some embodiments, the receiving unit 521 is further configured to:

[0498] Configuration information is sent to the terminal device, where the configuration information is used to configure the terminal device to use the target prediction model.

[0499] It should be understood that the apparatus embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. Specifically, the network device 520 shown in Figure 22 may correspond to the corresponding subject in the method 320 of the embodiment of the present application, and the aforementioned and other operations and / or functions of each unit in the network device 520 are respectively for implementing the corresponding processes in the method 320 provided in the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0500] FIG23 is a schematic block diagram of a network device 610 according to an embodiment of the present application.

[0501] As shown in FIG. 23 , the network device 610 may include:

[0502] The receiving unit 611 is configured to receive M historical performance signals sent by a terminal device;

[0503] A prediction unit 612 is configured to predict, based on the performance of the M historical signals, the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition using a target prediction model;

[0504] Wherein, M and N are both positive integers, and K≤N.

[0505] In some embodiments, the prediction unit 612 is specifically configured to:

[0506] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain.

[0507] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals at a first moment, then:

[0508] The performance of the N target signals includes: the performance of the N target signals at the first moment;

[0509] The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

[0510] In some embodiments, the prediction unit 612 is specifically configured to:

[0511] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the time domain.

[0512] In some embodiments, if the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then:

[0513] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0514] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0515] The F time units are located after the E time units, and E and F are both positive integers.

[0516] In some embodiments, the prediction unit 612 is specifically configured to:

[0517] Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain.

[0518] In some embodiments, if the performance of the M historical signals includes the performance of the M historical signals in each of E time units, then:

[0519] The performance of the N target signals includes: the performance of the N target signals in each of the F time units;

[0520] The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals;

[0521] The F time units are located after the E time units, and E and F are both positive integers.

[0522] In some embodiments, the prediction unit 612 is specifically configured to:

[0523] Based on the performance of the M historical signals in each of the E time units, using the first sub-model in the target prediction model, predict the performance of the N target signals in each of the E time units; and based on the performance of the N target signals in each of the E time units, using the second sub-model in the target prediction model, predict the performance of the N target signals in each of the F time units;

[0524] or,

[0525] Based on the performance of the M historical signals in each of the E time units, the second sub-model in the target prediction model is used to predict the performance of the M historical signals in each of the F time units; and based on the performance of the M historical signals in each of the F time units, the first sub-model in the target prediction model is used to predict the performance of the N target signals in each of the F time units.

[0526] In some embodiments, the M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein the M spatial filters are a subset of the N spatial filters; or, the M spatial filters and the N spatial filters are partially different; or, the M spatial filters and the N spatial filters are different from each other.

[0527] In some embodiments, the historical signal includes a reference signal and / or a physical channel.

[0528] In some embodiments, the reference signal includes a cell-specific reference signal and / or a terminal device-specific reference signal.

[0529] In some embodiments, the target signal is a beam failure detection reference signal BFD RS or a physical downlink control channel PDCCH.

[0530] In some embodiments, the prediction unit 612 is further configured to:

[0531] Based on the performance of the N target signals and the value of K, it is determined whether a beam failure event occurs.

[0532] In some embodiments, the prediction unit 612 is specifically configured to:

[0533] If the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, it is determined that a beam failure event has occurred; otherwise, it is determined that no beam failure event has occurred.

[0534] In some embodiments, the N target signals are N new beam finding reference signals NBI RS.

[0535] In some embodiments, the prediction unit 612 is specifically configured to:

[0536] If a beam failure event occurs, the target prediction model is used to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

[0537] In some embodiments, the prediction unit 612 is further configured to:

[0538] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

[0539] In some embodiments, the N target signals are RSs configured by a network device to the terminal device.

[0540] In some embodiments, the P target signals include all target signals corresponding to the target frequency band.

[0541] In some embodiments, the prediction unit 612 is further configured to:

[0542] If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, an indication message is sent to the terminal device, and the indication message includes the identifiers of the K target signals.

[0543] In some embodiments, the prediction unit 612 is further configured to:

[0544] After sending Q time units of the indication information, using the spatial domain filters corresponding to the K target signals for data transmission;

[0545] Wherein, Q is a positive integer.

[0546] In some embodiments, the indication information further includes information for indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

[0547] In some embodiments, the prediction unit 612 is further configured to:

[0548] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0549] The second moment is the moment of sending the indication information, and the third moment is determined according to the time unit of the occurrence of the beam failure event corresponding to the first target signal.

[0550] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

[0551] In some embodiments, the prediction unit 612 is further configured to:

[0552] Receiving capability information sent by the terminal device;

[0553] The capability information includes at least one of the following:

[0554] Information indicating whether the target prediction model is supported;

[0555] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0556] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0557] Information of the target prediction model.

[0558] It should be understood that the apparatus embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. Specifically, the network device 610 shown in Figure 23 may correspond to the corresponding subject in the method 410 of the embodiment of the present application, and the aforementioned and other operations and / or functions of each unit in the network device 610 are respectively for implementing the corresponding processes in the method 410 provided in the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0559] FIG24 is a schematic block diagram of a terminal device 620 according to an embodiment of the present application.

[0560] As shown in FIG. 24 , the terminal device 620 may include:

[0561] The receiving unit 621 is configured to receive instruction information sent by a network device;

[0562] The indication information includes identifiers of K target signals and information for indicating time units in which beam failure events corresponding to the K target signals occur.

[0563] In some embodiments, the receiving unit 621 is further configured to:

[0564] At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission;

[0565] The second moment is the moment when the terminal device receives the indication information, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

[0566] In some embodiments, the receiving unit 621 is further configured to:

[0567] Sending capability information of the terminal device to the network device;

[0568] The capability information includes at least one of the following:

[0569] Information indicating whether the target prediction model is supported;

[0570] Information indicating whether prediction in the airspace based on the target prediction model is supported;

[0571] Information indicating whether prediction in the time domain based on the target prediction model is supported;

[0572] Information of the target prediction model.

[0573] In some embodiments, the receiving unit 621 is further configured to:

[0574] A capability of sending M historical signals to the network device.

[0575] In some embodiments, the performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

[0576] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. Specifically, the terminal device 620 shown in Figure 24 may correspond to the corresponding subject in the method 420 of the embodiment of the present application, and the aforementioned and other operations and / or functions of each unit in the terminal device 620 are respectively for implementing the corresponding processes in the method 420 provided in the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0577] The communication device of the embodiment of the present application is described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, or can be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor for execution, or can be completed by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps in the above method embodiment in conjunction with its hardware.

[0578] For example, the processing unit and communication unit mentioned above may be implemented by a processor and a transceiver, respectively.

[0579] FIG25 is a schematic structural diagram of a communication device 700 according to an embodiment of the present application.

[0580] As shown in FIG. 25 , the communication device 700 may include a processor 710 .

[0581] The processor 710 may call and execute a computer program from the memory to implement the method in the embodiment of the present application.

[0582] As shown in FIG. 25 , the communication device 700 may further include a memory 720 .

[0583] The memory 720 can be used to store indication information and can also be used to store code, instructions, etc. executed by the processor 710. The processor 710 can call and run computer programs from the memory 720 to implement the methods in the embodiments of the present application. The memory 720 can be a separate device independent of the processor 710 or integrated into the processor 710.

[0584] As shown in FIG. 25 , the communication device 700 may further include a transceiver 730 .

[0585] The processor 710 may control the transceiver 730 to communicate with other devices. Specifically, the processor 710 may send information or data to other devices or receive information or data sent by other devices. The transceiver 730 may include a transmitter and a receiver. The transceiver 730 may further include one or more antennas.

[0586] It should be understood that the various components in the communication device 700 are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0587] It should also be understood that the communication device 700 may be a terminal device in an embodiment of the present application, and the communication device 700 may implement the corresponding processes implemented by the terminal device in each method in the embodiment of the present application, that is, the communication device 700 in an embodiment of the present application may correspond to the terminal device 510 or the terminal device 620 in an embodiment of the present application, and may correspond to the execution of the corresponding subject in the method 310 or 420 according to the embodiment of the present application. For the sake of brevity, it will not be repeated here. Similarly, the communication device 700 may be a network device in an embodiment of the present application, and the communication device 700 may implement the corresponding processes implemented by the network device in each method in the embodiment of the present application. That is, the communication device 700 in an embodiment of the present application may correspond to the network device 520 or the network device 610 in an embodiment of the present application, and may correspond to the execution of the corresponding subject in the method 320 or 410 according to the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0588] In addition, a chip is also provided in an embodiment of the present application.

[0589] For example, the chip may be an integrated circuit chip with signal processing capabilities that can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The chip may also be referred to as a system-on-chip, a system-on-chip, a system-on-chip, or a system-on-chip chip. Optionally, the chip can be applied to various communication devices, so that the communication devices equipped with the chip can execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0590] FIG26 is a schematic structural diagram of a chip 800 according to an embodiment of the present application.

[0591] As shown in FIG. 26 , the chip 800 includes a processor 810 .

[0592] The processor 810 may call and execute a computer program from the memory to implement the method in the embodiment of the present application.

[0593] As shown in FIG. 26 , the chip 800 may further include a memory 820 .

[0594] The processor 810 can call and execute a computer program from the memory 820 to implement the method in the embodiment of the present application. The memory 820 can be used to store instruction information and can also be used to store code, instructions, etc. executed by the processor 810. The memory 820 can be a separate device independent of the processor 810 or integrated into the processor 810.

[0595] As shown in FIG. 26 , the chip 800 may further include an input interface 830 .

[0596] The processor 810 may control the input interface 830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0597] As shown in FIG. 26 , the chip 800 may further include an output interface 840 .

[0598] The processor 810 may control the output interface 840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0599] It should be understood that the chip 800 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 the various methods of the embodiments of the present application, and can also implement the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0600] It should also be understood that the various components in the chip 800 are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus.

[0601] The processors mentioned above may include but are not limited to:

[0602] General-purpose processor, Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0603] The processor can be used to implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The steps of the methods disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in combination with its hardware, completes the steps of the above method.

[0604] The memories mentioned above include but are not limited to:

[0605] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as 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 DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0606] It should be noted that the memory described herein is intended to encompass these and any other suitable types of memory.

[0607] A computer-readable storage medium is also provided in an embodiment of the present application for storing a computer program. The computer-readable storage medium stores one or more programs, and the one or more programs include instructions, which, when executed by a portable electronic device including multiple applications, can enable the portable electronic device to perform the wireless communication method provided in the present application. Optionally, the computer-readable storage medium can be applied to the network device in the embodiment of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, it is not repeated here. Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiment of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in each method of the embodiment of the present application. For the sake of brevity, it is not repeated here.

[0608] The embodiments of the present application also provide a computer program product, including a computer program. Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, this will not be described in detail here. Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, this will not be described in detail here.

[0609] A computer program is also provided in an embodiment of the present application. When the computer program is executed by a computer, the computer can perform the wireless communication method provided in the present application. Optionally, the computer program can be applied to the network device in the embodiment of the present application. When the computer program is run on the computer, the computer can perform the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, it is not described here. Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiment of the present application. When the computer program is run on the computer, the computer can perform the corresponding processes implemented by the mobile terminal / terminal device in each method of the embodiment of the present application. For the sake of brevity, it is not described here.

[0610] The present application also provides a communication system, which may include the aforementioned terminal devices and network devices to form a communication system 100 as shown in FIG1 . For the sake of brevity, detailed description is omitted here. It should be noted that the term "system" herein may also be referred to as a "network management architecture" or "network system."

[0611] It should also be understood that the terms used in the embodiments of the present application and the appended claims are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present application. For example, the singular forms "a," "said," "above," and "the" used in the embodiments of the present application and the appended claims are intended to include the plural forms, unless the context clearly indicates otherwise.

[0612] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application. If implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0613] Those skilled in the art will also appreciate that, for ease of description and brevity, the specific operating 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. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the division of units, modules, or components in the device embodiments described above is merely a logical functional division, and in actual implementation, other division methods may be used. For example, multiple units, modules, or components can be combined or integrated into another system, or some units, modules, or components can be ignored or not executed. For another example, the units, modules, or components described above as separate / displayed components may or may not be physically separate, that is, they may be located in one place or distributed across multiple network units. Some or all of the units, modules, or components can be selected according to actual needs to achieve the objectives of the embodiments of this application. Finally, it should be noted that the mutual coupling, direct coupling, or communication connection shown or discussed above can be through some interface, indirect coupling, or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0614] The above content is only a specific implementation of the embodiment of the present application, but the scope of protection of the embodiment of the present application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the embodiment of the present application, and they should be included in the scope of protection of the embodiment of the present application. Therefore, the scope of protection of the embodiment of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: The method is applicable to a terminal device, and includes: Acquire performance of the M historical signals by detecting the M historical signals; Based on the performance of the M historical signals, using a target prediction model to predict the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition; Wherein, M and N are both positive integers, and K≤N.

2. The method according to claim 1, characterized in that The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain.

3. The method according to claim 1 or 2, characterized in that If the performance of the M historical signals includes the performance of the M historical signals at the first moment, then: The performance of the N target signals includes: the performance of the N target signals at the first moment; The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

4. The method according to claim 1, wherein The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the time domain.

5. The method according to claim 1 or 4, characterized in that If the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then: The performance of the N target signals includes: the performance of the N target signals in each of the F time units; The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals; The F time units are located after the E time units, and E and F are both positive integers.

6. The method according to claim 1, wherein The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain.

7. The method according to claim 1 or 6, characterized in that If the performance of the M historical signals includes the performance of the M historical signals in each of the E time units, then: The performance of the N target signals includes: the performance of the N target signals in each of the F time units; The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals; The F time units are located after the E time units, and E and F are both positive integers.

8. The method according to claim 7, characterized in that The predicting, based on the performance of the M historical signals in each of the E time units, using the target prediction model, the performance of the N target signals in each of the F time units includes: Based on the performance of the M historical signals in each of the E time units, using the first sub-model in the target prediction model, predict the performance of the N target signals in each of the E time units; and based on the performance of the N target signals in each of the E time units, using the second sub-model in the target prediction model, predict the performance of the N target signals in each of the F time units; or, Based on the performance of the M historical signals in each of the E time units, the second sub-model in the target prediction model is used to predict the performance of the M historical signals in each of the F time units; and based on the performance of the M historical signals in each of the F time units, the first sub-model in the target prediction model is used to predict the performance of the N target signals in each of the F time units.

9. The method according to any one of claims 2, 3, 6, 7 and 8, characterized in that The M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein, the M spatial filters are a subset of the N spatial filters; or, the M spatial filters are partially different from the N spatial filters; or, the M spatial filters and the N spatial filters are different from each other.

10. The method according to any one of claims 1 to 9, characterized in that The historical signal includes a reference signal and / or a physical channel.

11. The method according to claim 10, characterized in that The reference signal includes a cell-specific reference signal and / or a terminal device-specific reference signal.

12. The method according to any one of claims 1 to 11, characterized in that The target signal is a beam failure detection reference signal BFD RS or a physical downlink control channel PDCCH.

13. The method according to claim 11, characterized in that The method further comprises: Based on the performance of the N target signals and the value of K, it is determined whether a beam failure event occurs.

14. The method according to claim 13, characterized in that The determining whether a beam failure event occurs based on the performance of the N target signals and the value of K includes: If the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, it is determined that a beam failure event has occurred; otherwise, it is determined that no beam failure event has occurred.

15. The method according to any one of claims 1 to 11, characterized in that The N target signals are N new beam finding reference signals NBI RS.

16. The method according to claim 15, characterized in that The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: If a beam failure event occurs, the target prediction model is used to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

17. The method according to claim 15 or 16, characterized in that The method further comprises: If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

18. The method according to claim 17, characterized in that The N target signals are RSs configured by the network device.

19. The method according to claim 17, wherein The P target signals include all target signals corresponding to the target frequency band.

20. The method according to any one of claims 15 to 19, characterized in that The method further comprises: If the number of target signals whose performance is greater than or equal to the third preset threshold among the N target signals is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, sending a beam failure recovery request BFRQ to the network device; The BFRQ includes identifiers of the K target signals.

21. The method according to claim 20, characterized in that The method further comprises: After receiving the Q time units of the BFRR, using the spatial domain filters corresponding to the K target signals for data transmission; Wherein, Q is a positive integer.

22. The method according to claim 20, characterized in that The BFRQ also includes information for indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

23. The method according to claim 22, characterized in that The method further comprises: At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission; The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

24. The method according to any one of claims 1 to 23, characterized in that The performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

25. The method according to any one of claims 1 to 24, characterized in that The method further comprises: Sending capability information of the terminal device to the network device; The capability information includes at least one of the following: Information indicating whether the target prediction model is supported; Information indicating whether prediction in the airspace based on the target prediction model is supported; Information indicating whether prediction in the time domain based on the target prediction model is supported; Information of the target prediction model.

26. The method according to any one of claims 1 to 25, characterized in that The method further comprises: Receive configuration information sent by a network device, where the configuration information is used to configure the terminal device to use the target prediction model.

27. A wireless communication method, characterized in that: The method is applicable to a network device, and includes: Receive a beam failure recovery request (BFRQ) sent by a terminal device; The BFRQ includes identifiers of K target signals and information indicating time units of beam failure events corresponding to the K target signals.

28. The method according to claim 27, characterized in that The method further comprises: At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission; The second moment is the moment when the terminal device receives the BFRR, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

29. The method according to claim 27 or 28, characterized in that The method further comprises: Receiving capability information sent by the terminal device; The capability information includes at least one of the following: Information indicating whether the target prediction model is supported; Information indicating whether prediction in the airspace based on the target prediction model is supported; Information indicating whether prediction in the time domain based on the target prediction model is supported; Information of the target prediction model.

30. The method according to any one of claims 27 to 29, characterized in that The method further comprises: Configuration information is sent to the terminal device, where the configuration information is used to configure the terminal device to use the target prediction model.

31. A wireless communication method, characterized in that: The method is applicable to a network device, and includes: Performance of receiving M historical signals sent by the terminal device; Based on the performance of the M historical signals, using a target prediction model to predict the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition; Wherein, M and N are both positive integers, and K≤N.

32. The method according to claim 31, characterized in that The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain.

33. The method according to claim 31 or 32, characterized in that If the performance of the M historical signals includes the performance of the M historical signals at the first moment, then: The performance of the N target signals includes: the performance of the N target signals at the first moment; The K target signals include: at the first moment, the target signal whose performance meets the preset condition among the N target signals.

34. The method according to claim 31, wherein The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the time domain.

35. The method according to claim 31 or 34, characterized in that If the performance of the M historical signals includes the performance of the N target signals in each of the E time units, then: The performance of the N target signals includes: the performance of the N target signals in each of the F time units; The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals; The F time units are located after the E time units, and E and F are both positive integers.

36. The method according to claim 31, wherein The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: Based on the performance of the M historical signals, the target prediction model is used to predict the performance of the N target signals and / or the K target signals in the spatial domain and the time domain.

37. The method according to claim 31 or 36, characterized in that If the performance of the M historical signals includes the performance of the M historical signals in each of the E time units, then: The performance of the N target signals includes: the performance of the N target signals in each of the F time units; The K target signals include: target signals whose performance meets the preset conditions in each time unit of the F time units among the N target signals; The F time units are located after the E time units, and E and F are both positive integers.

38. The method according to claim 37, wherein The predicting, based on the performance of the M historical signals in each of the E time units, using the target prediction model, the performance of the N target signals in each of the F time units includes: Based on the performance of the M historical signals in each of the E time units, using the first sub-model in the target prediction model, predict the performance of the N target signals in each of the E time units; and based on the performance of the N target signals in each of the E time units, using the second sub-model in the target prediction model, predict the performance of the N target signals in each of the F time units; or, Based on the performance of the M historical signals in each of the E time units, the second sub-model in the target prediction model is used to predict the performance of the M historical signals in each of the F time units; and based on the performance of the M historical signals in each of the F time units, the first sub-model in the target prediction model is used to predict the performance of the N target signals in each of the F time units.

39. The method according to any one of claims 32, 33, 36, 37 and 38, characterized in that The M historical signals correspond to M spatial filters, and the N target signals correspond to N spatial filters; wherein, the M spatial filters are a subset of the N spatial filters; or, the M spatial filters are partially different from the N spatial filters; or, the M spatial filters and the N spatial filters are different from each other.

40. The method according to any one of claims 31 to 39, characterized in that The historical signal includes a reference signal and / or a physical channel.

41. The method according to claim 40, wherein The reference signal includes a cell-specific reference signal and / or a terminal device-specific reference signal.

42. The method according to any one of claims 31 to 41, characterized in that The target signal is a beam failure detection reference signal BFD RS or a physical downlink control channel PDCCH.

43. The method according to claim 41, wherein The method further comprises: Based on the performance of the N target signals and the value of K, it is determined whether a beam failure event occurs.

44. The method according to claim 43, wherein The determining whether a beam failure event occurs based on the performance of the N target signals and the value of K includes: If the number of target signals among the N target signals whose performance is less than or equal to the first preset threshold is not 0, or if the value of K is not 0 when the preset condition is less than or equal to the first preset threshold, it is determined that a beam failure event has occurred; otherwise, it is determined that no beam failure event has occurred.

45. The method according to any one of claims 31 to 41, characterized in that The N target signals are N new beam finding reference signals NBI RS.

46. ​​The method according to claim 45, characterized in that The method of predicting the performance of N target signals and / or K target signals whose performance meets a preset condition among the N target signals using a target prediction model based on the performance of the M historical signals includes: If a beam failure event occurs, the target prediction model is used to predict the performance of the N target signals and / or the K target signals based on the performance of the M historical signals.

47. The method according to claim 45 or 46, characterized in that The method further comprises: If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is 0, or the value of K is 0 when the preset condition is greater than or equal to the third preset value, the target prediction model is used to predict the performance of the P target signals and / or the K target signals among the P target signals whose performance meets the preset conditions; wherein the N target signals are a subset of the P target signals.

48. The method according to claim 47, wherein The N target signals are RSs configured by the network device for the terminal device.

49. The method according to claim 47, wherein The P target signals include all target signals corresponding to the target frequency band.

50. The method according to any one of claims 45 to 49, characterized in that The method further comprises: If the number of target signals among the N target signals whose performance is greater than or equal to the third preset threshold is not 0, or if the value of K is not 0 when the preset condition is greater than or equal to the third preset value, an indication message is sent to the terminal device, and the indication message includes the identifiers of the K target signals.

51. The method according to claim 50, characterized in that The method further comprises: After sending Q time units of the indication information, using the spatial domain filters corresponding to the K target signals for data transmission; Wherein, Q is a positive integer.

52. The method according to claim 50, wherein The indication information also includes information for indicating a time unit in which a beam failure event occurs corresponding to the K target signals.

53. The method according to claim 52, characterized in that The method further comprises: At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission; The second moment is the moment of sending the indication information, and the third moment is determined according to the time unit of the occurrence of the beam failure event corresponding to the first target signal.

54. The method according to any one of claims 31 to 53, characterized in that The performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

55. The method according to any one of claims 31 to 54, characterized in that The method further comprises: Receiving capability information sent by the terminal device; The capability information includes at least one of the following: Information indicating whether the target prediction model is supported; Information indicating whether prediction in the airspace based on the target prediction model is supported; Information indicating whether prediction in the time domain based on the target prediction model is supported; Information of the target prediction model.

56. A wireless communication method, characterized in that: The method is applicable to a terminal device, and includes: receiving instruction information sent by the network device; The indication information includes identifiers of K target signals and information for indicating time units in which beam failure events corresponding to the K target signals occur.

57. The method according to claim 56, characterized in that The method further comprises: At a later moment between the second moment and the third moment, using a spatial domain filter corresponding to a first target signal among the K target signals for data transmission; The second moment is the moment when the terminal device receives the indication information, and the third moment is determined according to the time unit of the beam failure event corresponding to the first target signal.

58. The method according to claim 56 or 57, characterized in that The method further comprises: Sending capability information of the terminal device to the network device; The capability information includes at least one of the following: Information indicating whether the target prediction model is supported; Information indicating whether prediction in the airspace based on the target prediction model is supported; Information indicating whether prediction in the time domain based on the target prediction model is supported; Information of the target prediction model.

59. The method according to any one of claims 56 to 58, characterized in that The method further comprises: A capability of sending M historical signals to the network device.

60. The method according to claim 59, wherein The performance of the historical signal or the performance of the target signal includes at least one of the following: layer 1 reference signal received power L1-RSRP, layer 1 signal to interference plus noise ratio L1-SINR, layer 1 reference signal received quality L1-RSRQ, and block error rate BLER.

61. A terminal device, characterized in that: include: an acquiring unit, configured to acquire performance of the M historical signals by detecting the M historical signals; A prediction unit, configured to predict, based on the performance of the M historical signals, the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition using a target prediction model; Wherein, M and N are both positive integers, and K≤N.

62. A network device, characterized in that include: A receiving unit, configured to receive a beam failure recovery request BFRQ sent by a terminal device; The BFRQ includes identifiers of K target signals and information indicating time units of beam failure events corresponding to the K target signals.

63. A network device, characterized in that include: a receiving unit, configured to receive the performance of M historical signals sent by a terminal device; A prediction unit, configured to predict, based on the performance of the M historical signals, the performance of N target signals and / or K target signals among the N target signals whose performance meets a preset condition using a target prediction model; Wherein, M and N are both positive integers, and K≤N.

64. A terminal device, characterized in that: include: A receiving unit, configured to receive instruction information sent by a network device; The indication information includes identifiers of K target signals and information for indicating time units in which beam failure events corresponding to the K target signals occur.

65. A terminal device, characterized in that: include: A transceiver, 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 processor and the transceiver perform the method according to any one of claims 1 to 26 or the method according to any one of claims 56 to 60.

66. A network device, characterized in that include: A transceiver, 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 processor and the transceiver perform the method according to any one of claims 27 to 30 or the method according to any one of claims 31 to 55.

67. A chip, characterized in that: include: A processor for calling and running a computer program from a memory so that a device equipped with the chip performs the method according to any one of claims 1 to 26, the method according to any one of claims 27 to 30, the method according to any one of claims 31 to 55, or the method according to any one of claims 56 to 60.

68. A computer-readable storage medium, characterized in that Used to store a computer program, the computer program causing a computer to perform the method of any one of claims 1 to 26, the method of any one of claims 27 to 30, the method of any one of claims 31 to 55, or the method of any one of claims 56 to 60.

69. A computer program product, characterized in that Comprising computer program instructions that cause a computer to perform the method of any one of claims 1 to 26, the method of any one of claims 27 to 30, the method of any one of claims 31 to 55, or the method of any one of claims 56 to 60.

70. A computer program, characterized in that The computer program causes a computer to perform the method of any one of claims 1 to 26, the method of any one of claims 27 to 30, the method of any one of claims 31 to 55, or the method of any one of claims 56 to 60.

Images