Beam management method and apparatus, terminal device, network device, chip, medium, and program product

Abstract

Embodiments of the present application provide a beam management method and apparatus, a terminal device, and a network device. The method comprises: on the basis of first beam information and second beam information, a terminal device determines third beam information corresponding to a second moment or a third moment; and the terminal device sends the third beam information to a network device. The first beam information is determined by the terminal device by performing measurement on the basis of a first reference signal resource set at a first moment; the second beam information is determined by the terminal device by performing measurement on the basis of a second reference signal resource set at a second moment; the third beam information is beam information corresponding to the first reference signal resource set; the second moment is after the first moment, and the third moment is after the second moment; and the second reference signal resource set comprises fewer reference signal resources than the first reference signal resource set.

Description

Beam management methods, devices, terminal equipment, network equipment, chips, media, and software products Technical Field

[0001] This application relates to the field of mobile communication technology, specifically to a beam management method, apparatus, terminal equipment, network equipment, chip, computer storage medium, and program product. Background Technology

[0002] In the current beam management scheme, in order to obtain the optimal downlink beam, the network device needs to send the reference signal corresponding to each beam in the complete beam set; correspondingly, the terminal device also needs to measure the reference signal corresponding to each beam in the complete beam set and report the measured beam information (such as the index of the optimal beam and the measurement result) to the network device.

[0003] However, if there are many candidate beams for network devices, a large amount of reference signal resources are required, and a long measurement time is needed to obtain the optimal beam (because reference signals of different beams cannot be transmitted simultaneously). This results in a large amount of resource overhead and measurement delay, which in turn affects the uplink and downlink data transmission rates.

[0004] Summary of the Invention

[0005] This application provides a beam management method, apparatus, terminal equipment, network equipment, chip, computer storage medium, and program product.

[0006] In a first aspect, the beam management method provided in the embodiments of this application includes:

[0007] The terminal device determines the third beam information corresponding to the second or third time moment based on the first beam information and the second beam information;

[0008] The terminal device sends the third beam information to the network device;

[0009] Wherein, the first beam information is determined by the terminal device based on a first reference signal resource set at a first moment; the second beam information is determined by the terminal device based on a second reference signal resource set at a second moment; and the third beam information is the beam information corresponding to the first reference signal resource set.

[0010] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0011] Secondly, the beam management method provided in the embodiments of this application includes:

[0012] The network device sends a reference signal on the resource corresponding to the first reference signal resource set at the first moment;

[0013] The network device sends a reference signal on the resource corresponding to the second reference signal resource set at a second time.

[0014] The network device receives the third beam information corresponding to the second or third time moment sent by the terminal device;

[0015] Wherein, the first reference signal resource set is used to determine the first beam information, the second reference signal resource set is used to determine the second beam information, and the third beam information corresponding to the second time or the third time is determined based on the first beam information and the second beam information; the third beam information is the beam information corresponding to the first reference signal resource set;

[0016] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0017] Thirdly, the beam management device provided in this application embodiment is applied to a terminal device, and the device includes:

[0018] The determining unit is configured to determine the third beam information corresponding to the second or third time moment based on the first beam information and the second beam information;

[0019] The first transmitting unit is configured to transmit the third beam information to the network device;

[0020] Wherein, the first beam information is determined by the terminal device based on a first reference signal resource set at a first moment; the second beam information is determined by the terminal device based on a second reference signal resource set at a second moment; and the third beam information is the beam information corresponding to the first reference signal resource set.

[0021] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0022] Fourthly, the beam management device provided in this application embodiment is applied to a network device, and the device includes:

[0023] The second transmitting unit is configured to transmit a reference signal on the resource corresponding to the first reference signal resource set at a first moment;

[0024] The second transmitting unit is further configured to transmit a reference signal on the resource corresponding to the second reference signal resource set at a second time.

[0025] The second receiving unit is configured to receive the third beam information corresponding to the second or third time moment sent by the terminal device.

[0026] Wherein, the first reference signal resource set is used to determine the first beam information, the second reference signal resource set is used to determine the second beam information, and the third beam information corresponding to the second time or the third time is determined based on the first beam information and the second beam information; the third beam information is the beam information corresponding to the first reference signal resource set;

[0027] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0028] Fifthly, the terminal device provided in the embodiments of this application includes a processor and a memory. The memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory to execute the beam management method described above.

[0029] Sixthly, the network device provided in the embodiments of this application includes a processor and a memory. The memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory to perform the beam management method described above.

[0030] The chip provided in this application embodiment is used to implement the beam management method described above.

[0031] Specifically, the chip includes a processor for calling and running a computer program from memory, causing a device equipped with the chip to perform the beam management method described above.

[0032] The computer-readable storage medium provided in this application embodiment is used to store a computer program that causes a computer to execute the beam management method described above.

[0033] The computer program product provided in this application includes computer program instructions that cause a computer to execute the beam management method described above.

[0034] The computer program provided in this application embodiment, when run on a computer, causes the computer to execute the beam management method described above.

[0035] In the beam management method provided in this application embodiment, the terminal device can determine the third beam information corresponding to a second or third time moment based on the first beam information and the second beam information, and report the obtained third beam information to the network device. The first beam information is determined by the terminal device based on a first reference signal resource set at the first time moment; the second beam information is determined by the terminal device based on a second reference signal resource set at the second time moment; the third beam information is the beam information corresponding to the first reference signal resource set; and the second time moment is after the first time moment, and the third time moment is after the second time moment; the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set. In other words, the terminal device can determine the third beam information corresponding to the complete beam set at the current or future time moment (third time moment) based on the first beam information corresponding to the complete beam set at a historical time (first time moment) and the second beam information corresponding to the partial beam set at the current time (second time moment). In this way, when measurements are required, network devices can send only the reference signals corresponding to a portion of the beam set, instead of sending the reference signals corresponding to the complete beam set, thereby reducing the resource overhead and power loss of the reference signals used for beam management. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 is a schematic diagram of a communication architecture provided in an embodiment of this application;

[0038] Figure 2 is a schematic diagram of a CSI reporting method provided in an embodiment of this application;

[0039] Figure 3 is a schematic diagram of a neuron structure provided in an embodiment of this application;

[0040] Figure 4 is a schematic diagram of a neural network structure provided in an embodiment of this application;

[0041] Figure 5 is a schematic flowchart of a beam management method provided in an embodiment of this application;

[0042] Figure 6 is a schematic diagram of a neural network structure provided in an embodiment of this application;

[0043] Figure 7 is a schematic diagram of a neural network structure provided in an embodiment of this application;

[0044] Figure 8 is a schematic diagram of a beam management method provided in an embodiment of this application;

[0045] Figure 9 is a structural schematic diagram of a beam management device 700 provided in an embodiment of this application;

[0046] Figure 10 is a structural schematic diagram of a beam management device 800 provided in an embodiment of this application;

[0047] Figure 11 is a schematic structural diagram of a communication device provided in an embodiment of this application;

[0048] Figure 12 is a schematic structural diagram of a chip according to an embodiment of this application;

[0049] Figure 13 is a schematic block diagram of a communication system provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0051] Figure 1 is a schematic diagram of an application scenario of an embodiment of this application.

[0052] As shown in Figure 1, the communication system 100 may include a terminal device 110 and a network device 120. The network device 120 can communicate with the terminal device 110 via an air interface. Multi-service transmission is supported between the terminal device 110 and the network device 120.

[0053] It should be understood that the embodiments of this application are only illustrated by way of example with communication system 100, but the embodiments of this application are not limited thereto. That is to say, the technical solutions of the embodiments of this 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, etc.

[0054] In the communication system 100 shown in Figure 1, network device 120 may be an access network device that communicates with terminal device 110. The access network device can provide communication coverage for a specific geographical area and can communicate with terminal device 110 (e.g., UE) located within that coverage area.

[0055] Network device 120 may be an evolved Node B (eNB or eNodeB) in a Long Term Evolution (LTE) system, a Next Generation Radio Access Network (NG RAN) device, a base station (gNB) in an NR system, a radio controller in a Cloud Radio Access Network (CRAN), or a relay station, access point, vehicle-mounted device, wearable device, hub, switch, bridge, router, or network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0056] Terminal device 110 can be any terminal device, including but not limited to terminal devices that are connected to network device 120 or other terminal devices via wired or wireless connections.

[0057] For example, the terminal device 110 can refer to an access terminal, user equipment (UE), user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The access terminal can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, IoT device, satellite handheld terminal, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in a 5G network, or terminal device in a future evolved network, etc.

[0058] Terminal device 110 can be used for device-to-device (D2D) communication.

[0059] The wireless communication system 100 may further include a core network device 130 that communicates with the network device 120. This 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 for 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 of both SMF and PGW-C. During network evolution, the aforementioned core network device may also be called by other names, or new network entities may be formed by dividing the core network functions; this embodiment does not limit this.

[0060] The various functional units in the communication system 100 can also establish connections and communicate with each other through the next generation (NG) interface.

[0061] For example, terminal devices establish air interface connections with access network devices through the NR interface for transmitting user plane data and control plane signaling; terminal devices can establish control plane signaling connections with the AMF through NG interface 1 (N1); access network devices, such as next-generation radio access base stations (gNB), can establish user plane data connections with the UPF through NG interface 3 (N3); access network devices can establish control plane signaling connections with the AMF through NG interface 2 (N2); the UPF can establish control plane signaling connections with the SMF through NG interface 4 (N4); the UPF can interact with the data network for user plane data through NG interface 6 (N6); the AMF can establish control plane signaling connections with the SMF through NG interface 11 (N11); and the SMF can establish control plane signaling connections with the PCF through NG interface 7 (N7).

[0062] Figure 1 exemplarily illustrates a network device, a core network device, and two terminal devices. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include other numbers of terminal devices within its coverage area. This application embodiment does not limit this.

[0063] It should be noted that Figure 1 is merely an example illustrating the system to which this application applies. Of course, the method shown in the embodiments of this application can also be applied to other systems. Furthermore, the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship. It should also be understood that "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a related relationship. For example, A instructing B can mean that A directly instructs B, for example, B can be obtained through A; it can also mean that A indirectly instructs B, for example, A instructs C, B can be obtained through C; or it can mean that there is a related relationship between A and B. It should also be understood that "correspondence" mentioned in the embodiments of this application can indicate a direct or indirect correspondence between two things, or an related relationship between two things, or a relationship of instruction and being instructed, configuration and being configured, etc. It should also be understood that the "predefined" or "predefined rules" mentioned in the embodiments of this application can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices), and this application does not limit the specific implementation method. For example, predefined can refer to those defined in a protocol. It should also be understood that in the embodiments of this application, the "protocol" can refer to standard protocols in the field of communication, such as LTE protocol, NR protocol, and related protocols applied to future communication systems, and this application does not limit this.

[0064] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0065] In beam management schemes, terminal devices can report beam information to network devices via CSI.

[0066] The following section details the feedback of Channel State Information (CSI).

[0067] To enable network devices to perform reasonable scheduling, terminal devices can report Channel State Information (CSI) to the network devices. This allows the network devices to determine scheduling information for the terminal devices, such as the transmission layer number, precoding matrix, transmission beam, and modulation / coding scheme. The terminal devices' CSI reporting is based on the CSI reporting configuration indicated by the network devices and the Channel State Information Reference Signal (CSI-RS) sent by the network devices. The uplink resources used for CSI reporting and the downlink reference signal used for CSI measurement are both indicated through the CSI reporting configuration.

[0068] In practical applications, each CSI reporting configuration corresponds to one CSI report. Each CSI report can contain different information such as the Channel State Information Reference Signal Resource Indicator (CSI-RS), Rank Indicator (RI), Precoding Matrix Indicator (PMI), and Channel Quality Indicator (CQI). This information is obtained based on the CSI-RS signals configured and transmitted by the network devices.

[0069] The content / information included in the CSI can be determined through the report quantity information in the CSI reporting configuration. This report quantity information can indicate one of the following report quantities:

[0070] CRI is used to determine the CSI-RS resource currently used for channel measurement and the Interference Measurement Resource (IMR) currently used for interference measurement from multiple CSI-RS resources.

[0071] RI is used to report the recommended number of transport layers.

[0072] PMI is used to determine the recommended precoding matrix from a predefined codebook.

[0073] CQI is used to report the current channel quality and can be determined based on the SINR estimated by the terminal device. The channel portion of SINR is determined based on the non-zero power CSI-RS configured for channel measurement by the network device, while the interference portion is determined based on the CSI-IM or non-zero power CSI-RS configured for interference measurement by the network device. CQI is calculated based on the reported RI and PMI.

[0074] Reference Signal Receiving Power (RSRP) is used to report the RSRP of the SSB or CSI-RS corresponding to the fed-back index, so that the network side can determine the beam used for downlink transmission.

[0075] The Layer Indicator (LI) is used to report the index of the transport layer associated with the Phase Tracking Reference Signals (PTRS).

[0076] RI / PMI / CQI can be determined based on SINR estimated by the terminal equipment. The channel portion of SINR is determined based on non-zero power CSI-RS configured for channel measurement in the network configuration, while the interference portion is determined based on CSI-IM or non-zero power CSI-RS configured for interference measurement in the network configuration. The CSI-RS resources used for channel measurement can include multiple antenna ports to measure the complete downlink channel and thus calculate the CSI.

[0077] In some embodiments, CSI reporting can take three forms: periodic CSI reporting, quasi-persistent CSI reporting, and aperiodic CSI reporting. Referring to Figure 2, periodic CSI reporting is transmitted on the Physical Uplink Control Channel (PUCCH), and its CSI reporting configuration is configured by Radio Resource Control (RRC). After receiving the corresponding RRC configuration, the terminal device periodically reports CSI to the network device.

[0078] Quasi-persistent CSI reporting can be transmitted on the PUCCH or the Physical Uplink Shared Channel (PUSCH). Specifically, the CSI reporting configuration corresponding to CSIs transmitted on the PUCCH is pre-configured by RRC signaling and activated or deactivated by Media Access Control (MAC) layer signaling; the CSI reporting configuration corresponding to CSIs transmitted on the PUSCH is dynamically indicated (activated or deactivated) by Downlink Control Information (DCI). After receiving the activation or indication signaling configured by the network device, the terminal device periodically transmits CSIs on the PUCCH or PUSCH until it receives the deactivation signaling and stops reporting.

[0079] Non-periodic CSI reporting also involves pre-configuring the CSI reporting configuration via RRC signaling, activating a portion of the configuration via MAC layer signaling, and then indicating the CSI reporting configuration for CSI reporting via CSI trigger signaling in DCI. After receiving the CSI trigger signaling, the terminal device reports the corresponding CSI on the scheduled PUSCH in one go according to the indicated CSI reporting configuration.

[0080] Given the tremendous success of artificial intelligence (AI) / machine learning (ML) technologies in areas such as computer vision and natural language processing, the communications field has begun to explore the use of AI / ML technologies to seek new technical solutions to technical challenges that are limited by traditional methods.

[0081] The neural network model will be described in detail below.

[0082] A neural network is a computational model consisting of multiple interconnected neurons. The connections between nodes represent weighted sums from the input signal to the output signal, called weights. Each node performs a weighted summation of different input signals and outputs the result through a specific activation function. Referring to the neuron structure diagram in Figure 3, a1, a2, ..., an and 1 are the neuron's inputs, w1, w2, ..., wn and b represent the weights, Sum represents the summation function, f represents the activation function, and t represents the output result.

[0083] A simple neural network, as shown in Figure 4, consists of an input layer, hidden layers, and an output layer. Through different connections, weights, and activation functions of multiple neurons, different outputs can be generated, thus fitting a mapping relationship from input to output. Each node in the previous level is connected to all its nodes in the next level. This fully connected model can also be called a DNN, or deep neural network.

[0084] A neural network model can be trained and obtained through processes such as dataset construction, training, validation, and testing. Training can be divided into offline training and online training. Offline training can yield a static training result. During the use of the neural network model by network devices or terminal devices, as the terminal devices further measure and / or report, the network devices can continue to collect more data for real-time online training to optimize the neural network model's parameters, achieving better inference and prediction results. After obtaining the neural network model, the corresponding model output can be obtained by inputting the currently obtained information into the model.

[0085] To achieve different communication functions, different AI / ML models can be introduced, defining corresponding inputs and outputs. For example, when using an AI / ML model for CSI feedback, channel information (such as feature vectors, beam information, and delay information) measured based on reference signals can be used as input to the model to infer the corresponding CSI quantized bits. On the network side, there is a corresponding neural network model that uses the CSI quantized bits as input to infer the corresponding channel information. For example, when using AI / ML for data detection, i.e., when using an AI receiver to detect downlink signals, the terminal device can use the received signal (and some additional information such as pilot sequences) as input to the AI ​​model for inference, thereby outputting the detected soft bit symbols (i.e., constellation points). In addition, AI models can also be used for other processes such as localization, channel coding, channel decoding, beam management, and channel estimation.

[0086] In existing technologies, to obtain the optimal downlink beam, the network device needs to send the reference signal corresponding to each beam in the complete beam set, so that the terminal can measure and obtain the complete beam information (i.e., the index and RSRP corresponding to the optimal beam) and indicate it to the network device. If the network device has many candidate beams, this method requires a large amount of reference signal resources and a long measurement time to obtain the optimal beam (because the reference signals of different beams cannot be transmitted simultaneously), which will affect the uplink and downlink data transmission rates.

[0087] Based on this, embodiments of this application provide a beam management method. Specifically, a terminal device can determine the third beam information corresponding to a second or third time point based on first beam information and second beam information, and report the obtained third beam information to a network device. The first beam information is determined by the terminal device through measurement based on a first reference signal resource set at a first time point; the second beam information is determined by the terminal device through measurement based on a second reference signal resource set at a second time point; the third beam information is the beam information corresponding to the first reference signal resource set; and the second time point is after the first time point, and the third time point is after the second time point; the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set. In other words, the terminal device can determine the third beam information corresponding to the complete beam set at the current or future time point (third time point) based on the first beam information corresponding to the complete beam set at a historical time (first time point) and the second beam information corresponding to the partial beam set at the current time (second time point). In this way, when measurements are required, network devices can send only the reference signals corresponding to a portion of the beam set, instead of sending the reference signals corresponding to the complete beam set, thereby reducing the resource overhead and power loss of the reference signals used for beam management.

[0088] To facilitate understanding of the technical solutions of the embodiments of this application, the technical solutions of this application are described in detail below through specific embodiments. The above-mentioned related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0089] Figure 5 illustrates a beam management method provided in an embodiment of this application, which may include the following steps.

[0090] S510, The network device transmits a reference signal on the resource corresponding to the first reference signal resource set at the first moment; correspondingly, the terminal device performs a measurement based on the first reference signal resource set at the first moment to obtain the first beam information.

[0091] S520: The network device transmits a reference signal on the resource corresponding to the second reference signal resource set at the second moment; correspondingly, the terminal device performs measurements based on the second reference signal resource set at the second moment to obtain the second beam information.

[0092] S530: The terminal device determines the third beam information corresponding to the second or third time based on the first beam information and the second beam information;

[0093] S540: The terminal device sends the third beam information corresponding to the second or third time moment, and the network device receives the third beam information corresponding to the second or third time moment.

[0094] It should be noted that the first reference signal resource set and the second reference signal resource set may include multiple reference signal resources. Each reference signal resource is used to transmit one reference signal.

[0095] For example, the first reference signal resource set and the second reference signal resource set are either CSI-RS resource sets or SSB resource sets.

[0096] In some embodiments, the first reference signal resource set and the second reference signal resource set may be of the same type. For example, both the first reference signal resource set and the second reference signal resource set may be CSI-RS resource sets or SSB resource sets.

[0097] In other embodiments, the first reference signal resource set and the second reference signal resource set may also be resource sets of different types. For example, the first reference signal resource set may be a CSI-RS resource set and the second reference signal resource set may be an SSB resource set; or, the first reference signal resource set may be an SSB resource set and the second reference signal resource set may be a CSI-RS resource set.

[0098] In this embodiment of the application, the first reference signal resource set and the second reference signal resource set contain different numbers of reference signal resources. Specifically, the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set.

[0099] For example, suppose the second reference signal resource set contains L reference signal resources and the first reference signal resource set contains N reference signal resources, then L <N。

[0100] It should be noted that network devices can pre-configure a first reference signal resource set and / or a second reference signal resource set for terminal devices. For example, network devices can configure the first reference signal resource set and / or the second reference signal resource set for terminal devices through CSI reporting.

[0101] In this embodiment, the network device transmits a reference signal on the resource corresponding to the first reference signal resource set at a first moment. Accordingly, the terminal device can perform measurements based on the first reference signal resource set at the first moment to obtain the first beam information corresponding to the first reference signal resource set at the first moment (corresponding to step S510).

[0102] It should be noted that the first moment can be a point in time, such as the time domain location of the CSI reference resource corresponding to the first set of reference signal resources; the first moment can also be a time window, that is, the time domain resources occupied by multiple reference signal resources in the first set of reference signal resources.

[0103] It should also be noted that the terminal device performs measurements based on the first set of reference signal resources at the first moment. This can be understood as the terminal device measuring the reference signals sent by the network device on each reference signal resource in the first set of reference signal resources.

[0104] In some embodiments, the first beam information may include any one of the following:

[0105] The measurement results corresponding to each reference signal resource in the first set of reference signal resources;

[0106] The indices of the M1 reference signal resources with the best measurement results in the first set of reference signal resources;

[0107] The indices of the M1 reference signal resources with the best measurement results in the first set of reference signal resources and their corresponding measurement results; where M1 is an integer greater than 0.

[0108] It should be noted that the measurement results may include RSRP and / or SINR, etc., and this application embodiment does not limit them.

[0109] Assuming the first reference signal resource set includes N reference signal resources, in one example, the first beam information may include N measurement results; wherein, the N measurement results in the first beam information can correspond one-to-one with the N reference signal resources in the first reference signal resource set according to the order of the resource index.

[0110] In another example, the first beam information may include the indices of the M1 reference signal resources with the best measurement results; where M1 is an integer less than N, for example, M1 = 2, 4, 8. M1 may be a parameter value predefined by the protocol or a parameter value configured by the network device, and this application embodiment does not limit this.

[0111] In another example, the first beam information may include the indices of the M1 reference signal resources with the best measurement results and the corresponding measurement results for those M1 reference signal resources. M1 is an integer less than N, for example, M1 = 2, 4, 8. M1 can be configured by the network device to the terminal device. For example, in the scenario where M1 = 2, the first beam information may include the index of the best reference signal resource (or the best beam) in the first set of reference signal resources and its corresponding measurement result, as well as the index of the second-best reference signal resource (or the second-best beam) and its corresponding measurement result.

[0112] In this embodiment, the network device can transmit a reference signal on the resource corresponding to the second reference signal resource set at a second time. Correspondingly, the terminal device can perform measurements based on the second reference signal resource set at the second time to obtain the second beam information corresponding to the second reference signal resource set at the second time (corresponding to step S520).

[0113] It should be noted that the second moment can be a point in time, such as the time domain location of the CSI reference resource corresponding to the second set of reference signal resources; the second moment can also be a time window, that is, the time domain resources occupied by multiple reference signal resources in the second set of reference signal resources.

[0114] In some embodiments, the second beam information may include any one of the following:

[0115] The measurement results corresponding to each reference signal resource in the second set of reference signal resources;

[0116] The indices of the M2 reference signal resources with the best measurement results in the second set of reference signal resources;

[0117] The indices of the M2 reference signal resources with the best measurement results in the second set of reference signal resources and their corresponding measurement results; where M2 is an integer greater than 0.

[0118] It should be noted that the measurement results may include RSRP, SINR, etc., and the embodiments of the present application do not limit this.

[0119] Assume that the second reference signal resource set includes L reference signal resources, where L < N, and N is the number of reference signal resources included in the first reference signal resource set.

[0120] In one example, the second beam information may include L measurement results; among them, the L measurement results in the second beam information may correspond one by one to the L reference signal resources in the second reference signal resource set in the order of resource indices.

[0121] In another example, the second beam information may include the indices of M2 reference signal resources with the best measurement results; where M2 is an integer less than L. For example, M2 = 2, 4, 8. M2 may be a parameter value predefined by the protocol or a parameter value configured by the network device, and the embodiments of the present application do not limit this.

[0122] In yet another example, the second beam information may include the indices of M2 reference signal resources with the best measurement results and the corresponding measurement results of these M2 reference signal resources. M2 is an integer less than L. For example, M2 = 2, 4, 8. M2 may be configured by the network device for the terminal device. For example, for the scenario where M2 = 2, the second beam information may include the index and corresponding measurement result of the optimal reference signal resource (or the optimal beam) in the second reference signal resource set, as well as the index and corresponding measurement result of the sub - optimal reference signal resource (or the sub - optimal beam).

[0123] It should be noted that M2 here may be the same as or different from M1 in the above embodiments, and the embodiments of the present application do not limit this.

[0124] In the embodiments of the present application, after obtaining the first beam information and the second beam information, the terminal device may determine the third beam information corresponding to the second moment or the third moment according to the first beam information and the second beam information (corresponding to step S530).

[0125] It should be noted that the third beam information is the beam information corresponding to the first reference signal resource set.

[0126] In some embodiments, the third beam information may include:

[0127] The indices of the K optimal reference signal resources in the first reference signal resource set; or,

[0128] The indices of the K optimal reference signal resources in the first reference signal resource set and the corresponding estimated measurement results;

[0129] Where K is an integer greater than 0.

[0130] It should be noted that K < N, where N is the total number of reference signal resources included in the first reference signal resource set.

[0131] It should be noted that K and M1 may be the same or different, and K and M2 may be the same or different. The embodiments of the present application do not limit this.

[0132] It should also be noted that the measurement results may include RSRP, SINR, etc. The embodiments of the present application do not limit this.

[0133] In one implementation, the third beam information is the index of the K reference signal resources with the highest RSRP / SINR estimation values in the first reference signal resource set. Alternatively, the third beam information is the index of the K reference signal resources with the highest RSRP / SINR estimation values in the first reference signal resource set and the corresponding RSRP / SINR estimation values of the resources.

[0134] It should be noted that the content included in the third beam information can be configured by the network device. Exemplarily, the network device can configure the content included in the third beam information for the terminal device through reportQuantity in the CSI report configuration.

[0135] In the embodiments of the present application, the second moment may be after the first moment, and the third moment is after the second moment. Here, the second moment being after the first moment can be understood as the time domain resources occupied by the second reference signal resource set being after the time domain resources occupied by the first reference signal resource set, or the CSI reference resources corresponding to the second reference signal resource set being after the CSI reference resources corresponding to the first reference signal resource set. The third moment being after the second moment can be understood as the third moment being after the time domain resources occupied by the second reference signal resource set, or the third moment being after the CSI reference resources corresponding to the second reference signal resource set.

[0136] In some embodiments, the first moment can be understood as a historical moment, the second moment can be understood as the current moment, and the third moment can be understood as a future moment. Exemplarily, the third moment may be after the moment when the terminal device sends the third beam information, or rather, the third moment is after the terminal device executes step S540.

[0137] It should be noted that in beam management measurement and reporting, reference signal resources are typically used to associate beams. For example, different beams can be indicated using different reference signal resource indices. In this embodiment, the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set; this can be understood as the second reference signal resource set corresponding to fewer beams than the first reference signal resource set. In some embodiments, the first reference signal resource set can be understood as a complete beam set, which may contain complete beams, while the second reference signal resource set can be understood as a partial beam set, which contains partial beams.

[0138] In one scenario (hereinafter referred to as Scenario 1), the terminal device determines the third beam information corresponding to the first reference signal resource set at the second time, based on the first beam information corresponding to the first reference signal resource set at the first time and the second beam information corresponding to the second reference signal resource set at the second time. This scenario can be understood as the terminal device determining the third beam information corresponding to the complete beam set at the current time, based on the first beam information corresponding to the complete beam set at a historical time and the second beam information corresponding to the partial beam set at the current time. In other words, Scenario 1 can recover the beam information corresponding to the complete beam set at the current time; that is, Scenario 1 can be used for beam information recovery.

[0139] In another scenario (hereinafter referred to as Scenario 2), the terminal device determines the third beam information corresponding to the first reference signal resource set at the third time, based on the first beam information corresponding to the first reference signal resource set at the first time and the second beam information corresponding to the second reference signal resource set at the second time. This scenario can be understood as the terminal device determining the third beam information corresponding to the complete beam set at a future time based on the first beam information corresponding to the complete beam set at a historical time and the second beam information corresponding to the partial beam set at the current time. In other words, Scenario 2 can predict the beam information corresponding to the complete beam set at a future time, meaning Scenario 1 can be used for beam prediction.

[0140] In this embodiment of the application, the terminal device can report the third beam information corresponding to the second or third time moment to the network device, so that the network device can perform subsequent downlink beamforming based on the third beam information.

[0141] In some embodiments, the terminal device may report the third beam information corresponding to the second or third time moment as CSI to the network device.

[0142] For example, network devices can configure a first reference signal resource set and a second reference signal resource set, the content of the third beam information, and the reporting method of the third beam information (refer to the periodic / semi-persistent / aperiodic CSI reporting shown in Figure 2) for terminal devices via CSI reporting configuration. Correspondingly, the terminal device can measure the first and second reference signal resource sets according to the CSI reporting configuration to obtain the corresponding first and second beam information. After obtaining the third beam information based on the first and second beam information, the terminal device can report the third beam information to the terminal device according to the reporting method indicated by the CSI reporting configuration.

[0143] In some embodiments, the network device receives the third beam information corresponding to the second or third time point, and can determine the optimal reference signal resource (beam) and the corresponding RSRP in the first reference signal resource set at the current or future time point. Then, the network device can use the transmission beam of the optimal reference signal resource as the transmission beam used for subsequently transmitting other downlink signals, and configure the corresponding reference signal resource as the QCL source signal to the terminal device.

[0144] The beam management method provided in this application allows network devices to transmit only a portion of the reference signals corresponding to the beam set at the current moment. Correspondingly, terminal devices can determine the third beam information corresponding to the complete beam set at the current or future moment based on the first beam information corresponding to the complete beam set at a historical moment and the second beam information corresponding to the partial beam set at the current moment. This eliminates the need for network devices to transmit the reference signals corresponding to the complete beam set at a high frequency, thereby reducing the resource overhead and power loss of the reference signals used for beam management.

[0145] In some embodiments, the beam management method provided in this application further includes:

[0146] S500: The terminal device sends capability information to the network device. This capability information is used to indicate that the terminal device has the ability to recover and / or predict beam information based on partial beam information.

[0147] It should be noted that step 500 can be executed before S510 or before S520, and this application embodiment does not limit this.

[0148] Understandably, prior to S510 or S520, terminal devices could instruct network devices on capability information indicating their ability to recover and / or predict beam information based on partial beam information. In other words, capability information could indicate whether the terminal device could determine the beam information corresponding to the complete beam set at the current or future time based on the beam information corresponding to the complete beam set at a historical time and the beam information corresponding to the partial beam set at the current time.

[0149] If the terminal device indicates that it has this capability, then the terminal device can determine the beam information corresponding to the complete beam set at the current or future time using methods S510 to S540. In this case, the network device configures the corresponding CSI reporting configuration, enabling the terminal device to execute the aforementioned beam management method, thereby reducing reference signal resource overhead. If the terminal device indicates that it does not have this capability, then the terminal device needs to determine the beam information based on the traditional beam management method, that is, based on the reference signal corresponding to the complete beam set.

[0150] In some embodiments, in addition to the difference in the number of resources contained in the first reference signal resource set and the second reference signal resource set, the periodic configuration and / or frequency domain density of the first reference signal resource set and the second reference signal resource set may also be different.

[0151] For example, the periodic configuration and / or frequency domain density of the first reference signal resource set and the second reference signal resource set are different, and may include one or more of the following:

[0152] The first reference signal resource set and the second reference signal resource set contain periodic reference signal resources, and the period of the reference signal resources in the first reference signal resource set is greater than the period of the reference signal resources in the second reference signal resource set;

[0153] The frequency domain density of the first reference signal resource set is less than that of the second reference signal resource set;

[0154] The first set of reference signal resources contains periodic reference signal resources, and the second set of reference signal resources contains non-periodic or semi-persistent reference signal resources;

[0155] The first set of reference signal resources contains aperiodic reference signal resources, and the second set of reference signal resources contains periodic or semi-persistent reference signal resources.

[0156] It should be noted that the first reference signal resource set can be understood as a complete beam set, while the second reference signal resource set can be understood as a partial beam set.

[0157] In some embodiments, if both the first reference signal resource set and the second reference signal resource set include periodic reference signals, in order to reduce the resource overhead and power loss of the reference signals used for beam management, the period of the reference signal resources in the first reference signal resource set is shorter than the period of the reference signal resources in the second reference signal resource set. That is, the network device can transmit the reference signal corresponding to the complete beam set (first reference signal resource set) at a lower frequency and transmit the reference signal corresponding to a portion of the beam set (second reference signal resource set) at a higher frequency.

[0158] In some embodiments, the first reference signal resource set may include periodic reference signal resources, and the second reference signal resource set may include non-periodic or semi-persistent reference signal resources. That is, the network device may periodically transmit reference signals corresponding to the complete beam set (the first reference signal resource set) to obtain first beam information. Furthermore, based on beam management needs (e.g., when the communication environment changes significantly, or when beam recovery performance is unsatisfactory), the network device may also, upon request from the terminal device or triggered proactively by the network device, transmit reference signals corresponding to a portion of the beam set (the second reference signal resource set) to the terminal device once, or semi-persistently, to obtain second beam information. This avoids the resource overhead and power loss caused by continuously transmitting reference signals corresponding to the second reference signal resource set.

[0159] In contrast to the previous embodiment, the first reference signal resource set includes aperiodic reference signal resources, while the second reference signal resource set includes periodic or semi-persistent reference signal resources. That is, the network device can periodically transmit reference signals corresponding to a portion of the beam set (the second reference signal resource set) to acquire second beam information. Furthermore, based on beam management needs (e.g., when the communication environment changes significantly, or when beam recovery performance is unsatisfactory), the network device can also, upon request from the terminal device or proactive triggering by the network device, transmit reference signals corresponding to the complete beam set (the first reference signal resource set) to the terminal device once, or semi-persistently transmit reference signals corresponding to the complete beam set (the first reference signal resource set) to the terminal device, to acquire first beam information. This avoids the resource overhead and power loss caused by continuously transmitting reference signals corresponding to the first reference signal resource set.

[0160] In some embodiments, there is an association between the first reference signal resource set and the second reference signal resource set.

[0161] For example, the association between the first reference signal resource set and the second reference signal resource set includes any one of the following:

[0162] The reference signal resources in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set;

[0163] The first reference signal resource set and the second reference signal resource set belong to the same reference signal resource set, and the period of the first reference signal resource set is different from the period of the second reference signal resource set;

[0164] Each reference signal resource in the second set of reference signal resources is quasi-co-addressable (QCL) with a reference signal resource in the first set of reference signal resources.

[0165] In some embodiments, the second reference signal resource set may be a subset of the first reference signal resource set, and all resources in the second reference signal resource set are included in the first reference signal resource set. That is, the reference signal resources included in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set.

[0166] In some embodiments, the first reference signal resource set and the second reference signal resource set are contained within the same reference signal resource set. That is, the network device can configure a reference signal resource set (such as a CSI-RS resource set or an SSB resource set) that includes both the first and second reference signal resource sets. The periods of the reference signal resources in the first and second reference signal resource sets are different. The periods of the reference signal resources in the second and first reference signal resource sets are shorter, while the periods of the reference signal resources in the first and second reference signal resource sets are longer. In other words, the network device can transmit the reference signal corresponding to the complete beam set (the first reference signal resource set) at a lower frequency and transmit the reference signal corresponding to a portion of the beam set (the second reference signal resource set) at a higher frequency.

[0167] In some embodiments, each reference signal resource in the second reference signal resource set shares a quasi-co-located QCL with one reference signal resource in the first reference signal resource set. That is, for each reference signal resource in the second reference signal resource set, the network device configures a reference signal resource in the first reference signal resource set with its QCL (i.e., as a QCL reference source signal). Based on the QCL relationship, the terminal device can determine which resources in the second reference signal resource set and the first reference signal resource set use the same beam.

[0168] It should be noted that the above-mentioned association between the first reference signal resource set and the second reference signal resource set can be predefined by the protocol. For example, the reference signal resources in the second reference signal resource set can be predefined as reference signal resources with odd resource indices in the first reference signal resource set; or, the first reference signal resource set can be predefined to include the first two-thirds of the reference signal resources in the CSI-RS resource set or SSB resource set configured by the network device, and the second reference signal resource set can include the last one-third of the reference signal resources.

[0169] It should also be noted that the above association between the first reference signal resource set and the second reference signal resource set can be configured by the network device. For example, the network device can send first information, and correspondingly, the terminal device receives the first information; the first information is used to indicate the association between the first reference signal resource set and the second reference signal resource set.

[0170] Understandably, network devices can use the first information to indicate the association between the first set of reference signal resources and the second set of reference signal resources.

[0171] For example, if each reference signal resource in the second reference signal resource set is a quasi-co-located (QCL) with a reference signal resource in the first reference signal resource set, the first information may carry L resource indices, where L is the total number of reference signal resources in the second reference signal resource set; wherein, the L resource indices indicated by the first information correspond one-to-one with the reference signal resources in the second reference signal resource set, and each resource index indicates a reference signal resource in the first reference signal resource set.

[0172] For example, a network device is configured with a CSI-RS resource set. The first information may carry a resource index value. Reference signal resources in the CSI-RS resource set whose index values ​​are less than the index value indicated by the first information belong to the first reference signal resource set, and reference signal resources in the CSI-RS resource set whose index values ​​are greater than or equal to the index value indicated by the first information belong to the second reference signal resource set. The first information may also indicate two periods, corresponding to the period of the first reference signal resource and the period of the second reference signal resource, respectively.

[0173] For example, if the reference signal resources in the second set of reference signal resources are part of the reference signal resources in the first set of reference signal resources, then the first information can indicate the position information of the second set of reference signal resources in the first set of reference signal resources. For example, the position information can use a bitmap to indicate the position of the reference signal resources in the second set of reference signal resources in the first set of reference signal resources, with each bit corresponding to a resource in the first set of reference signal resources. Another example is that the position information can use an indicator pattern to indicate the second set of reference signal resources from several predefined mapping patterns. Yet another example is that the first information can indicate that the second set of reference signal resources is the (n(K+1)th)th resource in the first set of reference signal resources, where K is indicated by the first information, n is a non-negative integer, and the value of n ranges from [0, N / K].

[0174] It should be noted that if the reference signal resources in the second reference signal resource set are part of the reference signal resources in the first reference signal resource set, the terminal device can determine the second reference signal resource set from the first reference signal resource set based on the first information. In this way, the network device can configure only the first reference signal resource set, thus eliminating the need for dedicated signaling to configure the second reference signal resource set. This reduces the signaling overhead of the network device.

[0175] It should be noted that the terminal device can determine the third beam information corresponding to the second or third moment based on the AI ​​model.

[0176] The following sections describe the detailed process of how the terminal device determines the third beam information from the perspectives of scenario 1 and scenario 2, respectively.

[0177] In scenario 1 (corresponding to the beam information recovery scenario), the terminal device can determine the third beam information corresponding to the first reference signal resource set at the second time (current time) based on the first beam information corresponding to the first reference signal resource set at the first time and the second beam information corresponding to the second reference signal resource set at the second time.

[0178] For scenario 1, in one possible implementation, the terminal device in S530 determines the third beam information corresponding to the second or third time step based on the first and second beam information. This can be achieved in the following way:

[0179] The terminal device uses the first beam information and the second beam information as input to the first AI model, and outputs the third beam information corresponding to the second time step through the first AI model.

[0180] It should be noted that the first AI model can be constructed based on the neurons shown in Figure 3 and the neural network model shown in Figure 4.

[0181] For example, the first AI model can be a neural network model as shown in Figure 6. This model is an optimal beam prediction model, which can be considered to solve a multi-classification problem. This model can be used to fit the relationship between the first beam information and the second beam information to the optimal K beams (pairs) in the complete beam set (first reference signal resource set). The first beam information and the second beam information can be used as inputs to the model, and the output can be the indices of the optimal K beams (pairs) selected from the complete beam set (first reference signal resource set), such as the K beams (pairs) with the highest RSRP or SINR in the first reference signal resource set.

[0182] For example, the first AI model can also be another neural network model as shown in Figure 7. This model is an optimal beam quality prediction model, which can be understood as a linear regression problem. The input part of this model is the same as the input of the model shown in Figure 6. The difference is that the output of this model is K (K≥1) optimal RSRPs or SINRs, and K beam (pair) indices corresponding to the K optimal RSRPs or SINRs.

[0183] It should be noted that the first AI model can be trained through processes such as dataset construction, training, validation, and testing.

[0184] It should also be noted that the first AI model can be trained in advance through offline training and / or online training.

[0185] It should be understood that the input parameters of the first AI model may include:

[0186] The RSRP / SINR measurement value corresponding to each reference signal resource in the first reference signal resource set at the first moment; or...

[0187] The M1 reference signal resource indices with the highest RSRP / SINR measurements in the first reference signal resource set at the first moment; or...

[0188] The indexes of the M1 reference signal resources with the highest RSRP / SINR measurements in the first reference signal resource set at the first moment, and their corresponding RSRP / SINR values.

[0189] In addition, the input parameters of the first AI model may also include:

[0190] The RSRP / SINR measurement value corresponding to each reference signal resource in the second reference signal resource set at the second time; or...

[0191] The M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set at the second time; or...

[0192] The indexes of the M2 reference signal resources with the highest RSRP / SINR measurements in the second reference signal resource set at the second time step, and their corresponding RSRP / SINR.

[0193] In some embodiments, the output parameters of the first AI model may include the index of the recommended (optimal) reference signal resource in the first reference signal resource set at the second time and / or the RSRP / SINR estimate of the recommended (optimal) reference signal resource.

[0194] In some embodiments, the input parameters of the first AI model may further include one or more of the following:

[0195] The location information of the second reference signal resource set within the first reference signal resource;

[0196] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0197] Considering the consistency between model training and inference, different positional relationships and / or QCL relationships between the first and second reference signal resource sets may affect the inference performance of the AI ​​model. Therefore, the terminal device can use the positional relationships and / or QCL relationships between the first and second reference signal resource sets as input parameters of the first AI model. In this way, the third beam information output by the first AI model can better match the current beam configuration, which can significantly improve the reliability of the third beam information inference.

[0198] In some embodiments, the first AI model is determined based on one or more of the following:

[0199] The network device sends a second message; wherein the second message is used to instruct the first AI model;

[0200] The location information of the second reference signal resource set within the first reference signal resource;

[0201] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0202] In some embodiments, the first AI model may be pre-configured by the network device for the terminal device. For example, the network device may configure the first AI model from among the AI ​​models supported by the terminal device by indicating a model ID, function ID, dataset ID, etc.

[0203] In some embodiments, different positional relationships and / or QCL relationships between the first and second reference signal resource sets can correspond to different AI models. Since different network devices may use different beamforming methods, corresponding AI models can be pre-set / trained for different positional relationships and / or QCL relationships. Thus, before determining the third beam information in S530, the terminal device can determine the first AI model to use based on the positional relationships and / or QCL relationships between the first and second reference signal resource sets. This allows the first AI model to effectively match the current beam direction, beamforming method, and other information, significantly improving the reliability of third beam information inference.

[0204] In some embodiments, the network device can configure candidate AI models for the terminal device (e.g., indicating multiple candidate AI models from the AI ​​models supported by the terminal device through model ID, function ID, dataset ID, etc.), and the candidate AI models may include the first AI model. Accordingly, the terminal device can determine the first AI model from the candidate AI models configured by the network device based on the positional relationship and / or QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0205] Understandably, in this embodiment, the terminal device can determine the first AI model based on the different positional relationships and / or QCL relationships between the first reference signal resource set and the second reference signal resource set. The first AI model can be used in different cells and different network devices, thus avoiding model interaction between the terminal device and the network device, thereby saving a significant amount of signaling and time related to model management.

[0206] For scenario 1, in another possible implementation, the S530 terminal device determines the third beam information corresponding to the second or third time moment based on the first and second beam information, which can also be achieved in the following way:

[0207] The terminal device determines the second AI model based on the first beam information;

[0208] The terminal device uses the second beam information as input to the second AI model, and outputs the third beam information corresponding to the second time step through the second AI model.

[0209] It should be noted that the second AI model can be constructed based on the neurons shown in Figure 3 and the neural network model shown in Figure 4.

[0210] For example, the second AI model can be a neural network model as shown in Figure 6. This model is an optimal beam prediction model, which can be considered to solve a multi-classification problem. The second AI model can be used to fit the relationship between the second beam information and the optimal K beams (pairs) in the complete beam set (first reference signal resource set). The second beam information can be used as the input to the model, and the output can be the indices of the optimal K beams (pairs) selected from the complete beam set (first reference signal resource set), such as the K beams (pairs) with the highest RSRP or SINR in the first reference signal resource set.

[0211] For example, the first AI model can also be another neural network model as shown in Figure 7, which is an optimal beam quality prediction model, and can be understood as a linear regression problem. The input of the second AI model can be the second beam information. Unlike the neural network model shown in Figure 7, the output is K (K≥1) optimal RSRPs or SINRs, and K beam (pair) indices corresponding to the K optimal RSRPs or SINRs.

[0212] It should be noted that the second AI model can be trained through processes such as dataset construction, training, validation, and testing.

[0213] It should also be noted that the second AI model can be trained in advance through offline training and / or online training.

[0214] In this embodiment, the first reference signal resource set can be understood as a complete beam set. Therefore, the first beam information corresponding to the first reference signal resource set can reflect information such as beam direction, beamforming method, and channel environment to a certain extent. The second AI model determined by the terminal device based on the first beam information can match the current beam direction, beamforming method, and channel environment information well, which can significantly improve the reliability of the third beam information inference.

[0215] In some embodiments, different first beam information (e.g., different optimal RSRP measurements) can correspond to different AI models. The terminal device can determine the second AI model corresponding to the current first beam information from among the AI ​​models supported by the terminal device, based on the first beam information.

[0216] In some embodiments, a second AI model can be determined using an AI model. Specifically, a model for determining the second AI model (referred to as the fifth AI model in this application embodiment) can be trained in advance. In this way, the terminal device can input the first beam information into the fifth AI model, and the fifth AI model outputs an AI model ID or an AI model index value to obtain the second AI model.

[0217] It should be noted that the terminal device can determine the second AI model based solely on the first beam information. Alternatively, the terminal device can combine the first beam information with one or more of the following to determine the second AI model:

[0218] The third information sent by the network device; the third information is used to indicate the candidate AI model; the candidate AI model includes the second AI model;

[0219] The location information of the second reference signal resource set within the first reference signal resource;

[0220] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0221] In some embodiments, the network device may pre-configure multiple candidate AI models for the terminal device, and the multiple candidate AI models may include a second AI model. For example, the network device may configure multiple candidate AI models by indicating model ID, function ID, dataset ID, etc. The terminal device can determine the second AI model from the multiple candidate AI models configured by the network device based on the first beam information.

[0222] In other embodiments, the terminal device can select a second AI model from among the AI ​​models it supports based on the first beam information and the positional relationship and / or QCL relationship between the first and second reference signal resource sets. For example, the terminal device can select a subset of AI models from among its supported AI models based on the first beam information, and then select the final second AI model from the subset of AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets. Alternatively, the terminal device can select a subset of AI models from among its supported AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets, and then select the final second AI model from the subset of AI models based on the first beam information.

[0223] In some other embodiments, the terminal device can select a second AI model for final use from multiple candidate AI models configured by the network device based on the first beam information and the positional relationship and / or QCL relationship between the first reference signal resource set and the second reference signal resource set. For example, the terminal device can select a subset of AI models from multiple candidate AI models configured by the network device based on the first beam information, and then select the second AI model for final use from the subset of AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets. Alternatively, the terminal device can select a subset of AI models from multiple candidate AI models configured by the network device based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets, and then select the second AI model for final use from the subset of AI models based on the first beam information.

[0224] In this embodiment of the application, after the terminal device determines the second AI model, it can use the second beam information as the input of the second AI model, and output the third beam information corresponding to the first reference signal resource set at the second time (current time) through the second AI model.

[0225] It should be understood that the input references for the second AI model may include:

[0226] The RSRP / SINR measurement value corresponding to each reference signal resource in the second reference signal resource set at the second time; or...

[0227] The M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set at the second time; or...

[0228] The indexes of the M2 reference signal resources with the highest RSRP / SINR measurements in the second reference signal resource set at the second time step, and the corresponding RSRP / SINR measurements.

[0229] Accordingly, the output parameters of the second AI model may include: the index of the recommended (optimal) reference signal resource in the first reference signal resource set at the second time step and / or the RSRP / SINR estimate of the recommended (optimal) reference signal resource.

[0230] It should be noted that the input parameters of the second AI model also include one or more of the following:

[0231] The location information of the second reference signal resource set within the first reference signal resource;

[0232] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0233] Considering the consistency between model training and inference, different positional relationships and / or QCL relationships between the first and second reference signal resource sets may affect the inference performance of the AI ​​model. Therefore, the terminal device can use the positional relationships and / or QCL relationships between the first and second reference signal resource sets as input parameters of the second AI model. In this way, the third beam information output by the second AI model can better match the current beam configuration, which can significantly improve the reliability of the third beam information inference.

[0234] Understandably, in this embodiment, the terminal device can determine the second AI model based on the first beam information. The determined second AI model can be used in different cells and different network devices, and model interaction between the terminal device and the network device can be avoided, thereby saving a significant amount of signaling and time related to model management.

[0235] As a specific implementation, for example, when the period of the first reference signal resource set is an integer multiple of the period of the second reference signal resource set, the terminal device receives the second reference signal resource set simultaneously with the first reference signal resource set. In this case, the first beam information and the second beam information correspond to the same time (i.e., the first time and the second time are the same). The terminal device can directly obtain the third beam information (such as the optimal beam index and RSRP value) at the same time based on the first beam information (complete beam information, such as the RSRP values ​​of each beam), without needing the second beam information. Alternatively, the terminal device can still use the method of this invention to obtain the third beam information based on the first beam information, the second beam information, and the first / second AI model, but the reliability of the third beam information is not as good as the former method. Which method is used depends on the terminal implementation.

[0236] In scenario 2 (corresponding to beam prediction scenario), the terminal device can determine the third beam information corresponding to the first reference signal resource set at the third time (i.e., the future time) based on the first beam information corresponding to the first reference signal resource set at the first time and the second beam information corresponding to the second reference signal resource set at the second time.

[0237] For scenario 2, in one possible implementation, S530 determines the third beam information corresponding to the second or third time step based on the first and second beam information, including:

[0238] The terminal device takes the first beam information and multiple second beam information as inputs to the third AI model, and outputs the third beam information corresponding to the third time moment through the third AI model.

[0239] It should be noted that the network device can transmit reference signals multiple times based on the second reference signal resource set between the first and third time points. For example, the second reference signal resource set includes periodic CSI-RS resources, and the network device needs to periodically transmit CSI-RS on the second reference signal resource set, resulting in multiple periodic CSI-RS transmissions between the first and third time points. Alternatively, the second reference signal resource set can also be aperiodic CSI-RS resources, and the network device can trigger multiple transmissions on the second reference signal resource set via DCI for beam information estimation at the third time point.

[0240] Accordingly, the terminal device can measure multiple reference signals transmitted by the network device on the second reference signal resource set to obtain multiple second beam information. These multiple second beam information are obtained by the terminal device measuring the second reference signal resource set at multiple second moments. Different second beam information corresponds to different second moments. Furthermore, all multiple second moments are after the first moment and before the third moment.

[0241] It should be noted that the third AI model can be constructed based on the neurons shown in Figure 2 and the neural network model shown in Figure 3.

[0242] For example, the third AI model can be a neural network model as shown in Figure 6. This model is an optimal beam prediction model, which can be considered to solve a multi-classification problem. The third AI model can be used to fit the relationship between the first beam information and multiple second beam information to the optimal K beams (pairs) in the complete beam set (first reference signal resource set). The first beam information and multiple second beam information can be used as inputs to the model, and the output can be the indices of the optimal K beams (pairs) selected from the complete beam set (first reference signal resource set), such as the K beams (pairs) with the highest RSRP or SINR in the first reference signal resource set.

[0243] For example, the third AI model can also be another neural network model as shown in Figure 7. This model is an optimal beam quality prediction model, which can be understood as a linear regression problem. The input of the third AI model can be the first beam information and multiple second beam information. The difference is that the output of the third AI model is K (K≥1) optimal RSRP or SINR, and K beam (pair) indices corresponding to the K optimal RSRP or SINR.

[0244] It should be noted that the third AI model can be trained through processes such as dataset construction, training, validation, and testing.

[0245] It should also be noted that the third AI model can be trained in advance through offline training and / or online training.

[0246] In this embodiment of the application, the input parameters of the third AI model may include:

[0247] The RSRP / SINR measurement value corresponding to each reference signal resource in the first reference signal resource set at the first moment; or...

[0248] The M1 reference signal resource indices with the highest RSRP / SINR measurements in the first reference signal resource set at the first moment; or...

[0249] The indexes of the M1 reference signal resources with the highest RSRP / SINR measurements in the first reference signal resource set at the first moment, and their corresponding RSRP / SINR measurements.

[0250] In addition, the input parameters of the third AI model may also include:

[0251] RSRP measurements corresponding to each reference signal resource in the second reference signal resource set at each of multiple second time points; or,

[0252] Multiple second time points, in each second time point, the M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set; or,

[0253] Multiple second time points: In each second time point, the M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set, and the corresponding RSRP / SINR measurements.

[0254] In this embodiment of the application, the output parameters of the third AI model include the index of the recommended (optimal) reference signal resource in the first reference signal resource set at the third time and / or the RSRP / SINR estimate of the recommended (optimal) reference signal resource.

[0255] Understandably, the third moment occurs after the second moment, and also after the time when the terminal device reports the third beam information. In other words, the third beam information at the third moment is the beam information of a future moment predicted by the terminal device, not the current or previous beam information.

[0256] It should be understood that multiple second beam information is measured at multiple second moments. Therefore, multiple second beam information can reflect, to some extent, the changes in beam direction, beamforming method, and channel environment over time. The terminal device can use the first beam information and multiple second beam information as input to the third AI model, which can more accurately predict the third beam information corresponding to the first reference signal resource set at future moments.

[0257] In some embodiments, the input parameters of the third AI model may also include one or more of the following:

[0258] The location information of the second reference signal resource set within the first reference signal resource;

[0259] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0260] Considering the consistency between model training and inference, the different positional relationships and / or QCL relationships between the first and second reference signal resource sets may affect the inference performance of the AI ​​model. Therefore, the terminal device can use the positional relationships and / or QCL relationships between the first and second reference signal resource sets as input parameters of the third AI model. In this way, the third beam information output by the third AI model can better match the beam configuration at the third time moment, which can significantly improve the reliability of the third beam information inference.

[0261] In some embodiments, the third AI model is determined based on one or more of the following:

[0262] The second information sent by the network device; wherein the second information is used to instruct the third AI model;

[0263] The location information of the second reference signal resource set within the first reference signal resource;

[0264] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0265] In some embodiments, the third AI model may be pre-configured by the network device to the terminal device. For example, the network device may configure the third AI model from among the AI ​​models supported by the terminal device by indicating a model ID, function ID, dataset ID, etc.

[0266] In some embodiments, different positional relationships and / or QCL relationships between the first and second reference signal resource sets can correspond to different AI models. Since different network devices may use different beamforming methods, corresponding AI models can be pre-set / trained for different positional relationships and / or QCL relationships. Thus, before determining the third beam information in S530, the terminal device can determine the third AI model to use based on the positional relationships and / or QCL relationships between the first and second reference signal resource sets. This allows the third AI model to match the current beam direction, beamforming method, and other information well, significantly improving the reliability of third beam information inference.

[0267] In some embodiments, the network device can configure candidate AI models for the terminal device (e.g., indicating multiple candidate AI models from the AI ​​models supported by the terminal device through model ID, function ID, dataset ID, etc.), and the candidate AI models may include the third AI model. Accordingly, the terminal device can determine the third AI model from the candidate AI models configured by the network device based on the positional relationship and / or QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0268] Understandably, in this embodiment, the terminal device can determine the third AI model based on the different positional relationships and / or QCL relationships between the first reference signal resource set and the second reference signal resource set. The third AI model can be used in different cells and different network devices, thus avoiding model interaction between the terminal device and the network device, thereby saving a significant amount of signaling and time related to model management.

[0269] For scenario 2, in another possible implementation, S530 determines the third beam information corresponding to the second or third time step based on the first and second beam information, including:

[0270] The terminal device determines the fourth AI model based on the first beam information;

[0271] The terminal device uses multiple second beam information as input to the fourth AI model, and outputs the third beam information corresponding to the third time step through the fourth AI model.

[0272] It should be noted that the fourth AI model can be constructed based on the neurons shown in Figure 3 and the neural network model shown in Figure 4.

[0273] For example, the fourth AI model can be a neural network model as shown in Figure 6. This model is an optimal beam prediction model, which can be considered to solve a multi-classification problem. The fourth AI model can be used to fit the relationship between multiple second beam information and the optimal K beams (pairs) in the complete beam set (first reference signal resource set). The multiple second beam information can be used as input to the fourth AI model, and the output can be the indices of the optimal K beams (pairs) selected from the complete beam set (first reference signal resource set), such as the K beams (pairs) with the highest RSRP or SINR in the first reference signal resource set.

[0274] For example, the fourth AI model can also be another neural network model as shown in Figure 7. The fourth AI model is an optimal beam quality prediction model, which can be understood as a linear regression problem. The input of this model can be multiple second beam information. The difference is that the output of this fourth AI model is K (K≥1) optimal RSRPs or SINRs, and K beam (pair) indices corresponding to the K optimal RSRPs or SINRs.

[0275] It should be noted that the fourth AI model can be trained through processes such as dataset construction, training, validation, and testing.

[0276] It should also be noted that the fourth AI model can be trained in advance through offline training and / or online training.

[0277] In this embodiment, the first reference signal resource set can be understood as a complete beam set. Therefore, the first beam information corresponding to the first reference signal resource set can reflect information such as beam direction, beamforming method, and channel environment to a certain extent. The fourth AI model determined by the terminal device based on the first beam information can match the current beam direction, beamforming method, and channel environment information well, which can significantly improve the reliability of the third beam information inference.

[0278] In some embodiments, different first beam information (e.g., different optimal RSRP measurements) may correspond to different AI models. The terminal device may determine the fourth AI model corresponding to the current first beam information from among the AI ​​models supported by the terminal device, based on the first beam information.

[0279] In some embodiments, a fourth AI model can be determined using an AI model. Specifically, a model for determining the fourth AI model (referred to as the sixth AI model in this embodiment) can be trained in advance. In this way, the terminal device can input the first beam information into the sixth AI model, and the sixth AI model outputs an AI model ID or an AI model index value to obtain the fourth AI model.

[0280] It should be noted that the terminal device can determine the fourth AI model based solely on the first beam information. Alternatively, the terminal device can also determine the fourth AI model by combining the first beam information with one or more of the following:

[0281] The third information sent by the network device; the third information is used to indicate the candidate AI model; the candidate AI model includes the fourth AI model;

[0282] The location information of the second reference signal resource set within the first reference signal resource;

[0283] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0284] In some embodiments, the network device may pre-configure multiple candidate AI models for the terminal device, and these candidate AI models may include a second AI model. For example, the network device may configure multiple candidate AI models by indicating a model ID, function ID, dataset ID, etc. The terminal device can determine a fourth AI model from the multiple candidate AI models configured by the network device based on the first beam information.

[0285] In other embodiments, the terminal device can select a fourth AI model from among the AI ​​models it supports based on the first beam information and the positional relationship and / or QCL relationship between the first and second reference signal resource sets. For example, the terminal device can select a subset of AI models from among its supported AI models based on the first beam information, and then select the fourth AI model to be used from the subset of AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets. Alternatively, the terminal device can select a subset of AI models from among its supported AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets, and then select the fourth AI model to be used from the subset of AI models based on the first beam information.

[0286] In some other embodiments, the terminal device can select a fourth AI model from multiple candidate AI models configured by the network device based on the first beam information and the positional relationship and / or QCL relationship between the first reference signal resource set and the second reference signal resource set. For example, the terminal device can select a subset of AI models from multiple candidate AI models configured by the network device based on the first beam information, and then select the fourth AI model from the subset of AI models based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets. Alternatively, the terminal device can select a subset of AI models from multiple candidate AI models configured by the network device based on the positional relationship and / or QCL relationship between the first and second reference signal resource sets, and then select the fourth AI model from the subset of AI models based on the first beam information.

[0287] In this embodiment of the application, after the terminal device determines the fourth AI model, it can use multiple second beam information as inputs to the fourth AI model and output the third beam information corresponding to the first reference signal resource set at the third time (future time) through the fourth AI model.

[0288] It should be noted that the explanation of the multiple second beam information can be found in the description in the above embodiments, and will not be repeated here for the sake of brevity.

[0289] In this embodiment of the application, the input parameters of the fourth AI model may further include:

[0290] RSRP / SINR measurements corresponding to each reference signal resource in the second reference signal resource set at each of multiple second time points; or,

[0291] Multiple second time points, in each second time point, the M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set; or,

[0292] Multiple second time points: In each second time point, the M2 reference signal resource indices with the highest RSRP / SINR measurements in the second reference signal resource set, and the corresponding RSRP / SINR measurements.

[0293] In this embodiment of the application, the output parameters of the fourth AI model include the index of the recommended (optimal) reference signal resource in the first reference signal resource set at the third time and / or the RSRP / SINR estimate of the recommended (optimal) reference signal resource.

[0294] It should be understood that multiple second beam information is measured at multiple second moments. Therefore, multiple second beam information can, to some extent, reflect the changes in beam direction, beamforming method, and channel environment over time. Terminal devices can use multiple second beam information as input to the fourth AI model, which can more accurately predict the third beam information corresponding to the first reference signal resource set at future moments.

[0295] It should be noted that the input parameters of the fourth AI model also include one or more of the following:

[0296] The location information of the second reference signal resource set within the first reference signal resource;

[0297] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0298] Considering the consistency between model training and inference, the different positional relationships and / or QCL relationships between the first and second reference signal resource sets may affect the inference performance of the AI ​​model. Therefore, the terminal device can use the positional relationships and / or QCL relationships between the first and second reference signal resource sets as input parameters of the fourth AI model. In this way, the third beam information output by the fourth AI model can better match the beam configuration at the third time moment, which can significantly improve the reliability of the third beam information inference.

[0299] Understandably, in this embodiment, the terminal device can determine the fourth AI model based on the first beam information. The determined fourth AI model can be used in different cells and different network devices, and model interaction between the terminal device and the network device can be avoided, thereby saving a significant amount of signaling and time related to model management.

[0300] As a specific implementation, for example, when the period of the first reference signal resource set is an integer multiple of the period of the second reference signal resource set, the terminal device will receive the second reference signal resource set at the same time as receiving the first reference signal resource set. In this case, the first beam information and the second beam information will correspond to the same time (i.e., the first time and the second time are the same). In this case, the terminal device can still use the method of the present invention to obtain the third beam information at the third time based on the first beam information, the second beam information, and the third / fourth AI model. That is, in scenario 2, when the third beam information is the beam information of a future time (the third time), the first time may not be before the second time (i.e., there is no restriction on the timing relationship between the first time and the second time), but the first time and the second time must both be before the third time.

[0301] It should be noted that in the beam management method provided in this application embodiment, the first beam information can also be used for performance monitoring of the AI ​​model; the AI ​​model is used to determine the third beam information.

[0302] The AI ​​model may include one or more of the following: a first AI model, a second AI model, a third AI model, and a fourth AI model.

[0303] Understandably, when a network device transmits reference signals on the first set of reference signal resources, the terminal device can measure the first beam information based on these reference signals. At this point, the terminal device can compare the first beam information with the third beam information output by the AI ​​model, and determine the performance of the current AI model based on their consistency. It is important to note that the first beam information must be the most recently measured beam information. In other words, performance monitoring can only be performed immediately after the terminal measures the first beam information; otherwise, the information may be outdated, and reliability cannot be guaranteed.

[0304] In some embodiments, the first beam information can be used for performance monitoring of a first AI model and a second AI model. The terminal device can compare the first beam information with the third beam information currently output by the AI ​​model (either the first or second AI model). That is, by comparing the actually measured first beam information with the most recently output third beam information from the AI ​​model, the performance of the model can be determined. For example, the first beam information is the RSRP / SINR measurement value corresponding to each resource in the first reference signal resource set, and the third beam information is the index of the K best reference signal resources in the first reference signal resource set and the corresponding RSRP / SINR estimate. The performance of the AI ​​model can be determined by whether the K reference signal resources with the highest RSRP / SINR measurement values ​​in the first beam information are consistent with the K reference signal resources in the third beam information, or by comparing the differences between the K highest RSRP / SINR measurement values ​​in the first beam information and the K RSRP / SINR estimate values ​​in the third beam information.

[0305] In other embodiments, the first beam information can be used for performance monitoring of the third and fourth AI models. Since the third and fourth AI models are used to output third beam information corresponding to future time moments, when monitoring the performance of the third or fourth AI model, the first beam information can be compared with the third beam information output by the third or fourth AI model at previous time moments (here, the third beam information is the third beam information predicted by the third or fourth AI model corresponding to the current time moment), and the performance of the current third or fourth AI model can be determined based on their consistency. In other words, by comparing the first beam information at time T with the third beam information predicted before time T corresponding to time T, the performance of the model can be determined. For example, the first beam information is the RSRP / SINR measurement value corresponding to each resource in the first reference signal resource set, and the third beam information is the index of the K best reference signal resources in the first reference signal resource set and the corresponding RSRP / SINR estimate. The performance of the AI ​​model can be determined by whether the K reference signal resources with the highest RSRP / SINR measurement values ​​in the first beam information are consistent with the K reference signal resources in the third beam information, or by comparing the difference between the K highest RSRP / SINR measurement values ​​in the first beam information and the K RSRP / SINR estimate values ​​in the third beam information.

[0306] Based on the method of this invention, the first beam information can be used to obtain the third beam information for CSI reporting, and also for performance monitoring of AI models. Network devices only need to use the reference signal resources for performance monitoring as the first reference signal resource set, without needing to configure additional dedicated reference signal resources (corresponding to the complete beam) to obtain the third beam information, thus saving significant resource overhead. In other words, the first reference signal resource set can reuse existing resources used for performance monitoring without increasing reference signal resource overhead.

[0307] In some embodiments, referring to FIG8, the beam management method provided in this application further includes the following steps:

[0308] S550, the terminal device sends the fourth information, and the corresponding network device receives the fourth information, which is used to request the third reference signal resource set.

[0309] S560, the network device transmits reference signals on the resources corresponding to the third reference signal resource set.

[0310] S570: The terminal equipment performs measurements based on the third reference signal resource set to obtain the fourth beam information;

[0311] S580 and terminal equipment determine the third beam information corresponding to the second or third time based on the fourth beam information and the second beam information.

[0312] Understandably, network devices can transmit reference signals on the first reference signal resource set at a lower frequency. Therefore, when a terminal device detects that the first beam information is outdated, causing a decrease in the output performance of the AI ​​model, it can request a new reference signal resource set (referred to as the third reference signal resource set in this embodiment) through the fourth information. Accordingly, the network device can respond to the fourth information and transmit reference signals on the resources corresponding to the third reference signal resource set. For example, the network device can transmit reference signals on the third reference signal resource set in an aperiodic manner. It should be noted that the fourth information may simply be a request message and does not need to contain resource information of the third reference signal resource set.

[0313] In some embodiments, the reference signal resources included in the third reference signal resource set are the same as those included in the first reference signal resource set.

[0314] or,

[0315] The reference signal resources in the third set of reference signal resources correspond one-to-one with the reference signal resources in the first set of reference signal resources, and the corresponding reference signal resources are quasi-co-addressable (QCL).

[0316] It is understandable that the third reference signal resource set and the first reference signal resource set can be the same resource set, containing the same reference signal resources. Alternatively, the third reference signal resource set and the first reference signal resource set can be different resource sets. When the third reference signal resource set and the first reference signal resource set are different resource sets, each reference signal resource in the third reference signal resource set can use the same beam or QCL relationship as a reference signal resource in the first reference signal resource set.

[0317] Furthermore, the terminal device performs measurements based on the third reference signal resource set to obtain the fourth beam information corresponding to the third reference signal resource set, and determines the third beam information corresponding to the first reference signal resource set at the second or third time based on the fourth beam information and the second beam information.

[0318] It should be noted that the method by which the terminal device determines the third beam information based on the fourth beam information and the second beam information is the same as the method by which the terminal device determines the third beam information based on the first beam information and the second beam information in the aforementioned embodiments. For the sake of simplicity, it will not be described again here. It is understood that the fourth beam information obtained by the terminal device using the third reference signal resource set can replace the previous first beam information to obtain the third beam information.

[0319] In some embodiments, the fourth beam information may include:

[0320] The measurement results corresponding to each reference signal resource in the third set of reference signal resources; or,

[0321] The indices of the M3 reference signal resources with the best measurement results in the third set of reference signal resources; or...

[0322] The indices of the M3 reference signal resources with the best measurement results in the third set of reference signal resources and their corresponding measurement results; where M3 is an integer greater than 0.

[0323] It should be noted that the measurement results may include RSRP and / or SINR, etc., and this application embodiment does not limit them.

[0324] It should be noted that, in order to ensure the consistency of the input parameter types of the AI ​​model, M3 has the same value as M1 in the above embodiment.

[0325] In this way, when the terminal device detects that the first beam information is outdated and causes the output performance of the AI ​​model to degrade, it can request the network device to send a new set of reference signal resources through the second indication information in order to obtain new beam information to update the first beam information, thereby ensuring the accuracy of the third beam information.

[0326] The method provided by the embodiments of the present application will be elaborated in detail in combination with specific application scenarios below.

[0327] The above method will be elaborated based on two different scenarios below.

[0328] Embodiment 1

[0329] Embodiment 1 corresponds to the beam information recovery scenario and includes the following steps:

[0330] S1. At time t1, the network device sends a reference signal on the first reference signal resource set.

[0331] It should be noted that the first reference signal resource set contains multiple reference signal resources, and each reference signal resource is used to send a reference signal. Typically, the first reference signal resource set is the first CSI-RS resource set (including multiple CSI-RS resources), or the first SSB set (including multiple SSBs).

[0332] It should be noted that the time t1 is the time domain resource occupied by the first reference signal resource set. For example, the time t1 can be a time point, that is, the time domain position of the CSI-RS resource corresponding to the first reference signal resource set, or the time t1 can be a time window, that is, the time domain resources occupied by multiple reference signal resources in the first reference signal resource set.

[0333] S2. The terminal device measures based on the first reference signal resource set and obtains the first beam information corresponding to the first reference signal resource set at time t1.

[0334] Among them, the first beam information can be one of the following three cases:

[0335] The measured RSRP values corresponding to each reference signal resource in the first reference signal resource set. For example, if the first reference signal resource set contains N reference signal resources, the first beam information can be N corresponding RSRP values (corresponding one by one in the order of resource indexes).

[0336] The indexes of the M1 reference signal resources with the highest RSRP measurement values in the first reference signal resource set. That is to say, the indexes of the M1 reference signal resources with the best measurement results in the first reference signal resource set. Among them, M1 < N. For example, M1 = 2, 4, 8.

[0337] The indices and corresponding RSRP measurement values of the M1 reference signal resources with the highest RSRP measurement values in the first reference signal resource set. That is, the indices of the M1 reference signal resources with the best measurement results in the first reference signal resource set and the RSRP measured from these resources. Here, M1 < N. For example, M1 = 2, 4, 8. For example, for M1 = 2, the first beam information may be the index and RSRP corresponding to the optimal beam, and the index and RSRP corresponding to the sub-optimal beam.

[0338] S3. The network device transmits a reference signal on the second reference signal resource set at time t2, where the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set, and t2 is after t1.

[0339] Optionally, before step S3, the terminal device may send capability information to the network device, and the capability information is used to indicate that the terminal device has the ability to recover beam information based on partial beam information. That is, this capability indicates whether the terminal device can obtain the beam information corresponding to the current complete beam based on the reference signal corresponding to the complete beam previously sent by the network device and the reference signal corresponding to the current partial beam. If the terminal device indicates that it has this ability, the network device may configure the terminal device to reduce the reference signal resource overhead through the method of the present invention; otherwise, the terminal device needs to obtain the beam information based on the reference signal corresponding to the complete beam.

[0340] It should be noted that the time t2 is the time domain resource occupied by the second reference signal resource set. For example, t2 may be a time point, that is, the time domain position of the CSI-RS resource corresponding to the second reference signal resource set, or t2 may be a time window, that is, the time domain resources occupied by multiple reference signal resources in the second reference signal resource set. Here, t2 being after t1 means that the time domain resources occupied by the second reference signal resource set are after the time domain resources occupied by the first reference signal resource set.

[0341] Assume that the second reference signal resource set contains L reference signal resources (such as CSI-RS resources), and the first reference signal resource set contains N reference signal resources (such as CSI-RS resources), then L < N, that is, they contain different numbers of resources.

[0342] In some embodiments, the network device may send the first information to the terminal device, and the first information is used to indicate the association relationship between the second reference signal resource set and the first reference signal resource set.

[0343] Exemplarily, the association relationship includes the position information of the reference signal resources in the second reference signal resource set in the first reference signal resource set. For example, the position information indicates the position of the reference signal resources in the second reference signal resource set in the first reference signal resource set in a bitmap manner, with each bit corresponding to a resource in the first reference signal resource set. Alternatively, the position information indicates the second reference signal resource set from a plurality of predefined mapping patterns in an indicative pattern manner. Alternatively, the position information indicates that the second reference signal resource set is the (nK + 1)-th resource in the first reference signal resource set, where K is indicated by the position information, n is a non-negative integer, and the value of n ranges from 0 to N / K.

[0344] In one implementation manner, through the association relationship, the terminal device can determine the second reference signal resource set from the first reference signal resource set, so that there is no need for dedicated signaling to configure the second reference signal resource set.

[0345] In another implementation manner, the association relationship is used for the terminal device to determine the AI model (such as the first AI model or the second AI model) used to calculate the third beam information. Different association relationships can correspond to different AI models. For example, the second reference signal resource set occupying different positions in the first reference signal resource set can correspond to different AI models to obtain the corresponding third beam information.

[0346] In another implementation manner, the association relationship serves as an input parameter of an AI model (such as the first AI model or the second AI model), so as to output the third beam information on the terminal device side.

[0347] S4, 4. The terminal device measures based on the second reference signal resource set and obtains the second beam information corresponding to the second reference signal resource set at time t2.

[0348] Among them, the second beam information can be one of the following three cases:

[0349] The measured RSRP values respectively corresponding to each reference signal resource in the second reference signal resource set. For example, if the second reference signal resource set includes L reference signal resources, the first beam information can be L corresponding RSRP values (corresponding one by one in the order of resource indexes).

[0350] The indexes of the M2 reference signal resources with the highest RSRP measurement values in the second reference signal resource set. That is to say, the indexes of the M2 reference signal resources with the best measurement results in the second reference signal resource set. Among them, M2 < L. For example, M2 = 2, 4, 8.

[0351] The indices and corresponding RSRP measurements of the M2 reference signal resources with the highest RSRP values ​​in the second reference signal resource set. In other words, the indices of the M2 reference signal resources with the best measurement results in the second reference signal resource set and the RSRP measured for these resources.

[0352] In one embodiment, the terminal device receives first information sent by the network device, the first information being used to indicate the association relationship between the second reference signal resource set and the first reference signal resource set.

[0353] The association relationship includes the location information of the reference signal resources in the second reference signal resource set within the first reference signal resource set. See the description in S3 for details.

[0354] In one implementation, through the association relationship, the terminal device can determine the second reference signal resource set from the first reference signal resource set, thereby eliminating the need for dedicated signaling to configure the second reference signal resource set.

[0355] In another implementation, the association relationship is used by the terminal device to determine the AI ​​model (such as a first AI model or a second AI model) used to calculate the third beam information. Different association relationships can correspond to different AI models.

[0356] In another implementation, the correlation is used as an input parameter for an AI model (such as the first AI model or the second AI model described below) to output the third beam information on the terminal device side.

[0357] In one implementation, the second reference signal resource set is a subset of the first reference signal resource set, meaning that all resources in the second reference signal resource set are included in the first reference signal resource set. For example, the resources in the second reference signal resource set have shorter periods, while the other resources in the first reference signal resource set have longer periods.

[0358] In another implementation, the second reference signal resource set and the first reference signal resource set are contained in the same reference signal resource set but have different configuration periods. That is, the network device can configure a reference signal resource set (such as a CSI-RS resource set) that includes both the second and first reference signal resource sets, but their configuration periods are different, with the first reference signal resource set having a longer period.

[0359] In another implementation, each reference signal resource in the second set of reference signal resources shares a quasi-co-located QCL with one reference signal resource in the first set of reference signal resources. That is, for each reference signal resource in the second set of reference signal resources, the network device configures a reference signal resource in the first set with its QCL (i.e., as a QCL reference source signal). Based on this QCL relationship, the terminal device can determine which resources in the second set of reference signal resources share the same beam with those in the first set.

[0360] In one implementation, the QCL relationship can be used to determine the AI ​​model, thereby obtaining third beam information.

[0361] S5. The terminal device determines the third beam information corresponding to the first reference signal resource set at time t2 based on the first beam information and the second beam information.

[0362] The third beam information is one of the following:

[0363] The indices of the K optimal reference signal resources in the first reference signal resource set, where K is an integer greater than 0. That is, based on the first and second beam information, the terminal device can estimate the indices of the K optimal reference signal resources (corresponding to the K optimal beams) in the first reference signal resource set at time t2 (i.e., the current time). Typically, K=1, meaning the third beam information is the index of the optimal reference signal resource (corresponding to the optimal beam) in the first reference signal resource set. Alternatively, the third beam information is the index of the K reference signal resources with the highest estimated RSRP values ​​in the first reference signal resource set.

[0364] The third beam information is the index of the K optimal reference signal resources in the first reference signal resource set and their corresponding RSRP estimates. In other words, based on the first and second beam information, the terminal device can estimate the indices of the K optimal reference signal resources (corresponding to the K optimal beams) in the first reference signal resource set at time t2 (i.e., the current time) and their corresponding RSRP values. Typically, K=1, meaning the third beam information is the index of the optimal reference signal resource (corresponding to the optimal beam) in the first reference signal resource set and its corresponding RSRP estimate. Alternatively, the third beam information is the index of the K reference signal resources with the highest RSRP estimates in the first reference signal resource set and their corresponding RSRP values.

[0365] In this embodiment of the application, the terminal device determines the third beam information corresponding to the first reference signal resource set at time t2 based on the first beam information and the second beam information, which can be achieved using one of the following two methods:

[0366] The terminal device takes the first beam information and the second beam information as input to the first AI model, and outputs the third beam information corresponding to the first reference signal resource set at time t2 through the first AI model. For example, the input information of the first AI model is a set of RSRPs corresponding to the first reference signal resource set at time t1, and a set of RSRPs corresponding to the second reference signal resource set at time t2, and the output is the index and RSRP corresponding to the recommended (optimal) reference signal resource in the first reference signal resource set at time t2.

[0367] The terminal device determines a second AI model based on the first beam information, uses the second beam information as input to the second AI model, and outputs the third beam information corresponding to the first reference signal resource set at time t2 through the second AI model. For example, the input information of the second AI model is a set of RSRPs corresponding to the second reference signal resource set at time t2, and the output is the index and RSRP corresponding to the recommended (optimal) reference signal resource in the first reference signal resource set at time t2.

[0368] In one implementation, the terminal device receives second or third information sent by the network device. The second information is used to configure the first AI model used to calculate the third beam information. That is, the aforementioned first AI model can be pre-configured to the terminal device by the network device. The third information is used to configure candidate AI models, including the second AI model. The terminal device can determine the second AI model from the candidate AI models based on the first beam information. It should be noted that the network device can configure the AI ​​model from the AI ​​models supported by the terminal device by indicating a model ID, function ID, dataset ID, etc.

[0369] In one implementation, the first reference signal resource set or the corresponding first beam information is also used for performance monitoring of the first AI model or the second AI model. Specifically, when the network device transmits reference signals on the first reference signal resource set, the terminal device can measure the first beam information based on these reference signals. At this time, the terminal device can compare the first beam information with the third beam information output by the current AI model, and determine the performance of the current AI model based on their consistency. That is, the performance of the model can be determined by comparing the first beam information with the third beam information at the most recent moment. For example, the first beam information is the RSRP measurement value corresponding to each resource in the first reference signal resource set, and the third beam information is the index of the K best reference signal resources in the first reference signal resource set and the corresponding RSRP estimate. The performance of the AI ​​model can be determined by whether the K reference signal resources with the highest RSRP measurement values ​​in the first beam information are consistent with the K reference signal resources in the third beam information, or by comparing the differences between the K highest RSRP measurement values ​​in the first beam information and the K RSRP estimate values ​​in the third beam information.

[0370] In one implementation, the terminal device sends a fourth message to the network device, the fourth message being a request for a third reference signal resource set. Accordingly, after receiving the fourth message from the terminal device, the network device can transmit reference signals on the third reference signal resource set in an aperiodic manner.

[0371] Furthermore, the terminal device performs measurements based on the third reference signal resource set to obtain the fourth beam information corresponding to the third reference signal resource set, and determines the third beam information corresponding to the first reference signal resource set at time t2 based on the fourth beam information and the second beam information. The method by which the terminal device determines the third beam information based on the fourth and second beam information is the same as the aforementioned method for determining the third beam information based on the first and second beam information, and will not be repeated here. In other words, the terminal device uses the beam information obtained from the measurement of the third reference signal resource set to replace the previous first beam information, thereby obtaining the third beam information.

[0372] In this way, when the terminal device detects that the first beam information is outdated and causes the output performance of the AI ​​model to degrade, it can request the network device to send a new set of reference signal resources through the second indication information in order to obtain new beam information to update the first beam information, thereby ensuring the accuracy of the third beam information.

[0373] The fourth beam information includes: the measured RSRP value corresponding to each reference signal resource in the third reference signal resource set; or, the indices of the M3 reference signal resources with the highest RSRP measured values ​​in the third reference signal resource set; or, the indices and corresponding RSRP measured values ​​of the M3 reference signal resources with the highest RSRP measured values ​​in the third reference signal resource set. M3 is an integer greater than 0.

[0374] S6. The terminal device sends the third beam information to the network device.

[0375] Specifically, the terminal device can report the third beam information as CSI to the network device, thereby enabling the network device to obtain the optimal reference signal resource (beam) and the corresponding RSRP in the first reference signal resource set at the current time.

[0376] S7. The network device receives the third beam information reported by the terminal device and uses it for subsequent downlink beamforming.

[0377] Specifically, after obtaining the optimal reference signal resource (beam) and the corresponding RSRP in the first reference signal resource set at the current moment, the network device can use the transmission beam of the optimal reference signal resource as the transmission beam used for transmitting other downlink signals in the future, and configure the corresponding reference signal resource as the QCL source signal to the terminal device.

[0378] The method provided in this application allows a terminal device to obtain information such as the beam direction, beamforming method, and channel environment based on the first beam information of the complete beam set. Therefore, it can complete the recovery process from the partial (second) beam information to the complete (first) beam information without the need for network device configuration and assistance. In this case, the same model can be used in different cells and different network devices, avoiding model interaction between the terminal device and the network device, thus saving significant signaling and time related to model management. Simultaneously, since the adopted AI model can effectively match the current beam direction, beamforming method, and channel environment information, the reliability of CSI measurements can be significantly improved. Because the network device only needs to transmit the first reference signal resource set at a very low frequency, beam information acquisition can be based on the second reference signal resource set, thereby significantly reducing the overhead of reference signals and the complexity of the terminal.

[0379] Example 2

[0380] Example 2 corresponds to the beam prediction scenario, and includes the following steps:

[0381] S1, Network device t1 sends a reference signal on the first reference signal resource set at time t1.

[0382] S2. The terminal device performs measurements based on the first reference signal resource set to obtain the first beam information corresponding to the first reference signal resource set at time t1.

[0383] It should be noted that the relevant descriptions of S1 and S2 can be found in the description in Embodiment 1 above, and will not be repeated here for the sake of brevity.

[0384] S3. The network device sends multiple reference signals on the second reference signal resource set between time t1 and time t3, wherein the second reference signal resource set contains fewer reference signal resources than the first reference signal resource set, and time t3 is after time t1.

[0385] It should be noted that prior to S3, the terminal device can send capability information to the network device. This capability information indicates that the terminal device possesses the ability to recover and predict beam information based on partial beam information. In other words, this capability indicates whether the terminal device can obtain the beam information corresponding to the complete beam at a future time based on the reference signal corresponding to the complete beam previously sent by the network device and the reference signal corresponding to the partial beam currently being sent. If the terminal device indicates that it possesses this capability, the network device can configure the terminal device to reduce reference signal resource overhead using the method of this invention; otherwise, the terminal device needs to obtain the current beam information based on the reference signal corresponding to the current complete beam.

[0386] In this embodiment, time t2 is between time t1 and time t3. The network device transmits multiple reference signals on the second reference signal resource set between time t1 and time t3, including the reference signal transmitted by the network device on the second reference signal resource set at time t2. Here, time t2 being between time t1 and time t3 indicates that the time-domain resources occupied by the second reference signal resource set are after the time-domain resources occupied by the first reference signal resource set, and before the time corresponding to the estimated third beam information. For example, if the second reference signal resource set is a periodic CSI-RS resource, the network device needs to periodically transmit CSI-RS on the second reference signal resource set, resulting in multiple periodic CSI-RS transmissions between time t1 and time t3.

[0387] S4. The terminal device performs measurements based on multiple reference signals transmitted on the second reference signal resource set between time t1 and time t3 to obtain the second beam information corresponding to the second reference signal resource set at multiple different times.

[0388] The second beam information corresponding to the multiple sets of second reference signal resources at different times includes the second beam information corresponding to the set of second reference signal resources at time t2.

[0389] S5. The terminal device determines the third beam information corresponding to the first reference signal resource set at time t3 based on the first beam information and the second beam information.

[0390] The time t3 is after time t2 and also after the time when the terminal device reports the third beam information. In other words, the third beam information is the beam information for a future time predicted by the terminal device, not the current or previous beam information.

[0391] In this embodiment of the application, the terminal device determines the third beam information corresponding to the first reference signal resource set at time t3 based on the first beam information and the second beam information, which can be achieved using one of the following two methods:

[0392] The terminal device takes the first beam information and multiple second beam information at different times as input to the third AI model, and outputs the third beam information corresponding to the first reference signal resource set at time t3 through the third AI model. For example, the input information of the first AI model is a set of RSRPs corresponding to the first reference signal resource set at time t1, and multiple sets of RSRPs corresponding to multiple second reference signal resource sets at different times, and the output is the index and RSRP corresponding to the recommended (optimal) reference signal resource in the first reference signal resource set at time t3.

[0393] The terminal device determines a fourth AI model based on the first beam information, uses second beam information from multiple different times as input to the fourth AI model, and outputs the third beam information corresponding to the first reference signal resource set at time t3 through the fourth AI model. For example, the input information of the second AI model is multiple sets of RSRPs corresponding to the second reference signal resource sets at multiple different times, and the output is the index and RSRP corresponding to the recommended (optimal) reference signal resource in the first reference signal resource set at time t3.

[0394] In one implementation, the first reference signal resource set or the corresponding first beam information is also used for performance monitoring of the third or fourth AI model. Specifically, when the network device transmits reference signals on the first reference signal resource set, the terminal device can measure the first beam information based on these reference signals. At this time, the terminal device can compare the first beam information with the third beam information output (predicted) by the previous AI model corresponding to the current time, and determine the performance of the current AI model based on their consistency. That is, by comparing the first beam information at time t4 with the third beam information predicted before t4 at time t4, the performance of the model can be determined. For example, the first beam information is the RSRP measurement value corresponding to each resource in the first reference signal resource set, and the third beam information is the index of the K best reference signal resources in the first reference signal resource set and the corresponding RSRP estimate. The performance of the AI ​​model can be determined by whether the K reference signal resources with the highest RSRP measurement values ​​in the first beam information are consistent with the K reference signal resources in the third beam information, or by comparing the difference between the K highest RSRP measurement values ​​in the first beam information and the K RSRP estimate values ​​in the third beam information.

[0395] In one implementation, the terminal device receives second or third information sent by the network device. The second information is used to configure a second AI model used to calculate the third beam information. That is, the aforementioned third AI model can be pre-configured to the terminal device by the network device. The third information is used to configure candidate AI models, including a fourth AI model. The terminal device can determine the fourth AI model from the candidate AI models based on the first beam information. It should be noted that the network device can configure the AI ​​model from the AI ​​models supported by the terminal device by indicating a model ID, function ID, dataset ID, etc.

[0396] S6. The terminal device sends the third beam information to the network device.

[0397] Specifically, the terminal device can report the third beam information as CSI to the network device, thereby enabling the network device to obtain the optimal reference signal resource (beam) and the corresponding RSRP in the first reference signal resource set at the current time.

[0398] S7. The network device receives the third beam information reported by the terminal device and uses it for subsequent downlink beamforming.

[0399] Specifically, after obtaining the optimal reference signal resource (beam) and the corresponding RSRP in the first reference signal resource set at the current moment, the network device can use the transmission beam of the optimal reference signal resource as the transmission beam used for transmitting other downlink signals in the future, and configure the corresponding reference signal resource as the QCL source signal to the terminal device.

[0400] The method provided in this application allows a terminal device to obtain information such as the used beam, beamforming method, and channel environment based on the first beam information of the complete beam set. Therefore, it can complete the prediction process from the currently measured partial (second) beam information to the complete (first) beam information without the need for network device configuration and assistance. In this case, the same model can be used for different cells and different terminal devices, and model interaction between the terminal device and network device can be avoided, thus saving a significant amount of signaling and time related to model management. Simultaneously, since the network device only needs to transmit the first reference signal resource set at a very low frequency, beam information prediction can be based on the second reference signal resource set, significantly reducing the overhead of reference signals and the complexity of the terminal.

[0401] In summary, in the beam management method provided in this application embodiment, the network device can send reference signals corresponding to the complete beam set at a lower frequency to measure the complete beam information, and send reference signals corresponding to a partial beam set at a higher frequency to measure the partial beam information, so that the terminal device can obtain the complete beam information at the current or future time based on these two pieces of information, thereby significantly reducing the resource overhead and power loss of the reference signals used for beam management.

[0402] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solutions of this application, and these simple modifications all fall within the protection scope of this application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this application will not describe the various possible combinations separately. Furthermore, various different embodiments of this application can also be arbitrarily combined, as long as they do not violate the spirit of this application, they should also be considered as the content disclosed in this application. Moreover, without conflict, the various embodiments and / or the technical features in the various embodiments described in this application can be arbitrarily combined with the prior art, and the resulting technical solutions should also fall within the protection scope of this application.

[0403] It should also be understood that in the various method embodiments of this application, the sequence number of each process does not imply 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 this application. Furthermore, in the embodiments of this application, the terms "downlink," "uplink," and "sidelink" are used to indicate the transmission direction of signals or data. "Downlink" indicates that the transmission direction of signals or data is a first direction from the site to the user equipment in the cell; "uplink" indicates that the transmission direction of signals or data is a second direction from the user equipment in the cell to the site; and "sidelink" indicates that the transmission direction of signals or data is a third direction from user equipment 1 to user equipment 2. For example, "downlink signal" indicates that the transmission direction of the signal is the first direction. Additionally, in the embodiments of this application, the term "and / or" is merely a description of the association relationship between related objects, indicating that three relationships can exist. Specifically, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0404] Figure 9 is a schematic diagram of the structure of a beam management device 900 provided in an embodiment of this application, which is applied to a terminal device. As shown in Figure 9, the beam management device 900 includes:

[0405] The determining unit 910 is configured to determine the third beam information corresponding to the second time moment or the third time moment based on the first beam information and the second beam information;

[0406] The first transmitting unit 920 transmits the third beam information to the network device;

[0407] Wherein, the first beam information is determined by the terminal device based on a first reference signal resource set at a first moment; the second beam information is determined by the terminal device based on a second reference signal resource set at a second moment; and the third beam information is the beam information corresponding to the first reference signal resource set.

[0408] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0409] In some embodiments, the determining unit 910 is further configured to take the first beam information and the second beam information as input to a first artificial intelligence (AI) model, and output the third beam information corresponding to the second time moment through the first AI model.

[0410] In some embodiments, the determining unit 910 is further configured to determine a second AI model based on the first beam information; use the second beam information as input to the second AI model; and output the third beam information corresponding to the second time moment through the second AI model.

[0411] In some embodiments, the number of the second beam information includes multiple types, and different second beam information corresponds to different second times.

[0412] The determining unit 910 is further configured to take the first beam information and a plurality of second beam information as input to a third AI model, and output the third beam information corresponding to the third time moment through the third AI model.

[0413] In some embodiments, the number of second beam information includes multiple types, and different second beam information corresponds to different second times; the determining unit 910 is further configured to determine a fourth AI model based on the first beam information; the multiple second beam information are used as inputs to the fourth AI model, and the third beam information corresponding to the third time is output through the fourth AI model.

[0414] In some embodiments, the periodic configuration and / or frequency domain density of the first reference signal resource set and the second reference signal resource set are different.

[0415] In some embodiments, one or more of the following are included:

[0416] The first reference signal resource set and the second reference signal resource set contain periodic reference signal resources, and the period of the reference signal resources in the first reference signal resource set is greater than the period of the reference signal resources in the second reference signal resource set;

[0417] The frequency domain density of the first reference signal resource set is less than the frequency domain density of the second reference signal resource set;

[0418] The first set of reference signal resources includes periodic reference signal resources, and the second set of reference signal resources includes aperiodic or semi-perpetual reference signal resources;

[0419] The first set of reference signal resources includes aperiodic reference signal resources, and the second set of reference signal resources includes periodic or semi-persistent reference signal resources.

[0420] In some embodiments, the association between the first reference signal resource set and the second reference signal resource set includes any one of the following:

[0421] The reference signal resources in the second set of reference signal resources are a portion of the reference signal resources in the first set of reference signal resources;

[0422] The first reference signal resource set and the second reference signal resource set belong to the same reference signal resource set, and the period of the first reference signal resource set is different from the period of the second reference signal resource set;

[0423] Each reference signal resource in the second set of reference signal resources is quasi-co-addressable (QCL) with one reference signal resource in the first set of reference signal resources.

[0424] In some embodiments, the beam management device 900 further includes a first receiving unit configured to receive first information; the first information is used to indicate the association relationship between the first reference signal resource set and the second reference signal resource set.

[0425] In some embodiments, the reference signal resources in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set, and the first information is used to indicate the position information of the second reference signal resource set in the first reference signal resources.

[0426] In some embodiments, the determining unit 910 is further configured to determine the second reference signal resource set from the first reference signal resource set based on the first information.

[0427] In some embodiments, the input parameters of one or more of the first AI model, the second AI model, the third AI model, and the fourth AI model may further include one or more of the following:

[0428] The location information of the second reference signal resource set within the first reference signal resource;

[0429] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0430] In some embodiments, the first AI model or the third AI model is determined based on one or more of the following:

[0431] The second information sent by the network device; the second information is used to instruct the first AI model or the third AI model;

[0432] The location information of the second reference signal resource set within the first reference signal resource;

[0433] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0434] In some embodiments, the second AI model or the fourth AI model is determined based on the first beam information and one or more of the following:

[0435] The third information sent by the network device; the third information is used to indicate a candidate AI model; the candidate AI model includes the second AI model or the fourth AI model;

[0436] The location information of the second reference signal resource set within the first reference signal resource;

[0437] The QCL relationship between the first reference signal resource set and the second reference signal resource set.

[0438] In some embodiments, the first transmitting unit 920 is further configured to transmit fourth information, the fourth information being used to request a third set of reference signal resources.

[0439] In some embodiments, the determining unit 910 is further configured to perform measurements based on the third reference signal resource set to obtain fourth beam information; and to determine third beam information corresponding to a second time moment or a third time moment based on the fourth beam information and the second beam information.

[0440] In some embodiments, the reference signal resources included in the third reference signal resource set are the same as those included in the first reference signal resource set.

[0441] Alternatively, the reference signal resources in the third set of reference signal resources correspond one-to-one with the reference signal resources in the first set of reference signal resources, and the corresponding reference signal resources are quasi-co-addressable (QCL).

[0442] In some embodiments, the third time point is after the time when the terminal device sends the third beam information.

[0443] In some embodiments, the first beam information is further used for performance monitoring of the AI ​​model; the AI ​​model is used to determine the third beam information.

[0444] In some embodiments, one or more of the first beam information, the second beam information, and the fourth beam information include:

[0445] The measurement results corresponding to each reference signal resource in the associated set of reference signal resources; or,

[0446] The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources; or,

[0447] The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources and their corresponding RSRP measurements;

[0448] Where M is an integer greater than 0.

[0449] In some embodiments, the third beam information includes:

[0450] The indices of the K best reference signal resources in the first set of reference signal resources; or,

[0451] The indices of the K best reference signal resources in the first reference signal resource set and the corresponding estimated measurement results;

[0452] Where K is an integer greater than 0.

[0453] In some embodiments, the first transmitting unit is further configured to transmit capability information to the network device, the capability information being used to indicate that the terminal device has the capability to perform beam information recovery and / or prediction based on partial beam information.

[0454] Those skilled in the art should understand that the description of the beam management device in the embodiments of this application can be understood with reference to the description of the beam management method in the embodiments of this application.

[0455] Figure 10 is a schematic diagram of the structure of a beam management device 1000 provided in an embodiment of this application, applied to a network device. As shown in Figure 10, the beam management device 1000 includes:

[0456] The second transmitting unit 1010 is configured to transmit a reference signal on the resource corresponding to the first reference signal resource set at a first moment.

[0457] The second transmitting unit 1010 is also configured to transmit a reference signal on the resource corresponding to the second reference signal resource set at a second time.

[0458] The second receiving unit 1020 is configured to receive third beam information corresponding to the second or third time moment sent by the terminal device.

[0459] Wherein, the first reference signal resource set is used to determine the first beam information, the second reference signal resource set is used to determine the second beam information, and the third beam information corresponding to the second time or the third time is determined based on the first beam information and the second beam information; the third beam information is the beam information corresponding to the first reference signal resource set;

[0460] The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

[0461] In some embodiments, the first reference signal resource set and the second reference signal resource set employ different periodic configurations and / or frequency domain densities.

[0462] In some embodiments, one or more of the following are included:

[0463] The first reference signal resource set and the second reference signal resource set contain periodic reference signal resources, and the period of the reference resources in the first reference signal resource set is greater than the period of the reference signal resources in the second reference signal resource set;

[0464] The frequency domain density of the first reference signal resource set is less than the frequency domain density of the second reference signal resource set;

[0465] The first set of reference signal resources includes periodic reference signal resources, and the second set of reference signal resources includes aperiodic or semi-perpetual reference signal resources;

[0466] The first set of reference signal resources includes aperiodic reference signal resources, and the second set of reference signal resources includes periodic or semi-persistent reference signal resources.

[0467] In some embodiments, the association between the first reference signal resource set and the second reference signal resource set includes any one of the following:

[0468] The reference signal resources in the second set of reference signal resources are a portion of the reference signal resources in the first set of reference signal resources;

[0469] The first reference signal resource set and the second reference signal resource set belong to the same reference signal resource set, and the period of the first reference signal resource set is different from the period of the second reference signal resource set;

[0470] Each reference signal resource in the second set of reference signal resources is quasi-co-addressable (QCL) with one reference signal resource in the first set of reference signal resources.

[0471] In some embodiments, the second transmitting unit 1010 is further configured to transmit first information; the first information is used to indicate the association relationship between the first reference signal resource set and the second reference signal resource set.

[0472] In some embodiments, the reference signal resources in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set, and the first information is used to indicate the position information of the second reference signal resource set in the first reference signal resources.

[0473] In some embodiments, the second transmitting unit 1010 is further configured to transmit second information, the second information being used to indicate a first AI model or a third AI model; the first AI model is used to determine the third beam information corresponding to the second time based on the first beam information and the second beam information, and the third AI model is used to determine the third beam information corresponding to the third time based on the first beam information and the second beam information.

[0474] In some embodiments, the second transmitting unit 1010 is further configured to transmit third information, the third information being used to indicate a candidate AI model, the candidate AI model and the first beam information being used to determine a second AI model or a fourth AI model, the second AI model being used to determine the third beam information corresponding to a second time based on the second beam information, and the fourth AI model being used to determine the third beam information corresponding to the third time based on the second beam information.

[0475] In some embodiments, the second receiving unit 1020 is further configured to receive fourth information, the fourth information being used to request a third set of reference signal resources.

[0476] In some embodiments, the second receiving unit 1020 is further configured to allow the network device to transmit reference signals on the resources corresponding to the third reference signal resource set.

[0477] In some embodiments, the reference signal resources included in the third reference signal resource set are the same as those included in the first reference signal resource set.

[0478] Alternatively, the reference signal resources in the third set of reference signal resources correspond one-to-one with the reference signal resources in the first set of reference signal resources, and the corresponding reference signal resources are quasi-co-addressable (QCL).

[0479] In some embodiments, the third time point is after the time when the terminal device sends the third beam information.

[0480] In some embodiments, the first beam information is further used for performance monitoring of the AI ​​model; the AI ​​model is used by the terminal device to determine the third beam information.

[0481] In some embodiments, one or more of the first beam information, the second beam information, and the fourth beam information include:

[0482] The measurement results corresponding to each reference signal resource in the associated set of reference signal resources; or,

[0483] The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources; or,

[0484] The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources and their corresponding measurement results;

[0485] Where M is an integer greater than 0.

[0486] In some embodiments, the third beam information includes:

[0487] The indices of the K best reference signal resources in the first set of reference signal resources; or,

[0488] The indices of the K best reference signal resources in the first reference signal resource set and the corresponding estimated measurement results;

[0489] Where K is an integer greater than 0.

[0490] In some embodiments, the second receiving unit 1020 is further configured to receive capability information sent by the terminal device, the capability information being used to indicate that the terminal device has the capability to perform beam information recovery and / or prediction based on partial beam information.

[0491] Those skilled in the art should understand that the description of the beam management device in the embodiments of this application can be understood with reference to the description of the beam management method in the embodiments of this application.

[0492] Figure 11 is a schematic structural diagram of a communication device 1100 provided in an embodiment of this application. This communication device can be a terminal device or a network device. The communication device 1100 shown in Figure 11 includes a processor 1110, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0493] Optionally, as shown in FIG11, the communication device 1100 may further include a memory 1120. The processor 1110 may retrieve and run computer programs from the memory 1120 to implement the methods described in the embodiments of this application.

[0494] The memory 1120 can be a separate device independent of the processor 1110, or it can be integrated into the processor 1110.

[0495] Optionally, as shown in FIG11, the communication device 1100 may further include a transceiver 1130, and the processor 1110 may control the transceiver 1130 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0496] The transceiver 1130 may include a transmitter and a receiver. The transceiver 1130 may further include an antenna, and the number of antennas may be one or more.

[0497] Optionally, the communication device 1100 may specifically be a network device in the embodiments of this application, and the communication device 1100 may implement the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0498] Optionally, the communication device 1100 may specifically be a mobile terminal / terminal device in the embodiments of this application, and the communication device 1100 may implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0499] Figure 12 is a schematic structural diagram of a chip according to an embodiment of this application. The chip 1200 shown in Figure 12 includes a processor 1210, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0500] Optionally, as shown in FIG12, chip 1200 may further include memory 1220. Processor 1210 may retrieve and run computer programs from memory 1220 to implement the methods in the embodiments of this application.

[0501] The memory 1220 can be a separate device independent of the processor 1210, or it can be integrated into the processor 1210.

[0502] Optionally, the chip 1200 may also include an input interface 1230. The processor 1210 can control the input interface 1230 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0503] Optionally, the chip 1200 may also include an output interface 1240. The processor 1210 can control the output interface 1240 to communicate with other devices or chips, specifically, to output information or data to other devices or chips.

[0504] Optionally, the chip can be applied to the network device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0505] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0506] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0507] This application also provides a computer storage medium storing one or more programs, which can be executed by one or more processors to implement the methods in this application.

[0508] Figure 13 is a schematic block diagram of a communication system 1300 provided in an embodiment of this application. As shown in Figure 13, the communication system 1300 includes a terminal device 1310 and a network device 1320.

[0509] The terminal device 1310 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 1320 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, these will not be elaborated here.

[0510] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0511] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The 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. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0512] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0513] This application also provides a computer-readable storage medium for storing computer programs.

[0514] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of this 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 this application. For the sake of brevity, it will not be described in detail here.

[0515] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of this 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 this application. For the sake of brevity, it will not be described in detail here.

[0516] This application also provides a computer program product, including computer program instructions.

[0517] Optionally, the computer program product can be applied to the network device in the embodiments of this application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0518] Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of this application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0519] This application also provides a computer program.

[0520] Optionally, the computer program can be applied to the network device in the embodiments of this application. When the computer program is run on the computer, it causes the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0521] Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiments of this application. When the computer program is run on a computer, it causes the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0522] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0523] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0524] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0525] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0526] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0527] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0528] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A beam management method applied to a terminal device, the method comprising: Based on the first beam information and the second beam information, determine the third beam information corresponding to the second or third time moment; Send the third beam information to the network device; Wherein, the first beam information is determined by the terminal device based on a first reference signal resource set at a first moment; the second beam information is determined by the terminal device based on a second reference signal resource set at a second moment; and the third beam information is the beam information corresponding to the first reference signal resource set. The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

2. The method according to claim 1, wherein, The step of determining the third beam information corresponding to the second or third time moment based on the first and second beam information includes: The terminal device uses the first beam information and the second beam information as input to the first artificial intelligence (AI) model, and outputs the third beam information corresponding to the second time moment through the first AI model.

3. The method according to claim 1, wherein, The step of determining the third beam information corresponding to the second or third time moment based on the first and second beam information includes: The terminal device determines the second AI model based on the first beam information; The terminal device uses the second beam information as input to the second AI model, and outputs the third beam information corresponding to the second time moment through the second AI model.

4. The method according to any one of claims 1-3, wherein, The number of second beam information includes multiple types, and different second beam information corresponds to different second time moments; the step of determining the third beam information corresponding to the second or third time moment based on the first and second beam information includes: The terminal device takes the first beam information and multiple second beam information as inputs to the third AI model, and outputs the third beam information corresponding to the third time moment through the third AI model.

5. The method according to any one of claims 1-3, wherein, The number of second beam information includes multiple types, and different second beam information corresponds to different second time moments; the step of determining the third beam information corresponding to the second or third time moment based on the first and second beam information includes: The terminal device determines the fourth AI model based on the first beam information; The terminal device uses multiple second beam information as input to the fourth AI model, and outputs the third beam information corresponding to the third time moment through the fourth AI model.

6. The method according to any one of claims 1 to 5, wherein, The first reference signal resource set and the second reference signal resource set have different periodic configurations and / or frequency domain densities.

7. The method according to claim 6, wherein, Includes one or more of the following: The first reference signal resource set and the second reference signal resource set contain periodic reference signal resources, and the period of the reference signal resources in the first reference signal resource set is greater than the period of the reference signal resources in the second reference signal resource set; The frequency domain density of the first reference signal resource set is less than the frequency domain density of the second reference signal resource set; The first set of reference signal resources includes periodic reference signal resources, and the second set of reference signal resources includes aperiodic or semi-perpetual reference signal resources; The first set of reference signal resources includes aperiodic reference signal resources, and the second set of reference signal resources includes periodic or semi-persistent reference signal resources.

8. The method according to any one of claims 1 to 7, wherein, The association between the first set of reference signal resources and the second set of reference signal resources includes any one of the following: The reference signal resources in the second set of reference signal resources are a portion of the reference signal resources in the first set of reference signal resources; The first reference signal resource set and the second reference signal resource set belong to the same reference signal resource set, and the period of the first reference signal resource set is different from the period of the second reference signal resource set; Each reference signal resource in the second set of reference signal resources is quasi-co-addressable (QCL) with one reference signal resource in the first set of reference signal resources.

9. The method according to any one of claims 1 to 8, wherein, Also includes: The terminal device receives the first information; The first information is used to indicate the association between the first reference signal resource set and the second reference signal resource set.

10. The method according to claim 9, wherein, The reference signal resources in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set, and the first information is used to indicate the position information of the second reference signal resource set in the first reference signal resources.

11. The method according to claim 10, wherein, Also includes: The terminal device determines the second reference signal resource set from the first reference signal resource set based on the first information.

12. The method according to any one of claims 1 to 11, wherein, The input parameters of one or more of the first, second, third, and fourth AI models may also include one or more of the following: The location information of the second reference signal resource set within the first reference signal resource; The QCL relationship between the first reference signal resource set and the second reference signal resource set.

13. The method according to any one of claims 1 to 12, wherein, The first or third AI model is determined based on one or more of the following: The second information sent by the network device; the second information is used to instruct the first AI model or the third AI model; The location information of the second reference signal resource set within the first reference signal resource; The QCL relationship between the first reference signal resource set and the second reference signal resource set.

14. The method according to any one of claims 1 to 13, wherein, The second or fourth AI model is determined based on the first beam information and one or more of the following: The third information sent by the network device; the third information is used to indicate a candidate AI model; the candidate AI model includes the second AI model or the fourth AI model; The location information of the second reference signal resource set within the first reference signal resource; The QCL relationship between the first reference signal resource set and the second reference signal resource set.

15. The method according to any one of claims 1 to 14, wherein, Also includes: The terminal device sends a fourth message, which is used to request a third set of reference signal resources.

16. The method according to claim 15, wherein, Also includes: The terminal device performs measurements based on the third reference signal resource set to obtain the fourth beam information; The terminal device determines the third beam information corresponding to the second or third time moment based on the fourth beam information and the second beam information.

17. The method according to claim 15 or 16, wherein, The reference signal resources included in the third reference signal resource set are the same as those included in the first reference signal resource set. or, The reference signal resources in the third set of reference signal resources correspond one-to-one with the reference signal resources in the first set of reference signal resources, and the corresponding reference signal resources are quasi-co-addressable (QCL).

18. The method according to any one of claims 1 to 17, wherein, The third moment is after the moment when the terminal device sends the third beam information.

19. The method according to any one of claims 1 to 18, wherein, The first beam information is also used for performance monitoring of the AI ​​model; the AI ​​model is used to determine the third beam information.

20. The method according to any one of claims 1 to 19, wherein, One or more of the first beam information, the second beam information, and the fourth beam information include: The measurement results corresponding to each reference signal resource in the associated set of reference signal resources; or, The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources; or, The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources and their corresponding measurement results; Where M is an integer greater than 0.

21. The method according to any one of claims 1 to 20, wherein, The third beam information includes: The indices of the K best reference signal resources in the first set of reference signal resources; or, The indices of the K best reference signal resources in the first reference signal resource set and the corresponding estimated measurement results; Where K is an integer greater than 0.

22. The method according to any one of claims 1 to 21, wherein, Also includes: The terminal device sends capability information to the network device, the capability information indicating that the terminal device has the capability based on partial wavelength. The ability to recover and / or predict beam information from beam information.

23. A beam management method applied to a network device, the method comprising: At the first moment, a reference signal is sent on the resource corresponding to the first reference signal resource set; At the second moment, a reference signal is sent on the resource corresponding to the second reference signal resource set; Receive the third beam information corresponding to the second or third time moment sent by the terminal device; Wherein, the first reference signal resource set is used to determine the first beam information, the second reference signal resource set is used to determine the second beam information, and the third beam information corresponding to the second time or the third time is determined based on the first beam information and the second beam information; the third beam information is the beam information corresponding to the first reference signal resource set; The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

24. The method according to claim 23, wherein, The first reference signal resource set and the second reference signal resource set adopt different periodic configurations and / or frequency domain densities.

25. The method according to claim 24, wherein, Includes one or more of the following: The first reference signal resource set and the second reference signal resource set contain periodic reference signal resources, and the period of the reference resources in the first reference signal resource set is greater than the period of the reference signal resources in the second reference signal resource set; The frequency domain density of the first reference signal resource set is less than the frequency domain density of the second reference signal resource set; The first set of reference signal resources includes periodic reference signal resources, and the second set of reference signal resources includes aperiodic or semi-perpetual reference signal resources; The first set of reference signal resources includes aperiodic reference signal resources, and the second set of reference signal resources includes periodic or semi-persistent reference signal resources.

26. The method according to any one of claims 24 to 25, wherein, The association between the first set of reference signal resources and the second set of reference signal resources includes any one of the following: The reference signal resources in the second set of reference signal resources are a portion of the reference signal resources in the first set of reference signal resources; The first reference signal resource set and the second reference signal resource set belong to the same reference signal resource set, and the period of the first reference signal resource set is different from the period of the second reference signal resource set; Each reference signal resource in the second set of reference signal resources is quasi-co-addressable (QCL) with one reference signal resource in the first set of reference signal resources.

27. The method according to any one of claims 24 to 26, wherein, Also includes: The network device sends the first information; The first information is used to indicate the association between the first reference signal resource set and the second reference signal resource set.

28. The method according to claim 27, wherein, The reference signal resources in the second reference signal resource set are a portion of the reference signal resources in the first reference signal resource set, and the first information is used to indicate the position information of the second reference signal resource set in the first reference signal resources.

29. The method according to any one of claims 24 to 28, wherein, Also includes: The network device sends second information, which is used to indicate a first AI model or a third AI model; the first AI model is used to determine the third beam information corresponding to the second time based on the first beam information and the second beam information, and the third AI model is used to determine the third beam information corresponding to the third time based on the first beam information and the second beam information.

30. The method according to any one of claims 24 to 31, wherein, Also includes: The network device sends third information, which is used to indicate a candidate AI model. The candidate AI model and the first beam information are used to determine a second AI model or a fourth AI model. The second AI model is used to determine the third beam information corresponding to the second time based on the second beam information. The fourth AI model is used to determine the third beam information corresponding to the third time based on the second beam information.

31. The method according to any one of claims 24 to 30, wherein, Also includes: The network device receives fourth information, which is used to request a third set of reference signal resources.

32. The method according to claim 31, wherein, Also includes: The network device transmits reference signals on the resources corresponding to the third reference signal resource set.

33. The method according to claim 31 or 32, wherein, The reference signal resources included in the third reference signal resource set are the same as those included in the first reference signal resource set. or, The reference signal resources in the third set of reference signal resources correspond one-to-one with the reference signal resources in the first set of reference signal resources, and the corresponding reference signal resources are quasi-co-addressable (QCL).

34. The method according to claims 24 to 33, wherein, The third moment is after the moment when the terminal device sends the third beam information.

35. The method according to any one of claims 24 to 34, wherein, The first beam information is also used for performance monitoring of the AI ​​model; the AI ​​model is used by the terminal device to determine the third beam information.

36. The method according to any one of claims 24 to 35, wherein, One or more of the first beam information, the second beam information, and the fourth beam information include: The measurement results corresponding to each reference signal resource in the associated set of reference signal resources; or, The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources; or, The indices of the M reference signal resources with the best measurement results in the associated set of reference signal resources and their corresponding measurement results; Where M is an integer greater than 0.

37. The method according to any one of claims 24 to 36, wherein, The third beam information includes: The indices of the K best reference signal resources in the first set of reference signal resources; or, The indices of the K best reference signal resources in the first reference signal resource set and the corresponding estimated measurement results; Where K is an integer greater than 0.

38. The method according to any one of claims 24 to 37, wherein, Also includes: The network device receives capability information sent by the terminal device, the capability information being used to indicate that the terminal device has the capability to recover and / or predict beam information based on partial beam information.

39. A beam management device applied to a terminal device, the device comprising: The determining unit is configured to determine the third beam information corresponding to the second or third time moment based on the first beam information and the second beam information; The first transmitting unit is configured to transmit the third beam information to the network device; Wherein, the first beam information is determined by the terminal device based on a first reference signal resource set at a first moment; the second beam information is determined by the terminal device based on a second reference signal resource set at a second moment; and the third beam information is the beam information corresponding to the first reference signal resource set. The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

40. A beam management device, applied to a network device, the device comprising: The second transmitting unit is configured to transmit a reference signal on the resource corresponding to the first reference signal resource set at a first moment; The second transmitting unit is further configured to transmit a reference signal on the resource corresponding to the second reference signal resource set at a second time. The second receiving unit is configured to receive the third beam information corresponding to the second or third time moment sent by the terminal device. Wherein, the first reference signal resource set is used to determine the first beam information, the second reference signal resource set is used to determine the second beam information, and the third beam information corresponding to the second time or the third time is determined based on the first beam information and the second beam information; the third beam information is the beam information corresponding to the first reference signal resource set; The second time point is after the first time point, and the third time point is after the second time point; the second set of reference signal resources contains fewer reference signal resources than the first set of reference signal resources.

41. A terminal device, comprising: Memory is used to store executable instructions for a computer; A processor, connected to the memory, is configured to implement the method of any one of claims 1 to 22 by executing the computer-executable instructions.

42. A network device, comprising: Memory is used to store executable instructions for a computer; A processor, connected to the memory, is configured to implement the method of any one of claims 23 to 38 by executing the computer-executable instructions.

43. A chip, the chip comprising: A processor for retrieving and running a computer program from memory, causing a device having the chip mounted to perform the method as described in any one of claims 1 to 22, or to perform the method as described in any one of claims 23 to 38.

44. A computer-readable storage medium storing a computer program that, when executed by at least one processor, implements the method as claimed in any one of claims 1 to 22, or implements the method as claimed in any one of claims 23 to 38.

45. A computer program product comprising a computer storage medium storing a computer program, the computer program comprising instructions executable by at least one processor, wherein when the instructions are executed by the at least one processor, the method of any one of claims 1 to 22 is implemented, or the method of any one of claims 23 to 38 is implemented.

46. ​​A computer program that causes a computer to perform the method as claimed in any one of claims 1 to 22, or to implement the method as claimed in any one of claims 23 to 38.

Images