Wireless communication methods, terminal devices, and network devices

Abstract

Provided are wireless communication methods, terminal devices, and network devices. A method comprises: a terminal device determining a first resource set and / or a second resource set on the basis of first information, wherein a first downlink reference signal corresponding to the first resource set is used for measurement to obtain a measurement result, and the measurement result is used for selecting a target spatial transmission filter from among spatial transmission filters which are used for downlink transmission and are indicated by the second resource set. In the embodiments of the present application, first information is introduced to configure a first resource set and / or a second resource set, which is conductive to improving the rationality of a time domain resource corresponding to the first resource set and a time domain resource corresponding to the second resource set.

Description

Method, terminal device and network device for wireless communication TECHNICAL FIELD

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

[0002] In known protocols, the time-domain resources for measurement (or time-domain resources for transmitting downlink reference signals) and the time-domain resources occupied by sending measurement results involved in the beam (also known as "spatial filter") management process are configured by one or more of the following: periodic configuration, aperiodic configuration, and semi-static scheduling. However, this configuration method is not applicable to model-based beam management.

[0003] SUMMARY

[0004] The present application provides a method, a terminal device and a network device for wireless communication. The various aspects of the present application are described below.

[0005] In a first aspect, a method for wireless communication is provided, comprising: determining, by a terminal device, a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal corresponding to the first resource set is used to measure a measurement result, and the measurement result is used to select a target spatial transmission filter from spatial transmission filters indicated by the second resource set.

[0006] In a second aspect, a method for wireless communication is provided, comprising: transmitting, by a terminal device, first channel state information (CSI) to a network device, wherein a time-domain resource for transmitting the first CSI is determined based on a reference resource, and a time-domain interval between the time-domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0007] In a third aspect, a method for wireless communication is provided, comprising: determining, by a network device, a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal transmitted in the first resource set is used to measure a measurement result, and the measurement result is used to select a target spatial transmission filter from spatial transmission filters indicated by the second resource set.

[0008] In a fourth aspect, a method for wireless communication is provided, comprising: receiving, by a network device, first channel state information (CSI) transmitted by a terminal device, wherein a time-domain resource for transmitting the first CSI is determined based on a reference resource, and a time-domain interval between the time-domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0009] In a fifth aspect, a terminal device is provided, comprising: a processing unit configured to determine a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal corresponding to the first resource set is used to measure a measurement result, and the measurement result is used to select a target spatial transmit filter from spatial transmit filters indicated by the second resource set.

[0010] In a sixth aspect, a terminal device is provided, comprising: a sending unit configured to send first channel state information (CSI) to a network device, wherein a time domain resource used to transmit the first CSI is determined based on a reference resource, and a time domain interval between the time domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0011] In a seventh aspect, a network device is provided, comprising: a processing unit configured to determine a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal transmitted in the first resource set is used to measure a measurement result, and the measurement result is used to select a target spatial transmit filter from spatial transmit filters indicated by the second resource set.

[0012] In an eighth aspect, a network device is provided, comprising: a receiving unit configured to receive first channel state information (CSI) sent by a terminal device, wherein a time domain resource used to transmit the first CSI is determined based on a reference resource, and a time domain interval between the time domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0013] In a ninth aspect, a terminal device is provided, comprising a processor, a memory and a communication interface, wherein the memory is configured to store one or more computer programs, and the processor is configured to invoke the computer programs in the memory, so that the terminal device performs part or all steps in the method of the above aspects.

[0014] In a tenth aspect, a network device is provided, comprising a processor, a memory and a transceiver, wherein the memory is configured to store one or more computer programs, and the processor is configured to invoke the computer programs in the memory, so that the network device performs part or all steps in the method of the second aspect.

[0015] In an eleventh aspect, an embodiment of the present application provides a communication system, which comprises the terminal device and / or the network device described above. In another possible design, the system can further comprise other devices interacting with the terminal device or the network device in the schemes provided by the embodiments of the present application.

[0016] In a twelfth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. The computer program causes a communication device (for example, a terminal device or a network device) to perform some or all of the steps of the methods in the various aspects described above.

[0017] In a thirteenth aspect, an embodiment of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a communication device (for example, a terminal device or a network device) to perform some or all of the steps of the methods in the various aspects described above. In some implementations, the computer program product can be a software installation package.

[0018] In a fourteenth aspect, an embodiment of the present application provides a chip. The chip includes a memory and a processor. The processor can invoke and run a computer program from the memory to implement some or all of the steps described in the methods in the various aspects described above.

[0019] The first information introduced in the embodiments of the present application is used to configure the first resource set and / or the second resource set, which helps to improve the rationality of the time domain resources corresponding to the first resource set and the time domain resources corresponding to the second resource set. BRIEF DESCRIPTION OF DRAWINGS

[0020] FIG. 1 is a wireless communication system 100 to which embodiments of the present application are applied.

[0021] FIGS. 2 to 3 introduce a communication process based on beam communication in the scenario of network device and terminal communication.

[0022] FIG. 4 is a schematic diagram of a basic flow of downlink beam selection to which embodiments of the present application are applied.

[0023] FIG. 5 is a schematic diagram of a basic flow of downlink beam selection to which another embodiment of the present application is applied.

[0024] FIG. 6 is a schematic diagram of a basic flow of downlink beam selection to which another embodiment of the present application is applied.

[0025] FIG. 7 is a schematic diagram of beam management based on BM-Case2.

[0026] FIGS. 8 to 10 introduce an AI model to which embodiments of the present application are applied.

[0027] FIG. 11 is a schematic flowchart of a wireless communication method according to an embodiment of the present application.

[0028] FIG. 12 is a schematic diagram of determining a first downlink reference signal based on a first bitmap according to an embodiment of the present application.

[0029] FIG. 13 is a schematic diagram of determining a first downlink reference signal based on a first time window according to an embodiment of the present application.

[0030] FIG. 14 is a schematic diagram of determining a plurality of first downlink reference signals based on first information according to an embodiment of the present application.

[0031] FIG. 15 is a schematic diagram of determining a downlink reference signal corresponding to a second resource set based on a second bitmap according to an embodiment of the present application.

[0032] FIG. 16 is a schematic diagram of determining a downlink reference signal corresponding to a second resource set based on a second time window according to an embodiment of the present application.

[0033] FIG. 17 is a schematic diagram of determining a plurality of downlink reference signals corresponding to a second resource set based on first information according to an embodiment of the present application.

[0034] FIG. 18 is a schematic diagram of determining a time domain resource based on a first bitmap and a second bitmap according to an embodiment of the present application.

[0035] FIG. 19 is a schematic diagram of determining a time domain resource based on a first time window and a second time window according to an embodiment of the present application.

[0036] FIG. 20 is a schematic diagram of determining a first downlink reference signal corresponding to a first resource set and a plurality of downlink reference signals corresponding to a second resource set based on first information according to an embodiment of the present application.

[0037] FIG. 21 is a schematic diagram of determining a time domain resource of a first downlink reference signal corresponding to a first resource set and a time domain resource of a plurality of downlink reference signals corresponding to a second resource set based on first information according to another embodiment of the present application.

[0038] FIG. 22 is a schematic diagram of determining a time domain resource based on a first timer and a second timer according to another embodiment of the present application.

[0039] FIG. 23 is a schematic diagram of determining a time domain resource occupied by a CSI report based on a CSI reference resource.

[0040] FIG. 24 is a schematic flowchart of a wireless communication method according to another embodiment of the present application.

[0041] FIG. 25 is a schematic diagram of determining a time domain resource occupied by a CSI report based on a CSI reference resource according to an embodiment of the present application.

[0042] FIG. 26 is a schematic diagram of a terminal device according to an embodiment of the present application.

[0043] FIG. 27 is a schematic diagram of a terminal device according to another embodiment of the present application.

[0044] FIG. 28 is a schematic diagram of a network device according to an embodiment of the present application.

[0045] FIG. 29 is a schematic diagram of a network device according to an embodiment of the present application.

[0046] FIG. 30 is a schematic structural diagram of a communication apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] The technical solutions in the present application will be described in conjunction with the accompanying drawings. In order to facilitate understanding, the following will first introduce the communication system to which the embodiments of the present application are applicable, as well as the related terms and communication processes.

[0048] FIG. 1 is a wireless communication system 100 to which embodiments of the present application are applied. The wireless communication system 100 can include a network device 110 and a terminal device 120. The network device 110 can be a device that communicates with the terminal device 120. The network device 110 can provide communication coverage for a specific geographic area and can communicate with the terminal device 120 located in the coverage area.

[0049] FIG. 1 exemplarily shows one network device and two terminals. Optionally, the wireless communication system 100 can include multiple network devices and each network device can include other numbers of terminal devices within its coverage, which is not limited in the embodiments of the present application.

[0050] Optionally, the wireless communication system 100 can further include a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0051] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as a 5th generation (5G) system or new radio (NR), a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), and the like. The technical solutions provided by the present application can also be applied to future communication systems, such as a 6th generation mobile communication system, a satellite communication system, and the like.

[0052] The terminal device in the embodiments of the present application can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station (MS), a mobile terminal (MT), a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user apparatus. The terminal device in the embodiments of the present application can refer to a device providing voice and / or data connectivity for a user, and can be used to connect people, things and machines, for example, handheld devices with wireless connection function, vehicle-mounted devices, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer (Pad), a notebook computer, a palm computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity, which provides a sidelink signal between UEs in V2X or D2D, etc. For example, a cellular phone and a car communicate with each other using a sidelink signal. The cellular phone and the smart home device communicate with each other without relaying the communication signal through the base station.

[0053] The network device in the embodiments of the present application can be a device for communicating with a terminal device, which can also be referred to as an access network device or a radio access network device, such as a network device, which can be a base station. The network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) that accesses a terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station MeNB, auxiliary station SeNB, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip for being arranged in the foregoing device or apparatus. The base station can also be a mobile switching center and a device that undertakes a base station function in device-to-device (D2D), vehicle-to-everything (V2X), machine-to-machine (M2M) communication, network side device in 6G network, device that undertakes a base station function in future communication system, etc. The base station can support networks of the same or different access technologies. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

[0054] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to act as a device that communicates with another base station.

[0055] In some deployments, the network device in the embodiments of the present application can refer to a CU or a DU, or the network device includes a CU and a DU. The gNB can also include an AAU.

[0056] The network device and the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water surface; and can also be deployed on aircraft, balloons and satellites in the air. The scenarios in which the network device and the terminal device are located are not limited in the embodiments of the present application.

[0057] It should be understood that all or part of the functions of the communication device in the present application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform).

[0058] Multi-beam system

[0059] The design goals of a communication system (for example, NR) include large-bandwidth communication in a high frequency band (for example, a frequency band above 6 GHz). When the working frequency becomes higher, the path loss in the transmission process increases, thereby affecting the coverage capability of the high frequency system. Therefore, in order to effectively ensure the coverage range of the high frequency band, an effective technical solution is to form a larger gain beam based on a large-scale antenna array (Massive multiple-in multiple-out, Massive MIMO), so as to overcome the propagation loss and ensure the coverage range of the communication system.

[0060] At present, a common large-scale antenna array is a millimeter wave antenna array. Due to the shorter wavelength emitted by the millimeter wave antenna array, the spacing between the antenna elements of the antenna array can be shorter, and the aperture of the antenna element can be smaller, so that more physical antenna elements can be integrated in a two-dimensional antenna array of a limited size.

[0061] In addition, due to the limited size of the millimeter wave antenna array, from the aspects of hardware complexity, cost overhead and power consumption, a digital beamforming mode cannot be used, and an analog beamforming mode is usually used, which can enhance network coverage while reducing the implementation complexity of the device.

[0062] In order to facilitate understanding of the multi-beam system, the following describes a communication process based on beam communication in the scenario of network device and terminal communication in combination with FIG. 2 to FIG. 3.

[0063] Referring to FIG. 2, in a traditional communication system (for example, an LTE communication system), a relatively wide beam 210 is usually used to cover the entire cell (or sector). In this way, the terminals (for example, terminals 211-215) in the cell can communicate with the network device through the relatively wide beam at each moment, for example, to obtain the transmission resources allocated by the network device.

[0064] Referring to FIG. 3, in a newer communication system (e.g., NR), a multi-beam system 310 can be used to cover the entire cell, that is, each beam (e.g., beams 311-314) in the multi-beam system covers a smaller range in the cell respectively, and the effect of covering the entire cell by multiple beams is achieved by means of beam sweeping.

[0065] In the process of beam sweeping, different beams are used to cover different areas in the cell at different times, for example, at time 1, the communication system can cover the area where terminal 321 is located by beam 311. At time 2, the communication system can cover the area where terminal 322 is located by beam 312. At time 3, the communication system can cover the area where terminal 323 and terminal 324 are located by beam 313. At time 4, the communication system can cover the area where terminal 325 is located by beam 314.

[0066] For the multi-beam system, because a narrower beam is used, the transmission energy can be more concentrated, so it can cover a longer distance. However, because the beam is narrower, each beam can only cover part of the area in the cell, so the multi-beam system can be understood as "trading time for space".

[0067] Generally, the beam used by the sending end to send signals is called "sending beam". The beam used by the receiving end to receive signals is called "receiving beam".

[0068] In some cases, the above-mentioned sending beam can also be called a spatial domain transmission filter or a spatial transmission filter. Correspondingly, the above-mentioned receiving beam can also be called a spatial domain reception filter or a spatial reception filter. In other cases, the above-mentioned sending beam can also be called a spatial domain transmission parameter, and correspondingly, the above-mentioned receiving beam can also be called a spatial domain reception parameter. For ease of understanding, the embodiments of the present application mainly take the beam as an example for introduction.

[0069] In other cases, the sending beam and the receiving beam can be collectively referred to as "beam", which can be called spatial filter or spatial filter.

[0070] In a communication scenario between a network device and a terminal, if the network device and the terminal support multi-beam transmission, the network device and the terminal need to select a suitable transmission beam and a suitable reception beam through a beam management process (for example, a process that can include beam selection, beam measurement, measurement reporting, etc.) before the network device and the terminal communicate. For example, in the process of selecting a transmission beam, the network device can use different transmission beams to send multiple downlink reference signals in turn, and the resources corresponding to the multiple downlink reference signals are different. Correspondingly, the terminal device also uses multiple reception beams to receive the multiple downlink reference signals respectively, and performs measurement on the detected reference signals to obtain beam measurement results (also referred to as "measurement results"). Then, the terminal device selects part of the detected multiple downlink reference signals, and feeds back the resource identifiers of the part of the downlink reference signals and the corresponding beam measurement results to the network device, so that the network device selects a suitable transmission beam as a transmission beam for subsequent communication with the terminal.

[0071] Generally, after the network device selects a suitable transmission beam, the terminal device needs to select a reception beam matched with the transmission beam to communicate with the network device. For ease of understanding, the following describes a beam management process taking downlink beam management as an example. Generally, beam management can include processes such as beam selection, beam measurement, and measurement reporting.

[0072] Beam selection

[0073] For ease of understanding, the following describes a basic process of beam selection taking FIG. 4 to FIG. 6 as an example. The pairing process of a transmission beam and a reception beam in downlink transmission can be generally divided into three main processes, which are denoted as P1, P2, and P3. P1 is a coarse pairing of a downlink transmission beam and a downlink reception beam. P2 is a fine adjustment of a downlink transmission beam on the network side. P3 is a fine adjustment of a downlink reception beam on the terminal side.

[0074] Referring to FIG. 4, it is assumed that the network device has four downlink transmission beams: transmission beam 0 to transmission beam 3, and the terminal device has four downlink reception beams: reception beam A to reception beam D. At initial access, coarse pairing can be achieved through a random access process, that is, after initial access, a beam pair with relatively good link quality can be established between the network device and the terminal device, which can support subsequent data transmission. At this time, if the transmission beam and the reception beam are relatively narrow, a relatively long time is needed to align with each other, which will bring a large time delay to the system. Therefore, in order to quickly complete the coarse pairing between the beams, the transmission beam and the reception beam can be relatively wide, and the beam pair formed can obtain good performance, but can not be the optimal pair.

[0075] On the basis of the rough pairing of P1, fine adjustment of the sending beam and the receiving beam (corresponding to P2 and P3 processes respectively) can be performed to further provide transmission performance using finer beams. Referring to FIG. 5, through the P1 process, rough pairing between the downlink sending beam 2 and the downlink receiving beam A is completed. Then, the sending beam 2 can be fine-adjusted. Accordingly, the network device can send three narrower beams: beam 2-1, beam 2-1, and beam 2-3. Accordingly, the terminal device uses the receiving beam A to receive signals transmitted on the beams 2-1, 2-1, and 2-3 respectively, and performs layer 1-reference signal receiving power (L1-RSRP) measurement. Then, based on the beam measurement result, the terminal device reports one or more selected beams to the network device.

[0076] Referring to FIG. 5, through the P1 process, rough synchronization between the downlink sending beam 2 and the downlink receiving beam A is completed. In order to fine-adjust the receiving beam, the network device can send a measurement signal on the beam 2 multiple times. Accordingly, the terminal device can use three narrower beams: beam A-1, beam A-2, and beam A-3 to receive signals transmitted on the beam 2, and perform measurement. Then, based on the beam measurement result, the terminal device can determine which narrow beam is better for receiving the sending beam 2. In this process, the terminal device does not need to report to the network device which narrow beam it has selected to receive the sending beam 2.

[0077] It should be noted that the P1-P3 processes introduced above indicate an exemplary process of beam selection. In the embodiments of the present application, the beam selection process can also be implemented in other ways, which are not limited in the embodiments of the present application.

[0078] The exemplary processes of beam selection are introduced above in combination with FIGS. 4-6, and the beam measurement process and the reporting process are still introduced below.

[0079] In addition, the sending beam and the receiving beam pairing process in the uplink transmission can also be divided into three main processes, which are denoted as U1, U2, and U3. Among them, U1 is the rough pairing of the uplink sending beam and the receiving beam. U2 is the fine adjustment of the network side uplink receiving beam. U3 is the fine adjustment of the terminal side uplink sending beam. The above U1-U3 processes are similar to the P1-P3 processes, and are not described again below for brevity.

[0080] Beam measurement

[0081] Generally, in the beam selection process, the beams need to be measured accordingly. At present, the measurement of a beam can be achieved by measuring the reference signal transmitted on the beam.

[0082] In some implementations, for the measurement of the downlink beam, the measurement can be implemented by the CSI-RS or SSB transmitted on the downlink beam. In some other implementations, for the measurement of the uplink beam, the measurement can be implemented by the SRS or SSB transmitted on the downlink beam.

[0083] In some implementations, for the measurement of the beam (the measurement of the uplink beam and the measurement of the downlink beam), the measurement quantity can adopt the measurement quantity of the layer 1 (L1) measurement. The L1 measurement can be directly processed at the physical layer, and has a shorter processing delay. Currently, the L1 measurement quantity for the beam measurement can include: the layer 1-reference signal receiving power (L1-RSRP) and the layer 1-signal to interference plus noise ratio (L1-SINR).

[0084] In some other implementations, for the measurement of the uplink beam, the measurement quantity can adopt the measurement quantity of the layer 1 (L1) measurement. The L1 measurement can be directly processed at the physical layer, and has a shorter processing delay. Currently, the L1 measurement quantity for the beam measurement can include: the layer 1-reference signal receiving power (L1-RSRP), the layer 1-signal to interference plus noise ratio (L1-SINR) and the layer 1-reference signal receiving quality (L1-RSRQ).

[0085] It should be noted that, in the embodiments of the present application, in addition to the L1 measurement quantity introduced above, other measurement quantities can also be used for the beam measurement, such as the L3 measurement quantity. Of course, the measurement quantity applicable to the embodiments of the present application can also be a new measurement quantity introduced in the future communication system.

[0086] Measurement reporting

[0087] In some implementations, the terminal device can report one or more information to the network device based on the beam measurement result (also referred to as "measurement result"), each information including beam indication information (such as the identification of the reference signal, the number of the reference signal, etc.) and the corresponding measurement quantity.

[0088] Model-based beam management

[0089] With the increase of the number of beams in future massive MIMO systems, using a beam management scheme based on beam sweeping will only bring greater reference signal transmission overhead and beam sweeping delay in order to match the optimal beam pair. Therefore, in order to avoid the above problems, a beam management based on an AI model is proposed, where the model can refer to an artificial intelligence (AI) model and / or a machine learning (ML) model.

[0090] Hereinafter, the model-based beam management scheme is introduced in combination with the model training process and the model prediction process, taking the AI model as an example.

[0091] Suppose the AI model is used to predict available beams in Set A, accordingly, in the model training phase, the beam measurement results of Set B can be used as AI model training data, that is, the AI model is trained based on the beam measurement results of Set B, so that the AI model can predict available beams from Set A.

[0092] It should be noted that the above beam measurement results of Set B can include measurement results corresponding to L1 measurement quantities, and / or indication information of beams selected in Set B (for example, transmission beam identifier, reception beam identifier, or beam pair identifier, etc.).

[0093] In some implementations, the training data can also include label information of Set A, which is used to indicate one or more beams in Set A: optimal transmission beam, optimal reception beam, optimal beam pair, multiple optimal transmission beams, multiple optimal reception beams, and multiple optimal beam pairs.

[0094] In the prediction phase, the input of the AI model can include the link quality measurement results (for example, L1 measurement quantities) corresponding to the beams in Set A, and the prediction result output by the AI model can include the target beam selected from Set A and the link quality corresponding to the target beam.

[0095] In some implementations, the above target beam can be one or more beams. Taking the target beam as one beam for example, the target beam can be the optimal beam or the optimal beam in Set A. Taking the target beam as multiple beams for example, the target beam can be multiple beams in Set A that meet the requirements, where meeting the requirements can be understood as the link quality corresponding to the beam meeting the requirements, for example, the link quality corresponding to the beam is greater than or equal to a threshold.

[0096] In some implementations, the target beam can be one or more beam pairs. For example, the target beam can be the best beam pair or the better beam pair in the set A. For example, the target beam can be one or more beam pairs in the set A that meet a requirement. For example, the requirement can be that the link quality corresponding to the beam pair is greater than or equal to a threshold.

[0097] It should be noted that the link quality in the embodiments of the present application can be determined by one or more of the above-mentioned measurement quantities. Of course, the link quality in the embodiments of the present application can also be determined based on other measurement quantities in future communication systems, which are not limited in the embodiments of the present application.

[0098] In addition, the link quality determined based on one or more measurement quantities can be understood as the link quality obtained by processing one or more measurement quantities. Of course, the link quality can also be a measurement quantity, which is not limited in the embodiments of the present application.

[0099] It should be further noted that if the prediction result only indicates one beam in the beam pair, the other beam in the beam pair can be determined by other methods. For example, the other beam can be determined by one or more of the above-mentioned P1-P3, or can be determined by one or more of U1-U3, which are not limited in the embodiments of the present application.

[0100] In some implementations, the set B can be different from the set A. In some implementations, the set B can be a subset of the set A. Accordingly, by measuring fewer beams (beams in the set B), the prediction for more beams (beams in the set A) can be achieved. Compared with the above-mentioned beam selection scheme based on traversing all combinations, the time for performing the beam selection process can be reduced. Of course, in the embodiments of the present application, the beams in the set B and the beams in the set A can be completely different beams. For example, the set B and the set A have no intersection, but the beam directions corresponding to the set B can be similar to the beam directions corresponding to the set A.

[0101] In some other implementations, the set B can be the same as the set A.

[0102] Currently, in some discussions, spatial domain (beam management-Case1, BM-Case1) and time domain (BM-Case2) downlink beam management are proposed for model-based beam management, i.e., for AI / ML-based beam management, BM-Case1 and BM-Case2 are supported for characterization and baseline performance evaluations.

[0103] For BM-Case1, spatial-domain DL beam prediction for Set A of beams is determined based on measurement results of Set B of beams.

[0104] For BM-Case2, temporal DL beam prediction for Set A of beams is determined based on the historic measurement results of Set B of beams.

[0105] It should be noted that for BM-Case1 and BM-Case2, beams in Set A and Set B can be in the same frequency range.

[0106] The following mainly introduces the basic situation of BM-Case2. For BM-Case2, the scheme can be understood as predicting the optimal beam and the link quality corresponding to the optimal beam from Set A by measuring the downlink reference signal (or measuring the downlink transmission beam) in Set B at one or more historical time instants.

[0107] As shown in FIG. 7, it is assumed that K (K = 4) measurements are performed in a time period T1 to obtain measurement results at historical time points, where the K measurements are for K downlink reference signals. The time domain interval between the K downlink reference signals is 100 ms. The measurement results obtained in the time period T1 are used to predict the optimal beams used at F time points (for example, F = 4, i.e., time point 1-time point 4) in a time period T2. That is, the input of the model is the measurement results of the K measurements (for example, the measurement results include reference signal indexes and / or corresponding link qualities), and accordingly, the output of the model is the optimal beam information at the F future time points (or prediction instances) and / or the link qualities corresponding to the optimal beams. The link quality can include the L1-RSRP introduced above.

[0108] It should be noted that the name of the set A and / or the set B is not limited in the embodiments of the present application. In some scenarios, the set B can also be referred to as a first resource set or a first resource. In other scenarios, the set A can also be referred to as a second resource set or a second resource.

[0109] For ease of understanding, the AI model applicable to the embodiments of the present application is introduced below in combination with FIGS. 8-10. Of course, the AI model of the embodiments of the present application can also be other models, which are not limited in the embodiments of the present application.

[0110] Neural network

[0111] In recent years, artificial intelligence research represented by neural networks has achieved very great results in many fields, and it will play an important role in people's production and life for a long time in the future. The neural network can be understood as an operation model composed of multiple neuron nodes connected to each other, where the connection between the nodes can represent the weighted value from the input signal to the output signal, usually referred to as the weight. Each node performs weighted summation on different input signals and outputs through a specific activation function.

[0112] Referring to FIG. 8, a neuron can rely on an activation function to realize nonlinear mapping, where the input of the neuron can be denoted as A, and each dimension of the input is denoted as a j The corresponding weight is denoted as w j The SU enhances or weakens the input together. In addition, the output of the SU can be input to the activation function f to obtain the output t, where j takes the value of 1, 2, …, n.

[0113] Common neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep neural networks (DNNs), and the like.

[0114] The neural network applicable to the embodiments of the present application is described below in conjunction with FIG. 9. The neural network shown in FIG. 9 can be divided into three categories according to the positions of different layers: an input layer 910, hidden layers 920, and an output layer 930. Generally, the first layer is the input layer 910, the last layer is the output layer 930, and the intermediate layers between the first layer and the last layer are the hidden layers 920.

[0115] The input layer 910 is configured to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layers 920 are configured to process the input data, for example, to perform decompression processing on the received signal. The output layer 930 is configured to output the processed output data, for example, to output the decompressed signal.

[0116] As shown in FIG. 9, the neural network includes multiple layers, each layer including multiple neurons, and the neurons between layers can be fully connected or partially connected. For the connected neurons, the output of the neurons of the previous layer can be used as the input of the neurons of the next layer.

[0117] Now that there are artificial neural networks and convolutional neural networks, why is there a recurrent neural network? The reason is simple. Whether it is a convolutional neural network or an artificial neural network, their premise assumption is that elements are independent of each other, and inputs and outputs are also independent, such as cats and dogs. However, in the real world, many elements are connected to each other, such as the change of a stock over time. A person said: I like traveling, and my favorite place is Yunnan. I will definitely go there if I have the opportunity. Here, the blank should be filled with "Yunnan". Because we infer it from the context, but it is quite difficult to achieve this. Therefore, there is now a recurrent neural network, which has the ability to remember like a person. Therefore, its output depends on the current input and memory.

[0118] The long short-term memory (LSTM) model and the gated recurrent unit (GRU) can be used as typical RNNs. Taking the LSTM model as an example, refer to FIG. 10. The LSTM introduces a new memory unit c t(Also can be referred to as "cell state") is used to perform linear recurrent information transmission while outputting information to the external state h of the hidden layer t At each time t, c t Records the historical information up to the current time. Unlike RNN, which only considers the latest state, the memory unit decides which states should be left and which states should be forgotten, solving the long-term memory defects of traditional RNN.

[0119] Referring to FIG. 10, in order to realize the selection of the above state, the memory unit introduces a gate control mechanism to control the path of information transmission, similar to the gate in the data circuit, "0" means closed, and "1" means open. The memory unit includes a forgetting gate 1010, an input gate 1020, and an output gate 1030. Among them, the forgetting gate is used to control the memory unit c t-1 How much information needs to be forgotten, the input gate is used to control the candidate state of the current time How much information needs to be stored, the output gate is used to control the memory unit c t How much information needs to be output to the external state h t .

[0120] In known protocols, the time domain resources used for measurement (or time domain resources for transmitting downlink reference signals) and the time domain resources occupied by sending measurement results involved in the beam management process are configured by one or more of the following: periodic configuration, aperiodic configuration, and semi-static scheduling. However, this configuration method is not suitable for model-based beam management processes.

[0121] The applicant found that the above configuration method is not suitable for model-based beam management processes because the time required for model-based prediction of the optimal beam is not considered. Referring to FIG. 7, in the model-based beam management process (for example, BM-Case2), the model needs to predict the optimal beam at F time points in the time period T2. However, if the time domain resources are configured according to the periodic configuration or aperiodic configuration method introduced above, there is no sufficient time reserved between adjacent time domain resources in the time domain for model prediction.

[0122] Therefore, to solve the above problem, the embodiment of the present application introduces first information to configure the first resource set and / or the second resource set, which helps to improve the rationality of the time domain resources corresponding to the first resource set and the time domain resources corresponding to the second resource set.

[0123] Referring to step S1110 shown in FIG. 11, the terminal device determines the first resource set and / or the second resource set based on the first information.

[0124] Referring to step S1120 shown in FIG. 11, the network device determines the first resource set and / or the second resource set based on the first information.

[0125] In some implementations, the first downlink reference signal corresponding to the first resource set is used to measure the measurement result. The first downlink reference signal corresponding to the first resource set can be understood as a first downlink reference signal transmitted through a spatial transmission filter (also referred to as a transmission beam) indicated by the first resource set. In other implementations, the first resource set can be set B, and the related description can be referred to above.

[0126] In some implementations, the measurement result is used to select a target spatial transmission filter from the spatial transmission filters (also referred to as downlink transmission beams) indicated by the second resource set for downlink transmission. In other implementations, the second resource set can be set A, and the related description can be referred to above.

[0127] In the embodiments of the present application, the downlink reference signal (for example, the first downlink reference signal or the plurality of downlink reference signals) is not limited. In some implementations, the downlink reference signal can be, for example, a channel state information-reference signal (CSI-RS) or a synchronization signal and PBCH block (SSB). Of course, in the embodiments of the present application, the downlink reference signal can also be other reference signals introduced in future communication systems.

[0128] In the embodiments of the present application, the selection of the target spatial transmission filter is not limited. In some implementations, the target spatial transmission filter can include one or more spatial transmission filters. Taking the target spatial transmission filter as one spatial transmission filter as an example, the target spatial transmission filter can be an optimal spatial transmission filter or a better spatial transmission filter in set A. Taking the target spatial transmission filter as a plurality of spatial transmission filters as an example, the target spatial transmission filter can be a plurality of spatial transmission filters in set A that meet the requirements, where the meeting of the requirements can be understood as that the link quality corresponding to the spatial transmission filter meets the requirements, for example, the link quality corresponding to the spatial transmission filter is greater than or equal to a threshold.

[0129] The first resource set and the second resource set of the embodiments of the present application are introduced above, and the first information in the embodiments of the present application is introduced below in combination with Embodiment 1 and Embodiment 2.

[0130] In some implementations, the first information is used to indicate the time domain resource corresponding to the first downlink reference signal from time domain resources corresponding to a plurality of downlink reference signals, wherein the time domain resources corresponding to the plurality of downlink reference signals are periodically configured or semi-persistently scheduled. The time domain resources corresponding to the plurality of downlink reference signals can be understood as time domain resources used for transmission of the plurality of downlink reference signals. The time domain resource corresponding to the first downlink reference signal can be understood as a time domain resource used for transmission of the first downlink reference signal.

[0131] In some implementations, the first information is used to indicate the time domain resource corresponding to the first downlink reference signal from time domain resources corresponding to a plurality of downlink reference signals, wherein the time domain resources corresponding to the plurality of downlink reference signals are periodically configured or semi-persistently scheduled. The time domain resources corresponding to the plurality of downlink reference signals can be understood as time domain resources used for transmission of the plurality of downlink reference signals. The time domain resource corresponding to the first downlink reference signal can be understood as a time domain resource used for transmission of the first downlink reference signal.

[0132] As introduced above, the first downlink reference signal corresponding to the first resource set is a reference signal for measurement (also referred to as a "measurement instance"), and accordingly, the time domain resource used for transmission of the first downlink reference signal can be understood as a time domain resource for measurement. Therefore, the first information can also be understood as used to indicate a time domain resource for measurement and / or a time domain resource not for measurement from time domain resources corresponding to a plurality of downlink reference signals.

[0133] That is, the first information can be used to adjust the time domain resource based on periodic configuration or semi-persistent scheduling (for example, time domain resources configured by a network device in a known communication system), which helps to improve the rationality of the time domain resource occupied by the first downlink reference signal from a plurality of downlink reference signals under the premise of compatibility with a traditional communication system.

[0134] In some implementations, if the time domain resource is a periodic time domain resource, the period of the time domain resource may, for example, be one or more of 60 ms, 80 ms, 160 ms or 320 ms.

[0135] In implementation 1-1, the first information indicates whether the time domain resource corresponding to the first downlink reference signal is the time domain resource corresponding to the first downlink reference signal from a plurality of time domain resources corresponding to a plurality of downlink reference signals, or in other words, the first information is used to indicate a first bitmap used to indicate the time domain resource used for transmission of the first downlink reference signal from the plurality of time domain resources corresponding to the plurality of downlink reference signals.

[0136] In some implementations, each bit in the first bitmap corresponds to one time domain resource in the plurality of time domain resources. If a value of a bit in the first bitmap is a first value, it indicates that the time domain resource corresponding to the bit is a time domain resource for transmitting the first downlink reference signal. Conversely, if a value of a bit in the first bitmap is a second value, it indicates that the time domain resource corresponding to the bit is a time domain resource not for transmitting the first downlink reference signal. The first value and the second value are different, for example, the first value can be 1 and the second value can be 0. For another example, the first value can be 0 and the second value can be 1.

[0137] In the embodiments of the present application, the transmission manner of the first bitmap is not limited. In some implementations, the first bitmap can be indicated by the network device to the terminal device. For example, the network device can send radio resource control (RRC) signaling (as an example of the first information) to the terminal device, and the RRC signaling is used to configure the first bitmap for the terminal device. For another example, the network device can send information (as an example of the first information) used to configure the first bitmap for the terminal device when indicating to activate or deactivate the downlink time domain resource to the terminal device. That is, the network device sends indication information 1 to the terminal device, the indication information 1 is used to indicate to activate or deactivate the downlink time domain resource, and the indication information 1 carries information (as an example of the first information) used to configure the first bitmap for the terminal device.

[0138] In some implementations, the first bitmap can correspond to a plurality of groups of time domain resources, and accordingly, the first bitmap can indicate whether each group of time domain resources in the plurality of groups of time domain resources is used for transmitting the first downlink reference signal, or in other words, the first bitmap can periodically indicate whether each group of time domain resources in the plurality of groups is used for transmitting the first downlink reference signal. This will be described below in conjunction with FIG. 12.

[0139] In the embodiments of the present application, the duration of the multiple groups of time domain resources is not limited by the first bitmap. For example, if the multiple groups of time domain resources are periodic time domain resources, the first bitmap can periodically indicate whether the multiple groups of time domain resources are used for transmitting the first downlink reference signal until the network device reconfigures the periodic time domain resources for the terminal device (for example, the network device reconfigures through RRC signaling). For another example, if the multiple groups of time domain resources are semi-persistent scheduling time domain resources, the first bitmap can periodically indicate whether the time domain resources are used for transmitting the first downlink reference signal until the network device indicates to activate new time domain resources (for example, the network device indicates to activate new time domain resources through a media access control control element (MAC CE)). For another example, if the multiple groups of time domain resources are semi-persistent scheduling time domain resources, the first bitmap can periodically indicate whether the time domain resources are used for transmitting the first downlink reference signal until the network device indicates to deactivate part or all of the multiple groups of time domain resources (for example, the network device indicates to deactivate part or all of the multiple groups of time domain resources through a MAC CE).

[0140] Suppose the format of the first bitmap is “11110000”, where the time domain resources corresponding to the bits with a value of 1 are used for transmitting the first downlink reference signal, and the time domain resources corresponding to the bits with a value of 0 are not used for transmitting the first reference signal. Referring to FIG. 12, the multiple groups of time domain resources include 8 time domain resources in group 1 and 8 time domain resources in group 2. Accordingly, the first bitmap can be used to indicate whether the time domain resources in group 1 and group 2 are used for transmitting the first downlink reference signal, respectively.

[0141] Accordingly, the first bitmap can indicate that the time domain resources (or time instances) corresponding to the first 4 periods in group 1 are used for transmitting the first downlink reference signal, and accordingly, the terminal device can perform measurement on the time domain resources corresponding to the first 4 periods, and the reference signals corresponding to the first 4 periods can be referred to as measurement instances. The first bitmap can also indicate that the time domain resources (or time instances) corresponding to the last 4 periods in group 1 are not used for transmitting the first downlink reference signal, and accordingly, the terminal device can not perform measurement on the time domain resources corresponding to the last 4 periods, and the reference signals corresponding to the last 4 periods can be referred to as prediction instances.

[0142] In addition, the measurement results (for example, the optimal beam and / or the link quality corresponding to the optimal beam) obtained by measuring the time domain resources corresponding to the first 4 periods can be used as input information of the model, so as to output the target spatial transmission filter of the model.

[0143] In the implementation 1-2, the first information can indicate, by the first time window, whether the time domain resource corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal.

[0144] In some implementations, the first information is used to indicate that the time domain resource, which is partially or entirely overlapped with the first time window, in the time domain resources corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal.

[0145] In some implementations, the time domain resource, which is entirely overlapped with the first time window, in the time domain resources corresponding to the multiple downlink reference signals can be understood as the time domain resource located in the first time window in the time domain resources corresponding to the multiple downlink reference signals. That is, the first information is used to indicate that the time domain resource located in the first time window in the time domain resources corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal, or the first information is used to indicate that the time domain resource located in the first time window in the time domain resources corresponding to the multiple downlink reference signals is used to transmit the first downlink reference signal.

[0146] In other implementations, the time domain resource, which is partially overlapped with the first time window, in the time domain resources corresponding to the multiple downlink reference signals can be understood as that some of the time domain resources in the time domain resources corresponding to the multiple downlink reference signals are partially overlapped with the first time window. For example, a part of the last time domain resource in the time domain resources corresponding to the multiple downlink reference signals is located in the first time window, and the time domain resource can be used to transmit the first downlink reference signal. For another example, a part of the earliest time domain resource in the time domain resources corresponding to the multiple downlink reference signals is located in the first time window, and the time domain resource can be used to transmit the first downlink reference signal.

[0147] Of course, in the embodiments of the present application, the first information can be used to indicate that the time domain resource, which is located outside the first time window, in the time domain resources corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal.

[0148] In some implementations, the time domain resources corresponding to the multiple downlink reference signals can be periodically configured time domain resources or semi-persistently scheduled time domain resources. Accordingly, in the embodiments of the present application, the time domain resources corresponding to the multiple downlink reference signals can be adjusted based on the first time window on the basis of the time domain resources corresponding to the multiple downlink reference signals to obtain the time domain resources corresponding to the first downlink reference signal, which helps to improve the rationality of the time domain resources corresponding to the first downlink reference signal. For example, the time domain interval between the first downlink reference signals can be adjusted by the first time window, so as to facilitate model inference, model monitoring, model training and the like in the time period corresponding to the time domain interval.

[0149] As described above, in some implementations, the terminal device measures the first downlink reference signal, and thus the first time window for indicating the first downlink reference signal can also be referred to as a "measurement window".

[0150] In the embodiments of the present application, the manner in which the first information indicates the first time window is not limited. In some implementations, the first information can include one or more of the following: a starting time domain position of the first time window, a length of the first time window, an ending time domain position of the first time window.

[0151] For ease of understanding, the scheme for determining the first downlink reference signal based on the first time window in the embodiments of the present application is introduced below in conjunction with FIG. 13. Referring to FIG. 13, it is assumed that the network device configures periodic time domain resources for the terminal device, and FIG. 13 shows 12 downlink time domain resources. Accordingly, the first information indicates that the starting time domain positions of the first time window are P1 and P2, and the length of the first time window is Q. The length Q of the first time window can include time domain resources corresponding to 4 downlink reference signals.

[0152] In this way, the first time window with the starting time domain position P1 contains downlink time domain resources 1-4, and the first time window with the starting time domain position P2 contains downlink time domain resources 9-12. That is, the time domain resources corresponding to the first downlink reference signal are time domain resources 1-4 and time domain resources 9-12. Accordingly, model prediction, model inference, and model monitoring can be performed in the time period corresponding to time domain resources 5-8.

[0153] In implementation 1-3, the first resource set corresponds to multiple first downlink reference signals, and the first information is used to indicate time domain resources corresponding to the multiple first downlink reference signals.

[0154] In some implementations, the first resource set corresponding to multiple first downlink reference signals can be understood as first downlink reference signals transmitted by multiple spatial transmission filters indicated by the first resource set.

[0155] In some implementations, the time domain resources corresponding to the multiple first downlink reference signals are aperiodic time domain resources. That is, the first information can be used to indicate triggering (or scheduling) transmission of multiple aperiodic first downlink reference signals.

[0156] In some implementations, the first information can be sent by the network device to the terminal device. For example, the first information can be carried in downlink control information (DCI). Of course, in the embodiments of the present application, the first information can also be carried in other downlink information.

[0157] In the embodiments of the present application, the time domain interval between the plurality of first downlink reference signals is not limited. In some scenarios, the first downlink reference signal for measurement can also be referred to as a "measurement instance", and accordingly, the time domain interval between the plurality of first downlink reference signals can also be referred to as a GapBetweenInstance.

[0158] In some implementations, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals is the same, that is, the plurality of first downlink reference signals are equally spaced measurement instances. For example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals is 40ms. For another example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals is 80ms.

[0159] In other implementations, the time domain interval between at least two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals is different, or in other words, the time domain interval between part or all of the two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals is different. That is, the plurality of first downlink reference signals are non-equally spaced measurement instances.

[0160] For example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals can be represented as GapBetweenInstance1~GapBetweenInstance K-1 wherein K is a positive integer greater than 1. Accordingly, if the value of K is 3, the values corresponding to GapBetweenInstance1~GapBetweenInstance2 are {40ms, 60ms, 80ms}.

[0161] In the embodiments of the present application, the configuration mode of the above-mentioned time domain interval is not limited. In some implementations, the configuration of the time domain interval can be determined based on pre-defined information, pre-configured information, or configuration information sent by the network device. For example, if the plurality of first downlink reference signals are non-equally spaced measurement instances, accordingly, the network device can configure a plurality of time domain intervals for the terminal device through RRC signaling.

[0162] In some embodiments, the time domain locations of the time domain resources corresponding to the plurality of first downlink reference signals (referred to as the plurality of time domain resources) can be determined based on the time domain location of the first information. That is, the plurality of time domain resources can be determined based on the time domain resource for transmitting the first information and the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources. In some scenarios, the time domain interval can also be referred to as a time domain offset.

[0163] In the embodiments of the present application, the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources is not limited. For example, the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources can include the time domain interval between the time domain resource for transmitting the first information and the starting time domain location of the plurality of time domain resources. For another example, the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources can include the time domain interval between the time domain resource for transmitting the first information and the ending time domain location of the plurality of time domain resources.

[0164] In some embodiments, the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources can be indicated by the first information, which helps to reduce the overhead of transmitting information. Of course, in the embodiments of the present application, the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources can be determined by pre-defined information or pre-configured information.

[0165] In known protocols, for aperiodic resources, one DCI has been supported to trigger multiple aperiodic CSI-RS resource sets, and each resource set can be configured with an independent offset. The offset refers to the time domain distance between the slot where the DCI triggering the aperiodic CSI-RS is located and the slot where the CSI-RS is transmitted. In the protocol, the offset is determined by the RRC parameter (i.e., aperiodicTriggeringOffset, aperiodicTriggeringOffset-r16, or aperiodicTriggeringOffset-r17). However, the value of the offset is up to more than 100 milliseconds. According to the simulation conditions and real use cases of the current model-based beam management process (e.g., BM-Case2), it cannot meet the needs of time domain beam prediction, which requires 320ms or more for the model-based beam management process. Therefore, in the embodiments of the present application, the value of the offset (i.e., the time domain offset) can be redefined to adapt to the model-based beam management process.

[0166] For ease of understanding, the following describes a scheme for indicating the time domain resources for transmitting the plurality of first downlink reference signals by the first information in the embodiments of the present application, taking the first downlink reference signal as CSI-RS for example and in conjunction with FIG. 14.

[0167] Referring to FIG. 14, it is assumed that the first information indicates that the time domain offset is L, and the first information is used to trigger 1 st CSI-RS ~ K th CSI-RS. The time domain resource for transmitting the first information is L0.1 st CSI-RS ~ K th The time domain distance between every two adjacent time domain resources in the time domain resources occupied by the CSI-RS is equal interval GapBetweenInstance1. Accordingly, the first information triggers 1 st CSI-RS ~ K th The time domain resources respectively occupied by the CSI-RS are L1~L K-1 , wherein the time domain distance between every two adjacent time domain resources in the time domain resources L1~L K-1 is equal interval GapBetweenInstance1. In addition, the time domain offset between the time domain resource L0 and the time domain resource L1 is L.

[0168] In the implementation manner 1-4, the first information indicates, through the first timer, whether the time domain resources corresponding to the multiple downlink reference signals are the time domain resources corresponding to the first downlink reference signal.

[0169] In some implementation manners, the downlink reference signal whose time domain position overlaps with the running time of the first timer is the first downlink reference signal. That is to say, the downlink reference signal sent by the network device during the running of the first timer (or the first timer is not overdue) is the first downlink reference signal.

[0170] In other implementation manners, the downlink reference signal whose time domain position does not overlap with the running time of the first timer is not the first downlink reference signal. That is to say, if the first timer is overdue or the first timer is not started, the downlink reference signal sent by the network device is not the first downlink reference signal.

[0171] Of course, in the embodiments of the present application, the downlink reference signal whose time domain position overlaps with the running time of the first timer is not the first downlink reference signal, and / or the downlink reference signal whose time domain position does not overlap with the running time of the first timer is the first downlink reference signal.

[0172] In some implementations, the time domain resources corresponding to the plurality of downlink reference signals can be periodically configured time domain resources or semi-persistently scheduled time domain resources. Accordingly, in the embodiments of the present application, the time domain resources corresponding to the plurality of downlink reference signals can be adjusted based on the first timer on the basis of the time domain resources corresponding to the plurality of downlink reference signals to obtain the time domain resources corresponding to the first downlink reference signal, which helps to improve the rationality of the time domain resources corresponding to the first downlink reference signal. For example, the time domain interval (e.g., 960 ms) between the first downlink reference signals can be adjusted by the first timer, so as to facilitate model inference, model monitoring, model training and the like within the time period corresponding to the time domain interval.

[0173] In the embodiments of the present application, the starting mode of the first timer is not limited. In some implementations, the first timer can be started after the terminal device measures the first resource set for the first time. In other implementations, the network device can send indication information to the terminal device to instruct the terminal device to start the first timer. Of course, in the embodiments of the present application, whether to start the first timer is determined based on whether to perform model inference, model monitoring or model prediction process.

[0174] In the embodiments of the present application, the configuration mode of the first timer is not limited. In some implementations, the first timer can be determined based on the configuration information sent by the network device, the predefined information or the preconfigured information. The following will be introduced in combination with FIG. 22.

[0175] Embodiment 2: The first information is used to configure the second resource set, or in other words, the first information is used to indicate the second resource set.

[0176] In some implementations, the first information is used to indicate the downlink reference signal transmitted through the spatial transmission filter from the plurality of downlink reference signals, wherein the downlink reference signal transmitted through the spatial transmission filter is used to select the target spatial transmission filter.

[0177] In some implementations, the first information is used to configure the time domain resources corresponding to the second resource set, or in other words, the first information is used to indicate the time domain resources corresponding to the second resource set. The time domain resources corresponding to the second resource set can be understood as the time domain resources occupied by the downlink reference signal transmitted by the spatial transmission filter indicated by the second resource set.

[0178] In some scenarios, the first information can indicate an index range of the indexes of the spatial transmit filters indicated by the second resource set. In some scenarios, the downlink reference signals corresponding to the second resource set can not be measured, for example, in the scenario of model monitoring or model measurement measurement, the downlink reference signals corresponding to the second resource set can not be measured, at this time, the first information can indicate an index range of the indexes of the spatial transmit filters indicated by the second resource set. Of course, in the embodiment of the application, the first information can indicate a reference signal resource set of the downlink reference signals corresponding to the second resource set, wherein the reference signal resource set can include a CSI-RS resource set and / or an SSB resource set, for example.

[0179] In implementation 2-1, the first information indicates, by the second bitmap, whether the time domain resources (referred to as multiple time domain resources for short) corresponding to the multiple downlink reference signals are time domain resources occupied by the downlink reference signals transmitted by the spatial transmit filters, wherein the spatial transmit filters are the spatial transmit filters indicated by the second resource set, and correspondingly, the downlink reference signals transmitted by the spatial transmit filters can be referred to as the downlink reference signals corresponding to the second resource set.

[0180] That is, the first information is used to indicate the second bitmap, which is used to indicate the time domain resources of the multiple time domain resources corresponding to the multiple downlink reference signals for transmitting the downlink reference signals corresponding to the second resource set.

[0181] In some implementations, each bit in the second bitmap corresponds to a time domain resource in the multiple time domain resources, and if the value of a bit in the second bitmap is a first value, it indicates that the time domain resource corresponding to the bit is a time domain resource for transmitting the downlink reference signals corresponding to the second resource set. Conversely, if the value of a bit in the second bitmap is a second value, it indicates that the time domain resource corresponding to the bit is a time domain resource not for transmitting the downlink reference signals corresponding to the second resource set. Wherein the first value and the second value are different, for example, the first value can be 1, and the second value can be 0. For another example, the first value can be 0, and the second value can be 1.

[0182] The transmission manner of the second bitmap is not limited in the embodiments of the present application. In some implementations, the second bitmap can be indicated by the network device to the terminal device. For example, the network device can send RRC signaling (as an example of the first information) to the terminal device, where the RRC signaling is used to configure the second bitmap for the terminal device. For another example, the network device can send information (as an example of the first information) used to configure the second bitmap for the terminal device when indicating to the terminal device to activate or deactivate the downlink time domain resource. That is, the network device sends indication information 1 to the terminal device, where the indication information 1 is used to indicate to activate or deactivate the downlink time domain resource, and the indication information 1 carries the information (as an example of the first information) used to configure the second bitmap for the terminal device.

[0183] In some implementations, the second bitmap can correspond to multiple groups of time domain resources, and accordingly, the second bitmap can indicate whether each group of time domain resources in the multiple groups of time domain resources is used to transmit the downlink reference signal corresponding to the second resource set, or in other words, the second bitmap can periodically indicate whether each group of time domain resources in the multiple groups is used to transmit the downlink reference signal corresponding to the second resource set. This will be described below in combination with FIG. 12.

[0184] In the embodiments of the present application, the duration of the second bitmap indicating the multiple groups of time domain resources is not limited. For example, if the multiple groups of time domain resources are periodic time domain resources, the second bitmap can periodically indicate whether the multiple groups of time domain resources are used to transmit the downlink reference signal corresponding to the second resource set until the network device reconfigures the periodic time domain resources for the terminal device (for example, the network device reconfigures through RRC signaling). For another example, if the multiple groups of time domain resources are semi-persistent scheduling time domain resources, the second bitmap can periodically indicate whether the time domain resources are used to transmit the downlink reference signal corresponding to the second resource set until the network device indicates to activate new time domain resources (for example, the network device indicates to activate new time domain resources through MAC CE). For another example, if the multiple groups of time domain resources are semi-persistent scheduling time domain resources, the second bitmap can periodically indicate whether the time domain resources are used to transmit the downlink reference signal corresponding to the second resource set until the network device indicates to deactivate part or all of the multiple groups of time domain resources (for example, the network device indicates to deactivate part or all of the multiple groups of time domain resources through MAC CE).

[0185] It is assumed that the format of the second bitmap is "00001111", wherein the time domain resources corresponding to the bits with value 1 are used for transmitting the downlink reference signals corresponding to the second resource set, and the time domain resources corresponding to the bits with value 0 are not used for transmitting the downlink reference signals corresponding to the second resource set. Referring to FIG. 15, the multiple groups of time domain resources include 8 time domain resources in group 1 and 8 time domain resources in group 2. Accordingly, the second bitmap can be used to indicate whether the time domain resources in group 1 and group 2 are used for transmitting the downlink reference signals corresponding to the second resource set, respectively.

[0186] Accordingly, the second bitmap can indicate that the time domain resources (or time instances) corresponding to the last 4 periods in group 1 are used for transmitting the downlink reference signals corresponding to the second resource set, and accordingly, the terminal device can perform measurement on the time domain resources corresponding to the last 4 periods. The second bitmap can also indicate that the time domain resources (or time instances) corresponding to the first 4 periods in group 1 are not used for transmitting the downlink reference signals corresponding to the second resource set, and accordingly, the terminal device can not perform measurement on the time domain resources corresponding to the first 4 periods.

[0187] In addition, the measurement results (for example, the optimal beam and / or the link quality corresponding to the optimal beam) obtained by measuring the time domain resources corresponding to the first 4 periods can be used as input information of the model, so as to output the target spatial transmission filter of the model.

[0188] In implementation 2-2, the first information can indicate, through the second time window, whether the time domain resources corresponding to the multiple downlink reference signals are the time domain resources corresponding to the downlink reference signals of the second resource set. The downlink reference signals corresponding to the second resource set can be understood as the downlink reference signals transmitted through the spatial transmission filter indicated by the second resource set.

[0189] In some implementations, the first information is used to indicate that the time domain resources, which are partially or entirely overlapped with the second time window, in the time domain resources corresponding to the multiple downlink reference signals are the time domain resources corresponding to the downlink reference signals of the second resource set.

[0190] In some implementations, the time domain resources, which are entirely overlapped with the second time window, in the time domain resources corresponding to the multiple downlink reference signals can be understood as the time domain resources located in the second time window in the time domain resources corresponding to the multiple downlink reference signals. That is, the first information is used to indicate that the time domain resources, which are located in the second time window, in the time domain resources corresponding to the multiple downlink reference signals are the time domain resources corresponding to the downlink reference signals of the second resource set, or the first information is used to indicate that the time domain resources, which are located in the second time window, in the time domain resources corresponding to the multiple downlink reference signals are used for transmitting the downlink reference signals corresponding to the second resource set.

[0191] In some implementations, the time domain resources corresponding to the plurality of downlink reference signals can be periodically configured time domain resources or semi-persistently scheduled time domain resources. Accordingly, in the embodiments of the present application, the time domain resources corresponding to the plurality of downlink reference signals can be adjusted based on the second time window on the basis of the time domain resources corresponding to the plurality of downlink reference signals to obtain the time domain resources corresponding to the downlink reference signals of the second resource set, which helps to improve the rationality of the time domain resources corresponding to the downlink reference signals of the second resource set. For example, the time domain interval between the downlink reference signals of the second resource set can be adjusted by the second time window, so as to facilitate model inference, model monitoring, model training and the like within the second time window.

[0192] Of course, in the embodiments of the present application, the first information can be used to indicate that the time domain resources outside the second time window among the time domain resources corresponding to the plurality of downlink reference signals are the time domain resources corresponding to the downlink reference signals of the second resource set.

[0193] In some implementations, the time domain resources corresponding to the plurality of downlink reference signals can be periodically configured time domain resources or semi-persistently scheduled time domain resources. Accordingly, in the embodiments of the present application, the time domain resources corresponding to the plurality of downlink reference signals can be adjusted based on the second time window on the basis of the time domain resources corresponding to the plurality of downlink reference signals to obtain the time domain resources corresponding to the downlink reference signals of the second resource set, which helps to improve the rationality of the time domain resources corresponding to the downlink reference signals of the second resource set. For example, the time domain interval between the downlink reference signals of the second resource set can be adjusted by the second time window, so as to facilitate model inference, model monitoring, model training and the like within the second time window.

[0194] As described above, in some implementations, model inference, model monitoring, model training and the like are performed within the second time window, and therefore, the second time window can also be referred to as a "prediction window". Accordingly, within the second time window, the model can measure the time domain resources occupied by the downlink reference signals corresponding to the second resource set for model prediction and the like, and therefore, the downlink reference signals corresponding to the second resource set can also be referred to as "prediction instances".

[0195] In the embodiments of the present application, the manner in which the first information indicates the second time window is not limited. In some implementations, the first information can include one or more of the following: a starting time domain position of the second time window, a time length of the second time window, an ending time domain position of the second time window.

[0196] For ease of understanding, the scheme for determining the downlink reference signal corresponding to the second resource set based on the second time window is introduced below in combination with FIG. 16. Referring to FIG. 16, it is assumed that the network device configures periodic time domain resources for the terminal device, and FIG. 16 shows 12 downlink time domain resources. Accordingly, the first information indicates that the starting time domain position of the second time window is P3, and the length of the second time window is Q. The length Q of the second time window can include the time domain resources corresponding to 4 downlink reference signals.

[0197] In this way, the second time window with the starting time domain position P3 contains the downlink time domain resources 5-8. That is, the time domain resources corresponding to the downlink reference signal corresponding to the second resource set are time domain resources 5-8. Accordingly, model prediction, model inference, and model monitoring can be performed in the time period corresponding to the time domain resources 5-8.

[0198] In some scenarios, the target spatial transmission filter is selected from the spatial transmission filter based on the measurement result by using the model, and the downlink reference signal in the first time window is used to determine the measurement result of the spatial transmission filter selected by the model. That is, the measurement result obtained by measuring the downlink reference signal in the first time window can be used as the real result of the output of the model. In the model training process, the real result can be used as the sample label used in the model training process. In the model monitoring process of the performance of the model, the real result can be compared with the model prediction result (model ideal result) to determine the performance of the model. For related introduction, please refer to FIG. 19.

[0199] In other scenarios, the measurement result obtained by measuring the downlink reference signal in the first time window can be used as the input of the model, so that the target spatial transmission filter is selected from the second resource set based on the measurement result by using the model. For related introduction, please refer to FIG. 18.

[0200] In implementation 2-3, the first information is used to indicate the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set.

[0201] In some implementations, the plurality of downlink reference signals corresponding to the second resource set can be understood as the downlink reference signals transmitted by the plurality of spatial transmission filters indicated by the second resource set.

[0202] In some implementations, the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set are aperiodic time domain resources. That is, the first information can be used to indicate the triggering (or scheduling) of the transmission of the plurality of aperiodic downlink reference signals corresponding to the second resource set.

[0203] In some implementations, the first information can be sent by the network device to the terminal device. For example, the first information can be carried in a downlink control information (DCI). Of course, in the embodiments of the present application, the first information can also be carried in other downlink information.

[0204] In the embodiments of the present application, the time domain interval between the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is not limited. The downlink reference signals corresponding to the second resource set are used for predicting the target spatial transmission filter, and therefore, the downlink reference signals corresponding to the second resource set can also be referred to as “prediction instances”, and correspondingly, the time domain interval between the plurality of downlink reference signals corresponding to the second resource set can also be referred to as a “gap between instances”.

[0205] In some implementations, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is the same, that is, the plurality of downlink reference signals corresponding to the second resource set are equally spaced prediction instances. For example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is 40 ms. For another example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is 80 ms.

[0206] In other implementations, the time domain interval between at least two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is different, or in other words, the time domain interval between some or all of the two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set is different. That is, the plurality of downlink reference signals corresponding to the second resource set are non-equally spaced prediction instances.

[0207] For example, the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set can be represented as GapBetweenInstance1~GapBetweenInstance K-1 Correspondingly, if the value of K is 3, the values corresponding to GapBetweenInstance1~GapBetweenInstance2 are {40 ms, 60 ms, 80 ms}.

[0208] In the embodiments of the present application, the configuration manner of the time domain interval is not limited. In some implementations, the configuration of the time domain interval can be determined based on pre-defined information, pre-configured information, or configuration information sent by the network device. For example, if the multiple downlink reference signals corresponding to the second resource set are non-equidistant prediction instances, the network device can configure multiple time domain intervals for the terminal device through RRC signaling accordingly.

[0209] In some implementations, the time domain positions of the time domain resources (referred to as multiple time domain resources) corresponding to the multiple downlink reference signals corresponding to the second resource set can be determined based on the time domain position of the first information. That is, the multiple time domain resources can be determined based on the time domain resource for transmitting the first information and the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources. In some scenarios, the time domain interval can also be referred to as a time domain offset.

[0210] In some implementations, the time domain offset can be configured based on the parameter "ApriodicTriggeringOffset".

[0211] In the embodiments of the present application, the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources is not limited. For example, the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources can include the time domain interval between the time domain resource for transmitting the first information and the starting time domain position of the multiple time domain resources. For another example, the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources can include the time domain interval between the time domain resource for transmitting the first information and the ending time domain position of the multiple time domain resources.

[0212] In some implementations, the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources can be indicated by the first information, which helps to reduce the overhead of transmitting information. Of course, in the embodiments of the present application, the time domain interval between the time domain resource for transmitting the first information and the multiple time domain resources can be determined based on pre-defined information or pre-configured information.

[0213] Referring to FIG. 17, it is assumed that the first information indicates that the time domain offset is L1, and the first information is used to trigger 1 st Prediction instance ~ K th The transmission of the prediction instance. The time domain resource for transmitting the first information is L0.1 st Prediction instance ~ K th The time domain distance between every two adjacent time domain resources occupied by the prediction instance is equidistant GapBetweenInstance1. Accordingly, the first information triggers 1 st Prediction instance ~ K th The time domain resources respectively occupied by the prediction instance are L1~L K-1wherein the time domain resources are L1-L K-1 The time domain distance between each two adjacent time domain resources in the time domain resources is equal interval GapBetweenInstance1. In addition, the time domain offset between the time domain resource L0 and the time domain resource L1 is L.

[0214] In the implementation manner 2-4, the first information indicates, by the second timer, whether the time domain resources corresponding to the plurality of downlink reference signals are the time domain resources corresponding to the downlink reference signals corresponding to the second resource set.

[0215] In some implementation manners, the downlink reference signals whose time domain positions overlap with the running time of the second timer are the downlink reference signals corresponding to the second resource set. That is to say, the downlink reference signals sent by the network device during the running time of the second timer (or the second timer is not overdue) are the downlink reference signals corresponding to the second resource set.

[0216] In other implementation manners, the downlink reference signals whose time domain positions do not overlap with the running time of the second timer are not the downlink reference signals corresponding to the second resource set, or the downlink reference signals whose time domain positions do not overlap with the running time of the second timer are not used to select the target spatial transmission filter. That is to say, the downlink reference signals sent by the network device when the second timer is overdue or the second timer is not started are not the downlink reference signals corresponding to the second resource set.

[0217] Of course, in the embodiments of the present application, the downlink reference signals whose time domain positions overlap with the running time of the second timer are not the downlink reference signals corresponding to the second resource set, and / or the downlink reference signals whose time domain positions do not overlap with the running time of the second timer are the downlink reference signals corresponding to the second resource set.

[0218] In some implementation manners, the time domain resources corresponding to the plurality of downlink reference signals can be periodically configured time domain resources or semi-persistently scheduled time domain resources. Accordingly, in the embodiments of the present application, the time domain resources corresponding to the plurality of downlink reference signals can be adjusted on the basis of the time domain resources corresponding to the plurality of downlink reference signals, based on the second timer, to obtain the time domain resources corresponding to the downlink reference signals corresponding to the second resource set, which helps to improve the rationality of the time domain resources corresponding to the downlink reference signals corresponding to the second resource set. For example, the time domain interval (for example, 960ms) between the downlink reference signals corresponding to the second resource set can be adjusted by the second timer, so as to facilitate model inference, model monitoring and model training and the like within the time period corresponding to the time domain interval.

[0219] In the embodiments of the present application, the starting manner of the second timer is not limited. In some implementations, the second timer can be started after the terminal device measures the second resource set for the first time. In other implementations, the network device can send indication information to the terminal device to indicate the terminal device to start the second timer. Of course, in the embodiments of the present application, whether to start the second timer is determined based on whether to perform the model inference, model monitoring or model prediction process.

[0220] In the embodiments of the present application, the configuration manner of the second timer is not limited. In some implementations, the second timer can be determined based on the configuration information sent by the network device, pre-defined information or pre-configured information. The following will be introduced in combination with FIG. 22.

[0221] The above describes the schemes of determining the first resource set based on the first information and determining the second resource set based on the first information in combination with Embodiment 1 and Embodiment 2 respectively. In some implementations, Embodiment 1 and Embodiment 2 can be used independently. In other implementations, the four embodiments in Embodiment 1 and the four embodiments in Embodiment 2 can be used in combination. The present application does not limit the combination manner of Embodiment 1 and Embodiment 2. In order to facilitate understanding, the following will introduce several typical combination manners in the embodiments of the present application in combination with FIG. 1-FIG. 6.

[0222] Combination manner 1: combination of Embodiment 1-1 and Embodiment 2-1.

[0223] Continuing to refer to FIG. 12, it is assumed that the format of the first bitmap is “11110000” and the format of the second bitmap is “00001111”. Among them, the time domain resources corresponding to the bits with a value of 1 are used to transmit the first downlink reference signal, and the time domain resources corresponding to the bits with a value of 0 are not used to transmit the first reference signal. The multiple groups of time domain resources include 8 time domain resources in group 1 and 8 time domain resources in group 2. Correspondingly, the first bitmap can be used to indicate whether the time domain resources in group 1 and group 2 are used to transmit the first downlink reference signal. The second bitmap can be used to indicate whether the time domain resources in group 1 and group 2 are used to transmit the downlink reference signal corresponding to the second resource set.

[0224] Correspondingly, the first bitmap can indicate that the time domain resources (or time instances) corresponding to the first 4 periods in group 1 are used to transmit the first downlink reference signal, and correspondingly, the terminal device can measure in the time domain resources corresponding to the first 4 periods. The second bitmap can indicate that the time domain resources (or time instances) corresponding to the last 4 periods in group 1 are used to transmit the downlink reference signal corresponding to the second resource set, and correspondingly, the terminal device can not measure in the time domain resources corresponding to the last 4 periods.

[0225] In addition, the measurement results (e.g., the optimal beam and / or the link quality corresponding to the optimal beam) obtained by measuring the time domain resources corresponding to the last 4 periods can be used as labels for the model training process, so as to train the model.

[0226] Combination mode 2: combination of embodiment 1-2 and embodiment 2-2.

[0227] Referring to FIG. 18, it is assumed that the network device configures periodic time domain resources for the terminal device, and 12 downlink time domain resources are shown. Accordingly, the first information indicates that the starting time domain positions of the first time window are P1 and P2, the starting time domain position of the second time window is P3, and the lengths of the first time window and the second time window are both Q. Among them, the length Q of the first time window and the second time window can include the time domain resources corresponding to 4 downlink reference signals.

[0228] In this way, the first time window with the starting time domain position P1 contains the downlink time domain resources 1-4, and the first time window with the starting time domain position P2 contains the downlink time domain resources 9-12. That is, the time domain resources corresponding to the first downlink reference signal are time domain resources 1-4 and time domain resources 9-12. Accordingly, the measurement can be performed in the time window corresponding to the time domain resources 1-4 and the time domain resources 9-12, which is also called a “measurement time window”. The second time window with the starting time domain position P3 contains the downlink time domain resources 5-9. That is, the time domain resources corresponding to the downlink reference signal corresponding to the second resource set are time domain resources 5-8. Accordingly, the model prediction can be performed in the time period corresponding to the time domain resources 5-8, which is also called a “prediction time window”.

[0229] Referring to FIG. 19, it is assumed that the network device configures periodic time domain resources for the terminal device, and 12 downlink time domain resources are shown. Accordingly, the first information indicates that the starting time domain positions of the first time window are P1 and P2, the starting time domain position of the second time window is P3, and the lengths of the first time window and the second time window are both Q. Among them, the length Q of the first time window and the second time window can include the time domain resources corresponding to 4 downlink reference signals.

[0230] Therefore, the first time window with the starting time domain position P1 contains the time domain resources 1-4, and the first time window with the starting time domain position P2 contains the time domain resources 9-12. That is, the time domain resources corresponding to the first downlink reference signal are the time domain resources 1-4 and the time domain resources 9-12. Accordingly, the measurement can be performed in the time window corresponding to the time domain resources 1-4 and the time domain resources 9-12, which is also referred to as a "measurement time window". The second time window with the starting time domain position P3 contains the time domain resources 5-8. That is, the time domain resources corresponding to the downlink reference signal corresponding to the second resource set are the time domain resources 5-8. Accordingly, the model training or model monitoring can be performed in the time period corresponding to the time domain resources 5-8, which is also referred to as a "training / monitoring time window".

[0231] In some scenarios, it can be understood that the measurement time window corresponding to the time domain resources 1-4 is used to collect input information of the model. The measurement time window corresponding to the time domain resources 5-8 is used to measure output information of the model. For the model training process, the output information can be used as a sample label for model training to train the model. For model monitoring, the output information can be used as a real measurement result to compare with the ideal result (or the model prediction result) of the model to determine the model performance of the model.

[0232] Combination mode 3: combination of embodiment 1-3 and embodiment 2-3.

[0233] In some implementations, the first information can be used to indicate the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set and the time domain resources corresponding to the plurality of first downlink reference signals.

[0234] In some implementations, the first information can carry the time domain offset 1 and the time domain offset 2, where the time domain offset 1 is used to indicate the time domain interval between the time domain resource for transmitting the first information and the plurality of time domain resources, and the time domain offset 2 is used to indicate the time domain resource for transmitting the first information and the time domain resources corresponding to the plurality of downlink reference signals corresponding to the second resource set. Of course, in the embodiments of the present application, the first information can also indicate the time domain offset 1, and the time domain interval between the time domain resources corresponding to the first resource set and the time domain resources corresponding to the second resource set.

[0235] Referring to FIG. 20, it is assumed that the first information indicates the time domain offset L, and the first information is used to trigger the first resource set corresponding to the time domain resources 1-4 and the second resource set corresponding to the time domain resources 9-12. st CSI-RS~K th CSI-RS transmission. The time domain resource for transmitting the first information is L0.1 stCSI-RS ~ K th The time distance between every two adjacent time resources in the time resources occupied by the CSI-RS is equal interval GapBetweenInstance1. Correspondingly, the first information triggers the transmission of K measurement instances corresponding to the first resource set. st CSI-RS ~ K th The time resources respectively occupied by the CSI-RS are L1~L K-1 , wherein the time resources are L1~L K-1 The time distance between every two adjacent time resources in the time resources is equal interval GapBetweenInstance1. In addition, the time offset between the time resource L0 and the time resource L1 is L1.

[0236] In addition, the first information indicates the time offset L1, and the first information is used to trigger the transmission of K measurement instances corresponding to the first resource set. st CSI-RS ~ K th The transmission of the CSI-RS. The time resource for transmitting the first information is L0.1 st CSI-RS ~ K th The time distance between every two adjacent time resources in the time resources occupied by the CSI-RS is equal interval GapBetweenInstance1. Correspondingly, the first information triggers the transmission of K measurement instances corresponding to the first resource set. st CSI-RS ~ K th The time resources respectively occupied by the CSI-RS are L P ~L P-1 , wherein the time resources are L P ~L P-1 The time distance between every two adjacent time resources in the time resources is equal interval GapBetweenInstance1. In addition, the time offset between the time resource L0 and the time resource L P is L1.

[0237] That is to say, the first information can trigger the transmission of K measurement instances associated with the first resource set and the transmission of P measurement instances associated with the first resource set, wherein K and P are positive integers greater than or equal to 0. The K measurement instances are used to obtain the input information of the model, and the P measurement instances are used to measure the output information of the model as the sample label predicted by the model.

[0238] Referring to FIG. 21, it is assumed that the first information indicates the time offset L, and the first information is used to trigger the transmission of K measurement instances corresponding to the first resource set. st CSI-RS ~ K th The transmission of the CSI-RS. The time resource for transmitting the first information is L0.1 st CSI-RS ~ K thThe time domain distance between every two adjacent time domain resources in the time domain resources occupied by the CSI-RS is equal interval GapBetweenInstance1. Correspondingly, the first information triggers the transmission of the 1 st CSI-RSs th The time domain resources respectively occupied by the CSI-RSs are L1~L K-1 , wherein the time domain resources are L1~L K-1 The time domain distance between every two adjacent time domain resources in the time domain resources is equal interval GapBetweenInstance1. In addition, the time domain offset between the time domain resource L0 and the time domain resource L1 is L.

[0239] In addition, the first information indicates that the time domain offset is L1, and the first information is used to trigger the transmission of the 1 st Predicted instances th The transmission of the predicted instances. The time domain resource for transmitting the first information is L0.1 st Predicted instances th The time domain distance between every two adjacent time domain resources in the time domain resources occupied by the predicted instances is equal interval GapBetweenInstance1. Correspondingly, the first information triggers the transmission of the 1 st Predicted instances th The time domain resources respectively occupied by the predicted instances are L1~L K-1 , wherein the time domain resources are L1~L K-1 The time domain distance between every two adjacent time domain resources in the time domain resources is equal interval GapBetweenInstance1. In addition, the time domain offset between the time domain resource L0 and the time domain resource L1 is L.

[0240] Combination mode 4: combination of embodiment 1-4 and embodiment 2-4.

[0241] Referring to FIG. 22, it is assumed that the network device configures periodic time domain resources for the terminal device, and FIG. 22 shows 8 downlink time domain resources. Correspondingly, the starting time of the first timer (also referred to as a “measurement timer”) indicated by the first information is P1, the starting time of the second timer (also referred to as a “prediction timer”) indicated by the first information is P2, and the time length of the first timer and the second timer is Q. Wherein, the time length Q can include the time domain resources corresponding to 4 downlink reference signals.

[0242] Thus, in the running period of the first timer, the downlink reference signals are transmitted through the time domain resource 1 to the time domain resource 4. After the first timer expires, the second timer starts. In the running period of the second timer, the downlink reference signals are transmitted through the time domain resource 5 to the time domain resource 8. Accordingly, the terminal device can measure the downlink reference signals in the running period of the first timer to obtain input information of the model. In the running period of the second timer, the model performs model prediction by using the input information to obtain the target spatial transmission filter.

[0243] In some implementations, the first timer and the second timer can be independent timers. For example, the duration of the first timer and the duration of the second timer can be different. Of course, in the embodiments of the present application, the duration of the first timer and the duration of the second timer can be the same.

[0244] As described above, the first resource set and the second resource set can be used in the scenarios of model training, model prediction, and model monitoring. Accordingly, for the first resource set, the measurement result obtained by measuring the first resource set can be used in the scenarios of model training, model prediction, and model monitoring. At this time, the first information can be used to indicate the time domain resources corresponding to the first resource set.

[0245] For the second resource set, the measurement result obtained by measuring the second resource set can be used in the scenarios of model training and model monitoring. At this time, the first information can indicate the time domain resources corresponding to the second resource set. However, in the scenario of model prediction, there is no need to measure the second resource set. At this time, the first information can indicate the reference signal resource set corresponding to the second resource set and / or the index range of the index of the spatial transmission filter in the second resource set. For example, for the second resource set containing 64 spatial transmission filters, the first information can indicate the index range {0, …, 63} of the index of the spatial transmission filter.

[0246] In some scenarios, the model for beam management can be deployed in the terminal device or the network device. For different deployment modes of the model, the content of the first information can be adjusted, which helps to improve the rationality of configuring the first resource set or the second resource set by the first information.

[0247] In some implementations, if the model is located in the network device and the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set, that is, the first information is used to indicate the time domain position of the first resource set. In the above scenario, the terminal device does not need to know the time domain configuration information of the second resource set, which belongs to the implementation of the network device side model, so the first information does not need to configure the time domain information of the second resource set for the terminal device.

[0248] In some implementations, the first information is used to determine the time domain resources corresponding to the first resource set and the time domain resources corresponding to the second resource set. In some implementations, the first information is used to determine the time domain resources corresponding to the first resource set and the time domain resources corresponding to the second resource set.

[0249] CSI-RS reference resource definition

[0250] In some protocols, the CSI-RS reference resource in a serving cell is defined as follows.

[0251] In the frequency domain, the CSI reference resource is defined by the group of downlink physical resource blocks corresponding to the band to which the derived CSI relates.

[0252] In the time domain, the CSI reference resource for a CSI reporting in uplink slot n'is defined by a single downlink slot where K offset is a parameter configured by higher layer, is the value of Ko ffset when the frequency domain range is 1. (In the time domain, the CSI reference resource for a CSI reporting in uplink slot n'is defined by a singledownlink slot where K offset is a parameter configured by higher layer as specified in clause 4.2 of[6 TS 38.213],and where is the subcarrier spacing configuration for K offset with a value of 0for frequency range 1,

[0253] where, μ DL and μ UL are the subcarrier spacing configurations for DL and UL, respectively, and μ offset is determined by the higher layer parameter ca-SlotOffset configured by the cell transmitting uplink and downlink.

[0254] The above scheme is used to define where for periodic and semi-persistent CSI reporting.

[0255] If a single CSI-RS / SSB resource is configured for channel measurement n CSI_ref is the smallest value greater than or equal to such that it corresponds to a valid downlink slot. (if a single CSI-RS / SSB resource is configured for channel measurement n CSI_ref is the smallest value greater than or equal to such that it corresponds to a valid downlink slot). Or if multiple CSI-RS / SSB resources are configured for channel measurement n CSI_ref is the smallest value greater than or equal to such that it corresponds to a valid downlink slot. (if multiple CSI-RS / SSB resources are configured for channel measurement n CSI_ref is the smallest value greater than or equal to such that it corresponds to a valid downlink slot).

[0256] For periodic CSI reporting, if the DCI indicates the UE to report the CSI in the same slot as the CSI request, n CSI_rref The reference resource is in the same valid downlink slot as the corresponding CSI request. Otherwise, n CSI_ref The minimum value of n The time slot n―n CSI_ref corresponds to a valid downlink slot.

[0257] As described above, the CSI reference resource is a time-frequency resource defined for CSI feedback. Assuming that the time slot index of CSI reporting is n, the time slot index of the CSI reference resource can be simply represented as n―n CSI_ref , where n CSI_ref is 4 ms (in the case of only one CSI measurement resource) or 5 ms (in the case of multiple CSI measurement resources). In addition, the protocol also stipulates that the downlink reference signal transmitted by the network device for CSI measurement should not be later than the CSI reference signal resource. That is, between the time slot where the CSI reference resource is located and the time slot where the CSI is reported, the terminal device needs to process the downlink measurement result, calculate the CSI to be reported, and prepare to report it to the NW. The length of time between the time slot where the CSI reference resource is located and the time slot where the CSI is reported is not sufficient for model-based beam management. Therefore, the scheme of determining CSI feedback based on the CSI reference resource cannot be applied to the scenario of model-based model management (for example, BM-CASE2 introduced above).

[0258] Especially in some scenarios, the model in the terminal device takes the measurement results of K historical time points as the input of the model and outputs and reports the beam prediction results and predicted link quality results of F future time points at one time. In this case, the CSI reference resource under the CSI framework is reused. As shown in FIG. 23, there is only one CSI reference resource, and the reference signals of all K historical time points should not be later than the CSI reference resource in the time domain. The distance between the CSI reference resource and the CSI reporting time slot is still n CSI_ref milliseconds, which causes the terminal device to be unable to report the CSI in time at the CSI reporting time slot.

[0259] Therefore, to solve the above problems, the embodiment of the present application further provides a wireless communication method, which adjusts the time domain interval between the time domain resource of reporting CSI and the reference resource (for example, the CSI reference resource), which is helpful to adapt to the scenario of model-based beam management. The wireless communication method of the embodiment of the present application is introduced below in combination with FIG. 24. The method shown in FIG. 24 includes step S2410.

[0260] In step S2410, the terminal device sends first CSI to the network device.

[0261] In some embodiments, the time domain resource for transmitting the first CSI is determined based on a reference resource, and a time domain interval between the time domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0262] In some embodiments, the reference resource is a CSI reference resource, and the time domain interval is a product of a target time domain interval and the measurement number, and the target time domain interval is a time domain interval between the time domain resource and the CSI reference resource.

[0263] In some embodiments, the first CSI is generated based on historical measurement results by using a model, and the model is used to predict spatial filters corresponding to multiple time points, and the spatial filters corresponding to the multiple time points are indicated by the first CSI; or the spatial filters corresponding to the multiple time points are indicated by multiple CSIs containing the first CSI.

[0264] In some embodiments, if the spatial filters corresponding to the multiple time points are indicated by the multiple CSIs, the time domain resources of different CSIs in the multiple CSIs are determined based on one reference resource, that is, the time domain resources of the multiple CSIs are respectively determined based on different reference resources, so as to improve the flexibility of CSI reporting. Of course, in the embodiments of the present application, the time domain resources of the multiple CSIs can be determined based on one reference resource.

[0265] In some embodiments, the spatial filters corresponding to the multiple time points can be understood as target spatial filters used at the multiple time points, and the target spatial filters will be described below.

[0266] In order to facilitate understanding, the following describes a scheme for determining the spatial filters corresponding to the multiple time points by reporting the multiple CSIs in the embodiments of the present application in combination with FIG. 25. It is assumed that a model at the terminal device side takes the measurement results at K historical time points as inputs of the model, and reports the beam prediction results and the link quality at F future time points. Wherein, the prediction results at one future time point are reported each time. As shown in FIG. 25, the value of F is 4, which introduces four CSI reference resources, and accordingly, the terminal device can determine the time slots for reporting the CSIs four times based on the four CSI reference resources, which helps to improve the flexibility of reporting the CSIs by the terminal device.

[0267] In some embodiments, the time domain details of the multiple CSI reference resources are as follows: the time slot indexes where the CSIs are reported are n0, n1, n2, and n3 respectively; the time slot indexes where the CSI reference resources are located are n0-n CSI_ref0 , n1-n CSI_ref1 , n2-n CSI_ref2 , and n3-n CSI_ref3 , respectively, where n CSI_ref0 , n CSI_ref1 , n CSI_ref2, n CSI_ref3 The values of n can be the same or different, depending on the configuration of the network device.

[0268] It should be noted that the embodiments of the present application do not limit the time domain resources. In some implementations, the time domain resources can be, for example, time slots, symbols, subframes, etc. Of course, in the embodiments of the present application, the time domain resources can also be new time domain units introduced in future communication systems.

[0269] The embodiments of the present application do not limit the time domain intervals. In some implementations, the time domain intervals can be determined based on one or more of the following: the number of symbols, the number of subframes, the time interval, and the number of time slots.

[0270] The method embodiments of the present application are described in detail above in conjunction with FIGS. 1-25, and the device embodiments of the present application are described in detail below in conjunction with FIGS. 26-30. It should be understood that the description of the method embodiments corresponds to the description of the device embodiments, and therefore, the parts not described in detail can be referred to the foregoing method embodiments.

[0271] FIG. 26 is a schematic diagram of a terminal device according to an embodiment of the present application. The terminal device 2600 shown in FIG. 26 includes a processing unit 2610.

[0272] The processing unit 2610 is configured to determine a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal corresponding to the first resource set is used to obtain a measurement result, and the measurement result is used to select a target spatial transmit filter from spatial transmit filters indicated by the second resource set for downlink transmission.

[0273] In some implementations, the first information is used to indicate a time domain resource corresponding to the first downlink reference signal from a plurality of time domain resources corresponding to a plurality of downlink reference signals, wherein the plurality of time domain resources corresponding to the plurality of downlink reference signals are periodically configured or semi-persistently scheduled.

[0274] In some implementations, the first information is used to indicate a first bitmap, and the first bitmap is used to indicate whether a time domain resource corresponding to the plurality of downlink reference signals is a time domain resource corresponding to the first downlink reference signal.

[0275] In some implementations, the first information is used to indicate that a time domain resource located within a first time window in the plurality of time domain resources corresponding to the plurality of downlink reference signals is a time domain resource corresponding to the first downlink reference signal.

[0276] In some embodiments, the first information is used to indicate a first timer, and a downlink reference signal whose time domain position overlaps with a running time of the first timer among the plurality of downlink reference signals is the first downlink reference signal; and / or a downlink reference signal whose time domain position does not overlap with the running time of the first timer among the plurality of downlink reference signals is not the first downlink reference signal.

[0277] In some embodiments, the terminal device further includes a first receiving unit configured to receive the first information sent by the network device.

[0278] In some embodiments, the first information is used to indicate, from time domain resources corresponding to the plurality of downlink reference signals, a time domain resource corresponding to a downlink reference signal transmitted through the spatial transmit filter, wherein the downlink reference signal transmitted through the spatial transmit filter is used to select the target spatial transmit filter.

[0279] In some embodiments, the first information includes a second bitmap, and the second bitmap is used to indicate whether a time domain resource corresponding to the plurality of downlink reference signals is a time domain resource corresponding to a downlink reference signal transmitted through the spatial transmit filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

[0280] In some embodiments, the first information is used to indicate that a downlink reference signal located in a second time window among the plurality of downlink reference signals is transmitted through the spatial transmit filter.

[0281] In some embodiments, the target spatial transmit filter is selected from the spatial transmit filter based on the measurement result by using a model, and the downlink reference signal in the second time window is used to determine the measurement result of the spatial transmit filter selected by the model.

[0282] In some embodiments, the first information includes a second timer, and a downlink reference signal whose time domain position overlaps with a running time of the second timer among the plurality of downlink reference signals is transmitted through the spatial transmit filter; and / or a downlink reference signal whose time domain position does not overlap with the running time of the first timer among the plurality of downlink reference signals is not used to select the target spatial transmit filter.

[0283] In some embodiments, the first information is used to indicate an index range of an index of a spatial transmit filter indicated by the second resource set, or the first information is used to indicate a reference signal resource set of a downlink reference signal corresponding to the second resource set.

[0284] In some embodiments, the first resource set corresponds to a plurality of the first downlink reference signals, and the first information is used to indicate time domain resources corresponding to the plurality of the first downlink reference signals, and the time domain resources corresponding to the plurality of the first downlink reference signals are aperiodic time domain resources.

[0285] In some embodiments, the first information is used to indicate a time domain interval between a time domain resource for transmitting the first information and a time domain position corresponding to the plurality of the first downlink reference signals.

[0286] In some embodiments, a time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of the first downlink reference signals is the same, or a time domain interval between at least two adjacent time domain resources in the time domain resources corresponding to the plurality of the first downlink reference signals is different.

[0287] In some embodiments, the terminal device further includes a second receiving unit configured to receive configuration information sent by the network device, and the configuration information is used to configure a time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the plurality of the first downlink reference signals.

[0288] In some embodiments, the target spatial transmission filter is selected from the spatial transmission filter based on the measurement result by using a model, and the model is located in the network device, if the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set; if the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

[0289] FIG. 27 is a schematic diagram of a terminal device according to another embodiment of the present application. The terminal device 2700 shown in FIG. 27 includes a sending unit 2710.

[0290] The sending unit 2710 is configured to send first channel state information (CSI) to a network device, and a time domain resource for transmitting the first CSI is determined based on a reference resource, and a time domain interval between the time domain resource and the reference resource is associated with a measurement number corresponding to the first CSI.

[0291] In some embodiments, the reference resource is a CSI reference resource, and the time domain interval is a product of a target time domain interval and the measurement number, and the target time domain interval is a time domain interval between the time domain resource and the CSI reference resource.

[0292] In some embodiments, the first CSI is generated based on historical measurements by using a model for predicting spatial filters corresponding to multiple time instants, the spatial filters corresponding to the multiple time instants being indicated by the first CSI; or the spatial filters corresponding to the multiple time instants being indicated by multiple CSIs including the first CSI.

[0293] Fig. 28 is a schematic diagram of a network device according to an embodiment of the present application. The network device 2800 shown in Fig. 28 includes a processing unit 2810.

[0294] The processing unit 2810 is configured to determine a first resource set and / or a second resource set based on first information, wherein a first downlink reference signal transmitted in the first resource set is used to measure a measurement result, and the measurement result is used to select a target spatial transmit filter from spatial transmit filters indicated by the second resource set.

[0295] In some embodiments, the first information is used to indicate, from time domain resources corresponding to multiple downlink reference signals, a time domain resource corresponding to the first downlink reference signal, wherein the time domain resources corresponding to the multiple downlink reference signals are periodically configured or semi-persistently scheduled.

[0296] In some embodiments, the first information is used to indicate a first bitmap, and the first bitmap is used to indicate whether a time domain resource corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal.

[0297] In some embodiments, the first information is used to indicate that a time domain resource located in a first time window in the time domain resources corresponding to the multiple downlink reference signals is the time domain resource corresponding to the first downlink reference signal.

[0298] In some embodiments, the first information is used to indicate a first timer, and a downlink reference signal whose time domain position overlaps with a running time of the first timer in the multiple downlink reference signals is the first downlink reference signal; and / or a downlink reference signal whose time domain position does not overlap with the running time of the first timer in the multiple downlink reference signals is not the first downlink reference signal.

[0299] In some embodiments, the network device further includes a first sending unit configured to send the first information to a terminal device.

[0300] In some embodiments, the first information is used to indicate, from time domain resources corresponding to multiple downlink reference signals, a time domain resource corresponding to a downlink reference signal transmitted by the spatial transmit filter, wherein the downlink reference signal transmitted by the spatial transmit filter is used to select the target spatial transmit filter.

[0301] In some embodiments, the first information comprises a second bitmap, the second bitmap being used to indicate whether time domain resources corresponding to the plurality of downlink reference signals are time domain resources corresponding to downlink reference signals transmitted through the spatial transmit filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

[0302] In some embodiments, the first information is used to indicate that downlink reference signals located within a second time window among the plurality of downlink reference signals are transmitted through the spatial transmit filter.

[0303] In some embodiments, the target spatial transmit filter is selected from the spatial transmit filter based on the measurement results by using a model, and the downlink reference signals within the second time window are used to determine the measurement results of the spatial transmit filter selected by the model.

[0304] In some embodiments, the first information comprises a second timer, and downlink reference signals of the plurality of downlink reference signals whose time domain positions overlap with a running time of the second timer are transmitted through the spatial transmit filter; and / or downlink reference signals of the plurality of downlink reference signals whose time domain positions do not overlap with a running time of the first timer are not used to select the target spatial transmit filter.

[0305] In some embodiments, the first information is used to indicate an index range of indexes of spatial transmit filters indicated by the second resource set, or the first information is used to indicate a reference signal resource set of downlink reference signals corresponding to the second resource set.

[0306] In some embodiments, the first resource set corresponds to a plurality of the first downlink reference signals, and the first information is used to indicate time domain resources corresponding to the plurality of the first downlink reference signals, wherein the time domain resources corresponding to the plurality of the first downlink reference signals are aperiodic time domain resources.

[0307] In some embodiments, the first information is used to indicate a time domain interval between a time domain resource at which the first information is transmitted and time domain positions corresponding to the plurality of the first downlink reference signals.

[0308] In some embodiments, a time domain interval between every two adjacent time domain resources among time domain resources corresponding to the plurality of the first downlink reference signals is the same, or a time domain interval between at least two adjacent time domain resources among time domain resources corresponding to the plurality of the first downlink reference signals is different.

[0309] In some embodiments, the network device further includes a second sending unit configured to send configuration information to the terminal device, the configuration information being used to configure a time domain interval between each two adjacent time domain resources in the time domain resources corresponding to the plurality of first downlink reference signals.

[0310] In some embodiments, the target spatial transmission filter is selected from the spatial transmission filter based on the measurement result by using a model, and the model is located in a network device, if the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set; if the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

[0311] FIG. 29 is a schematic diagram of a network device according to an embodiment of the present application. The network device 2900 shown in FIG. 29 includes a receiving unit 2910.

[0312] The receiving unit 2910 is configured to receive a first CSI sent by a terminal device, a time domain resource for transmitting the first CSI being determined based on a reference resource, a time domain interval between the time domain resource and the reference resource being associated with a measurement number corresponding to the first CSI.

[0313] In some embodiments, the reference resource is a CSI reference resource, and the time domain interval is a product of a target time domain interval and the measurement number, the target time domain interval being a time domain interval between the time domain resource and the CSI reference resource.

[0314] In some embodiments, the first CSI is generated based on historical measurement results by using a model, the model being used to predict spatial filters corresponding to a plurality of time instants, the spatial filters corresponding to the plurality of time instants being indicated by the first CSI; or the spatial filters corresponding to the plurality of time instants being indicated by a plurality of CSIs containing the first CSI.

[0315] FIG. 30 is a schematic structural diagram of a communication apparatus according to an embodiment of the present application. The dashed line in FIG. 30 indicates that the unit or module is optional. The apparatus 3000 can be used to implement the methods described in the above method embodiments. The apparatus 3000 can be a chip, a terminal device or a network device.

[0316] The apparatus 3000 can include one or more processors 3010. The processor 3010 can support the apparatus 3000 to implement the methods described in the foregoing method embodiments. The processor 3010 can be a general processor or a dedicated processor. For example, the processor can be a central processing unit (CPU). Alternatively, the processor can also be other general processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can also be any conventional processor.

[0317] The apparatus 3000 can also include one or more memories 3020. The memory 3020 stores a program that can be executed by the processor 3010, so that the processor 3010 executes the methods described in the foregoing method embodiments. The memory 3020 can be independent of the processor 3010 or integrated in the processor 3010.

[0318] The apparatus 3000 can also include a transceiver 3030. The processor 3010 can communicate with other devices or chips through the transceiver 3030. For example, the processor 3010 can perform data transceiving with other devices or chips through the transceiver 3030.

[0319] The embodiments of the present application also provide a computer readable storage medium for storing a program. The computer readable storage medium can be applied to the terminal or network device provided by the embodiments of the present application, and the program causes the computer to execute the method performed by the terminal or network device in the various embodiments of the present application.

[0320] The embodiments of the present application also provide a computer program product. The computer program product includes a program. The computer program product can be applied to the terminal or network device provided by the embodiments of the present application, and the program causes the computer to execute the method performed by the terminal or network device in the various embodiments of the present application.

[0321] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided by the embodiments of the present application, and the computer program causes the computer to execute the method performed by the terminal or network device in the various embodiments of the present application.

[0322] It should be understood that the terms "system" and "network" can be used interchangeably in this application. In addition, the terms used in this application are only used to explain the specific embodiments of the application, and are not intended to limit the application. The terms "first", "second", "third", and "fourth" and the like in the specification and claims of the application and the drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0323] In embodiments of the present application, the term "indicate" can be direct indication or indirect indication, or can represent an associated relationship. For example, A indicates B, which can mean that B can be obtained by A; or A indirectly indicates B, for example, A indicates C, and B can be obtained by C; or A and B have an associated relationship.

[0324] In embodiments of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0325] In embodiments of the present application, the term "corresponding" can represent a direct or indirect corresponding relationship between the two, or can represent an associated relationship between the two, or can represent an indication and being indicated, configuration and being configured, and the like.

[0326] In embodiments of the present application, "predefined" or "preconfigured" can be achieved by pre-saving corresponding codes, tables or other information that can be used to indicate related information in devices (such as terminal devices and network devices), and the specific implementation of the present application is not limited. For example, predefinition can refer to definition in a protocol.

[0327] In embodiments of the present application, the "protocol" can refer to a standard protocol in the communication field, which can include LTE protocol, NR protocol and related protocols applied to future communication systems, and the present application is not limited thereto.

[0328] In embodiments of the present application, the term "and / or" is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents an "or" relationship between the front and rear associated objects.

[0329] In various embodiments of the present application, the size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0330] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the division of the above-described device embodiments is only a logical function division, and there can be another division manner for actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0331] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0332] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0333] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server, data center and the like integrated with one or more available media sets. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, digital video disc (DVD)) or semiconductor media (for example, solid state disk (SSD)) and the like.

[0334] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for wireless communication, characterized in that, include: The terminal device determines a first resource set and / or a second resource set based on the first information. Wherein, the first downlink reference signal corresponding to the first resource set is used to measure the measurement result, and the measurement result is used to select a target space transmission filter from the space transmission filters for downlink transmission indicated by the second resource set.

2. The method as described in claim 1, characterized in that, The first information is used to indicate the time-domain resources corresponding to the first downlink reference signal from the time-domain resources corresponding to the multiple downlink reference signals, wherein the time-domain resources corresponding to the multiple downlink reference signals are periodically configured or semi-persistently scheduled.

3. The method as described in claim 2, characterized in that, The first information is used to indicate the first bit map, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are the time-domain resources corresponding to the first downlink reference signal.

4. The method as described in claim 2, characterized in that, The first information is used to indicate that the time-domain resource located within the first time window among the time-domain resources corresponding to the plurality of downlink reference signals is the time-domain resource corresponding to the first downlink reference signal.

5. The method as described in claim 2, characterized in that, The first information is used to indicate the first timer, and the downlink reference signal whose time domain position overlaps with the running time of the first timer is the first downlink reference signal; and / or The downlink reference signal whose time domain position does not overlap with the running time of the first timer is not the first downlink reference signal.

6. The method according to any one of claims 2-5, characterized in that, The method further includes: The terminal device receives the first information sent by the network device.

7. The method according to any one of claims 1-6, characterized in that, The first information is used to indicate the time-domain resources corresponding to the downlink reference signal transmitted through the space transmission filter from the time-domain resources corresponding to multiple downlink reference signals, wherein the downlink reference signal transmitted through the space transmission filter is used to select the target space transmission filter.

8. The method as described in claim 7, characterized in that, The first information includes a second bitmap, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are time-domain resources corresponding to the downlink reference signals transmitted through the spatial transmission filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

9. The method as described in claim 7, characterized in that, The first information is used to indicate that the downlink reference signal located within the second time window among the plurality of downlink reference signals is transmitted through the spatial transmission filter.

10. The method as described in claim 9, characterized in that, The target space transmission filter is selected from the space transmission filters based on the measurement results using a model, and the downlink reference signal within the second time window is used to determine the measurement results of the space transmission filter selected by the model.

11. The method as described in claim 7, characterized in that, The first information includes a second timer, wherein the downlink reference signals whose time-domain positions overlap with the running time of the second timer are transmitted through the spatial transmission filter; and / or Downlink reference signals whose time-domain positions do not overlap with the running time of the first timer are not used to select the target space transmission filter.

12. The method according to any one of claims 1-6, characterized in that, The first information is used to indicate the index range of the spatial emission filter index indicated by the second resource set, or The first information is used to indicate the reference signal resource set of the downlink reference signal corresponding to the second resource set.

13. The method as described in claim 1, characterized in that, The first resource set corresponds to multiple first downlink reference signals, and the first information is used to indicate the time-domain resources corresponding to the multiple first downlink reference signals. The time-domain resources corresponding to the multiple first downlink reference signals are aperiodic time-domain resources.

14. The method as described in claim 13, characterized in that, The first information is used to indicate the time-domain interval between the time-domain resources that transmit the first information and the time-domain locations corresponding to the plurality of first downlink reference signals.

15. The method as described in claim 13 or 14, characterized in that, In the time-domain resources corresponding to multiple first downlink reference signals, the time-domain interval between any two adjacent time-domain resources is the same, or The time-domain intervals between at least two adjacent time-domain resources corresponding to the multiple first downlink reference signals are different.

16. The method as described in claim 15, characterized in that, The method further includes: The terminal device receives configuration information sent by the network device. The configuration information is used to configure the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the multiple first downlink reference signals.

17. The method according to any one of claims 1-16, characterized in that, The target space emission filter is selected from the space emission filters based on the measurement results using a model, and the model is located in the network device. If the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first Resource collection; If the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

18. A method for wireless communication, characterized in that, include: The terminal device sends a first channel state information (CSI) to the network device. The time-domain resources for transmitting the first CSI are determined based on reference resources, and the time-domain interval between the time-domain resources and the reference resources is associated with the number of measurements corresponding to the first CSI.

19. The method as described in claim 18, characterized in that, The reference resource is a CSI reference resource, the time domain interval is the product of the target time domain interval and the number of measurements, and the target time domain interval is the time domain interval between the time domain resource and the CSI reference resource.

20. The method as described in claim 18 or 19, characterized in that, The first CSI is generated using a model based on historical measurement results. This model is used to predict spatial filters corresponding to multiple time points. The spatial filters corresponding to the multiple time points are indicated by the first CSI; or The spatial filters corresponding to the plurality of times are indicated by a plurality of CSIs including the first CSI.

21. A method for wireless communication, characterized in that, include: The network device determines a first resource set and / or a second resource set based on the first information. The first downlink reference signal transmitted in the first resource set is used to measure the measurement result, and the measurement result is used to select a target space transmission filter from the space transmission filter indicated by the second resource set.

22. The method as described in claim 21, characterized in that, The first information is used to indicate the time-domain resources corresponding to the first downlink reference signal from the time-domain resources corresponding to the multiple downlink reference signals, wherein the time-domain resources corresponding to the multiple downlink reference signals are periodically configured or semi-persistently scheduled.

23. The method as described in claim 22, characterized in that, The first information is used to indicate the first bit map, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are the time-domain resources corresponding to the first downlink reference signal.

24. The method as described in claim 22, characterized in that, The first information is used to indicate that the time-domain resource located within the first time window among the time-domain resources corresponding to the plurality of downlink reference signals is the time-domain resource corresponding to the first downlink reference signal.

25. The method as described in claim 22, characterized in that, The first information is used to indicate the first timer, and the downlink reference signal whose time domain position overlaps with the running time of the first timer is the first downlink reference signal; and / or The downlink reference signal whose time domain position does not overlap with the running time of the first timer is not the first downlink reference signal.

26. The method according to any one of claims 22-25, characterized in that, The method further includes: The network device sends the first information to the terminal device.

27. The method according to any one of claims 21-26, characterized in that, The first information is used to indicate the time-domain resources corresponding to the downlink reference signal transmitted through the space transmission filter from the time-domain resources corresponding to multiple downlink reference signals, wherein the downlink reference signal transmitted through the space transmission filter is used to select the target space transmission filter.

28. The method as described in claim 27, characterized in that, The first information includes a second bitmap, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are time-domain resources corresponding to the downlink reference signals transmitted through the spatial transmission filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

29. The method as described in claim 27, characterized in that, The first information is used to indicate that the downlink reference signal located within the second time window among the plurality of downlink reference signals is transmitted through the spatial transmission filter.

30. The method as described in claim 29, characterized in that, The target space transmission filter is selected from the space transmission filters based on the measurement results using a model, and the downlink reference signal within the second time window is used to determine the measurement results of the space transmission filter selected by the model.

31. The method as described in claim 27, characterized in that, The first information includes a second timer, wherein the downlink reference signals whose time-domain positions overlap with the running time of the second timer are transmitted through the spatial transmission filter; and / or Downlink reference signals whose time-domain positions do not overlap with the running time of the first timer are not used to select the target space transmission filter.

32. The method according to any one of claims 21-26, characterized in that, The first information is used to indicate the index range of the spatial emission filter index indicated by the second resource set, or The first information is used to indicate the reference signal resource set of the downlink reference signal corresponding to the second resource set.

33. The method as described in claim 21, characterized in that, The first resource set corresponds to multiple first downlink reference signals, and the first information is used to indicate the time-domain resources corresponding to the multiple first downlink reference signals. The time-domain resources corresponding to the multiple first downlink reference signals are aperiodic time-domain resources.

34. The method as described in claim 33, characterized in that, The first information is used to indicate the time-domain interval between the time-domain resources that transmit the first information and the time-domain locations corresponding to the plurality of first downlink reference signals.

35. The method as described in claim 33 or 34, characterized in that, In the time-domain resources corresponding to multiple first downlink reference signals, the time-domain interval between any two adjacent time-domain resources is the same, or The time-domain intervals between at least two adjacent time-domain resources corresponding to the multiple first downlink reference signals are different.

36. The method as described in claim 35, characterized in that, The method further includes: The network device sends configuration information to the terminal device. The configuration information is used to configure the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the multiple first downlink reference signals.

37. The method according to any one of claims 21-36, characterized in that, The target space emission filter is selected from the space emission filters based on the measurement results using a model, and the model is located in the network device. If the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set; If the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

38. A method for wireless communication, characterized in that, include: The network device receives a first CSI sent by the terminal device. The time domain resources for transmitting the first CSI are determined based on reference resources. The time domain interval between the time domain resources and the reference resources is associated with the number of measurements corresponding to the first CSI.

39. The method as described in claim 38, characterized in that, The reference resource is a CSI reference resource, the time domain interval is the product of the target time domain interval and the number of measurements, and the target time domain interval is the time domain interval between the time domain resource and the CSI reference resource.

40. The method as described in claim 38 or 39, characterized in that, The first CSI is generated using a model based on historical measurement results. This model is used to predict spatial filters corresponding to multiple time points. The spatial filters corresponding to the multiple time points are indicated by the first CSI; or The spatial filters corresponding to the plurality of times are indicated by a plurality of CSIs including the first CSI.

41. A terminal device, characterized in that, include: Processing unit, configured to determine a first resource set and / or a second resource set based on first information. Wherein, the first downlink reference signal corresponding to the first resource set is used to measure the measurement result, and the measurement result is used to select a target space transmission filter from the space transmission filters for downlink transmission indicated by the second resource set.

42. The terminal device as described in claim 41, characterized in that, The first information is used to indicate the time-domain resources corresponding to the first downlink reference signal from the time-domain resources corresponding to the multiple downlink reference signals, wherein the time-domain resources corresponding to the multiple downlink reference signals are periodically configured or semi-persistently scheduled.

43. The terminal device as described in claim 42, characterized in that, The first information is used to indicate the first bit map, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are the time-domain resources corresponding to the first downlink reference signal.

44. The terminal device as described in claim 42, characterized in that, The first information is used to indicate that the time-domain resource located within the first time window among the time-domain resources corresponding to the plurality of downlink reference signals is the time-domain resource corresponding to the first downlink reference signal.

45. The terminal device as described in claim 42, characterized in that, The first information is used to indicate the first timer, and the downlink reference signal whose time domain position overlaps with the running time of the first timer is the first downlink reference signal; and / or The downlink reference signal whose time domain position does not overlap with the running time of the first timer is not the first downlink reference signal.

46. ​​The terminal device as described in any one of claims 42-45, characterized in that, The terminal device also includes: The first receiving unit is used to receive the first information sent by the network device.

47. The terminal device as described in any one of claims 41-46, characterized in that, The first information is used to indicate the time-domain resources corresponding to the downlink reference signal transmitted through the space transmission filter from the time-domain resources corresponding to multiple downlink reference signals, wherein the downlink reference signal transmitted through the space transmission filter is used to select the target space transmission filter.

48. The terminal device as described in claim 47, characterized in that, The first information includes a second bitmap, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are time-domain resources corresponding to the downlink reference signals transmitted through the spatial transmission filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

49. The terminal device as described in claim 47, characterized in that, The first information is used to indicate that the downlink reference signal located within the second time window among the plurality of downlink reference signals is transmitted through the spatial transmission filter.

50. The terminal device as described in claim 49, characterized in that, The target space transmission filter is selected from the space transmission filters based on the measurement results using a model, and the downlink reference signal within the second time window is used to determine the measurement results of the space transmission filter selected by the model.

51. The terminal device as described in claim 47, characterized in that, The first information includes a second timer, wherein the downlink reference signals whose time-domain positions overlap with the running time of the second timer are transmitted through the spatial transmission filter; and / or Downlink reference signals whose time-domain positions do not overlap with the running time of the first timer are not used to select the target space transmission filter.

52. The terminal device as described in any one of claims 41-46, characterized in that, The first information is used to indicate the index range of the spatial emission filter index indicated by the second resource set, or The first information is used to indicate the reference signal resource set of the downlink reference signal corresponding to the second resource set.

53. The terminal device as described in claim 41, characterized in that, The first resource set corresponds to multiple first downlink reference signals, and the first information is used to indicate the time-domain resources corresponding to the multiple first downlink reference signals. The time-domain resources corresponding to the multiple first downlink reference signals are aperiodic time-domain resources.

54. The terminal device as described in claim 53, characterized in that, The first information is used to indicate the time-domain interval between the time-domain resources that transmit the first information and the time-domain locations corresponding to the plurality of first downlink reference signals.

55. The terminal device as described in claim 53 or 54, characterized in that, In the time-domain resources corresponding to multiple first downlink reference signals, the time-domain interval between any two adjacent time-domain resources is the same, or The time-domain intervals between at least two adjacent time-domain resources corresponding to the multiple first downlink reference signals are different.

56. The terminal device as described in claim 55, characterized in that, The terminal device also includes: The second receiving unit is used to receive configuration information sent by the network device. The configuration information is used to configure the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the multiple first downlink reference signals.

57. The terminal device as described in any one of claims 41-56, characterized in that, The target space emission filter is selected from the space emission filters based on the measurement results using a model, and the model is located in the network device. If the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set; If the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

58. A terminal device, characterized in that, include: The transmitting unit is used to transmit first channel state information (CSI) to the network device. The time-domain resources for transmitting the first CSI are determined based on reference resources, and the time-domain interval between the time-domain resources and the reference resources is associated with the number of measurements corresponding to the first CSI.

59. The terminal device as described in claim 58, characterized in that, The reference resource is a CSI reference resource, the time domain interval is the product of the target time domain interval and the number of measurements, and the target time domain interval is the time domain interval between the time domain resource and the CSI reference resource.

60. The terminal device as described in claim 58 or 59, characterized in that, The first CSI is generated using a model based on historical measurement results. This model is used to predict spatial filters corresponding to multiple time points. The spatial filters corresponding to the multiple time points are indicated by the first CSI; or The spatial filters corresponding to the plurality of times are indicated by a plurality of CSIs including the first CSI.

61. A network device, characterized in that, include: Processing unit, configured to determine a first resource set and / or a second resource set based on first information. The first downlink reference signal transmitted in the first resource set is used to measure the measurement result, and the measurement result is used to select a target space transmission filter from the space transmission filter indicated by the second resource set.

62. The network device as described in claim 61, characterized in that, The first information is used to indicate the time-domain resources corresponding to the first downlink reference signal from the time-domain resources corresponding to the multiple downlink reference signals, wherein the time-domain resources corresponding to the multiple downlink reference signals are periodically configured or semi-persistently scheduled.

63. The network device as described in claim 62, characterized in that, The first information is used to indicate the first bit map, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are the time-domain resources corresponding to the first downlink reference signal.

64. The network device as described in claim 62, characterized in that, The first information is used to indicate that the time-domain resource located within the first time window among the time-domain resources corresponding to the plurality of downlink reference signals is the time-domain resource corresponding to the first downlink reference signal.

65. The network device as described in claim 62, characterized in that, The first information is used to indicate the first timer, and the downlink reference signal whose time domain position overlaps with the running time of the first timer is the first downlink reference signal; and / or The downlink reference signal whose time domain position does not overlap with the running time of the first timer is not the first downlink reference signal.

66. The network device as described in any one of claims 62-65, characterized in that, The network device also includes: The first sending unit is used to send the first information to the terminal device.

67. The network device as described in any one of claims 61-66, characterized in that, The first information is used to indicate the time-domain resources corresponding to the downlink reference signal transmitted through the space transmission filter from the time-domain resources corresponding to multiple downlink reference signals, wherein the downlink reference signal transmitted through the space transmission filter is used to select the target space transmission filter.

68. The network device as described in claim 67, characterized in that, The first information includes a second bitmap, which is used to indicate whether the time-domain resources corresponding to the plurality of downlink reference signals are time-domain resources corresponding to the downlink reference signals transmitted through the spatial transmission filter, wherein the plurality of downlink reference signals are periodic reference signals or semi-persistent scheduling reference signals.

69. The network device as described in claim 67, characterized in that, The first information is used to indicate that the downlink reference signal located within the second time window among the plurality of downlink reference signals is transmitted through the spatial transmission filter.

70. The network device as described in claim 69, characterized in that, The target space transmission filter is selected from the space transmission filters based on the measurement results using a model, and the downlink reference signal within the second time window is used to determine the measurement results of the space transmission filter selected by the model.

71. The network device as described in claim 67, characterized in that, The first information includes a second timer, wherein the downlink reference signals whose time-domain positions overlap with the running time of the second timer are transmitted through the spatial transmission filter; and / or Downlink reference signals whose time-domain positions do not overlap with the running time of the first timer are not used to select the target space transmission filter.

72. The network device as described in any one of claims 61-66, characterized in that, The first information is used to indicate the index range of the spatial emission filter index indicated by the second resource set, or The first information is used to indicate the reference signal resource set of the downlink reference signal corresponding to the second resource set.

73. The network device as described in claim 61, characterized in that, The first resource set corresponds to multiple first downlink reference signals, and the first information is used to indicate the time-domain resources corresponding to the multiple first downlink reference signals. The time-domain resources corresponding to the multiple first downlink reference signals are aperiodic time-domain resources.

74. The network device as described in claim 73, characterized in that, The first information is used to indicate the time-domain interval between the time-domain resources that transmit the first information and the time-domain locations corresponding to the plurality of first downlink reference signals.

75. The network device as described in claim 73 or 74, characterized in that, In the time-domain resources corresponding to multiple first downlink reference signals, the time-domain interval between any two adjacent time-domain resources is the same, or The time-domain intervals between at least two adjacent time-domain resources corresponding to the multiple first downlink reference signals are different.

76. The network device as described in claim 75, characterized in that, The network device also includes: The second transmitting unit is used to transmit configuration information to the terminal device. The configuration information is used to configure the time domain interval between every two adjacent time domain resources in the time domain resources corresponding to the multiple first downlink reference signals.

77. The network device as described in any one of claims 61-76, characterized in that, The target space emission filter is selected from the space emission filters based on the measurement results using a model, and the model is located in the network device. If the first resource set and the second resource set are used for model inference of the model, the first information is used to determine the first resource set; If the first resource set and the second resource set are used for model training and / or model monitoring of the model, the first information is used to determine the first resource set and the second resource set.

78. A network device, characterized in that, include: The receiving unit is used to receive a first CSI sent by the terminal device. The time domain resources for transmitting the first CSI are determined based on reference resources, and the time domain interval between the time domain resources and the reference resources is associated with the number of measurements corresponding to the first CSI.

79. The network device as described in claim 78, characterized in that, The reference resource is a CSI reference resource, the time domain interval is the product of the target time domain interval and the number of measurements, and the target time domain interval is the time domain interval between the time domain resource and the CSI reference resource.

80. The network device as described in claim 78 or 79, characterized in that, The first CSI is generated using a model based on historical measurement results. This model is used to predict spatial filters corresponding to multiple time points. The spatial filters corresponding to the multiple time points are indicated by the first CSI; or The spatial filters corresponding to the plurality of times are indicated by a plurality of CSIs including the first CSI.

81. A terminal device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals, so that the terminal device performs the method as described in any one of claims 1-17, or performs the method as described in any one of claims 18-20.

82. A network device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals to cause the network device to perform the method as described in any one of claims 21-37, or to perform the method as described in any one of claims 38-47.

83. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the device to perform the method as described in any one of claims 1-40.

84. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-40.

85. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-40.

86. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-40.

87. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-40.

Images