Method, device and medium for communication

Abstract

Example embodiments of the present disclosure relate to beam reporting based on artificial intelligence prediction. In an example method, a communication method at a terminal device includes receiving a configuration for a first beam report from a network device; generating a first beam report using an artificial intelligence (AI) model without performing beam measurements on a first set of reference signals associated with the first beam report; and sending the first beam report to the network device. Thus, the load of beam reporting can be reduced, thereby saving uplink resources.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of communications, and more particularly, to terminal devices, network devices, methods, apparatuses, and computer-readable storage media for communications. Background Art

[0002] In a wireless access network, a network device can generate a set of beams to a terminal device. The terminal device can send a beam report to the network device to indicate a beam or a subset of beams that performs better than other beams. However, when generating a beam report, the terminal needs to measure the reference signal (RS) from the network device and needs to report the reference signal quality information to the network device. This requires more load in the report, and thus more uplink resources. Sending reference signals from the network device also requires more downlink resources. Summary of the invention

[0003] In general, example embodiments of the present disclosure provide a beam reporting solution for artificial intelligence based prediction.

[0004] In a first aspect, a communication method at a terminal device is provided. The method includes: receiving a configuration of a first beam report from a network device; generating the first beam report using an artificial intelligence (AI) model without performing beam measurement on a first set of reference signals associated with the first beam report; and sending the first beam report to the network device.

[0005] In a second aspect, a communication method at a network device is provided. The method includes: sending a configuration of a first beam report to a terminal device; and receiving a first beam report of the network device from the terminal device, the first beam report being generated using an artificial intelligence (AI) model, and no beam measurement is performed on a first set of reference signals associated with the first beam report.

[0006] In a third aspect, there is a terminal device. The terminal device comprises: a processor; and a memory storing a computer program code; the memory and the computer program code are configured to, together with the processor, enable the terminal device to execute the method of the first aspect.

[0007] In a fourth aspect, there is a network device. The network device comprises: a processor; and a memory storing a computer program code; the memory and the computer program code are configured to, together with the processor, enable the network device to execute the method of the second aspect.

[0008] In a fifth aspect, a computer-readable medium is provided, on which instructions are stored, and when the instructions are executed by a processor of a device, the device executes the method of the first and second aspects.

[0009] It should be understood that the summary is not intended to identify the key or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0011] Figure 1A An example of a network environment is described in which some example embodiments of the present disclosure may be implemented;

[0012] Figure 1B An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0013] Figure 2 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0014] Figure 3 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0015] Figure 4 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0016] Figure 5 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0017] Figure 6 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0018] Figure 7 An example of a process for beam reporting based on artificial intelligence prediction according to some example embodiments of the present disclosure is described;

[0019] Figure 8 An example of a method implemented at a terminal device according to some example embodiments of the present disclosure is described;

[0020] Fig. 9 An example of a method implemented at a network device according to some example embodiments of the present disclosure is described;

[0021] Fig.10 A simplified block diagram illustrating a device suitable for implementing an embodiment of the present disclosure.

[0022] Throughout the drawings, the same or similar reference numbers represent the same or similar elements. DETAILED DESCRIPTION

[0023] The principle of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described only to illustrate and help those skilled in the art understand and implement the present disclosure, and do not imply any limitation on the scope of the present disclosure. The disclosure described herein can be implemented in various ways except as described below.

[0024] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0025] References to "one embodiment," "an embodiment," "an example embodiment," and the like in this disclosure indicate that the described embodiment may include certain features, structures, or characteristics, but not every embodiment must include certain features, structures, or characteristics. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, whether or not explicitly described, the claimed feature, structure, or characteristic affects the combination of such features, structures, or characteristics with other embodiments within the knowledge of those skilled in the art.

[0026] It should be understood that although the terms "first" and "second" etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are simply used to distinguish one element from another element. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0027] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that when used herein, the terms "include", "comprise", "consist of", "have", "have", "include" and / or "contain" refer to the presence of the features, elements and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0028] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementations only (e.g., implementations only in analog and / or digital circuitry) and (b) a combination of hardware circuitry and software, such as (as applicable):

[0029] (i) a combination of analog and / or digital hardware circuitry and software / firmware, and

[0030] (ii) hardware processors and software (including digital signal processors), any portion of software and memory, which work together to enable a device such as a mobile phone or server to perform various functions, and (c) hardware circuits and / or processors, such as a microprocessor or a portion of a microprocessor, which require software (such as firmware) to run, but the software may not be present when the software is not required to run.

[0031] This definition of circuitry applies to all uses of this term in this application, including in any claims. By way of further example, the term circuitry as used in this application also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. For example, the term circuitry also covers a baseband integrated circuit or processor integrated circuit of a mobile device, or a similar integrated circuit in a server, cellular network device, or other computing or network device, if applicable to the particular claim element.

[0032] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT), etc. In addition, the communication between the terminal device and the network device in the communication network can be performed according to any suitable generation of communication protocols, including but not limited to the Fourth Generation (4G), 4.5G, the Fifth Generation (5G) communication protocol and / or any other protocol currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development in communication, there will certainly be future types of communication technologies and systems that can be used in combination with the contents of the present disclosure. It should not be considered that the scope of the present disclosure is limited to the above-mentioned systems.

[0033] As used herein, the term "network device" refers to a node in a communication network, via which a terminal device accesses the network and receives services therefrom. A network device may refer to a base station (BS) or an access point (AP), such as a NodeB (NB), an evolved NodeB (eNodeB or eNB), an NR NB (also known as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a repeater, an integrated and access backhaul (IAB) node, a low-power node such as a femto, a micro, a non-terrestrial network (NTN) or a non-terrestrial network device, such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, etc., depending on the terminology and technology of the application.

[0034] The term "terminal device" refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS) or access terminal (AT). Terminal devices may include, but are not limited to, mobile phones, cellular phones, smart phones, Voice over IP (VoIP), wireless local loop phones, tablet computers, wearable terminal devices, personal digital assistants (PDA), portable computers, desktop computers, image capture terminal devices (such as digital cameras), game terminal devices, music storage and playback devices, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMD), vehicles, drones, medical equipment and applications (such as remote surgery), industrial equipment and applications (such as robots and / or other wireless devices operating in industrial and / or automated processing chain environments), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. In the following description, the terms "terminal device", "communication device" and "terminal" may be used interchangeably.

[0035] In a wireless access network, a network device may generate a set of beams to a terminal device. The terminal device may send a beam report to the network device to indicate a beam or a subset of beams that performs better than other beams. However, when generating a beam report, the terminal needs to measure a reference signal from the network device and needs to report the reference signal quality information and an indication of the reference signal to the network device. This requires more load in the report, and thus more uplink resources. Sending reference signals from the network device also requires more downlink resources.

[0036] The example embodiments of the present disclosure provide a mechanism to solve the problems discussed above. The inventors have found that if a terminal device generates a beam report without measuring a reference signal when using the location information of the terminal device, and the beam report may only contain an indication of a reference signal generated by artificial intelligence (AI) prediction, without reference signal quality information. In this way, the load of the beam report can be reduced, thereby saving uplink resources. Beam reports can be generated in model reasoning. Accordingly, the network device may not always send a reference signal, thereby saving downlink resources. In model monitoring, reference signals and AI predictions can be measured to determine whether the AI ​​model is available. An indication of whether the AI ​​model is available can be carried in a beam report. The principles and some example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0037] Figure 1A An example of a network environment in which some example embodiments of the present disclosure may be implemented is described. In the description of the example embodiments of the present disclosure, the network environment 100 may also be referred to as a communication system 100 (e.g., a portion of a communication network). For illustrative purposes only, various aspects of the example embodiments will be described in the context of one or more network devices and terminal devices that communicate with each other. However, it should be understood that the description herein may be applicable to other types of devices or other similar devices referenced using other terms.

[0038] The communication system 100 includes a network device 101 and a terminal device 102. According to an exemplary embodiment of the present disclosure, the network device 101 may generate a set of beams, such as 106, 107, 108, 109, 110, and 111. It will be appreciated by those skilled in the art that the number of potential beams may be different from the number of beams in FIG. 1, such as 8, 16, or 32, etc. Associated with each beam, there is a reference signal. The reference signal may be a channel state information-reference signal (CSI-RS). Alternatively or additionally, the reference signal may be a synchronization signal (SS) / physical broadcast channel (PBCH). The CRI-RS and SS / PBCH associated with the group of beams may be included in a set of reference signals. For each CSI-RS, there is a Channel State Information (CSI)-Reference Signal (RS) Resource Indicator (CSI-RS Resource Indicator, CRI), and for each SS / PBCH, there is a Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) Block Resource Indicator (SSBRI). Therefore, CRI and SSBRI can indicate the beam associated with them.

[0039] In an example embodiment of the present disclosure, terminal device 102 moves from position 104 to position 105 in direction or trajectory 103. Using AI or machine learning (ML) model prediction, terminal device 102 can determine a first group of beams whose reference signal quality is better than other beams in the group of beams without measuring the reference signal set from network device 101, only through the location information of terminal device 102. The first group of beams can be a beam, such as 107, or can be a subset of beams, such as 107, 108, 109, and 110. Therefore, in the first beam report, the terminal can only report the CRI or SSBRI of beam 107, or the CRI or SSBRI of beam subsets 107, 108, 109, and 110, without performing beam measurement on the first group of reference signals associated with the first group of beams. The bit width of the first beam report can be determined by the number of CRIs or SSBRIs to be reported. The first beam report can also be generated using the direction or trajectory of terminal device 102.

[0040] Figure 1BAn example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, the network device 101 sends (111) a configuration for a first beam report to the terminal device 102. After receiving (111) the configuration, the terminal device 102 generates (112) a first beam report using an artificial intelligence (AI) model without performing beam measurement on a first set of reference signals associated with the first beam report. Then, the terminal device 102 sends (113) the first beam report to the network device 101. Accordingly, the network device 101 receives (113) the first beam report 113 from the terminal device 102. In this way, the resources for the beam report can be reduced, thereby reducing the uplink resources.

[0041] In an exemplary embodiment of the present disclosure, although the RS is configured in the first beam report 113 generated using the AI ​​model, if the network device sends the RS, the terminal device 102 can ignore or omit the RS. In other words, the terminal device 102 does not receive the RS, or does not perform beam measurement (i.e., calculate the L1-RSRP of the beam corresponding to the received RS, and find the top N beams based on the calculated L1-RSRP). The terminal device 102 does not expect to receive the RS associated with the AI ​​beam report.

[0042] In the exemplary embodiment of the present disclosure, since the terminal device 102 does not need to receive the RS, it can be considered that although the RS is configured in the AI ​​beam report, the network device 101 does not send the RS. The terminal device 102 does not expect to receive the RS associated with the AI ​​beam report.

[0043] In an exemplary embodiment of the present disclosure, for an AI-based, triggered first beam report, even if the reporting number of the AI ​​beam report is configured as "cri-RSRP" or "ssb-Index-RSRP", the terminal device 102 only reports the CRI / SSBRI (e.g., the CIR / SSBRI corresponding to the predicted first N beams) to the gNB. N refers to a positive integer greater than or equal to 1. The value of N may be configured or indicated by the gNB and may depend on the capability reported by the UE. The capability refers to the maximum number of beams that the AI ​​model can predict.

[0044] In this way, the terminal device 102 does not need to send a beam report with reference signal quality information to reduce uplink resources. In an exemplary embodiment of the present disclosure, in order to determine the first N (N>=1) beams in the group of beams, the terminal device 102 calculates the layer 1 reference signal received power (Layer 1 Reference Signal Received Power, L1-RSRP) and layer 1 signal to interference plus noise ratio (Layer 1 Signal to Interference plus Noise Ratio, L1-SINR) corresponding to a group of RS associated with the beam report (i.e., corresponding to the group of beams).

[0045] In an example embodiment of the present disclosure, for the first beam report using AI, the corresponding bit width is determined according to the N CRI / SSBRIs to be reported. The terminal device 102 may report the CRI / SSBRI corresponding to the predicted first N beams in the uplink control information (UCI) or the physical uplink control channel (PUCCH) according to the mapping order applied to report only the CRI / SSBRI. The mapping order of CRI / SSBRI is as follows.

[0046] The following table can be implemented as a beam report with CRI or SSBRI. Those skilled in the art will appreciate that the beam report can be in other formats, such as with different field names, etc. In this way, the bit width of the beam report can be reduced, thereby reducing uplink resources.

[0047]

[0048] The first beam report may also carry reference signal quality information with prediction, such as L1-RSRP and L1-SINR. The bit width of the first beam report may also be determined by L1-RSRP and L1-SINR.

[0049] In an exemplary embodiment of the present disclosure, the terminal device 102 may also generate and send a beam report by measuring a reference signal from the network device 101 without performing AI / ML model prediction. When a first AI-based beam report conflicts with another beam report in the time domain, the priority needs to be determined based on the following items: whether the two beam reports carry only CRI or SSBRI, and whether the two beam reports are configured as AI beam reports.

[0050] The terminal device 102 may be configured to periodically or semi-continuously send multiple beam reports generated using the AI ​​model. The first beam report may be one of the multiple beam reports. The terminal device 102 may also be triggered by the network device 101 to send a beam report at any time. The first beam report may conflict with the second beam report. The terminal device 102 may determine a first priority for the first beam report and a second priority for the second beam report. The first priority may be determined by whether the first beam report includes only CRI or SSBRI. The second priority may be determined by whether the second beam report includes only CRI or SSBRI.

[0051] In an exemplary embodiment of the present disclosure, a beam report carrying only CRI / SSBRI may have a lower priority than a beam report carrying L1-RSRP / L1-SINR. In an exemplary embodiment of the present disclosure, a priority value k of a beam report may be determined as follows: k=0 for a beam report carrying L1-RSRP, L1-SINR, and CRI or SSBRI, and k=1 for a beam report carrying only CRI or SSBRI without L1-RSRP or L1-SINR. A priority with a value k=0 is higher than a priority with a value k=1.

[0052] In an example embodiment of the present disclosure, the priority of a beam report carrying only CRI / SSBRI may be lower than the priority of a beam report carrying L1-RSRP / L1-SINR. In an example embodiment of the present disclosure, when a first beam report based on AI conflicts with another beam report carrying CRI / SSBRI+L1-RSRP / L1-SINR (i.e., the PUCCH / Physical Uplink Share Channel (PUSCH) resources carrying the first beam report based on AI overlap with the PUCCH / PUSCH resources carrying another beam report), the terminal device may give priority to the transmission of the other beam report.

[0053] In an exemplary embodiment of the present disclosure, for carrying only L1-RSRP, L1-SINR, k=0, for carrying L1-RSRP, L1-SINR and CRI or SSBIR, k=1, for carrying only CRI or SSBIR, k=2. The priority value of k=0 is higher than the priority value of k=1, and the priority value of k=1 is higher than the priority value of k=2.

[0054] In an example embodiment of the present disclosure, the priority of an AI beam report configured as an AI beam report may be lower than the priority of a beam port that is not configured with an AI beam report. For example, an AI beam report that also carries CRI+L1-RSRP conflicts with another beam report that carries CRI+L1-RSRP, and the terminal device may prioritize the transmission of the other beam report. In this way, a beam report with more information RS measurement can be sent with a higher priority.

[0055] Alternatively or additionally, the first priority may be determined by whether the first beam report is generated using the AI ​​model. The second priority may also be determined by whether the second beam report is also generated using the AI ​​model. The priority without the AI ​​model is higher than the priority with the AI ​​model.

[0056] In an exemplary embodiment of the present disclosure, if the terminal device 102 receives an RS associated with an AI beam report between an AI beam report and a latest AI beam report, the terminal device 102 reports CRI / SSBRI+L1-RSRP / L1-SINR. The corresponding bit width is determined based on the K CRI / SSBRI+L1-RSRP / L1-SINRs to be reported.

[0057] In an exemplary embodiment of the present disclosure, if the terminal device 102 does not receive the RS associated with the AI ​​beam report between the AI ​​beam report and the latest AI beam report, the terminal device 102 only reports the CRI / SSBRI. The corresponding bit width is determined based on the N CRI / SSBRIs to be reported.

[0058] Figure 2 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, at 201, the network device 101 sends a configuration for a first beam report, or triggers a first beam report. At 202, the network device 101 sends a reference signal, such as a CRI-RS or SSB, to the terminal device 102. At 203, the terminal device 102 uses the received reference signal to implement beam measurement. At 204, the terminal device 102 sends a non-AI-based beam report with CRI / SSBRI and L1-RSRP / L1-SINR. At 205, without using reference signal measurement, the terminal device 102 implements model reasoning. At 206, the terminal device sends a first beam report with only CRI / SSBRI.

[0059] In the following blocks 205, 207 and 209, the terminal device 102 implements model inference without a reference signal, and then sends a first beam report at 206, 208 and 210. At 211, the network device 101 sends a reference signal such as CRI-RS or SSB to the terminal device 102. At 212, the terminal device 102 implements beam measurement and receives a reference signal. At 213, the terminal device 102 sends a non-AI-based beam report with CRI / SSBRI and L1-RSRP / L1-SINR. The period of the reference signal 214 is different from the period of the beam report 215. In an example embodiment of the present disclosure, the period of the reference signal 214 may be 40 time slots, while the period of the beam report 215 may be 10 time slots.

[0060] In an exemplary embodiment of the present disclosure, the terminal device 102 may send multiple beam reports periodically or semi-persistently (P / SP). The first beam report may be one of multiple beam reports. In an exemplary embodiment of the present disclosure, the period of the P / SP AI beam report is configured to be 10 time slots, and the period of the RS is configured to be 40 time slots. Before the first beam report and the fifth beam report, the terminal device 102 will receive RSs (or be configured or provided with RS), in which case the terminal device 102 performs beam measurement based on the received RS and reports the CRI+L1-RSRP corresponding to the first K (e.g., K=1 / 2 / 3 / 4) beams. However, for the second, third, fourth, and sixth beam reports, the terminal device 102 will not receive RS (or will not be configured or provided with RS), in which case the terminal device 102 will not perform beam measurement and only report the CRI corresponding to the first N beams predicted based on the AI ​​model.

[0061] In the example embodiment of the present disclosure, more strictly, the terminal device 102 needs to determine whether RS ​​is received between the AI ​​beam report (i.e., the current beam report, or the beam report to be reported or sent), and the latest AI beam report. Specifically, between the first symbol or time slot of the PUCCH / PUSCH resource carrying the AI ​​beam report or the CSI reference resource corresponding to the AI ​​beam report, and the last symbol or time slot of the PUCCH / PUSCH resource carrying the latest AI beam report. In this way, the terminal device can use RS measurement to generate a more accurate beam report.

[0062] In an example embodiment of the present disclosure, the first beam report using the AI ​​model may not be configured with RS. Although receiving RS is not necessary for the terminal device, the terminal device 102 may know the configuration information of RS, such as the number or identifier of CSI-RS / SSB resource sets or CSI-RS / SSB resources. The first group of reference signals associated with the first beam report may be determined based on the second group of reference signals configured in the second beam report. The second beam report may be closest to the first beam report in the time domain. Alternatively or additionally, the second beam report may be generated using the AI ​​model, or may not be generated using the AI ​​model. Alternatively or additionally, the number of the second group of RS configured in the second beam report is less than or equal to a predefined threshold. The predefined threshold is used to indicate the maximum number of beams that the AI ​​model can support. Alternatively or additionally, the second beam report is indicated by the index of the CSI report configured in the first beam report. Alternatively, the first RS may be determined based on the RS configured in the indicated second beam report.

[0063] In an exemplary embodiment of the present disclosure, an RS (referred to as a "first RS") associated with an AI beam report ("first beam report") may be determined based on an RS ("second RS") configured in another beam report ("second beam report"). The second beam report needs to meet at least one of the following criteria: the second beam report is the closest beam report to the first beam report in the time domain, the second beam report is not an AI beam report, i.e., a non-AI beam report, and the number of RSs configured in the second beam report is less than or equal to a predefined threshold, which is used to indicate the maximum number of beams that the AI ​​model can support.

[0064] In an exemplary embodiment of the present disclosure, the second beam report is indicated by an ID or index of a CSI report indicating the second beam report, and the ID or index of the CSI report is configured in the first beam report. In other words, the first RS can be determined based on the RS configured in the indicated second beam report.

[0065] In an example embodiment of the present disclosure, the RS associated with the AI ​​beam report can be determined based on an RS (referred to as a "third RS") that satisfies at least one of the following criteria: the RS resource set corresponding to the third RS is associated with repetition or is configured with repetition (e.g., repetition is turned off or on), the RS resource set corresponding to the third RS is the RS resource set closest to the first beam report in the time domain, and the number of the third RS is less than or equal to a predefined threshold. In this way, the terminal device can obtain RS configuration without configuration.

[0066] In an example embodiment of the present disclosure, for an AI beam report, the bit width of a report amount (e.g., CRI / SSBRI) may be determined based on the RS associated with the beam report. For example, the determination of the bit width for reporting CRI / SSBRI depends on the number of RSs configured in the beam report. When the terminal device 102 is not configured with an RS configured in the AI ​​beam report, the terminal device 102 may first determine the RS associated with the AI ​​beam report based on a previous second beam report, and then determine the bit width for reporting CRI / SSBRI based on the determined number of RSs.

[0067] CRI, SSBRI, RSRP and the bit width of different RSRPs can be determined according to the following table.

[0068]

[0069] in, is the number of CSI-RS resources in the corresponding resource set or in the associated resource set, The number of SS / PBCH blocks configured in the corresponding resource set or the associated resource set for reporting "ssb-Index-RSRP". In this way, the bit width of CRI, SSBRI, RSRP and differential RSRP can be determined, thereby reducing uplink resources.

[0070] In an example embodiment of the present disclosure, the terminal device 102 may determine that the beam report is an AI beam report if at least one of the following conditions is met: the terminal device 102 reports AI-related capabilities, for example, indicating that the terminal device supports AI / ML, model reasoning, and beam prediction capabilities based on location information. The network device configures the terminal device 102 with AI-related configurations, for example, enabling parameters indicating AI / ML / model reasoning / beam prediction based on location information. The terminal device 102 is not configured with an RS associated with a beam report, and the period of the RS configured in the beam report is different from the period of the beam report. The period of the RS configured in the beam report is different from the period of the beam report.

[0071] In this way, the resources for beam reporting can be reduced and the resources for uplink can be reduced.

[0072] In an example embodiment of the present disclosure, for the first beam report, model reasoning can be used to predict CRI, SSBRI, RSRP using an AI model, and model monitoring can be used to monitor whether the AI ​​model is available. For monitoring-based reporting, the terminal device 102 reports at least CRI and first information to the network device, where the first information is used to indicate whether the AI ​​model is available. Specifically, the terminal device 102 can report: K / N CRIs, K / N L1-RSRPs, and first information, i.e., CRI and L1-RSRP corresponding to the first K / N beams and the first information. The terminal device 102 can report K / N CRIs and the first information. The first information occupies 1 bit in the UCI. "1" indicates that the AI ​​model is available. "0" indicates that the AI ​​model is not available. The beam report with the first information can be shown in the following table.

[0073]

[0074]

[0075] In an exemplary embodiment of the present disclosure, for inference-based reporting, the terminal device 102 reports at least CRI to the network device. Specifically, the terminal device may report N CRIs. The terminal device may also report N CRIs and N L1-RSRPs.

[0076] For monitoring-based reporting, the terminal device 102 expects to receive RS associated with a joint model inference and model monitoring (JIM) beam report. For inference-based reporting, the terminal device does not expect to receive RS associated with a JIM beam report. In this way, monitoring-based reporting can use only one bit to carry the availability of the AI ​​model, thereby reducing uplink resources.

[0077] Figure 3 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, the first beam report sent by the terminal device 102 is a first report type for model reasoning without RS measurement. The third beam report can be a second report type for model monitoring.

[0078] In model monitoring, the terminal device 102 measures the RS from the network device 101 and calculates L1-RSRP or L1-SINR, and CRI / SSBRI. In model monitoring, the terminal device 102 can also generate CRI / SSBRI using the AI ​​model, and generate L1-RSRP or L1-SINR using the location information of the terminal device 102. By comparing the CRI, SSBRI, L1-RSRP and L1-SINR measured from the RS, and the CRI, SSBRI, L1-RSRP and L1-SINR generated by the AI ​​model, it can be determined whether the AI ​​model is available. The terminal device 102 can send an indication of whether the AI ​​model is available in a third beam report. The beam report carrying an indication of whether the AI ​​model is available can be a second report type for model monitoring.

[0079] In an exemplary embodiment of the present disclosure, at 301, the network device 101 sends a configuration for a first beam report to the terminal device 102 using an AI model without performing beam measurement on a set of RSs associated with the first beam report. At 302, the network device 101 sends the RS to the terminal device 102. At 303, the terminal device implements model monitoring and then sends a third beam report for model monitoring to the network device 101 at 304. At 305, without receiving and measuring the RS, the terminal device 102 implements model reasoning and sends the first beam report for model reasoning to the network device 101 at 306. In subsequent blocks 307 and 309, the terminal device 102 implements model reasoning and then sends the first beam report for model reasoning to the network device 101 at 308 and 310. After receiving the RS at 311, the terminal device 102 implements beam monitoring at 312 and then sends the third beam report for model monitoring.

[0080] In an exemplary embodiment of the present disclosure, the terminal device 102 may determine that the report type is model monitoring according to the offset for model monitoring and the period for model monitoring. Figure 3 In the configuration information, the offset for model monitoring can be 0, and the period for model monitoring can be 40 time slots. The offset for model reasoning can be 0, and the period for model reasoning can be 10 time slots. Based on the configuration information, the terminal device can determine whether the JIM beam report is a monitoring-based report or a reasoning-based beam report. In addition, the monitoring-specific offset and period can be configured in the JIM beam report. Optionally, the configuration of the reasoning-specific offset and period can also be considered. In this way, the timing of the beam reports for model reasoning and model monitoring can be flexibly controlled.

[0081] Figure 4 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, Figure 4 Operations 301, 302, ..., and 313 in Figure 3 The operations are the same as those in . The terminal device 102 can determine the report type as model monitoring by the cycle duration. The offset and period of the JIM beam report are 0 and 10 time slots. In addition, the terminal device is configured with a cycle duration. It is assumed that the starting offset and period of the cycle duration are configured as 0 and 40 time slots.

[0082] The cycle duration further includes an inference duration (e.g., 30 time slots) and a monitoring duration (e.g., 10 time slots), wherein the inference duration may be before the monitoring duration, or may be after the monitoring duration. Figure 4 As shown, the terminal device first enters the reasoning duration. During the reasoning duration, the JIM beam report is a report based on reasoning. This means that the terminal device does not receive RS and at least reports CRI. Then, the terminal device enters the monitoring duration. During the monitoring duration, the JIM beam report is a report based on monitoring. This means that the terminal device receives RS and reports at least CRI and the first information. In this way, the beam report timing of model reasoning and model monitoring can be flexibly controlled.

[0083] Figure 5 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, Figure 5 Operations 301, 302, ..., and 313 in Figure 3 The operations in are the same as those in . The terminal device 102 can determine that the report type is model monitoring through dynamic instructions from the network device 101. Figure 5 In the embodiment, the dynamic indication may be indications 501 and 502 for the monitored beam report sent by the network device 101 before sending the RS. After the terminal device receives the indication, the next JIM beam report indicated by the indication is a report based on the monitoring. For example, the network device may use the "CSI request" in the downlink control information (DCI) to indicate the access point (AP) trigger status associated with the JIM beam report. The DCI is encrypted using a new Radio Network Temporary Identity (RNTI) or a specific RNTI. In this way, the beam reporting time for model reasoning and model monitoring can be flexibly controlled.

[0084] Figure 6 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, Figure 6 Operations 301, 302, ..., and 313 in Figure 3 The operations in are the same as those in . The terminal device 102 can determine that the report type is model monitoring through dynamic instructions from the network device 101. Figure 6 In the embodiment, the dynamic indication may be activation and deactivation of the beam report for monitoring. At 601, the network device 101 sends activation for the beam report for monitoring to the terminal device 102, and then sends the RS at 602. In response to receiving the activation for the beam report for monitoring, the terminal device 102 implements model monitoring, and then sends the beam report for monitoring at 304. The terminal device 102 repeats the model monitoring and the sending of the beam report for monitoring until deactivation of the beam report for monitoring is received at 602.

[0085] In an example embodiment of the present disclosure, the timing of beam reporting for reasoning and monitoring can be controlled based on two dynamic indications: an activation indication for model monitoring and a deactivation indication for model monitoring. Optionally, an indication for model monitoring and an indication for model reasoning.

[0086] In an exemplary embodiment of the present disclosure, after the terminal device 102 receives an activation indication for model monitoring (and after the control instruction carrying the indication takes effect), the terminal device 102 starts to perform model monitoring, which means that the next JIM beam report is a monitoring-based report. After the terminal device 102 receives a deactivation indication for model monitoring, the terminal device 102 stops performing model monitoring, and the next JIM beam report is a reasoning-based report. In addition, the indication may be carried by DCI or a Media Access Control-Control Element (MAC-CE). For example, a new MAC-CE may be introduced. The new MAC-CE includes two indications: activation and deactivation for model monitoring. A new field (e.g., 1 bit) may be introduced in the DCI. "1" and "0" refer to activation and deactivation of model monitoring. Alternatively, it is reasonable to reuse the "CSI request" in the DCI to indicate activation and deactivation of model monitoring. Extend 1 bit in the "CSI request" field. "1" and "0" refer to activation and deactivation of model monitoring. The "111" and "000" in the submitted "CSI request" refer to the activation and deactivation for model monitoring. At the same time, the DCI is scrambled with a new RNTI or a specific RNTI. In this way, the timing of beam reporting for model inference and model monitoring can be flexibly controlled.

[0087] Figure 7 An example of a beam reporting process based on artificial intelligence prediction according to some example embodiments of the present disclosure is described. In an example embodiment of the present disclosure, Figure 7 Operations 301, 302, ... and 313 in Figure 3 The operations in are the same as those in. The terminal device 102 can determine that the report type is model monitoring by receiving a first set of reference signals from the network device. In response to receiving the RS, the terminal device 102 generates a third beam report for monitoring. In response to not receiving the RS, the terminal device 102 generates a first beam report for inference.

[0088] In an example embodiment of the present disclosure, the terminal device 102 may be configured with an RS whose period is different from the beam report period. If the terminal device 102 receives an RS associated with a JIM beam report between a JIM beam report and the latest JIM beam report, the JIM beam report is a monitoring-based report. If the terminal device 102 does not receive an RS associated with a JIM beam report between a JIM beam report and the latest JIM beam report, the JIM beam report is an inference-based report. Therefore, the terminal device 102 may determine whether the JIM beam report is a monitoring-based beam report or an inference-based beam report based on whether an RS associated with a JIM beam report is received. In this way, the timing of the beam reports of model inference and model monitoring may be flexibly controlled.

[0089] In an exemplary embodiment of the present disclosure, the dynamic indication may be indicated by downlink control information (DCI) in a physical downlink control channel (PDCCH). The dynamic indication may also be indicated by a medium access control-control element (MAC-CE).

[0090] In an example embodiment of the present disclosure, the number of CPUs required for model inference may be P, and the number of CPUs required for model monitoring may be P+1, which is one more than model inference for RS measurement. "P" refers to an integer greater than or equal to 0.

[0091] In an example embodiment of the present disclosure, for a beam report having the following: CPU =1, the higher layer parameter reportQuantity of CSI-ReportConfig is set to "cri-RSRP", "ssb-lndex-RSRP", "cri-SINR", "ssb-lndex-SINR", or "None", and the higher layer parameter trs-Info of CSI-RS-ResourceSet is not configured, and the beam report is not indicated for AI beam reporting.

[0092] For beam reports with the following, O CPU=P, the higher layer parameter reportQuantity of CSI-ReportConfig is set to "cri-RSRP", "ssb-lndex-RSRP", "cri-SINR", "ssb-lndex-SINR" or "None", and the higher layer parameter trs-lnfo of CSI-RS-ResourceSet is not configured, and the beam report is indicated for model inference.

[0093] For beam reports with the following, O CPU =1+P, the higher layer parameter reportQuanntity of CSI-ReportConfig is set to "cri-RSRP", "sab-lndex-RSRP", "cri-SINR", "ssb-lndex-SINR", or "None", and the higher layer parameter trs-lnfo of CSI-RS-ResourceSet is not configured, and the beam report is indicated for model monitoring.

[0094] In this way, the CPU resources used for model inference and model monitoring can be determined efficiently.

[0095] In an example embodiment of the present disclosure, the terminal device 102 may determine that the beam report is a JIM beam report if at least one of the following conditions is met: the terminal device 102 reports AI-related capabilities, for example, capabilities indicating the following items: the UE supports AI / machine learning (ML), model reasoning, model monitoring, joint model reasoning and model monitoring, and beam prediction based on location information. The terminal device 102 is configured with AI-related configurations through the network device 101, for example, parameters indicating AI / ML / model reasoning / model monitoring / joint model reasoning and model monitoring / beam prediction based on location information are enabled. The period of the RS configured in the beam report is different from the period of the beam report. The terminal device 102 is configured with a monitoring / inference specific offset and period, or a cycle duration, and the cycle duration includes a monitoring duration and an inference duration.

[0096] Figure 8 An example of a method 800 implemented at a terminal device according to some exemplary embodiments of the present disclosure is described. For ease of discussion, reference will be made to Figure 1B The method 800 is stated from the perspective of the terminal device 102 .

[0097] In an example embodiment of the present disclosure, in block 801, the terminal device 102 receives a configuration for a first beam report from the network device 101. In block 802, the terminal device 102 generates the first beam report using an artificial intelligence (AI) model without performing beam measurement on a first set of reference signals associated with the first beam report. In block 803, the terminal device 102 sends the first beam report to the network device 101.

[0098] In one embodiment, the terminal device 102 further omits receiving the set of reference signals from the network device.

[0099] In one embodiment, the first beam report includes a channel state information (CSI)-reference signal (RS) resource indicator (CRI) or a synchronization signal (SS) / physical broadcast channel (PBCH) block resource indicator (SSBRI).

[0100] In one embodiment, in response to determining that sending a first beam report conflicts with sending a second beam report, based on a comparison between a first priority of the first beam report and a second priority of the second beam report, the terminal device 102 further sends one of the first beam report and the second beam report.

[0101] In one embodiment, the first priority and the second priority are determined based on at least one of the following items: whether the first beam report includes CRI or SSBRI, and whether the first beam report is generated using an AI model.

[0102] In one embodiment, sending the first beam report includes: periodically or semi-continuously sending multiple beam reports, the first beam report being one of the multiple beam reports.

[0103] In one embodiment, in response to receiving a first set of reference signals before sending a first beam report and after sending a most recent beam report, the terminal device 102 further generates a first beam report to include at least one of a CRI, a SSBRI, a layer 1 reference signal received power (L1-RSRP), and a layer 1 signal to interference plus noise ratio (L1-SINR).

[0104] In one embodiment, in response to not receiving the first set of reference signals before sending the first beam report and after sending the most recent beam report, the terminal device 102 further generates the first beam report to include at least one of the CRI and the SSBRI.

[0105] In one embodiment, the terminal device 102 further determines the first group of reference signals associated with the first beam report based on the second group of reference signals configured in the second beam report.

[0106] In one embodiment, the second beam report satisfies at least one of the following conditions: the second beam report is closest to the first beam report in the time domain, the second beam report is not generated using an AI model, the number of reference signals in the second group of reference signals is less than or equal to a predefined threshold, and the second beam report is indicated by an index of the CSI report configured in the first beam report.

[0107] In one embodiment, in the above method, the terminal device 102 further determines the first group of reference signals associated with the first beam report based on the second group of reference signals.

[0108] In one embodiment, the second group of reference signals satisfies at least one of the following conditions: the second group of reference signals is associated with a repetitive configuration, the second group of reference signals is closest to the first beam report in the time domain, and the number of reference signals in the second group of reference signals is less than or equal to a predetermined threshold.

[0109] In one embodiment, the terminal device 102 further determines that the first beam report will be generated using the AI ​​model based on at least one of the following conditions: the configuration includes AI-related parameters, the configuration does not include the first group of reference signals, and the configuration includes the first group of reference signals, and the period of the first group of reference signals is different from the period of the first beam report.

[0110] In one embodiment, the first beam report is a first report type for model inference.

[0111] In one embodiment, the terminal device 102 further generates a third beam report without using the AI ​​model and performing beam measurement on the first set of reference signals associated with the first beam report, and sends at least an indication of whether the AI ​​model is available to the network device in the third beam report, and the third beam report is a second report type for model monitoring.

[0112] In one embodiment, the terminal device 102 desires to receive a first set of reference signals associated with a first beam report, which is a second report type for model monitoring.

[0113] In one embodiment, the number of CPUs occupied by the model monitoring process is one more than the number of CPUs occupied by the model inference process.

[0114] In one embodiment, the terminal device 102 further determines that the report type is model monitoring based on at least one of the following items: the offset and period of model monitoring, the cycle duration (including the duration of model inference and the duration of model monitoring), the dynamic indication from the network device, and the reception of the first set of reference signals from the network device.

[0115] In one embodiment, the dynamic indication is indicated by downlink control information (DCI) or medium access control-control element (MAC-CE).

[0116] In one embodiment, the DCI is scrambled using a specific Radio Network Temporary Identifier (RNTI).

[0117] Fig. 9 An example of a method 900 implemented at a network device according to some example embodiments of the present disclosure is described. For ease of discussion, reference will be made to Figure 1B Method 900 is stated from the perspective of network device 101 .

[0118] In block 901, the network device 101 sends a configuration for a first beam report to the terminal device 102. In block 902, the network device 101 receives a first beam report for the network device from the terminal device 102, the first beam report being generated using an artificial intelligence (AI) model, and beam measurement is not performed on a first set of reference signals associated with the first beam report.

[0119] In one embodiment, the network device 101 further omits sending the group of reference signals to the terminal device 102 .

[0120] In one embodiment, the network device 101 further receives an indication from the terminal device 102 regarding whether the AI ​​model in the terminal device 102 is available.

[0121] Fig.10 A simplified block diagram of a device 1000 suitable for implementing an embodiment of the present disclosure is shown. The device 1000 may be viewed as Figure 1B A further example implementation of the terminal device 102 and the network device 101 is shown. Thus, the device 1000 may be implemented on the terminal device 102 or the network device 101, or at least implemented as a part of the terminal device 102 or the network device 101.

[0122] As shown, the device 1000 includes a processor 1010, a memory 1020 coupled to the processor 1010, a suitable transmitter (Transmitter, TX) and receiver (Receiver, RX) 1040 coupled to the processor 1010, and a communication interface coupled to the TX / RX 1040. The memory 1010 stores at least a portion of the program 1030. The TX / RX 1040 is used for bidirectional communication. The TX / RX 1040 has at least one antenna to facilitate communication, although in fact the access node mentioned in the present disclosure may have multiple antennas. The communication interface may represent any interface required for communication with other network elements, such as an X2 interface for bidirectional communication between eNBs, an S1 interface for communication between a Mobility Management Entity (MME) / Serving Gateway (S-GW) and an eNB, a Un interface for communication between an eNB and a relay node (RN), or a Uu interface for communication between an eNB and a terminal device.

[0123] Assume that program 1030 includes program instructions that, when executed by associated processor 1010, cause device 1000 to operate in accordance with embodiments of the present disclosure, as described herein with reference to Figure 2-9 The embodiments herein may be implemented by computer software executable by the processor 1010 of the device 1000, or may be implemented by hardware, or by a combination of software and hardware. The processor 1010 may be configured to implement various embodiments of the present disclosure. In addition, the combination of the processor 1010 and the memory 1020 may form a processing component 1050 suitable for implementing various embodiments of the present disclosure.

[0124] Memory 1020 may be of any type suitable for a local technology network and may be implemented using any suitable data storage technology, such as non-transitory computer-readable storage media, semiconductor-based storage devices, magnetic storage devices and systems, optical storage devices and systems, fixed memory, and removable memory, as non-limiting examples. Although only one memory 1020 is shown in device 1000, there may be multiple physically distinct memory modules in device 1000. Processor 1010 may be of any type suitable for a local technology network and may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as non-limiting examples. Device 1000 may have multiple processors, such as dedicated integrated circuit chips that are time-slave to a clock synchronized with a main processor.

[0125] In summary, the embodiments of the present disclosure may provide the following solutions.

[0126] A communication method includes: receiving a configuration for a first beam report from a network device on a terminal device; generating the first beam report using an artificial intelligence (AI) model without performing beam measurement on a first set of reference signals associated with the first beam report; and sending the first beam report to the network device.

[0127] In one embodiment, the method further comprises: omitting receiving the set of reference signals from the network device.

[0128] In one embodiment, in the method described above, the first beam report includes a channel state information (CSI)-reference signal (RS) resource indicator (CRI), or a synchronization signal (SS) / physical broadcast channel (PBCH) block resource indicator (SSBRI).

[0129] In one embodiment, the above method further includes: in response to determining that sending the first beam report conflicts with sending the second beam report, sending one of the first beam report and the second beam report based on a comparison between a first priority of the first beam report and a second priority of the second beam report.

[0130] In one embodiment, in the method described above, the first priority and the second priority are determined based on at least one of the following: whether the first beam report includes CRI or SSBRI, and whether the first beam report is generated using an AI model.

[0131] In one embodiment, in the method described above, sending the first beam report includes: periodically or semi-continuously sending multiple beam reports, and the first beam report is one of the multiple beam reports.

[0132] In one embodiment, the above method further includes: in response to receiving a first set of reference signals before sending the first beam report and after sending the most recent beam report, generating a first beam report to include at least one of CRI, SSBRI, layer 1 reference signal received power (L1-RSRP) and layer 1 signal to interference plus noise ratio (L1-SINR).

[0133] In one embodiment, the method further comprises: in response to not receiving the first set of reference signals before sending the first beam report and after sending the most recent beam report, generating the first beam report to include at least one of the CRI and the SSBRI.

[0134] In one embodiment, the method further comprises: determining a first group of reference signals associated with the first beam report based on a second group of reference signals configured in the second beam report.

[0135] In one embodiment, in the method as described above, the second beam report satisfies at least one of the following conditions: the second beam report is closest to the first beam report in the time domain, the second beam report is not generated using an AI model, the number of reference signals in the second group of reference signals is less than or equal to a predefined threshold, and the second beam report is indicated by the index of the CSI report configured in the first beam report.

[0136] In one embodiment, the method further comprises: determining a first group of reference signals associated with the first beam report based on the second group of reference signals.

[0137] In one embodiment, in the method as described above, the second group of reference signals satisfies at least one of the following conditions: the second group of reference signals is associated with a repeated configuration, the second group of reference signals is closest to the first beam report in the time domain, and the number of reference signals in the second group of reference signals is less than or equal to a predefined threshold.

[0138] In one embodiment, the method as described above further includes: determining to use the AI ​​model to generate a first beam report based on at least one of the following conditions: the configuration includes AI-related parameters, the configuration does not include a first set of reference signals, and the configuration includes a first set of reference signals, and the period of the first set of reference signals is different from the period of the first beam report.

[0139] In one embodiment, in the method described above, the first beam report has a first report type for model reasoning.

[0140] In one embodiment, the method as described above further includes: generating a third beam report without using an AI model by performing beam measurement on a first set of reference signals associated with the first beam report, wherein at least an indication as to whether the AI ​​model is available is sent to a network device in the third beam report, and the third beam report has a second report type for model monitoring.

[0141] In one embodiment, in the method as described above, the terminal device expects to receive a first set of reference signals associated with a first beam report having a second report type for model monitoring.

[0142] In one embodiment, in the method described above, the number of CPUs occupied by the process monitored by the model is one more than the number of CPUs occupied by the process inferred by the model.

[0143] In one embodiment, the method as described above further includes: determining the report type as model monitoring based on at least one of the following items: the offset and period of model monitoring, the cycle duration (including the duration for model reasoning, and the duration for model monitoring), the dynamic indication from the network device, and receiving a first set of reference signals from the network device.

[0144] In one embodiment, in the method described above, the dynamic indication is indicated by downlink control information (DCI) or medium access control-control element (MAC-CE).

[0145] In one embodiment, in the method described above, the DCI is scrambled using a specific Radio Network Temporary Identifier (RNTI).

[0146] A communication method comprises: at a network device, sending a configuration for a first beam report to a terminal device; and receiving a first beam report of the network device from the terminal device, wherein the first beam report is generated using an artificial intelligence (AI) model, and beam measurement is not performed on a first set of reference signals associated with the first beam report.

[0147] In one embodiment, the above method further comprises: omitting sending the group of reference signals to the terminal device.

[0148] In one embodiment, the above method further includes: receiving an indication from the terminal device as to whether the AI ​​model in the terminal device is available.

Claims

1. A communication method, comprising: receiving, at a terminal device, from a network device, a configuration for a first beam report; At a terminal device, generating the first beam report using an artificial intelligence (AI) model without performing beam measurements on a first set of reference signals associated with the first beam report; and Send the first beam report to the network device.

2. The method according to claim 1, further comprising: Receiving the set of reference signals from the network device is omitted.

3. The method of claim 1, wherein the first beam report comprises: Channel State Information (CSI)-Reference Signal (RS) Resource Indicator (CRI), or Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) Block Resource Indicator (SSBRI).

4. The method according to claim 1, further comprising: In response to determining that sending the first beam report conflicts with sending the second beam report, one of the first beam report and the second beam report is sent based on a comparison between a first priority of the first beam report and a second priority of the second beam report.

5. The method of claim 1 , wherein the priority associated with the first beam report is determined based on at least one of: whether the first beam report contains CRI or SSBRI, and Whether the first beam report is generated using the AI ​​model.

6. The method of claim 1, wherein sending the first beam report comprises: A plurality of beam reports are sent periodically or semi-continuously, and the first beam report is one of the plurality of beam reports.

7. The method according to claim 6, further comprising: In response to receiving the first set of reference signals before sending the first beam report and after sending the most recent beam report, the first beam report is generated to include at least one of the following items: CRI, SSBRI, layer 1 reference signal received power (L1-RSRP) and layer 1 signal to interference plus noise ratio (L1-SINR).

8. The method according to claim 6, further comprising: In response to not receiving the first set of reference signals before sending the first beam report and after sending the most recent beam report, generating the first beam report to include at least one of a CRI and a SSBRI.

9. The method according to claim 1, further comprising: The first set of reference signals associated with the first beam report is determined based on a second set of reference signals configured in a second beam report.

10. The method according to claim 9, wherein the second beam report satisfies at least one of the following conditions: The second beam report is closest to the first beam report in the time domain, The second beam report is not generated using the AI ​​model, The number of reference signals in the second set of reference signals is less than or equal to a predefined threshold, and The second beam report is indicated by an index of a CSI report configured in the first beam report.

11. The method according to claim 1, further comprising: The first set of reference signals associated with the first beam report is determined based on a second set of reference signals.

12. The method according to claim 11, wherein the second set of reference signals satisfies at least one of the following conditions: The second set of reference signals is associated with a repeated configuration, The second set of reference signals is closest to the first beam report in the time domain, and The number of the reference signals in the second group of reference signals is less than or equal to a predefined threshold.

13. The method according to claim 1, further comprising: Based on at least one of the following conditions, determining to use the AI ​​model to generate the first beam report: The configuration includes AI related parameters, The configuration does not include the first set of reference signals, and The configuration includes the first set of reference signals, and a periodicity of the first set of reference signals is different from a periodicity of the first beam report. The method of claim 1 , wherein the first beam report has a first report type for model inference.

15. The method according to claim 1, further comprising: generating a third beam report without using the AI ​​model by performing beam measurements on the first set of reference signals associated with the first beam report, In the third beam report, at least an indication of whether the AI ​​model is available is sent to the network device, The third beam report has a second report type for model monitoring.

16. The method of claim 15, wherein: The terminal device expects to receive the first set of reference signals associated with the first beam report having the second report type for model monitoring.

17. The method of claim 15, wherein: The number of CPUs occupied by the processing monitored by the model is one more than the number of CPUs occupied by the processing inferred by the model.

18. The method according to claim 15, further comprising: determining whether the first beam report has the second report type for model monitoring based on at least one of: Offset and period for model monitoring, The cycle duration, including the duration used for model inference and the duration used for model monitoring, dynamic indications from said network devices, and The first set of reference signals is received from the network device.

19. The method of claim 18, wherein the dynamic indication is indicated by downlink control information (DCI) or medium access control-control element (MAC-CE).

20. The method of claim 19, wherein: The DCI is scrambled using a specific Radio Network Temporary Identifier (RNTI).

21. A communication method, comprising: At the network device, sending a configuration for a first beam report to the terminal device; as well as The first beam report for the network device is received from the terminal device, the first beam report being generated using an artificial intelligence (AI) model without performing beam measurements on a first set of reference signals associated with the first beam report.

22. The method according to claim 21, further comprising: Omit sending the set of reference signals to the terminal device.

23. The method according to claim 21, further comprising: An indication is received from the terminal device as to whether the AI ​​model in the terminal device is available.

24. A terminal device, comprising: processor; as well as a memory storing computer program code; The memory and the computer program code are configured to, together with the processor, cause the terminal device to perform the method according to any one of claims 1-20.

25. A network device comprising: processor; as well as a memory storing computer program code; The memory and the computer program code are configured to, together with the processor, cause the network device to perform a method according to any one of claims 21-23.

26. A computer readable medium having instructions stored thereon, which, when executed by a processor of a device, cause the device to perform the method according to any one of claims 1 to 23.

Images