Communication method, apparatus, terminal device and network device

Abstract

The present application relates to the technical field of communications. Disclosed are a communication method, an apparatus, a terminal device and a network device. When AI technology is applied to a CSI framework, as a first AI model will perform CSI compression on input information in sequence, the present application needs to determine grouping of the input information. Thus, the first AI model can be used for performing CSI compression on first input information within a group, and using historical input information within the group for CSI compression on non-first input information within the group, so as to enhance CSI-related processing. Alternatively, as the input information and / or processing information of the first AI model that should have been reported may not be reported due to certain factors and is thus discarded, in the case of the discarding, the present application needs to determine CSI reporting of the input information and / or the processing information that should have been reported but fails to be reported, so as to enhance CSI-related processing.

Description

Communication method and device, terminal equipment and network equipment

[0001] This invention claims priority from the prior application No. 202311869286.2 filed on December 29, 2023, entitled “Communication Method and Apparatus, Terminal Equipment and Network Equipment”. The contents of the aforementioned prior application are incorporated into this text by way of introduction. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a communication method and apparatus, terminal equipment, and network equipment. Background Art

[0003] Artificial intelligence (AI) technology can solve problems that are difficult to solve using traditional modeling methods, such as nonlinear problems and problems with overly complex parameters. By training with large amounts of data, it can establish problem-solving models and provide relatively accurate prediction results. AI can include machine learning (ML) and deep learning (DL), and AI models can include various linear and nonlinear network models, such as linear regression, vector machines, convolutional neural networks (CNN), and deep neural networks (DNN).

[0004] With the continuous development of AI technology and the evolution of wireless communication systems, the 3rd Generation Partnership Project (3GPP) is currently discussing the integration of AI technology with wireless communication systems. One area of ​​discussion is the application of AI technology to the channel state information (CSI) framework / domain to improve air interface performance and reduce air interface overhead. However, when AI technology is applied to the CSI framework, how to enhance CSI-related processing requires further research. Summary of the Invention

[0005] The present application provides a communication method and apparatus, a terminal device, and a network device, in the hope of enhancing CSI-related processing when AI technology is applied to the CSI framework.

[0006] The first aspect is a communication method of the present application, comprising:

[0007] Determining grouping of first input information of the first AI model, or determining channel state information (CSI) reporting of the first input information and / or the first processed information;

[0008] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0009] It can be seen that when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model will perform CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, the first obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or the first obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this application needs to determine the grouping of input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0010] Alternatively, when a terminal device needs to report / feedback input information and / or processed information, some input information and / or processed information that was originally required to be reported / feedback may not be reported due to some factors, resulting in the input information and / or processed information being discarded. Thus, in the case of input information and / or processed information that was originally required to be reported but was not, this embodiment can determine the CSI reporting of the input information and / or processed information that was originally required to be reported but was not, thereby enhancing CSI-related processing.

[0011] The second aspect is a communication method of the present application, comprising:

[0012] Sending configuration information, where the configuration information is used to configure a time window, where the time window is used to determine the grouping of first input information of the first AI model; or

[0013] Sending instruction information, where the instruction information is used to indicate grouping of first input information of the first AI model;

[0014] The first AI model is used for channel state information CSI compression.

[0015] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, the first AI model performs CSI compression on the input information in sequence, and historical input information can participate in the CSI compression of the current input information. The previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or the previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0016] The third aspect is a communication method of the present application, comprising:

[0017] If the first CSI report containing the first input information and / or first processing information of the first AI model fails to be reported, a second CSI report is received, where the second CSI report includes the first input information and / or the first processing information, or the second CSI report includes the first input information and / or the first processing information and second input information and / or second processing information, where the first input information and the second input information are different input information; or

[0018] If the first CSI report containing the first input information and / or first processed information of the first AI model fails to be reported, receiving the first input information and / or the first processed information at an available time domain position after the time domain position of the first CSI report; or

[0019] If the first CSI report containing the first input information and / or the first processing information of the first AI model fails to be reported, receiving a third CSI report, where the third CSI report includes third input information and / or third processing information, where the first input information and the third input information are different input information;

[0020] The first AI model is used for CSI compression, the first processed information is information obtained by inputting the first input information into the first AI model, or information further processed by the information obtained by inputting the first input information into the first AI model, the second processed information is information obtained by inputting the second input information into the first AI model, or information further processed by the information obtained by inputting the second input information into the first AI model, and the third processed information is information obtained by inputting the third input information into the first AI model, or information further processed by the information obtained by inputting the third input information into the first AI model.

[0021] It can be seen that when it was originally hoped to report the first input information and / or the first processing information through the first CSI report, the first CSI report failed to report, which resulted in the first input information and / or the first processing information that was originally required to be reported failing to be reported. Therefore, the first input information and / or the first processing information is carried through the second CSI report, thereby achieving continued reporting of the first input information and / or the first processing information that was originally required to be reported but was not reported.

[0022] Alternatively, when the first input information and / or first processing information that was originally required to be reported cannot be reported, the first input information and / or first processing information as well as the second input information and / or second processing information are carried through the second CSI report, so that the second CSI report can both postpone the reporting of the first input information and / or first processing information and report the second input information and / or second processing information required to be reported in the second CSI report, thereby avoiding the loss of the second input information and / or second processing information.

[0023] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or first processing information is received at an available time domain position after the time domain position of the first CSI report, thereby achieving continued reporting / postponed reporting of the first input information and / or first processing information.

[0024] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or the first processing information are no longer reported, but the third input information and / or the third processing information are reported through the third CSI report, so as to report the new input information and / or the new processing information and avoid the loss of the new input information and / or the new processing information.

[0025] A fourth aspect is a communication device of the present application, comprising:

[0026] a determining unit, configured to group first input information of a first AI model, or determine channel state information (CSI) reporting of the first input information and / or first processed information;

[0027] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0028] A fifth aspect is a communication device of the present application, comprising:

[0029] a sending unit, configured to send configuration information for configuring a time window for determining grouping of first input information of the first AI model; or to send indication information for indicating grouping of the first input information of the first AI model;

[0030] The first AI model is used for channel state information CSI compression.

[0031] A sixth aspect is a communication device of the present application, comprising a receiving unit, wherein the receiving unit is configured to:

[0032] If the first CSI report containing the first input information and / or first processing information of the first AI model fails to be reported, a second CSI report is received, where the second CSI report includes the first input information and / or the first processing information, or the second CSI report includes the first input information and / or the first processing information and second input information and / or second processing information, where the first input information and the second input information are different input information; or

[0033] If the first CSI report containing the first input information and / or first processed information of the first AI model fails to be reported, receiving the first input information and / or the first processed information at an available time domain position after the time domain position of the first CSI report; or

[0034] If the first CSI report containing the first input information and / or the first processing information of the first AI model fails to be reported, receiving a third CSI report, where the third CSI report includes third input information and / or third processing information, where the first input information and the third input information are different input information;

[0035] The first AI model is used for CSI compression, the first processed information is information obtained by inputting the first input information into the first AI model, or information further processed by the information obtained by inputting the first input information into the first AI model, the second processed information is information obtained by inputting the second input information into the first AI model, or information further processed by the information obtained by inputting the second input information into the first AI model, and the third processed information is information obtained by inputting the third input information into the first AI model, or information further processed by the information obtained by inputting the third input information into the first AI model.

[0036] In the seventh aspect, the steps in the method designed in the above-mentioned first aspect are applied to a terminal device or in a terminal device.

[0037] In an eighth aspect, the steps in the method designed in the second aspect are applied to a network device or in a network device.

[0038] The ninth aspect is a terminal device of the present application, comprising a processor, a memory, and a computer program or instructions stored on the memory, wherein the processor executes the computer program or instructions to implement the steps in the method designed in the first aspect above.

[0039] The tenth aspect is a network device of the present application, comprising a processor, a memory, and a computer program or instructions stored on the memory, wherein the processor executes the computer program or instructions to implement the steps in the method designed in the second or third aspect above.

[0040] The eleventh aspect is a chip of the present application, comprising a processor, wherein the processor executes the steps in the method designed in the first aspect, second aspect or third aspect above.

[0041] Optionally, the chip further includes a communication interface, and the processor executes the sending step and / or receiving step in the method designed in the above-mentioned first aspect, second aspect or third aspect through the communication interface.

[0042] The twelfth aspect is a chip module of the present application, comprising a chip, wherein the chip comprises a processor, wherein the processor executes the steps in the method designed in the above-mentioned first aspect, second aspect or third aspect.

[0043] Optionally, the chip module further includes a transceiver component, and the processor executes the sending step and / or receiving step in the method designed in the above-mentioned first aspect, second aspect or third aspect through the transceiver component.

[0044] A thirteenth aspect is a computer-readable storage medium of the present application, wherein the computer program or instructions are stored therein, and when the computer program or instructions are executed, the steps of the method according to the first, second, or third aspects are implemented. For example, the computer program or instructions are executed by a processor.

[0045] A fourteenth aspect is a computer program product of the present application, comprising a computer program or instructions, wherein when the computer program or instructions are executed, the steps of the method according to the first, second, or third aspect are performed. For example, the computer program or instructions are executed by a processor.

[0046] The fifteenth aspect is a communication system of the present application, comprising a communication device (for example, a terminal device or chip) for executing any one of the methods provided in the first aspect, and / or, comprising a communication device (for example, a network device or chip) for executing any one of the methods provided in the second aspect or the third aspect.

[0047] The beneficial effects brought about by the technical solutions of the second to fifteenth aspects can be referred to the technical effects brought about by the technical solution of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] FIG1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present application;

[0049] FIG2 is a schematic structural diagram of a measurement resource configuration according to an embodiment of the present application;

[0050] FIG3 is a schematic diagram of the structure of a bilateral AI model according to an embodiment of the present application;

[0051] FIG4 is a schematic diagram of the structure of an enhanced bilateral AI model according to an embodiment of the present application;

[0052] FIG5 is a schematic diagram of the structure of another enhanced bilateral AI model according to an embodiment of the present application;

[0053] 6 to 11 are schematic flow charts of a monitoring method according to an embodiment of the present application;

[0054] FIG12 is a block diagram of functional units of a communication device according to an embodiment of the present application;

[0055] FIG13 is a block diagram of functional units of another communication device according to an embodiment of the present application;

[0056] FIG14 is a block diagram of functional units of another communication device according to an embodiment of the present application;

[0057] FIG15 is a schematic structural diagram of a terminal device according to an embodiment of the present application;

[0058] FIG16 is a schematic structural diagram of a network device according to an embodiment of the present application;

[0059] FIG17 is a schematic structural diagram of another network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0060] It should be understood that the terms "first," "second," and the like in the embodiments of the present application are used to distinguish between different objects, rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, software, product, or device comprising a series of steps or units is not limited to the listed steps or units, but may also include steps or units not listed, or may also include other steps or units inherent to these processes, methods, products, or devices.

[0061] The term "embodiment" as used in the embodiments of this application means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various locations in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive with other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0062] In the embodiments of this application, "and / or" describes the relationship between associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent the following three situations: A exists alone; A and B exist simultaneously; and B exists alone. A and B can be singular or plural.

[0063] In the embodiment of the present application, the symbol “ / ” can indicate that the previous and next associated objects are in an “or” relationship.

[0064] In the embodiments of the present application, "at least one item" or similar expressions refers to any combination of these items, including any combination of single items or plural items, and refers to one or more, and multiple refers to two or more. For example, at least one item among a, b or c can represent the following seven situations: "a", "b", "c", "a and b", "a and c", "b and c", "a, b and c". Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0065] In the embodiments of the present application, "higher than" can be used to express the same concept as "greater than", "lower than" can be used to express the same concept as "less than", "not lower than" can be used to express the same concept as "higher than or equal to" or "greater than or equal to", and "not higher than" can be used to express the same concept as "lower than or equal to" or "less than or equal to". In the present application, for the same solution, "equal to" can be used in conjunction with "less than" or with "greater than", but not with "less than" and "greater than" at the same time. When "equal to" is used in conjunction with "less than", the technical solution adopted by "less than" is applicable. When "equal to" is used in conjunction with "greater than", the technical solution adopted by "greater than" is applicable.

[0066] In the embodiments of the present application, the terms “of”, “corresponding / relevant”, “corresponding”, “indicated”, “associated”, etc. may be used interchangeably.

[0067] In the embodiments of the present application, “associated with,” “corresponding to,” “is,” “of,” “for,” “belong to,” “as,” and “regarded as” can sometimes be used interchangeably.

[0068] In the embodiments of the present application, the “monitoring metric / mechanism” and the “monitoring method / approach / scheme / solution” can be used interchangeably.

[0069] The "connection" in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and there is no limitation on this.

[0070] The “network” in the embodiments of the present application can be expressed as the same concept as the “system”, and the communication system is the communication network.

[0071] The following describes the relevant contents, concepts, meanings, technical issues, technical solutions and beneficial effects involved in the embodiments of this application.

[0072] 1. Communication systems, terminal equipment, and network equipment

[0073]

Communication System

[0074] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-based Access to Unlicensed Spectrum, LTE-U) system, NR on unlicensed spectrum (NR-based Access to Unlicensed Spectrum, NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), 6th Generation (6G) communication system or other communication systems.

[0075] It should be noted that the number of connections supported by traditional communication systems is limited. With the development of communication technology, the communication system of the present application can not only be a traditional communication system, but also device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine type communication (MTC), vehicle-to-vehicle (V2V) communication, vehicle-to-everything (V2X) communication, narrowband Internet of Things (NB-IoT) communication, etc.

[0076] Optionally, the technical solutions of the embodiments of the present application can be applied to beamforming (beamforming), carrier aggregation (CA), dual connectivity (DC) or standalone (SA) deployment scenarios, etc.

[0077] Optionally, the spectrum used for communication between the terminal device and the network device can be a licensed frequency band or an unlicensed frequency band, without limitation. In addition, the unlicensed frequency band can be understood as a shared frequency band, and the licensed spectrum can be understood as a non-shared frequency band.

[0078] Since the embodiments of the present application describe various embodiments in conjunction with terminal devices and network devices, the terminal devices and network devices involved will be described in detail below.

[0079]

Terminal equipment

[0080] A terminal device can be a device with transceiver functions and can also be called a terminal, user equipment (UE), remote terminal equipment (remote UE), relay UE, access terminal equipment, user unit, user station, mobile station, mobile station, remote station, mobile device, user terminal equipment, intelligent terminal equipment, wireless communication equipment, user agent, or user device. It should be noted that a relay device is a terminal device that can provide relay forwarding services for other terminal devices (including remote terminal devices).

[0081] Optionally, the terminal device is a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in unmanned autonomous driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0082] Optionally, the terminal device can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system (such as an NR communication system, a 6G communication system), or a terminal device in a future evolved public land mobile communication network (PLMN), etc., without specific limitation.

[0083] Optionally, the terminal device is deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can be deployed on the water surface (such as ships, etc.); it can be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0084] Optionally, the terminal device includes a device with wireless communication function, such as a chip system, a chip, or a chip module. For example, the chip system may include a chip and may also include other discrete devices.

[0085] Optionally, the terminal device may include a chip, a chip module, a device, a unit, etc., without specific limitation.

[0086] Optionally, the terminal device includes an intelligent module. The intelligent module may be a software unit and / or hardware unit that utilizes an AI model to perform air interface transmission processing. For example, the intelligent module may be used to perform compression / decompression and other processing on channel-related information.

[0087] Optionally, the intelligent module includes chips, chip modules, etc.

[0088] Network equipment

[0089] A network device may be a device with transceiver functions and may be used to communicate with a terminal device.

[0090] Optionally, the network device may be responsible for radio resource management (RRM), quality of service (QoS) management, data compression and encryption, data transmission and reception, etc. on the air interface side.

[0091] Optionally, the network device may include a base station (BS) in a communication system or a device deployed in a radio access network (RAN) for providing wireless communication functions, that is, the network device may include a device in the RAN.

[0092] For example, the devices in the RAN may include an evolved node B (eNB or eNodeB) in an LTE communication system, a next generation evolved node B (ng-eNB) in an NR communication system, a next generation node B (gNB) in an NR communication system, a master node (MN) in a dual-connection architecture, a second node or secondary node (SN) in a dual-connection architecture, etc., without specific limitation.

[0093] Optionally, the network device includes a device in a core network (CN).

[0094] For example, the equipment in the CN may include an access and mobility management function (AMF), a user plane function (UPF), a session management function (SMF), etc.

[0095] Optionally, the network device further includes an access point (AP) in a wireless local area network (WLAN), a relay station, a communication device in a future evolved PLMN network, a communication device in an NTN network, and the like.

[0096] Optionally, the network device may include a device that provides wireless communication functionality for the terminal device, such as a chip system, a chip, or a chip module. For example, the chip system may include a chip, or may include other discrete devices.

[0097] Optionally, the network device may include a transmission and reception point (TRP).

[0098] Optionally, the network device can communicate with an Internet Protocol (IP) network, such as the Internet, a private IP network, or other data networks.

[0099] Optionally, the network device may include an independent node to implement the functions of the above-mentioned base station, or may include two or more independent nodes to implement the functions of the above-mentioned base station. For example, the network device includes a centralized unit (CU) and a distributed unit (DU), such as a gNB-CU and a gNB-DU. Furthermore, in other embodiments of the present application, the network device may also include an active antenna unit (AAU). The CU implements part of the functions of the network device, and the DU implements another part of the functions of the network device. For example, the CU is responsible for processing non-real-time protocols and services, and implements the functions of the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and the packet data convergence protocol (PDCP) layer. The DU is responsible for processing physical layer protocols and real-time services, and implements the functions of the radio link control (RLC) layer, the medium access control (MAC) layer, and the physical (PHY) layer. In addition, the AAU can implement some physical layer processing functions, RF processing, and related functions of the active antenna. Because RRC layer information ultimately becomes PHY layer information, or is converted from PHY layer information, in this network deployment, high-layer signaling (such as RRC signaling) can be considered to be generated by the CU and sent by the DU, or sent jointly by the DU and AAU. It is understood that network devices may include at least one of the CU, DU, and AAU. Furthermore, the CU may be classified as a RAN device, or as a core network device, without specific limitation.

[0100] Optionally, the network device can be any site in the multi-site coherent joint transmission (CJT) with the terminal device, or other sites outside the multi-site, or other network devices that communicate with the terminal device in the network, and there is no specific limitation on this. Among them, multi-site coherent joint transmission can be multiple sites coherent transmission, or different data belonging to the same physical downlink shared channel (PDSCH) are sent from different sites to the terminal device, or multiple sites are virtualized into one site for transmission, or other forms of collaborative transmission, or names with the same meaning specified in other standards are also applicable to this application, that is, this application does not limit the names of these parameters. The sites in the multi-site coherent joint transmission can be remote radio heads (RRHs), TRPs, etc., and there is no specific limitation on this.

[0101] Optionally, the network device can be any site in the multi-site that performs non-coherent joint transmission with the terminal device, or other sites outside the multi-site, or other network devices that perform network communication with the terminal device, and there is no specific limitation on this. Among them, multi-site non-coherent joint transmission can be multiple sites joint non-coherent transmission, or different data belonging to the same PDSCH are sent from different sites to the terminal device, or other forms of non-cooperative transmission, or names with the same meaning specified in other standards are also applicable to this application, that is, this application does not limit the names of these parameters. The sites in the multi-site non-coherent joint transmission can be RRH, TRP, etc., and there is no specific limitation on this.

[0102] It should be noted that the TRP of the present application is not limited to coherent joint transmission or incoherent joint transmission scenarios, but can also be applied to other scenarios without specific restrictions.

[0103] Optionally, the network device may be mobile, for example, a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Alternatively, the network device may be a base station located on land or in water.

[0104] Optionally, the network device can provide services for a cell, and the terminal device in the cell can communicate with the network device using transmission resources (such as spectrum resources). The cell can be a macro cell, a small cell, a metro cell, a micro cell, a pico cell, or a femto cell.

[0105] Optionally, the network device may be a chip, a chip module, a device or a unit, etc., and there is no specific limitation on this.

[0106] Optionally, the network device may include an intelligent module. The intelligent module may be a software unit and / or hardware unit that utilizes an AI model to perform air interface transmission processing. For example, the intelligent module may be used to perform compression / decompression processing on channel-related information.

[0107] Optionally, the intelligent module can be a chip, a chip module, etc.

[0108] [Example description]

[0109] The following is an exemplary description of the communication system in an embodiment of the present application.

[0110] For example, a network architecture of a communication system according to an embodiment of the present application can be seen in Figure 1. As shown in Figure 1, the communication system 10 may include a network device 110 and a terminal device 120. The terminal device 120 may communicate with the network device 110 wirelessly.

[0111] FIG1 is merely an example of a network architecture of a communication system and does not limit the network architecture of the communication system in the embodiment of the present application.

[0112] For example, the communication system 10 may also include a server or other devices.

[0113] For another example, the communication system 10 may include other network devices in addition to the network device 110 .

[0114] For another example, the communication system 10 may include other terminal devices in addition to the terminal device 120.

[0115] 2. Combining AI Technology with the CSI Framework

[0116] 1. CSI-related configuration

[0117] Measurement Resources

[0118] CSI-related configurations may include CSI resource configuration and / or CSI report configuration, which may be defined by the higher-level parameter CSI-MeasConfig (CSI measurement configuration). The higher-level parameter CSI-MeasConfig may indicate / configure / include the following two higher-level parameters: CSI-ResourceConfig (CSI resource configuration) and CSI-ReportConfig (CSI report configuration).

[0119] Since the higher-layer parameter CSI-ReportConfig may indicate / include the parameter CSI-ResourceConfigId (CSI resource configuration identifier), the higher-layer parameter CSI-ResourceConfig is associated / corresponds / mapped to the higher-layer parameter CSI-ResourceConfig through the parameter CSI-ResourceConfigId.

[0120] The high-level parameter CSI-ReportConfig can be used to configure the CSI report, that is, to configure the CSI report.

[0121] The high-level parameter CSI-ResourceConfig can be used to configure the measurement resources for CSI measurement. In addition, the high-level parameter CSI-ResourceConfig can configure the parameter CSI-Resource-Set (CSI resource set), which can include the most basic channel state information-reference signal (CSI-RS) resources.

[0122] The parameter CSI-Resource-Set may indicate / include at least one of the following: a parameter non-zero power CSI-RS resource set (Non-Zero-Power-CSI-RS-ResourceSet, NZP-CSI-RS-ResourceSet), a parameter CSI interference measurement resource set (CSI-Interference-Measurement-ResourceSet, CSI-IM-ResourceSet), and a parameter CSI synchronization signal block resource set (CSI-SSB-ResourceSet).

[0123] The parameter NZP-CSI-RS-ResourceSet can be used for channel measurement and / or interference measurement; the parameter CSI-IM-ResourceSet can be used for interference measurement; and the parameter CSI-SSB-ResourceSet can be used for channel measurement.

[0124] The parameter CSI-ResourceConfig and / or the parameter NZP-CSI-RS-ResourceSet can configure one or more NZP-CSI-RS resource sets. Each NZP-CSI-RS resource set can include K (K≥1) NZP-CSI-RS resources.

[0125] For example, the network device sends a CSI resource configuration (CSI resource setting) to the terminal device through RRC signaling. Each CSI resource setting includes S (S ≥ 1, and S is an integer) CSI resource sets, and each CSI resource set includes K (K ≥ 1, and K is an integer) NZP-CSI-RS resources. The terminal device can receive CSI-RS on the K NZP-CSI-RS resources indicated by the network device.

[0126] In summary, measurement resources may include at least one of NZP-CSI-RS resources, CSI-IM resources, and CSI-SSB resources. NZP-CSI-RS resources can be used for channel measurement and / or interference measurement; CSI-IM resources can be used for interference measurement; and CSI-SSB resources can be used for channel measurement.

[0127] In addition, measurement resources may also include channel measurement resources (CMR) and / or interference measurement resources (IMR). Channel measurement resources refer to measurement resources used for channel measurement, such as NZP-CSI-RS resources or CSI-SSB resources; interference measurement resources refer to measurement resources used for interference measurement, such as NZP-CSI-RS resources and CSI-IM resources.

[0128] Time domain behavior

[0129] Time domain behaviors can include periodic, semi-persistent, and aperiodic. Time domain behaviors include the time domain behaviors of measurement resources and the time domain behaviors of CSI reports. These are described in detail below.

[0130] The time domain behavior of the measurement resource may include periodic measurement resources, aperiodic measurement resources, and semi-persistent measurement resources. The time domain behavior of the measurement resource may be indicated by a high-level parameter (such as resource type resourceType).

[0131] For periodic measurement resources, after the network device configures the periodic measurement resources, the network device will periodically send the measurement resources.

[0132] For non-periodic measurement resources, after the network device configures the non-periodic measurement resources, the network device does not send the measurement resources immediately, but triggers them through trigger signaling, and then sends the non-periodic measurement resources to the terminal device after the triggering.

[0133] For semi-persistent measurement resources, after the network device configures the semi-persistent measurement resources, it does not immediately send CSI-RS. Instead, it first sends activation signaling, and then sends the semi-persistent measurement resources to the terminal device after activation. Once the network device triggers the sending of semi-persistent measurement resources, it will periodically send the measurement resources until the network device sends deactivation signaling.

[0134] The time domain behavior of CSI reporting can include periodic CSI reporting, aperiodic CSI reporting, semi-persistent CSI reporting carried on the physical uplink control channel (PUCCH), and semi-persistent CSI reporting carried on the physical uplink shared channel (PUSCH). The time domain behavior of CSI reporting can be indicated by a higher-layer parameter (such as the report configuration type (reportConfigType)).

[0135] For aperiodic CSI reporting and semi-persistent CSI reporting carried on PUSCH, the network device will also configure the higher-layer parameters TriggerState and reportTriggerSize to cooperate with the CSI request field (CSI request field) in the downlink control information (DCI).

[0136] For periodic CSI reporting, once the periodic CSI-RS Resource and Report parameters are configured through RRC signaling, they will take effect immediately without the need to activate / trigger measurement resource transmission and CSI reporting through MAC-CE / DCI.

[0137] For semi-persistent CSI reporting carried on PUCCH, if the sending of semi-persistent measurement resources is configured through RRC signaling, it is necessary to first activate the measurement resource sending through MAC CE1, and then activate the CSI reporting through MAC CE2. If the sending of periodic measurement resources is configured through RRC signaling, it is not necessary to activate the measurement resource sending through MAC CE1, and only the CSI reporting needs to be activated through MAC CE2.

[0138] For semi-persistent CSI reporting carried on PUSCH, if the transmission of semi-persistent measurement resources is configured through RRC signaling, it is necessary to first activate the measurement resource transmission through MAC CE1, and then trigger the CSI report through DCI. If the transmission of periodic measurement resources is configured through RRC signaling, there is no need to activate the measurement resource transmission through MAC CE1, and only the CSI report needs to be triggered through DCI.

[0139] It should be noted that for DCI, the DCI can be DCI format (format) 0_1 scrambled using SP-CSI-RNTI (semi-persistent CSI RNTI), and the CSI request field in the DCI can be associated with the corresponding trigger state (TriggerState) by setting the codepoint. The associated CSI-ReportConfig will be defined in the TriggerState, so that the CSI-ReportConfig associated with the semi-persistent CSI report carried on the PUSCH can be found through the TriggerState.

[0140] For aperiodic CSI reporting, aperiodic CSI reporting is triggered by DCI, and the process is similar to the semi-persistent CSI reporting described above. When the codepoint of the CSI request field in DCI format 0_1 / 0_2 is used to associate the corresponding TriggerState, unlike the DCI trigger in the semi-persistent CSI reporting described above, if the CSI request field value is 0, it indicates that the semi-periodic CSI reporting is not required; if the CSI request field value is 1, it indicates that the aperiodic CSI reporting associated with TriggerState 1 is triggered, and so on.

[0141] Table 1

[0142] It should be noted that the CSI reporting configuration is related to the measurement resource configuration, as shown in Table 1. In Table 1, for periodic CSI reporting, it can only be associated with / use periodic resources; for semi-persistent CSI reporting carried on PUCCH, it can be associated with / use periodic measurement resources and semi-persistent measurement resources, and activated / deactivated through MAC CE; for semi-persistent CSI reporting carried on PUSCH, it can be associated with / use periodic measurement resources and semi-persistent measurement resources, and triggered by DCI; for aperiodic CSI reporting, it can be associated with / use periodic measurement resources, semi-persistent measurement resources, and aperiodic measurement resources, and triggered by DCI.

[0143]

CSI measurement and CSI reporting

[0144] During the CSI measurement, CSI acquisition and CSI reporting process, the terminal device can perform channel measurement / interference measurement on the downlink channel according to the measurement resources to obtain channel information / CSI information, and then report the channel information / CSI information to the network device.

[0145] Optionally, the CSI information includes at least one of the following items: CSI reference signal resource indicator index (CSI-RS Resource indicator, CRI), synchronization signal block resource indicator index (SSB resource indicator, SSBRI), rank indicator index (rank indicator, RI), precoding matrix indicator index (precoding matrix indicator, PMI), channel quality indicator index (channel quality indicator, CQI), layer indicator index (layer indicator, LI), capability index (CapabilityIndex), time-domain channel properties (time-domain channel properties, TDCP), etc.

[0146] It should be noted that CRI can represent the CSI-RS resource recommended (or selected) by the terminal device, and SSBRI can represent the SSB resource recommended (or selected) by the terminal device. Among them, one CSI-RS resource can represent one beam or antenna direction, and one SSB resource can represent one beam or antenna direction.

[0147] The RI indicates the number of layers recommended (or selected) by the terminal device, and the number of layers determines the codebook used. Each layer corresponds to a codebook, and a codebook consists of one or more codewords. For example, a codebook with 2 layers or a codebook with 1 layer can be used.

[0148] The PMI can represent the index of a codeword in the codebook recommended (or selected) by the terminal device, or quantized precoding information. One codeword corresponds to one precoding matrix. The RI and PMI can collectively represent the number of layers and precoding matrix recommended by the terminal device.

[0149] The CQI can indicate the quality of the current channel fed back by the terminal device to the network device. The terminal device needs to calculate the CQI.

[0150] Optionally, the channel information may include relevant information obtained by performing channel measurement based on a reference signal (such as CSI-RS, DMRS, SSB, etc.).

[0151] For example, the channel information includes at least one of the following: channel matrix H, equivalent channel matrix, precoding matrix W (precoding matrix W can be derived from channel matrix H), right singular vector V of channel matrix H, square matrix H T The eigenvector of H (i.e., the conjugate transpose of the channel matrix H T The eigenvector of the matrix obtained by multiplying the channel matrix H by the channel matrix H), at least one vector associated with the channel matrix H (such as at least one vector of the channel matrix H under a certain deformation, etc.), time domain information of the channel, channel information in the delay-Doppler domain, CRI, SSBRI, RI, PMI, CQI, LI, CSI, etc.

[0152] CSI reference resource

[0153] It should be noted that a CSI report corresponds to a CSI reference resource. For example, for periodic CSI reporting, CSI is reported periodically, and each CSI report corresponds to a CSI reference resource.

[0154] The time domain of the CSI reference resource may be a time slot, and the frequency domain of the CSI reference resource may be a frequency resource for obtaining CSI measurement.

[0155] Optionally, when the uplink time slot where the CSI report is located is time slot n' (n' represents the time slot index), the downlink time slot where the CSI reference resource is located is time slot K offset Indicates the parameters of high-level configuration, Indicates that in frequency range 1 and K offset =0, μ DL Indicates the downlink subcarrier spacing configuration.

[0156] Since the CSI reference resource is a downlink resource, the time domain of the CSI reference resource is the downlink time slot. In this way, time slot n represents the downlink time slot corresponding to time slot n′ and is calculated as follows:

[0157] Among them, μ UL Indicates the uplink subcarrier spacing configuration, Downlink timeslot offset, μ offset,DL Indicates the maximum value of the minimum value of the downlink subcarrier spacing configuration of the primary cell (Pcell) / primary secondary cell (PScell) and the minimum value of the downlink subcarrier spacing configuration of the secondary cell (Scell). Uplink timeslot offset, μ offset,UL Indicates the maximum value of the minimum value of the Pcell / PScell ​​uplink subcarrier spacing configuration and the minimum value of the Scell ​​uplink subcarrier spacing configuration.

[0158] n CSI_ref Indicates the time slot offset between time slot n and the valid downlink time slot in which the CSI reference resource is located. Whether a downlink time slot is a "valid downlink time slot" requires the following conditions to be met: the downlink time slot contains at least one downlink symbol or flexible symbol configured by higher-layer signaling; and / or the downlink time slot is not within a configured measurement gap.

[0159] Optionally, for periodic or semi-persistent CSI reporting, if the CSI report is associated with a channel measurement resource (such as a CSI-RS / SSB for channel measurement), then n CSI_ref is greater than or equal to The CSI reference resource corresponding to the CSI report is located at the minimum value of the valid downlink time slot.

[0160] For example, assuming that the uplink and downlink subcarrier spacing configurations are the same, that is, μ DL =μ UL = 0. From greater than or equal to Starting from the minimum value in CSI_ref for Calculated And determine whether time slot n-4 is a valid downlink time slot. If time slot n-4 is a valid downlink time slot, the CSI reference resource is located in time slot n-4; if time slot n-4 is not a valid downlink time slot, then set n CSI_ref for Calculated It then determines whether time slot n-5 is a valid downlink time slot. If so, the CSI reference resource is located in time slot n-5. If not, the search continues until a valid downlink time slot is found.

[0161] Optionally, for periodic or semi-continuous CSI reporting, if the CSI report is associated with multiple channel measurement resources (such as multiple CSI-RS / SSBs for channel measurement), then n CSI_ref is greater than or equal to The CSI reference resource corresponding to the CSI report is located at the minimum value of the valid downlink time slot.

[0162] Optionally, for aperiodic CSI reporting, if the DCI used to trigger the CSI report is in the same time slot as the CSI report, the CSI reference resource is located in the time slot where the DCI is located; otherwise, n CSI_ref is greater than or equal to The minimum value that makes the CSI reference resource corresponding to the CSI report located in the valid downlink time slot, It represents the number of symbols contained in a time slot, and Z′ represents the processing time of CSI calculation.

[0163] Optionally, the CSI reference resource may have the following two functions.

[0164] Function 1: Used to calculate channel quality indicator (CQI)

[0165] Channel measurement is inherently dependent on the implementation of the terminal device. For example, some terminal devices are very capable and can achieve the target block error rate (BLER) requirement using a certain modulation and coding scheme (MCS) at an SINR of 10dB. However, some terminal devices are less capable and require an SINR of 12dB to achieve the target BLER (the target BLER is configured by the network equipment). Therefore, if two terminal devices both measure an SINR of 10dB, the CQI values ​​they report back may be different.

[0166] Furthermore, even for the same terminal device, different packet sizes (TBS) can result in different BLERs. For example, if SINR = 10dB, and the current TBS is 1000 bits, using a specific MCS, the BLER is 0.01. However, if the TBS is 500 bits and the same MCS is used, the corresponding BLER might be 0.1. These two differences are significant.

[0167] Therefore, when quantizing CQI, a concept such as CSI reference resource is needed so that the terminal device can obtain CQI / CSI through the CSI reference resource.

[0168] Assume that a terminal device uses CSI-RS for channel measurement to obtain channel conditions, such as SINR. The terminal device then assumes that a downlink data packet is transmitted on the CSI reference resource, and the corresponding channel conditions are those measured by the CSI-RS. At this point, the terminal device selects a CQI from the CQI table that ensures that the BLER of the hypothetical downlink data packet transmitted under the measured channel conditions is less than the target BLER.

[0169] Function 2: Used to determine the measurement resources associated with CSI reports

[0170] The network device may configure one or more measurement resources for CSI measurement on the terminal device. The time domain location of the measurement resources associated with the CSI report may be located before the CSI reference resources corresponding to the CSI report. In other words, the measurement resources located before the CSI reference resources corresponding to the CSI report may be used as the measurement resources associated with the CSI report. The specific measurement resources that can be used as the measurement resources associated with the CSI report may be configured through higher-layer signaling, protocol provisions, pre-configuration, or determined autonomously by the terminal device.

[0171] For example, taking periodic measurement resources as an example, as shown in Figure 2, the periodic measurement resources include measurement resources associated with the CSI report, and the time domain location of the measurement resources associated with the CSI report is located before the CSI reference resource corresponding to the CSI report. In other words, only the measurement resources before the CSI reference resource corresponding to the CSI report can be used as the measurement resources associated with the CSI report. As for which resource measurements can be used as the measurement resources associated with the CSI report, the network can further configure them through higher-layer signaling. For example, the network can configure the resource measurement 210 closest to / adjacent to the CSI reference resource as the measurement resource associated with the CSI report.

[0172] It should be noted that this embodiment does not impose any specific restrictions on the content of the "CSI reference resource", and this part of the content does not exclude new content included in the further evolution of the standard protocol.

[0173] 2. Enhanced CSI-related processing

[0174]

describe

[0175] AI can include ML, DL, etc., and AI models can have certain model parameters and model architectures, etc., and AI models can include various linear and nonlinear network models, such as linear regression, vector machines, CNN, DNN, etc.

[0176] It should be noted that the "AI model" appearing in this embodiment can be understood as an ML model, DL model, intelligent model, AI algorithm, AI module, or intelligent module, etc., without specific limitation.

[0177] When AI technology is applied to the CSI framework, AI models can be used for CSI compression and CSI resume / recovery to achieve intelligent communication and reduce air interface overhead.

[0178] Of course, in addition to CSI compression and CSI recovery, other processing in the communication process may also be included, such as encoding / decoding, quantization / dequantization, etc., and there is no specific limitation on this.

[0179] Enhancements to CSI Compression and CSI Recovery

[0180] During the CSI measurement / CSI reporting process, the terminal device can perform channel measurement / interference measurement based on the measurement resources to obtain channel information / CSI information. However, the channel information / CSI information may have characteristics such as a large number of bits, and directly feeding back the channel information / CSI information through the CSI report will lead to problems such as more occupied resources and high signaling overhead. Therefore, in order to reduce occupied resources and signaling overhead, etc., this embodiment can perform CSI compression on the channel information / CSI information so that the compressed information has characteristics such as a smaller number of bits. Corresponding to CSI compression is CSI recovery, so that the compressed information can be restored to the original channel information / CSI information through CSI recovery.

[0181] During traditional CSI compression and recovery, a terminal device may input channel information / CSI information into its own AI model (of course, this AI model can be considered an "encoder" or "CSI compression model") for compression and other processing to obtain processed information, which is then sent to a network device. In this embodiment, the information input into the terminal device's AI model may be referred to as "input information."

[0182] In addition, the "processed information" in this embodiment may be information obtained by inputting the input information into the AI ​​model, or information obtained by further processing the information obtained by inputting the input information into the AI ​​model. The information obtained by inputting the input information into the AI ​​model may include CSI compression information; and the "further processing" herein may include at least one of encoding, quantization, dequantization, or decoding.

[0183] Correspondingly, the network device receives the processed information and inputs it into its own AI model (of course, this AI model can be called a "decoder" or CSI recovery model, etc.) for decoding to recover the channel information / CSI information as much as possible. In this embodiment, the information output by the AI ​​model of the network device can be referred to as "output information."

[0184] In this way, the CSI compression and CSI recovery processes are implemented through the AI ​​model of the terminal device and the AI ​​model of the network device.

[0185] It should be noted that since CSI compression and CSI recovery are two coexisting processes, the AI ​​model of the terminal device and the AI ​​model of the network device need to appear in pairs. Thus, the AI ​​model of the terminal device and the AI ​​model of the network device can be referred to as an "AI model pair" or a "two-sided AI model." For ease of description, in this embodiment, the AI ​​model used for CSI compression in the two-sided AI model may be referred to as the "first AI model," and the AI ​​model used for CSI recovery in the two-sided AI model may be referred to as the "second AI model."

[0186] For example, a bilateral AI model including an encoder and a decoder is used as an example, as shown in FIG3. In FIG3, for the terminal device side, the input information V is compressed by the encoder 311 to obtain the processed information V E , then process the information V E After being quantized by the quantizer 312, the quantized processing information V is obtained. Q For the network equipment side, the quantized processing information V Q First, it is dequantized by the dequantizer 321, and then the CSI is recovered by the decoder 322 to obtain the output information.

[0187] Different from the traditional CSI compression and CSI recovery process, in order to improve the accuracy of CSI compression and CSI recovery and save air interface overhead, this embodiment needs to consider enhancing CSI compression and CSI recovery.

[0188] Regarding the enhancement of CSI compression, this embodiment considers that the AI ​​model of the terminal device can use first historical information to participate in the CSI compression of the current input information. The first historical information may include at least one of historical input information, historical processing information, or historical compression intermediate information.

[0189] Historical input information can be defined according to the order in which the input information is arranged, or according to the order in which the first AI model processes the input information, or according to the time in which the input information is generated, or according to the order in which the input information is input into the first AI model, and so on.

[0190] For the definition based on the order of input information, the input information that is arranged before the current input information may be referred to as “historical input information”.

[0191] Regarding the definition of the order in which the input information is processed by the first AI model, when the first AI model is processing the current input information, the input information processed before the current input information can be called "historical input information".

[0192] Regarding the definition based on the time sequence of input information generation, the input information generated before the current input information can be referred to as “historical input information”.

[0193] Regarding the definition based on the order in which input information is input into the first AI model, the input information input into the first AI model before the current input information may be referred to as “historical input information”.

[0194] Historical processing information can be the information that appears in the process from the bilateral AI model inputting historical input information to outputting historical output information, or the information obtained by inputting historical input information into the first AI model, or the information obtained by further processing the information obtained by inputting historical input information into the first AI model.

[0195] The historical compression intermediate information may be information generated by the bilateral AI model / the first AI model in the process of compressing historical input information.

[0196] It can be understood that when CSI compression introduces the first historical information, since the first historical information and the current input information can reflect the time domain changes or time domain correlations of the channel, the first AI model can consider the time domain changes or time domain correlations of the channel when performing CSI compression on the current input information, which is conducive to improving the accuracy of CSI compression, enhancing the performance of CSI compression, and achieving enhanced CSI compression.

[0197] To enhance CSI recovery, this embodiment considers that the AI ​​model of the network device can use second historical information to participate in CSI recovery of the current output information. The second historical information may include at least one of historical output information, historical processing information, or historical recovery intermediate information.

[0198] Historical output information can be defined based on the order in which the output information is arranged, or based on the order in which the second AI model outputs the output information, or based on the time in which the output information is generated, or based on the output information corresponding to the historical input information. It should be noted that the various definitions of historical output information can be understood by referring to the description of historical input information above, and will not be repeated here.

[0199] The historical recovery intermediate information may be information generated by the second AI model in the process of restoring the historical output information.

[0200] It can be understood that when CSI recovery introduces the second historical information, since the second historical information and the current output information can reflect the time domain changes or time domain correlations of the channel, the second AI model can consider the time domain changes or time domain correlations of the channel when performing CSI recovery on the currently processed information, which is conducive to improving the accuracy of CSI recovery, enhancing the performance of CSI recovery, and achieving enhanced CSI recovery.

[0201] In the enhancements to CSI compression and CSI recovery, the AI ​​model of the terminal device and the AI ​​model of the network device may be referred to as an "enhanced AI model pair" or an "enhanced bilateral AI model." For ease of description, in this embodiment, the AI ​​model used for CSI compression in the enhanced bilateral AI model may also be referred to as the "first AI model," and the AI ​​model used for CSI recovery in the enhanced bilateral AI model may also be referred to as the "second AI model."

[0202] For example, the enhanced bilateral AI model includes an encoder, a quantizer, a dequantizer, and a decoder, as shown in Figure 4. In Figure 4, for the terminal device side, when the input information V1 is input to the encoder 411, the encoder 411 performs CSI compression on the input information V1 to obtain the processed information V E1 , the quantizer 412 processes the information V E1 Quantize to obtain quantized processing information V Q1 In addition, the input information V1 can be stored as historical input information, and the processing information V E1 and / or quantized processing information V Q1 It can be stored as historical processing information, and the information generated during the compression of the input information V1 can be stored as historical compression intermediate information. Q1 First, it is dequantized by the dequantizer 421, and then the CSI is recovered by the decoder 422 to obtain the output information. In addition, the output information Can be stored as historical output information and restored when output information is restored The information generated during the process can be stored as history to restore intermediate information.

[0203] In FIG4 , for the terminal device side, when the input information V2 is input to the encoder 411, the encoder 411 can use the first historical information to perform CSI compression on the input information V2 to obtain the processed information V E2 , the quantizer 412 processes the information V E2 Quantize to obtain quantized processing information V Q2 In addition, the input information V2 can be stored as historical input information, and the processing information V E2 and / or quantized processing information V Q2 It can be stored as historical processing information, and the information generated during the compression of the input information V2 can be stored as historical compression intermediate information. Q2 First, it is dequantized by the dequantizer 421, and then the CSI is recovered by the decoder 422 to obtain the output information. In addition, the output information Can be stored as historical output information and restored when output information is restored The information generated during the process can be stored as history to restore intermediate information.

[0204] In FIG4 , for the terminal device side, when the input information V i (i=2,3,...) is input to the encoder 411, the encoder 411 can use the first historical information to i Perform CSI compression to obtain processing information V Ei , the quantizer 412 processes the information V Ei Quantize to obtain quantized processing information V Qi In addition, input information V i Can be stored as historical input information, processing information V Ei and / or quantized processing information V Qi Can be stored as historical processing information, and compressed input information V i The information generated during the process can be stored as historical compressed intermediate information. For the network device side, the quantized processing information V Qi First, it is dequantized by the dequantizer 421, and then the CSI is recovered by the decoder 422 to obtain the output information. In addition, the output information Can be stored as historical output information and restored when output information is restored The information generated during the process can be stored as history to restore intermediate information.

[0205] It should be noted that, in the temporal, spatial, and frequency domains, the traditional bilateral AI model can be used for CSI compression and CSI recovery in the space-frequency (SF) domain, and the AI ​​model in the traditional bilateral AI model can be referred to as the "space-frequency (SF) domain AI model." The enhanced bilateral AI model can be used for CSI compression and CSI recovery in the space-time-frequency (TSF) domain, and the AI ​​model in the enhanced bilateral AI model can be referred to as the "space-time-frequency (TSF) domain AI model." Of course, the traditional bilateral AI model and the enhanced bilateral AI model can also be described using other terms, without specific limitation.

[0206]

Input information

[0207] The input information of the enhanced bilateral first AI model may refer to information input into the enhanced bilateral first AI model.

[0208] For the input information of the enhanced bilateral AI model, the input information involves concepts such as "historical input information", "first input information", "non-first input information", and "current input information".

[0209] Historical input information can be defined by the order in which the input information is arranged, or by the order in which the first AI model processes the input information, or by the time in which the input information is generated, or by the order in which the input information is input into the first AI model, etc. For example, in FIG4 , when input information V2 is currently input into encoder 411, since information V1 has already been input into encoder 411 before input information V2, input information V1 can be considered historical input information.

[0210] The first input information may refer to the information initially / first input to the first AI model for CSI compression within a certain time range. Because it is the initial / first input information, the first historical information has not yet been stored, so CSI compression can only be performed directly on the first input information. For example, the input information V1 in Figure 4 can be considered the first input information.

[0211] Non-first input information may refer to information that is not the initial or first input to the first AI model for CSI compression within a certain time range, or information that is input to the first AI model for CSI compression after the first input information. In this case, since the first historical information has been stored, the first AI model can use the first historical information to perform CSI compression on the non-first input information. For example, the input information V2 and the input information V in FIG4 are i It can be considered as non-first input information. At the same time, when performing CSI processing on non-first input information, the first input information can be considered as historical input information, and the processing information corresponding to the first input information can be considered as historical processing information. In addition, the previous non-first input information can be considered as historical input information for the next non-first input information, and the processing information corresponding to the previous non-first input information can be considered as historical processing information for the next non-first input information.

[0212] The current input information may refer to the input information at the current moment / specific moment, or may refer to the input information input to the first AI model at the current moment / specific moment, etc.

[0213] In summary, the first AI model can be used to perform CSI compression on the first input information, and use the first historical information to perform CSI compression on non-first input information.

[0214] Output information

[0215] The output information of the enhanced bilateral AI model may be the information output by the second AI model, and the output information corresponds one-to-one to the input information.

[0216] Regarding the output information of the enhanced bilateral AI model, the output information involves concepts such as "historical output information", "first output information", and "non-first output information".

[0217] The historical output information can be defined according to the order in which the output information is arranged, or according to the order in which the second AI model outputs the output information, or according to the time in which the output information is generated, or according to the output information corresponding to the historical input information. For example, in FIG4 , when the input information V2 is input to the encoder 411 at the current moment, since the information V1 has been input to the encoder 411 before the input information V2, the input information V1 can be regarded as the historical input information, and the output information It can be regarded as historical output information.

[0218] The first output information may refer to the information initially / first output by the second AI model within a certain time range. Since it is the initial / first output information, the second historical information has not yet been stored. For example, the output information in FIG4 It can be regarded as the first output information.

[0219] Non-first output information can refer to information that is not the initial / first output of the second AI model within a certain time range, or information that is output by the second AI model after the first output information, or information that is output corresponding to non-first input information. In this case, since the second historical information has been stored, the second AI model can use the second historical information to participate in CSI recovery of non-first output information. For example, the output information in Figure 4 and output information It can be regarded as non-first output information. At the same time, for the CSI recovery process of non-first output information, the first output information can be regarded as historical output information. In addition, the previous non-first output information can be regarded as historical output information of the next non-first output information.

[0220] In summary, the second AI model can be used for CSI recovery of the first output information, and can participate in CSI recovery of non-first output information using the second historical information.

[0221]

Differentiation of input information

[0222] As can be seen from the above "CSI-related configurations," CSI resource configuration is used to configure measurement resources, while CSI report configuration is used to configure CSI reporting. Furthermore, CSI reporting is associated with certain measurement resources. Therefore, in enhanced CSI measurement and CSI reporting, a terminal device can perform channel measurement / interference measurement based on the measurement resources associated with the CSI report to obtain channel information / CSI information. This channel information / CSI information is then input into the enhanced bilateral AI model for CSI compression. The information input into the terminal device's AI model is referred to as "input information."

[0223] The CSI report and the measurement resources associated with the CSI report are two different concepts. In this embodiment, either the CSI report or the measurement resources can be used to define the input information. The specific method used can be determined by network configuration, terminal device autonomy, or protocol regulations, and is not specifically limited. When the CSI report is used to define the input information, the input information in this embodiment can be the channel information / CSI information corresponding to the CSI report. When the measurement resources are used to define the input information, the input information in this embodiment can be the channel information / CSI information corresponding to the measurement resources.

[0224] Regarding the input information corresponding to the CSI report, when the network is configured with multiple CSI reports, this embodiment can distinguish different input information based on the differences between these CSI reports. For example, when a network device triggers multiple aperiodic CSI reports via a single DCI, the terminal device can perform CSI measurements based on the measurement resources associated with these aperiodic CSI reports to obtain the input information corresponding to each of these aperiodic CSI reports.

[0225] Optionally, for distinguishing different input information based on different CSI reports, this embodiment can distinguish different input information based on the time domain position of the CSI report (such as the uplink time slot where the CSI report is located), or distinguish different input information based on the ID / index of the CSI report.

[0226] Optionally, since the CSI report includes a periodic CSI report, an aperiodic CSI report, and a semi-persistent CSI report, the input information corresponding to the CSI report may include at least one item of the input information corresponding to the periodic CSI report, the input information corresponding to the aperiodic CSI report, or the input information corresponding to the semi-persistent CSI report, and may be specifically determined based on the time domain behavior of the CSI report configured / indicated by the network.

[0227] For example, the terminal device may perform CSI measurement according to the measurement resources associated with the periodic CSI report to obtain input information corresponding to the periodic CSI report, so as to group the input information corresponding to the periodic CSI reports.

[0228] Regarding the input information corresponding to the measurement resources, when the network configures multiple measurement resources and the multiple measurement resources are associated with at least one CSI report, this embodiment can distinguish different input information according to different measurement resources.

[0229] Optionally, for distinguishing different input information based on different measurement resources, this embodiment can distinguish different input information based on different time domain positions of the measurement resources, or distinguish different input information based on different IDs / indexes of the measurement resources.

[0230] Optionally, since the measurement resources include periodic measurement resources, non-periodic measurement resources, and semi-persistent measurement resources, the input information corresponding to the measurement resources may include at least one item of input information corresponding to the periodic measurement resources, input information corresponding to the non-periodic measurement resources, or input information corresponding to the semi-persistent measurement resources, and may be specifically determined based on the time domain behavior of the measurement resources configured / indicated by the network.

[0231] [Input order of input information and output order of output information]

[0232] It should be noted that during the enhanced CSI compression and CSI recovery process, the enhanced bilateral AI model performs CSI compression on the input information in sequence. In addition, since the input information and output information are one-to-one corresponding, the input order of the input information corresponds one-to-one to the output order of the output information.

[0233] Optionally, the input information corresponding to the CSI reports can be input into the enhanced bilateral AI model in the order of the time domain positions of the CSI reports (e.g., the uplink timeslot in which the CSI reports are located). That is, the input information corresponding to the CSI reports with earlier time domain positions will be input into the enhanced bilateral AI model earlier / earlier for CSI compression and CSI recovery, while the input information corresponding to the CSI reports with later / latter time domain positions will be input into the enhanced bilateral AI model later / latter for CSI compression and CSI recovery.

[0234] In this way, the input information corresponding to the first CSI report may refer to the input information corresponding to the CSI report at the front in the time domain, the input information corresponding to the second CSI report may refer to the input information after the input information corresponding to the first CSI report, and so on.

[0235] Optionally, the input information corresponding to the CSI reports can be input into the enhanced bilateral AI model in the order of the size of the CSI report IDs / indexes. For example, the input information corresponding to CSI reports with smaller IDs / indexes will be input into the enhanced bilateral AI model first / early for CSI compression and CSI recovery, while the input information corresponding to CSI reports with larger IDs / indexes will be input into the enhanced bilateral AI model later / latter for CSI compression and CSI recovery.

[0236] In this way, the input information corresponding to the first CSI report may refer to the input information corresponding to the CSI report with a smaller ID / index, the input information corresponding to the second CSI report may refer to the input information after the input information corresponding to the first CSI report, and so on.

[0237] Optionally, the input information corresponding to the measurement resources can be input into the enhanced bilateral AI model in the order of the time domain positions of the measurement resources. That is, the input information corresponding to the measurement resources with an earlier / closer time domain position will be input into the enhanced bilateral AI model earlier / earlier for CSI compression and CSI recovery, while the input information corresponding to the measurement resources with a later / closer time domain position will be input into the enhanced bilateral AI model later / latter for CSI compression and CSI recovery.

[0238] In this way, the input information corresponding to the first measurement resource may refer to the input information corresponding to the measurement resource at the front in the time domain, the input information corresponding to the second measurement resource may refer to the input information after the input information corresponding to the first measurement resource, and so on.

[0239] Optionally, the input information corresponding to the measurement resources may be input into the enhanced bilateral AI model in the order of the measurement resource IDs / indexes. For example, the input information corresponding to measurement resources with smaller IDs / indexes may be input into the enhanced bilateral AI model earlier / earlier for CSI compression and CSI recovery, while the input information corresponding to measurement resources with larger IDs / indexes may be input into the enhanced bilateral AI model later / latter for CSI compression and CSI recovery.

[0240] In this way, the input information corresponding to the first measurement resource may refer to the input information corresponding to the measurement resource with a smaller ID / index, the input information corresponding to the second measurement resource may refer to the input information subsequent to the input information corresponding to the first measurement resource, and so on.

[0241] In combination with the above content, the following embodiment specifically describes the enhancement of CSI-related processing through the following solutions. These solutions can be related to each other or independent of each other, and the same content between different solutions can be referenced by each other, which will not be described in detail.

[0242] [Scheme 1]

[0243] During the enhanced CSI compression and CSI recovery process, since the bilateral AI model performs CSI compression and recovery on the input information in sequence, and historical input information can participate in the CSI compression of the current input information, the first-obtained processed information can be used as historical processing information to participate in the CSI compression of the current input information, and / or the first-obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information.

[0244] Based on this, in "Solution 1", this embodiment considers grouping the input information. The purpose of grouping is to ensure that historical input information within a group can participate in CSI compression of non-first input information within the same group, and that all input information in a group does not participate in CSI compression of any input information in other groups.

[0245] For example, taking the input information as being divided into two groups, the first input information in the first group is directly subjected to CSI compression, and the historical input information in the first group will only participate in the CSI compression of non-first input information in the group, and will not participate in the CSI compression of any input information in the second group; the first input information in the second group is directly subjected to CSI compression, and the historical input information in the second group will only participate in the CSI compression of non-first input information in the group.

[0246] In this way, the enhanced bilateral AI model can be used to perform CSI compression on the first input information in a group, and to perform CSI compression on non-first input information in the group using historical input information in the group.

[0247] For example, when the input information in FIG4 is grouped, if the input information V1 to the input information V i-1 Divided into the same group, and input information V i-1 The subsequent input information is divided into another group, and the encoder 511, quantizer 512, dequantizer 521 and decoder 522 in the enhanced bilateral AI model process the information in sequence as shown in Figure 5.

[0248] Optionally, the group may have a group length, wherein the group length may be the maximum number of input information in the group.

[0249] Optionally, the packet length may be finite or infinite, and may be specifically specified by the network configuration or protocol.

[0250] It should be noted that when the packet length is finite, this embodiment can determine one or more packets based on the packet length, meaning that all input information can be contained in one or more packets. When the packet length is infinite, it is generally assumed that there can only be one packet, meaning that all input information is contained in one packet. Furthermore, when the packet length is finite, this indicates that there is a definite maximum number of input information. When the packet length is finite, it is generally assumed that the maximum number of input information is infinite.

[0251] Optionally, the packet lengths of different packets may be different or the same.

[0252] It should be noted that a packet may have an identifier (ID) or index so that different packets can be distinguished by the identifier / index. In addition, the packet lengths of different packets can be different or the same. When the network configures the packet length, the network can flexibly configure different packet lengths for different packets to increase the flexibility of packet length configuration; alternatively, the network can configure the same packet length for different packets in a single configuration to save the signaling overhead required for configuration.

[0253] In combination with the content in the above “differentiation of input information”, this embodiment may group the input information corresponding to the CSI report or group the input information corresponding to the measurement resources.

[0254] The input information corresponding to the CSI report may be only the input information corresponding to the periodic CSI report, or only the input information corresponding to the aperiodic CSI report, or only the input information corresponding to the semi-persistent CSI report, or a combination of the input information corresponding to the periodic CSI report, the input information corresponding to the aperiodic CSI report, and / or the input information corresponding to the semi-persistent CSI report, etc., and may be specifically determined according to the time domain behavior of the CSI report configured / indicated by the network.

[0255] The input information corresponding to the measurement resources may be only the input information corresponding to the periodic measurement resources, or only the input information corresponding to the aperiodic measurement resources, or only the input information corresponding to the semi-persistent measurement resources, or a combination of the input information corresponding to the periodic measurement resources, the input information corresponding to the aperiodic measurement resources, and / or the input information corresponding to the semi-persistent measurement resources, etc., and may be specifically determined according to the time domain behavior of the measurement resources configured / indicated by the network.

[0256] For example, taking CSI reporting as an example to define input information, the terminal device performs CSI measurement according to the measurement resources associated with the periodic CSI reporting to obtain input information corresponding to the periodic CSI reporting, so as to group the input information corresponding to these periodic CSI reports.

[0257] For another example, taking CSI reporting as an example to define input information, the terminal device performs CSI measurement based on the measurement resources associated with the semi-persistent CSI reporting to obtain input information corresponding to the semi-persistent CSI reporting, so as to group the input information corresponding to these semi-persistent CSI reports.

[0258] For another example, taking CSI reports as an example to define input information, the terminal device performs CSI measurement based on the measurement resources associated with multiple non-periodic CSI reports triggered by a DCI to obtain the input information corresponding to each non-periodic CSI report, so as to group the input information corresponding to these non-periodic CSI reports.

[0259] For another example, using CSI reporting as an example to define input information, a terminal device performs CSI measurements based on the measurement resources associated with periodic CSI reporting, semi-persistent CSI reporting, and aperiodic CSI reporting, respectively, to obtain the corresponding input information. In this case, this embodiment can group the input information corresponding to periodic CSI reporting, semi-persistent CSI reporting, and aperiodic CSI reporting together, or group them separately. The specific method can be determined by network configuration, terminal device autonomy, or protocol provisions, and is not specifically limited to this.

[0260] In addition, after the input information is grouped, since CSI compression and CSI recovery coexist, and the input information in a group needs to be CSI compressed in sequence, and the processing information needs to be used for CSI recovery in sequence, after CSI compression is performed on a certain input information in a group to obtain the processing information, the terminal device may need to report the position of the input information in the group or the position of the processing information in the group to the network device.

[0261] In this way, when the network device knows the position of the input information in the packet or the position of the processed information in the packet, the network device can determine the order of the processed information in CSI recovery based on the position of the input information or the position of the processed information in the packet.

[0262] It is worth noting that this embodiment mainly describes the grouping of input information. However, since there is a one-to-one correspondence between input information, processed information, and output information, the grouping of input information can also be the grouping of processed information or the grouping of output information, and the content of the grouping of input information can be adapted to the grouping of processed information or the grouping of output information. This will not be further described.

[0263] The following embodiment specifically describes how to determine the grouping of input information through the following methods. These methods may be related to each other or independent of each other, and the same contents between different methods may be referenced to each other, which will not be described in detail.

[0264] Method 1

[0265] In "method 1", this embodiment may introduce a time window.

[0266] Among them, if the time domain position of at least one CSI report is within the time window, the input information corresponding to the at least one CSI report belongs to the same group; or, if the time domain position of at least one measurement resource or the time domain position of the CSI report associated with the at least one measurement resource is within the time window, the input information corresponding to the at least one measurement resource belongs to the same group.

[0267] In this way, the input information is grouped by time windows.

[0268] Of course, the time window can be described using other terms, such as a window, a time period, or a duration, and there is no specific limitation on this. Optionally, the length of the time window is configured by the network. For example, the network device can configure the length of the time window to the terminal device through higher-layer signaling (such as RRC signaling, MAC signaling) or DCI.

[0269] Optionally, for periodic CSI reporting or semi-persistent CSI reporting, the length of the time window may be an integer multiple of the CSI reporting period. In this way, the time domain locations of multiple periodic CSI reports or multiple semi-persistent CSI reports may be within one time window.

[0270] Optionally, for periodic CSI reporting or CSI reporting carried on PUCCH, the starting position of the time window satisfies the following:

[0271] Wherein, μ represents the subcarrier spacing configuration of the uplink bandwidth part (UL BWP) for transmitting the CSI report; Indicates the number of time slots in a frame under the subcarrier spacing configuration μ; n f Indicates the system frame number where the CSI report is located; Indicates the time slot number where the CSI report is located; T offset Indicates the time slot offset; N indicates the maximum number of input information in a group; T CSI Indicates the CSI reporting period.

[0272] Optionally, for CSI reports carried on the PUSCH, the starting position of the time window satisfies the following:

[0273] in, Indicates the system frame number of the PUSCH where the first CSI report is sent after DCI activation; Indicates the timeslot number of the PUSCH where the first CSI report is sent after DCI activation.

[0274] Optionally, the starting position of the time window is configured by the network. For example, the network device may configure an offset to the terminal device via high-layer signaling (such as RRC signaling, MAC signaling) or DCI, and the offset may determine the starting position of the time window.

[0275] Optionally, the time window is periodic, and the period of the time window is configured by the network. For example, the network device may configure the period of the time window to the terminal device via high-layer signaling (such as RRC signaling, MAC signaling) or DCI.

[0276] The following uses the interaction between a network device and a terminal device as an example to illustrate "Method 1". As shown in Figure 6, Figure 6 is a flow chart of a communication method according to an embodiment of the present application. The method includes the following steps:

[0277] S610. The network device sends configuration information, where the configuration information is used to configure a time window, and the time window is used to determine the grouping of first input information of a first AI model.

[0278] Correspondingly, the terminal device receives the configuration information.

[0279] It can be seen that this embodiment implements the network configuration time window through configuration information.

[0280] It should be noted that, with respect to the first input information, this embodiment also involves first processed information and first output information. The first processed information is information obtained by inputting the first input information into the first AI model, or information further processed from information obtained by inputting the first input information into the first AI model; the first output information is information obtained by inputting the first processed information into the first AI model, or information further processed from information obtained by inputting the first processed information into the first AI model.

[0281] It's worth noting that "Method 1" primarily describes the grouping of the first input information. However, since there's a one-to-one correspondence between the first input information, the first processed information, and the first output information, the grouping of the first input information can also be considered the grouping of the first processed information or the first output information. Furthermore, the content of the grouping of the first input information can be adapted to the grouping of the first processed information or the first output information, and this will not be further elaborated.

[0282] Optionally, the “first AI model” here refers to the AI ​​model used for CSI compression in the enhanced bilateral AI model.

[0283] Optionally, the configuration information includes at least one of length information, start information, or period information;

[0284] Length information, used to configure the length of the time window and / or to configure the packet length of the input information;

[0285] Start information, used to configure the start position of the time window;

[0286] Period information, used to configure the period of the time window.

[0287] Optionally, the length of the time window is an integer multiple of the CSI reporting period.

[0288] Optionally, the starting position of the time window satisfies the following conditions:

[0289] or,

[0290]

[0291] Optionally, the configuration information is carried by functionality registration (functionality identification) information or model registration (model identification) information.

[0292] Optionally, the configuration information is carried by higher-layer signaling (such as RRC signaling or MAC signaling) or DCI.

[0293] Optionally, the first input information is in input information corresponding to at least one CSI report, and a time domain behavior of the at least one CSI report is at least one of periodic, semi-continuous, or non-periodic.

[0294] It is understood that the input information corresponding to the at least one CSI report includes at least one of input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report. Furthermore, the first input information may be input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report.

[0295] Optionally, the first input information may be the first input information and / or non-first input information among the input information corresponding to the at least one CSI report.

[0296] Optionally, the input information corresponding to the at least one CSI report is input into the first AI model in the order of the time domain positions of the CSI reports or the order of the size of the IDs / indexes of the CSI reports.

[0297] Optionally, the at least one CSI report includes all non-periodic CSI reports triggered by one DCI.

[0298] It can be understood that the input information corresponding to the at least one CSI report includes input information corresponding to all non-periodic CSI reports triggered by one DCI.

[0299] Optionally, the first input information is in input information corresponding to at least one measurement resource, and a time domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

[0300] It is understood that the input information corresponding to the at least one measurement resource includes at least one of input information corresponding to a periodic measurement resource, input information corresponding to a semi-persistent measurement resource, or input information corresponding to an aperiodic CSI report. Furthermore, the first input information may be input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report.

[0301] Optionally, the first input information may be the first input information and / or non-first input information among the input information corresponding to the at least one measurement resource.

[0302] Optionally, the input information corresponding to the at least one measurement resource is input into the first AI model in the order of the time domain positions of the measurement resources or the order of the size of the ID / index of the measurement resources.

[0303] S620. The terminal device determines the grouping of the first input information according to the time window.

[0304] Optionally, if the first input information is in the input information corresponding to at least one CSI report, and the time domain position of the at least one CSI report is within the time window, then the input information corresponding to the at least one CSI report belongs to the same group.

[0305] In this way, for the group to which the input information corresponding to the at least one CSI report belongs, when the first input information is the first input information in the group, the first AI model can directly perform CSI compression on the first input information; when the first input information is not the first input information in the group, the first AI model can use the historical input information in the group to perform CSI compression on the first input information.

[0306] Optionally, if the first input information is in the input information corresponding to at least one measurement resource, and the time domain position of the at least one measurement resource is within the time window or the time domain position of the CSI report associated with at least one measurement resource is within the time window, then the input information corresponding to the at least one measurement resource belongs to the same group.

[0307] In this way, for the group to which the input information corresponding to the at least one measurement resource belongs, when the first input information is the first input information in the group, the first AI model can directly perform CSI compression on the first input information; when the first input information is not the first input information in the group, the first AI model can use the historical input information in the group to perform CSI compression on the first input information.

[0308] Optionally, after S620, the method may further include:

[0309] The terminal device sends first position information, where the first position information is used to indicate a position of the first input information in the group or a position of the first processed information in the group.

[0310] Correspondingly, the network device receives the first location information.

[0311] It can be seen that since CSI compression and CSI recovery coexist, and the input information in a group needs to be CSI compressed in sequence to obtain processing information, and this processing information needs to be CSI recovered in sequence, after CSI compression is performed on the first input information to obtain the first processing information, the terminal device reports the position of the first input information in the group or the position of the first processing information in the group to the network device through the first position information. In this way, the network device can know the order of the CSI recovery process of the first processing information based on the position of the first input information in the group or the position of the first processing information in the group, so as to perform CSI recovery on the first processing information in sequence.

[0312] Optionally, the first location information is carried by one of a CSI report, a higher layer signaling (such as an RRC signaling or a MAC signaling), or a UCI.

[0313] Method 2

[0314] In "Method 2", this embodiment can configure / indicate the grouping of input information through high-layer signaling (such as RRC signaling or MAC signaling) or DCI.

[0315] For example, the network device may configure / indicate the group ID associated with the CSI report through higher-layer signaling (such as RRC signaling or MAC signaling) or DCI, etc. In this way, the input information corresponding to the CSI report will be associated with the group ID, and the input information corresponding to the CSI reports associated with the same group ID will be divided into one group.

[0316] For another example, the network device may configure / indicate the group ID associated with the measurement resource through higher layer signaling (such as RRC signaling or MAC signaling) or DCI. In this way, the input information corresponding to the measurement resource will be associated with the group ID, and the input information corresponding to the measurement resources associated with the same group ID will be divided into one group.

[0317] The following uses the interaction between a network device and a terminal device as an example to illustrate "Method 2". As shown in Figure 7, Figure 7 is a flow chart of another communication method according to an embodiment of the present application. The method includes the following steps:

[0318] S710. The network device sends indication information, where the indication information is used to indicate grouping of first input information of a first AI model.

[0319] Correspondingly, the terminal device receives the indication information.

[0320] S720. The terminal device determines the grouping of the first input information according to the indication information.

[0321] It can be seen that this embodiment implements the grouping of network indication input information through indication information.

[0322] Optionally, the “first AI model” here refers to the AI ​​model used for CSI compression in the enhanced bilateral AI model.

[0323] Optionally, the indication information is carried by the function registration information or the model registration information.

[0324] Optionally, the indication information is carried by higher-layer signaling (such as RRC signaling or MAC signaling) or DCI.

[0325] Optionally, the first input information is in input information corresponding to at least one CSI report, and a time domain behavior of the at least one CSI report is at least one of periodic, semi-continuous, or non-periodic.

[0326] It is understood that the input information corresponding to the at least one CSI report includes at least one of input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report. Furthermore, the first input information may be input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report.

[0327] Optionally, the first input information may be the first input information or non-first input information among the input information corresponding to the at least one CSI report.

[0328] Optionally, the input information corresponding to the at least one CSI report is input into the first AI model in the order of the time domain positions of the CSI reports or in the order of the size of the IDs / indexes of the CSI reports.

[0329] Optionally, the at least one CSI report includes all non-periodic CSI reports triggered by a DCI.

[0330] It can be understood that the input information corresponding to the at least one CSI report includes input information corresponding to all non-periodic CSI reports triggered by one DCI.

[0331] Optionally, the first input information is in input information corresponding to at least one measurement resource, and a time domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

[0332] It is understood that the input information corresponding to the at least one measurement resource includes at least one of input information corresponding to a periodic measurement resource, input information corresponding to a semi-persistent measurement resource, or input information corresponding to an aperiodic CSI report. Furthermore, the first input information may be input information corresponding to a periodic CSI report, input information corresponding to a semi-persistent CSI report, or input information corresponding to an aperiodic CSI report.

[0333] Optionally, the first input information may be the first input information or non-first input information among the input information corresponding to the at least one measurement resource.

[0334] Optionally, the input information corresponding to the at least one measurement resource is input into the first AI model in the order of the time domain positions of the measurement resources or the order of the size of the ID / index of the measurement resources.

[0335] Optionally, after S720, the method may further include:

[0336] The terminal device sends first position information, where the first position information is used to indicate a position of the first input information in the group or a position of the first processed information in the group.

[0337] Correspondingly, the network device receives the first location information.

[0338] It can be seen that since CSI compression and CSI recovery coexist, and the input information in a group needs to be CSI compressed in sequence to obtain processing information, and this processing information needs to be CSI recovered in sequence, after CSI compression is performed on the first input information to obtain the first processing information, the terminal device reports the position of the first input information in the group or the position of the first processing information in the group to the network device through the first position information. In this way, the network device can know the order of the CSI recovery process of the first processing information based on the position of the first input information in the group or the position of the first processing information in the group, so as to perform CSI recovery on the first processing information in sequence.

[0339] [Scheme 2]

[0340] During the enhanced CSI compression and CSI recovery process, the terminal device may need to report / feedback input information and / or processed information. However, some input information and / or processed information that should be reported / feedback may not be reported due to various factors, resulting in the possibility of input information and / or processed information being dropped / omissioned.

[0341] For example, when uplink resources are limited, input information and / or processing information that originally needs to be reported may not be reported due to insufficient uplink resources.

[0342] Based on this, in "Scheme 2", this embodiment needs to determine how the input information and / or processing information that originally needed to be reported but was not reported should be reported in the CSI. The specific details can be determined by the network configuration, the terminal device itself, or the protocol regulations, etc., and there are no specific restrictions on this.

[0343] Optionally, the terminal device may continue to report / postpone reporting of input information and / or processed information that was originally required to be reported but was not reported. It is understood that when input information and / or processed information that was originally required to be reported is not reported at the current moment / current CSI reporting process, the terminal device may report the input information and / or processed information at a subsequent moment / subsequent CSI reporting process. For example, the input information and / or processed information may be carried in a subsequent CSI report.

[0344] Optionally, the terminal device may no longer report input information and / or processing information that was originally required to be reported but was not reported. It is understood that when input information and / or processing information that was originally required to be reported is not reported at the current moment / current CSI reporting process, the terminal device will no longer report the input information and / or processing information at a subsequent moment / subsequent CSI reporting process.

[0345] It should be noted that the input information discussed in "Scheme 2" can be grouped according to the above "Scheme 1" or not, and there is no specific limitation on this.

[0346] The following embodiment specifically describes how to determine the reporting of input information and / or processing information that was originally required to be reported but was not reported. These methods can be related to each other or independent of each other, and the same content between different methods can be referenced by each other, which is not described in detail.

[0347] Method 1

[0348] Since the traditional bilateral AI model / enhanced bilateral AI model needs to use input information and / or processed information to recover CSI, when faced with input information and / or processed information that should have been reported but was not reported, the network device cannot recover CSI because it fails to receive the input information and / or processed information. In addition, in the traditional bilateral AI model / enhanced bilateral AI model, CSI recovery needs to be performed sequentially between different information. For example, in Figure 4, the quantized processed information V Q1 It is necessary to input the dequantizer 421 and the decoder 422 in sequence to recover the CSI to obtain the output information Then comes the quantized processing information V Q2 The dequantizer 421 and the decoder 422 are input in sequence to perform CSI recovery to obtain output information

[0349] Based on this, in "Method 1", the terminal device can continue to report / postpone reporting of input information and / or processing information that originally needed to be reported but was not reported.

[0350] In this way, by continuing to report / postponing reporting, the input information and / or current processing information that was originally required to be reported but was not reported can continue to be reported, thereby avoiding the inability to recover CSI of this part of information and subsequent information due to the network device being unable to receive the input information and / or processing information.

[0351] Optionally, if the current CSI report containing the input information and / or processing information that was originally required to be reported fails to report, the terminal device may carry the input information and / or processing information in a subsequent CSI report, thereby continuing to report / postponing reporting of the input information and / or processing information that was originally required to be reported but was not reported through subsequent CSI reports.

[0352] Optionally, if the current CSI report containing the input information and / or processing information that was originally required to be reported fails to report, the terminal device may send the input information and / or processing information at an available time domain position after the time domain position of the current CSI report, thereby continuing to report / postponing reporting of the input information and / or processing information that was originally required to be reported but was not reported through subsequent available time domain positions.

[0353] For example, the terminal device may send the input information and / or the processing information in an available uplink time slot following the uplink time slot where the current CSI report is located.

[0354] The following uses the interaction between a network device and a terminal device as an example to illustrate "Method 1". As shown in Figure 8, Figure 8 is a flow chart of another communication method according to an embodiment of the present application. The method includes the following steps:

[0355] S810. If the first CSI report containing the first input information and / or the first processing information fails to be reported, the terminal device sends a second CSI report containing the first input information and / or the first processing information, or the terminal device sends the first input information and / or the first processing information at an available time domain position after the time domain position of the first CSI report.

[0356] The first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0357] Correspondingly, the network device receives the second CSI report, or receives the first input information and / or the first processing information at an available time domain position after the time domain position of the first CSI report.

[0358] It can be seen that when it was originally hoped to report the first input information and / or the first processing information through the first CSI report, the first CSI report failed to report, which resulted in the first input information and / or the first processing information that was originally required to be reported failing to be reported. Therefore, the terminal device can carry the first input information and / or the first processing information through the second CSI report, thereby realizing continued reporting of the first input information and / or the first processing information that was originally required to be reported but was not reported.

[0359] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the terminal device can send the first input information and / or first processing information at an available time domain position after the time domain position of the first CSI report, thereby continuing to report / postponing reporting of the first input information and / or first processing information.

[0360] Optionally, the time domain position of the second CSI report is later than the time domain position of the first CSI report. In this way, since the time domain position of the second CSI report is later than the time domain position of the first CSI report, the first input information and / or first processed information that originally needed to be reported but was not reported is deferred through the second CSI report.

[0361] Optionally, the second CSI report is the next CSI report adjacent to the first CSI report. In this way, the first input information and / or the first processed information can be deferred by using the next CSI report adjacent to the first CSI report. Furthermore, since the second CSI report is adjacent to the first CSI report, the reporting delay can be shortened.

[0362] Optionally, the method further includes:

[0363] The terminal device sends postponement information, where the postponement information is used to indicate that the first input information and / or the first processing information is a postponed reporting of the first CSI report.

[0364] Correspondingly, the network device receives the deferral information.

[0365] It can be seen that the postponement information is used to indicate to the network device which CSI reporting the first input information and / or the first processing information is postponed for, so as to know the original order of the postponed information in CSI recovery.

[0366] Optionally, the deferral information may be carried in a second CSI report. In this way, the terminal device can use the second CSI report to both defer reporting of the first input information and / or first processed information that was originally required to be reported but was not, and to indicate to the network device which reporting of the first input information and / or first processed information is deferred.

[0367] Optionally, the deferral information is carried by one of a CSI report, a higher layer signaling (such as RRC signaling or MAC signaling), or UCI.

[0368] Method 2

[0369] In "Method 2," the terminal device can defer reporting of input information and / or processed information that was originally required to be reported but was not reported. This deferral allows the reporting of the input information and / or processed information that was originally required to be reported but was not reported, thus avoiding the inability to recover CSI for this information due to the network device being unable to receive the input information and / or processed information.

[0370] At the same time, when the input information and / or processing information that was originally required to be reported but was not reported is postponed to be reported, since the input information and / or processing information that was originally required to be reported but was not reported will be postponed to the subsequent CSI reporting, and the subsequent CSI reporting may have the input information and / or processing information that needs to be reported, the terminal device not only needs to report the input information and / or processing information that was originally required to be reported in the subsequent CSI reporting, but can also report the input information and / or the processing information that was originally required to be reported but was not reported.

[0371] Optionally, the input information that was originally required to be reported in the subsequent CSI report may be the input information after the input information and / or processing information that was originally required to be reported was not reported; the processing information that was originally required to be reported in the subsequent CSI report may be the processing information after the processing information that was originally required to be reported was not reported.

[0372] Optionally, the input information that is originally required to be reported in the subsequent CSI reporting may be the remaining input information in the group where the input information that was originally required to be reported but was not reported is located.

[0373] Optionally, the input information that is originally required to be reported in the subsequent CSI reporting and the input information that is originally required to be reported but is not reported belong to the same group or belong to different groups.

[0374] Optionally, if the input information that is originally required to be reported in the subsequent CSI report and the input information that is originally required to be reported but is not reported belong to different groups, the input information that is originally required to be reported in the subsequent CSI report may be the first input information in the new group.

[0375] The following uses the interaction between a network device and a terminal device as an example to illustrate "Method 2". As shown in Figure 9, Figure 9 is a flow chart of another communication method according to an embodiment of the present application. The method includes the following steps:

[0376] S910. If the first CSI report containing the first input information and / or the first processing information fails to be reported, the terminal device sends a second CSI report, which includes the first input information and / or the first processing information and the second input information and / or the second processing information.

[0377] The second processed information is information obtained by inputting the second input information into the first AI model or information obtained by further processing the information obtained by inputting the second input information into the first AI model.

[0378] The first input information and the second input information are different input information.

[0379] Correspondingly, the network device receives the second CSI report.

[0380] It can be seen that when it is originally desired to report the first input information and / or the first processing information through the first CSI report, the first input information and / or the first processing information that originally needed to be reported cannot be reported due to the failure of the first CSI report to report. Therefore, the first input information and / or the first processing information as well as the second input information and / or the second processing information are carried through the second CSI report. Therefore, the second CSI report can achieve the purpose of delaying the reporting of the first input information and / or the first processing information and reporting the second input information and / or the second processing information required to be reported in the second CSI report, thereby avoiding the loss of the second input information and / or the second processing information.

[0381] Optionally, the second input information and / or second processing information may be the input information and / or processing information that the second CSI report originally needs to carry. In this way, the second input information and / or second processing information that is originally required to be reported can be reported through the second CSI report, and the first input information and / or first processing information can also be reported through the second CSI report.

[0382] Optionally, the second input information may be input information subsequent to the first input information; and the second processed information may be processed information subsequent to the first processed information.

[0383] Optionally, the second input information may be the remaining input information in the group where the first input information is located.

[0384] Optionally, the first input information and the second input information are in the same group or different groups. If the first input information and the second input information are in different groups, the second input information is the first input information in the group.

[0385] It can be seen that when the input information (i.e., the first input information) in the original group that originally needed to be reported but was not reported is delayed, this embodiment may not reconstruct the group with the remaining input information (i.e., the second input information) after the input information in the original group, but continue to report the input information and the remaining input information after the output information in the original group.

[0386] Alternatively, this embodiment can reconstruct the remaining input information after the input information (i.e., the first input information) in the original group into a new group, so that the remaining input information after the input information (i.e., the second input information) serves as the first input information in the new group, so that the terminal device can continue to report the input information and the first input information in the new group.

[0387] Optionally, the time domain position of the second CSI report is later than the time domain position of the first CSI report. In this way, since the time domain position of the second CSI report is later than the time domain position of the first CSI report, the first input information and / or first processed information that originally needed to be reported but was not reported is deferred through the second CSI report.

[0388] Optionally, the second CSI report is the next CSI report adjacent to the first CSI report. In this way, the first input information and / or the first processed information can be deferred by using the next CSI report adjacent to the first CSI report. Furthermore, since the second CSI report is adjacent to the first CSI report, the reporting delay can be shortened.

[0389] Optionally, the method further includes:

[0390] The terminal device sends postponement information, where the postponement information is used to indicate that the first input information and / or the first processing information is a postponed reporting of the first CSI report.

[0391] Correspondingly, the network device receives the deferral information.

[0392] It can be seen that the postponement information is used to indicate to the network device which CSI reporting the first input information and / or the first processing information is postponed for, so as to know the original order of the postponed information in CSI recovery.

[0393] Optionally, the deferral information may be carried in a second CSI report. In this way, the terminal device can use the second CSI report to both defer reporting of the first input information and / or first processed information that was originally required to be reported but was not, and to indicate to the network device which reporting of the first input information and / or first processed information is deferred.

[0394] Optionally, the deferral information is carried by one of a CSI report, a higher layer signaling (such as RRC signaling or MAC signaling), or UCI.

[0395] Method 3

[0396] In "Method 3", when faced with input information and / or processing information that was originally required to be reported but was not reported, the terminal device may choose not to report the input information and / or processing information that was originally required to be reported but was not reported.

[0397] Based on this, in "Method 3", when the terminal device no longer reports the current input information and / or the current processing information, the terminal device can start to report other input information.

[0398] The following uses the interaction between a network device and a terminal device as an example to illustrate "Method 3". As shown in Figure 10, Figure 10 is a flow chart of another communication method according to an embodiment of the present application. The method includes the following steps:

[0399] S1010. If the first CSI report containing the first input information and / or the first processing information fails to be reported, the terminal device no longer sends the first input information and / or the first processing information, and sends a third CSI report, which contains the third input information and / or the third processing information.

[0400] The third processed information is information obtained by inputting the third input information into the first AI model or information obtained by further processing the information obtained by inputting the third input information into the first AI model.

[0401] The first input information and the third input information are different input information.

[0402] Correspondingly, the network device receives the third CSI report.

[0403] It can be seen that when it was originally hoped to report the first input information and / or the first processing information through the first CSI report, the first CSI report failed to report, which resulted in the first input information and / or the first processing information that originally needed to be reported failing to be reported. Therefore, the terminal device no longer reports the first input information and / or the first processing information, but reports the third input information and / or the third processing information through the third CSI report, thereby reporting the new input information and / or the new processing information and avoiding the loss of the new input information and / or the new processing information.

[0404] Optionally, the third input information and / or third processing information may be the input information and / or processing information that the third CSI report originally needs to carry. In this way, the third input information and / or third processing information that originally needs to be reported is reported through the third CSI report.

[0405] Optionally, the third input information may be input information subsequent to the first input information; and the third processed information may be processed information subsequent to the first processed information.

[0406] Optionally, the third input information may be the remaining input information in the group where the first input information is located.

[0407] Optionally, the time domain position of the third CSI report is after the time domain position of the first CSI report.

[0408] Optionally, the first input information and the third input information are in different groups, and the third input information is the first input information in the group.

[0409] It can be seen that when the input information that originally needed to be reported but was not reported in the original group (i.e., the first input information) is no longer reported, this embodiment can reconstruct the remaining input information after the input information in the original group into a group, so that the remaining input information after the input information is used as the first input information in the new group (i.e., the third input information), so that the terminal device can report the first input information in the new group.

[0410] Optionally, the third CSI report is a next CSI report adjacent to the first CSI report. In this way, postponing the reporting of the third input information and / or the third processing information is achieved through the next CSI report adjacent to the first CSI report.

[0411] [Example of a communication method]

[0412] In combination with the above content, another communication method of an embodiment of the present application is illustrated below, as shown in Figure 11. In Figure 11, the method can be applied to a terminal device. The method includes the following steps:

[0413] S1110. Determine grouping of first input information of a first AI model, or determine CSI reporting of the first input information and / or first processed information; the first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model, or information obtained by further processing the first input information input into the first AI model.

[0414] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model performs CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0415] Alternatively, when a terminal device may need to report / feedback input information and / or processed information, some input information and / or processed information that was originally required to be reported / feedback may not be reported due to some factors, resulting in the input information and / or processed information being discarded. Thus, in the case of input information and / or processed information that was originally required to be reported but was not, this embodiment can determine the CSI reporting of the input information and / or processed information that was originally required to be reported but was not, thereby enhancing CSI-related processing.

[0416] Optionally, the first AI model is used to perform CSI compression on the first input information, and to perform CSI compression on non-first input information using the first historical information;

[0417] The first historical information includes at least one of historical input information, historical processing information, or historical compressed intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained by further processing the historical input information input into the first AI model. The historical compressed intermediate information is the information generated by the first AI model in the process of compressing the historical input information.

[0418] Optionally, historical input information in a group participates in CSI compression of non-first input information in the same group, and all input information in a group does not participate in CSI compression of any input information in other groups.

[0419] Optionally, the first input information is in input information corresponding to at least one CSI report, and a time domain behavior of the at least one CSI report is at least one of periodic, semi-persistent, or aperiodic; or,

[0420] The first input information is in the input information corresponding to at least one measurement resource;

[0421] The time domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

[0422] Optionally, input information corresponding to at least one CSI report is input into the first AI model in the order of the time domain positions of the CSI reports or in the order of the size of the identification IDs of the CSI reports; or,

[0423] Input information corresponding to at least one measurement resource is input into the first AI model in the order of the time domain positions of the measurement resources or in the order of the size of the IDs of the measurement resources.

[0424] Optionally, at least one CSI report includes all non-periodic CSI reports triggered by downlink control information DCI.

[0425] Optionally, in S1110, determining the grouping of the first input information of the first AI model includes:

[0426] Receive configuration information, where the configuration information is used to configure a time window;

[0427] Determine the grouping of first input information of the first AI model according to the time window.

[0428] Optionally, if the first input information is in the input information corresponding to at least one CSI report, and the time domain position of the at least one CSI report is within the time window, the input information corresponding to the at least one CSI report belongs to the same group.

[0429] Optionally, if the first input information is in the input information corresponding to at least one measurement resource, and the time domain position of at least one measurement resource is within the time window or the time domain position of the CSI report associated with at least one measurement resource is within the time window, then the input information corresponding to at least one measurement resource belongs to the same group.

[0430] Optionally, the configuration information includes at least one of length information, start information, or period information;

[0431] Length information, used to configure the length of the time window;

[0432] Start information, used to configure the start position of the time window;

[0433] Period information, used to configure the period of the time window.

[0434] Optionally, the length of the time window is an integer multiple of the CSI reporting period.

[0435] Optionally, the starting position of the time window satisfies the following conditions:

[0436] or,

[0437]

[0438] Wherein, μ represents the subcarrier spacing configuration of the uplink bandwidth part BWP for transmitting CSI reports; Indicates the number of time slots in a frame under the subcarrier spacing configuration μ; n f Indicates the system frame number where the CSI report is located; Indicates the time slot number where the CSI report is located; T offset Indicates the time slot offset; N indicates the maximum number of input information in a group; T CSI Indicates the CSI reporting period; Indicates the system frame number of the physical uplink shared channel PUSCH where the first CSI report is sent after DCI activation; Indicates the timeslot number of the PUSCH where the first CSI report is sent after DCI activation.

[0439] Optionally, in S1110, determining the grouping of the first input information of the first AI model includes:

[0440] receiving instruction information, where the instruction information is used to indicate grouping of first input information of the first AI model;

[0441] The grouping of the first input information is determined according to the indication information.

[0442] Optionally, the method further includes:

[0443] First position information is sent, where the first position information is used to indicate a position of the first input information in the group or a position of the first processed information in the group.

[0444] Optionally, in S1110, determining CSI reporting of the first input information and / or the first processed information includes:

[0445] If the first CSI report containing the first input information and / or the first processing information fails to be reported, a second CSI report is sent, the second CSI report includes the first input information and / or the first processing information, or the first input information and / or the first processing information is sent at an available time domain position after the time domain position of the first CSI report.

[0446] Optionally, in S1110, determining a CSI report of the first input information and / or the first processed information includes:

[0447] If the first CSI report containing the first input information and / or the first processing information fails to be reported, sending a second CSI report, where the second CSI report includes the first input information and / or the first processing information and the second input information and / or the second processing information;

[0448] The second processed information is information obtained by inputting the second input information into the first AI model, or information obtained by further processing the information obtained by inputting the second input information into the first AI model;

[0449] The first input information and the second input information are different input information.

[0450] Optionally, the time domain position of the second CSI report is after the time domain position of the first CSI report.

[0451] Optionally, the first input information and the second input information are in the same group or different groups; if the first input information and the second input information are in different groups, the second input information is the first input information in the group.

[0452] Optionally, the method further includes:

[0453] Sending deferral information, where the deferral information is used to indicate that the first input information and / or the first processing information is a deferral of reporting the first CSI report.

[0454] Optionally, in S1110, determining a CSI report of the first input information and / or the first processed information includes:

[0455] If the first CSI report containing the first input information and / or the first processed information fails to be reported, the first input information and / or the first processed information are no longer sent, and a third CSI report is sent, where the third CSI report includes the third input information and / or the third processed information;

[0456] The third processed information is information obtained by inputting the third input information into the first AI model or information obtained by further processing the information obtained by inputting the third input information into the first AI model;

[0457] The first input information and the third input information are different input information.

[0458] Optionally, the time domain position of the third CSI report is after the time domain position of the first CSI report. Optionally, the first input information and the third input information are in different groups, and the third input information is the first input information in the group.

[0459] 3. Example of a communication device

[0460]

describe

[0461] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the method side. It is understandable that, in order to realize the above functions, the terminal device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0462] The embodiments of the present application can divide the terminal device into functional units according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software program module. It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, other division methods can be used.

[0463] In the case of using integrated units, FIG12 is a block diagram of functional units of a communication device according to an embodiment of the present application, wherein the communication device 1200 includes a determining unit 1201 .

[0464] Optionally, the determining unit 1201 may be a module unit for receiving and processing signals, information, etc. or determining a monitoring mechanism, and there is no specific limitation on this.

[0465] Optionally, the communication device 1200 may further include a storage unit for storing computer program codes or instructions executed by the communication device 1200. The storage unit may be a memory.

[0466] Optionally, the communication device 1200 may be a chip or a chip module.

[0467] Optionally, the determining unit 1201 may be integrated into a communication unit. The communication unit may be a communication interface, a transceiver, a transceiver circuit, etc.

[0468] Optionally, the determining unit 1201 may be integrated into the processing unit.

[0469] It should be noted that the processing unit can be a processor or controller, for example, a baseband processor, a baseband chip, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute the various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0470] Optionally, the communication device 1200 is used to execute any step performed by the terminal device / chip / chip module, etc. in the above method embodiment.

[0471] In specific implementation, the determining unit 1201 is used to execute any step in the above method embodiment, and when executing an action such as sending, it can selectively call other units to complete the corresponding operation.

[0472] A determining unit 1201 is configured to determine grouping of first input information of a first AI model, or determine CSI reporting of the first input information and / or first processed information;

[0473] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0474] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model performs CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0475] Alternatively, when a terminal device may need to report / feedback input information and / or processed information, some input information and / or processed information that was originally required to be reported / feedback may not be reported due to some factors, resulting in possible loss of input information and / or processed information. In the event that input information and / or processed information that was originally required to be reported is not reported, this embodiment needs to determine the CSI reporting of the input information and / or processed information that was originally required to be reported but was not reported, thereby achieving enhanced CSI-related processing.

[0476] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 12 can be found in the description of the method embodiment shown above, and will not be detailed here.

[0477] Some possible implementations

[0478] Optionally, the first AI model is used to perform CSI compression on the first input information, and to perform CSI compression on non-first input information using the first historical information;

[0479] The first historical information includes at least one of historical input information, historical processing information, or historical compressed intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained by further processing the historical input information input into the first AI model. The historical compressed intermediate information is the information generated by the first AI model in the process of compressing the historical input information.

[0480] Optionally, historical input information in a group participates in CSI compression of non-first input information in the same group, and all input information in a group does not participate in CSI compression of any input information in other groups.

[0481] Optionally, the first input information is in input information corresponding to at least one CSI report, and a time domain behavior of the at least one CSI report is at least one of periodic, semi-persistent, or aperiodic; or,

[0482] The first input information is in the input information corresponding to at least one measurement resource;

[0483] The time domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

[0484] Optionally, input information corresponding to at least one CSI report is input into the first AI model in the order of the time domain positions of the CSI reports or in the order of the size of the identification IDs of the CSI reports; or,

[0485] Input information corresponding to at least one measurement resource is input into the first AI model in the order of the time domain positions of the measurement resources or in the order of the size of the IDs of the measurement resources.

[0486] Optionally, at least one CSI report includes all non-periodic CSI reports triggered by one DCI.

[0487] Optionally, in determining the grouping of the first input information of the first AI model, the determining unit 1201 is configured to:

[0488] Receive configuration information, where the configuration information is used to configure a time window;

[0489] Determine the grouping of first input information of the first AI model according to the time window.

[0490] Optionally, if the first input information is in the input information corresponding to at least one CSI report, and the time domain position of the at least one CSI report is within the time window, the input information corresponding to the at least one CSI report belongs to the same group.

[0491] Optionally, if the first input information is in the input information corresponding to at least one measurement resource, and the time domain position of at least one measurement resource is within the time window or the time domain position of the CSI report associated with at least one measurement resource is within the time window, then the input information corresponding to at least one measurement resource belongs to the same group.

[0492] Optionally, the configuration information includes at least one of length information, start information, or period information;

[0493] Length information, used to configure the length of the time window;

[0494] Start information, used to configure the start position of the time window;

[0495] Period information, used to configure the period of the time window.

[0496] Optionally, the length of the time window is an integer multiple of the CSI reporting period.

[0497] Optionally, the starting position of the time window satisfies the following conditions:

[0498] or,

[0499]

[0500] Wherein, μ represents the subcarrier spacing configuration of the uplink bandwidth part BWP for transmitting CSI reports; Indicates the number of time slots in a frame under the subcarrier spacing configuration μ; n f Indicates the system frame number where the CSI report is located; Indicates the time slot number where the CSI report is located; T offset Indicates the time slot offset; N indicates the maximum number of input information in a group; T CSI Indicates the CSI reporting period; Indicates the system frame number of the physical uplink shared channel PUSCH where the first CSI report is sent after DCI activation; Indicates the timeslot number of the PUSCH where the first CSI report is sent after DCI activation.

[0501] Optionally, in determining the grouping of the first input information of the first AI model, the determining unit 1201 is configured to:

[0502] receiving instruction information, where the instruction information is used to indicate grouping of first input information of the first AI model;

[0503] The grouping of the first input information is determined according to the indication information.

[0504] Optionally, the communication device 1200 further includes a sending unit;

[0505] The sending unit is used to send first position information, where the first position information is used to indicate the position of the first input information in the group or the position of the first processed information in the group.

[0506] Optionally, in determining the CSI reporting of the first input information and / or the first processed information, the determining unit 1201 is configured to:

[0507] If the first CSI report containing the first input information and / or the first processing information fails to be reported, a second CSI report is sent, the second CSI report includes the first input information and / or the first processing information, or the first input information and / or the first processing information is sent at an available time domain position after the time domain position of the first CSI report.

[0508] Optionally, in determining the CSI reporting of the first input information and / or the first processed information, the determining unit 1201 is configured to:

[0509] If the first CSI report containing the first input information and / or the first processing information fails to be reported, sending a second CSI report, where the second CSI report includes the first input information and / or the first processing information and the second input information and / or the second processing information;

[0510] The second processed information is information obtained by inputting the second input information into the first AI model, or information obtained by further processing the information obtained by inputting the second input information into the first AI model;

[0511] The first input information and the second input information are different input information.

[0512] Optionally, the time domain position of the second CSI report is after the time domain position of the first CSI report.

[0513] Optionally, the first input information and the second input information are in the same group or different groups; if the first input information and the second input information are in different groups, the second input information is the first input information in the group.

[0514] Optionally, the communication device 1200 further includes a sending unit;

[0515] The sending unit is configured to send deferral information, where the deferral information is used to indicate that the first input information and / or the first processing information is a deferral of reporting the first CSI report.

[0516] Optionally, in determining the CSI reporting of the first input information and / or the first processed information, the determining unit 1201 is configured to:

[0517] If the first CSI report containing the first input information and / or the first processed information fails to be reported, the first input information and / or the first processed information are no longer sent, and a third CSI report is sent, where the third CSI report includes the third input information and / or the third processed information;

[0518] The third processed information is information obtained by inputting the third input information into the first AI model or information obtained by further processing the information obtained by inputting the third input information into the first AI model;

[0519] The first input information and the third input information are different input information.

[0520] Optionally, the time domain position of the third CSI report is after the time domain position of the first CSI report.

[0521] Optionally, the first input information and the third input information are in different groups, and the third input information is the first input information in the group.

[0522] 4. Example of another communication device

[0523]

describe

[0524] The above mainly introduces the solution of the embodiment of the present application from the perspective of the method side. It is understandable that, in order to implement the above functions, the network device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0525] The embodiments of the present application can divide the network device into functional units according to the above-mentioned method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into a processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software program module. It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, other division methods can be used.

[0526] In the case of using integrated units, FIG13 is a block diagram of functional units of another communication device according to an embodiment of the present application, wherein the communication device 1300 includes a sending unit 1301 .

[0527] Optionally, the sending unit 1301 may be a module unit for sending and processing signals, information, etc., and there is no specific limitation on this.

[0528] Optionally, the communication device 1300 may further include a receiving unit, wherein the receiving unit may be a module unit for receiving and processing signals, information, etc., and is not specifically limited thereto.

[0529] Optionally, the communication device 1300 may further include a storage unit for storing computer program codes or instructions executed by the communication device 1300. The storage unit may be a memory.

[0530] Optionally, the communication device 1300 may be a chip or a chip module.

[0531] Optionally, the sending unit 1301 may be integrated into a communication unit, wherein the communication unit may be a communication interface, a transceiver, a transceiver circuit, etc.

[0532] Optionally, the sending unit 1301 may be integrated into the processing unit.

[0533] It should be noted that the processing unit can be a processor or controller, for example, a baseband processor, a baseband chip, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute the various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0534] Optionally, the communication device 1300 is used to execute any step executed by the chip / chip module / network device, etc. in the above method embodiment.

[0535] In specific implementation, the sending unit 1301 is used to execute any step in the above method embodiment, and when performing an action such as receiving, it can selectively call other units to complete the corresponding operation.

[0536] A sending unit 1301 is configured to send configuration information for configuring a time window for determining grouping of first input information of a first AI model; or to send indication information for indicating grouping of first input information of the first AI model; the first AI model is configured for channel state information (CSI) compression.

[0537] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model performs CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0538] It should be noted that the specific implementation of each operation in the embodiment shown in Figure 13 can be found in the description of the method embodiment shown above, and will not be detailed here.

[0539] Some possible implementations

[0540] Optionally, the first AI model is used to perform CSI compression on the first input information, and to perform CSI compression on non-first input information using the first historical information;

[0541] The first historical information includes at least one of historical input information, historical processing information, or historical compressed intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained by further processing the historical input information input into the first AI model. The historical compressed intermediate information is the information generated by the first AI model in the process of compressing the historical input information.

[0542] Optionally, historical input information in a group participates in CSI compression of non-first input information in the same group, and all input information in a group does not participate in CSI compression of any input information in other groups.

[0543] Optionally, if the first input information is in the input information corresponding to at least one CSI report, and the time domain position of the at least one CSI report is within the time window, then the input information corresponding to the at least one CSI report belongs to the same group; or,

[0544] If the first input information is in the input information corresponding to at least one measurement resource, and the time domain position of the at least one measurement resource is within the time window or the time domain position of the CSI report associated with the at least one measurement resource is within the time window, then the input information corresponding to the at least one measurement resource belongs to the same group.

[0545] Optionally, the configuration information includes at least one of length information, start information, or period information;

[0546] Length information, used to configure the length of the time window;

[0547] Start information, used to configure the start position of the time window;

[0548] Period information, used to configure the period of the time window.

[0549] Optionally, the length of the time window is an integer multiple of the CSI reporting period; or,

[0550] The starting position of the time window satisfies the following conditions:

[0551] or,

[0552]

[0553] Wherein, μ represents the subcarrier spacing configuration of the uplink bandwidth part BWP for transmitting CSI reports; Indicates the number of time slots in a frame under the subcarrier spacing configuration μ; n f Indicates the system frame number where the CSI report is located; Indicates the time slot number where the CSI report is located; T offset Indicates the time slot offset; N indicates the maximum number of input information in a group; T CSI Indicates the CSI reporting period; Indicates the system frame number of the physical uplink shared channel PUSCH where the first CSI report is sent after DCI activation; Indicates the timeslot number of the PUSCH where the first CSI report is sent after DCI activation.

[0554] Optionally, the communication device 1300 further includes a receiving unit;

[0555] The receiving unit is configured to receive first position information, where the first position information is used to indicate a position of the first input information in the group or a position of the first processed information in the group.

[0556] 5. Example of Yet Another Communication Device

[0557]

describe

[0558] In the case of using integrated units, FIG14 is a block diagram of functional units of another communication device according to an embodiment of the present application, wherein the communication device 1400 includes a receiving unit 1401 .

[0559] Optionally, the receiving unit 1401 may be a module unit for receiving and processing signals, information, etc., and there is no specific limitation on this.

[0560] Optionally, the communication device 1400 may further include a receiving unit, wherein the receiving unit may be a module unit for receiving and processing signals, information, etc., and is not specifically limited thereto.

[0561] Optionally, the communication device 1400 may further include a storage unit for storing computer program codes or instructions executed by the communication device 1400. The storage unit may be a memory.

[0562] Optionally, the communication device 1400 may be a chip or a chip module.

[0563] Optionally, the receiving unit 1401 may be integrated into a communication unit, wherein the communication unit may be a communication interface, a transceiver, a transceiver circuit, etc.

[0564] Optionally, the receiving unit 1401 may be integrated into the processing unit.

[0565] It should be noted that the processing unit can be a processor or controller, for example, a baseband processor, a baseband chip, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute the various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0566] Optionally, the communication device 1400 is used to execute any step executed by the chip / chip module / network device, etc. in the above method embodiment.

[0567] In specific implementation, the receiving unit 1401 is used to execute any step in the above method embodiment, and when executing an action such as receiving, it can selectively call other units to complete corresponding operations. Detailed description is given below.

[0568] The receiving unit 1401 is configured to receive a second CSI report if the first CSI report containing the first input information and / or the first processing information of the first AI model fails to be reported, where the second CSI report includes the first input information and / or the first processing information, or the second CSI report includes the first input information and / or the first processing information and the second input information and / or the second processing information, where the first input information and the second input information are different input information; or

[0569] If the first CSI report containing the first input information and / or first processed information of the first AI model fails to be reported, the first input information and / or first processed information is received at an available time domain position after the time domain position of the first CSI report; or

[0570] If the first CSI report containing the first input information and / or the first processed information of the first AI model fails to be reported, receiving a third CSI report, where the third CSI report includes third input information and / or third processed information, where the first input information and the third input information are different input information;

[0571] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0572] It can be seen that when it was originally hoped to report the first input information and / or the first processing information through the first CSI report, the first CSI report failed to report, which resulted in the first input information and / or the first processing information that was originally required to be reported failing to be reported. Therefore, the first input information and / or the first processing information is carried through the second CSI report, thereby achieving continued reporting of the first input information and / or the first processing information that was originally required to be reported but was not reported.

[0573] Alternatively, when the first input information and / or first processing information that was originally required to be reported cannot be reported, the first input information and / or first processing information as well as the second input information and / or second processing information are carried through the second CSI report, so that the second CSI report can both postpone the reporting of the first input information and / or first processing information and report the second input information and / or second processing information required to be reported in the second CSI report, thereby avoiding the loss of the second input information and / or second processing information.

[0574] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or first processing information is received at an available time domain position after the time domain position of the first CSI report, thereby achieving continued reporting / postponed reporting of the first input information and / or first processing information.

[0575] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or first processing information is received at an available time domain position after the time domain position of the first CSI report, thereby achieving continued reporting / postponed reporting of the first input information and / or first processing information.

[0576] It should be noted that the specific implementation of each operation in the embodiment described in FIG14 can be found in the description of the method embodiment shown above, and will not be described in detail here.

[0577] Some possible implementations

[0578] Optionally, the time domain position of the second CSI report is after the time domain position of the first CSI report.

[0579] Optionally, the time domain position of the third CSI report is after the time domain position of the first CSI report.

[0580] Optionally, the first input information and the second input information are in the same group or different groups; if the first input information and the second input information are in different groups, the second input information is the first input information in the group; or,

[0581] The first input information and the third input information are in different groups, and the third input information is the first input information in the group.

[0582] Optionally, the receiving unit 1401 is further configured to receive postponement information, where the postponement information is used to indicate that the first input information and / or the first processing information is a postponed reporting of the first CSI report.

[0583] 6. Example of a terminal device

[0584] Please refer to Figure 15, which is a schematic diagram of the structure of a terminal device according to an embodiment of the present application. The terminal device 1500 may include a processor 1510, a memory 1520, and a communication bus for connecting the processor 1510 and the memory 1520.

[0585] Optionally, the memory 1520 includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or portable read-only memory (CD-ROM), and the memory 1520 is used to store the program code executed by the terminal device 1500 and the transmitted data.

[0586] Optionally, the terminal device 1500 further includes a communication interface for receiving and sending data.

[0587] Optionally, the terminal device 1500 may be the first terminal device mentioned above.

[0588] Optionally, the processor 1510 may be one or more CPUs. In the case where the processor 1510 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0589] Optionally, the processor 1510 may be a baseband chip, a chip, a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof.

[0590] In a specific implementation, the processor 1510 in the terminal device 1500 is configured to execute the computer program or instruction 1521 stored in the memory 1520 to perform the following operations:

[0591] Determining grouping of first input information of the first AI model, or determining CSI reporting of the first input information and / or first processed information;

[0592] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0593] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model performs CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0594] Alternatively, when a terminal device needs to report / feedback input information and / or processed information, some input information and / or processed information that was originally required to be reported / feedback may not be reported due to some factors, resulting in the input information and / or processed information being discarded. Thus, in the case of input information and / or processed information that was originally required to be reported but was not, this embodiment can determine the CSI reporting of the input information and / or processed information that was originally required to be reported but was not, thereby enhancing CSI-related processing.

[0595] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above, and the terminal device 1500 can be used to execute the above method embodiment of this application, which will not be repeated here.

[0596] VII. Example of a Network Device

[0597] Please refer to Figure 16, which is a schematic diagram of the structure of a network device provided in an embodiment of the present application. In particular, the network device 1600 includes a processor 1610, a memory 1620, and a communication bus for connecting the processor 1610 and the memory 1620.

[0598] Optionally, the memory 1620 includes but is not limited to RAM, ROM, EPROM or CD-ROM, and the memory 1620 is used to store relevant instructions and data.

[0599] Optionally, the network device 1600 further includes a communication interface for receiving and sending data.

[0600] Optionally, the processor 1610 may be one or more CPUs. When the processor 1610 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0601] Optionally, the processor 1610 may be a baseband chip, a chip, a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof.

[0602] Optionally, the processor 1610 in the network device 1600 is configured to execute a computer program or instruction 1621 stored in the memory 1620 to perform the following operations:

[0603] Send configuration information, where the configuration information is used to configure a time window, where the time window is used to determine the grouping of first input information of a first artificial intelligence (AI) model; or send indication information, where the indication information is used to indicate the grouping of first input information of the first AI model; the first AI model is used for channel state information (CSI) compression.

[0604] As can be seen, when AI technology is applied to the CSI framework, in order to enhance CSI compression and CSI recovery, since the first AI model performs CSI compression on the input information in sequence, historical input information can participate in the CSI compression of the current input information, previously obtained processed information can be used as historical processed information to participate in the CSI compression of the current input information, and / or previously obtained compressed intermediate information can be used as historical compressed intermediate information to participate in the CSI compression of the current input information. Therefore, this embodiment requires determining the grouping of the input information. In this way, the first AI model can be used to perform CSI compression on the first input information in a group, and use the historical input information in the group to perform CSI compression on non-first input information in the group, thereby achieving enhanced CSI-related processing.

[0605] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above, and the network device 1600 can be used to execute the above method embodiment of this application, which will not be repeated here.

[0606] 8. Another example of network equipment

[0607] Please refer to Figure 17, which is a schematic diagram of the structure of a network device provided in an embodiment of the present application. In particular, the network device 1700 includes a processor 1710, a memory 1720, and a communication bus for connecting the processor 1710 and the memory 1720.

[0608] Optionally, the memory 1720 includes but is not limited to RAM, ROM, EPROM or CD-ROM, and the memory 1720 is used to store relevant instructions and data.

[0609] Optionally, the network device 1700 further includes a communication interface for receiving and sending data.

[0610] Optionally, the processor 1710 may be one or more CPUs. When the processor 1710 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0611] Optionally, the processor 1710 may be a baseband chip, a chip, a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof.

[0612] Optionally, the processor 1710 in the network device 1700 is configured to execute a computer program or instruction 1721 stored in the memory 1720 to perform the following operations:

[0613] If the first CSI report containing the first input information and / or the first processed information of the first AI model fails to be reported, a second CSI report is received, where the second CSI report includes the first input information and / or the first processed information, or the second CSI report includes the first input information and / or the first processed information and the second input information and / or the second processed information, the time domain position of the second CSI report is later than the time domain position of the first CSI report, and the first input information and the second input information are different input information; or

[0614] If the first CSI report containing the first input information and / or first processed information of the first AI model fails to be reported, the first input information and / or first processed information is received at an available time domain position after the time domain position of the first CSI report; or

[0615] If the first CSI report containing the first input information and / or the first processed information of the first AI model fails to be reported, a third CSI report is received, where the third CSI report includes third input information and / or third processed information, and the time domain position of the third CSI report is later than the time domain position of the first CSI report; the first input information and the third input information are different input information;

[0616] The first AI model is used for CSI compression, and the first processed information is information obtained by inputting the first input information into the first AI model or information obtained by further processing the information obtained by inputting the first input information into the first AI model.

[0617] It can be seen that when it was originally hoped to report the first input information and / or the first processing information through the first CSI report, the first CSI report failed to report, which resulted in the first input information and / or the first processing information that was originally required to be reported failing to be reported. Therefore, the first input information and / or the first processing information is carried through the second CSI report, thereby achieving continued reporting of the first input information and / or the first processing information that was originally required to be reported but was not reported.

[0618] Alternatively, when the first input information and / or first processing information that was originally required to be reported cannot be reported, the first input information and / or first processing information as well as the second input information and / or second processing information are carried through the second CSI report, so that the second CSI report can both postpone the reporting of the first input information and / or first processing information and report the second input information and / or second processing information required to be reported in the second CSI report, thereby avoiding the loss of the second input information and / or second processing information.

[0619] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or first processing information is received at an available time domain position after the time domain position of the first CSI report, thereby achieving continued reporting / postponed reporting of the first input information and / or first processing information.

[0620] Alternatively, when the first input information and / or first processing information that were originally required to be reported fail to be reported, the first input information and / or the first processing information are no longer reported, but the third input information and / or the third processing information are reported through the third CSI report, so as to report the new input information and / or the new processing information and avoid the loss of the new input information and / or the new processing information.

[0621] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above, and the network device 1700 can be used to execute the above method embodiment of this application, which will not be repeated here.

[0622] 9. Other related examples

[0623] Optionally, the above method embodiments may be applied to or within a terminal device. In other words, the execution subject of the above method embodiments may be a terminal device, a chip, a chip module, or a module, etc., without any specific limitation.

[0624] Optionally, the above method embodiment can be applied to or in a network device. In other words, the execution subject of the above method embodiment can be a network device, a chip, a chip module or a module, etc., without specific limitation.

[0625] An embodiment of the present application also provides a chip, including a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps described in the above method embodiment.

[0626] An embodiment of the present application also provides a chip module, including a transceiver component and a chip, wherein the chip includes a processor, a memory, and a computer program or instructions stored on the memory, wherein the processor executes the computer program or instructions to implement the steps described in the above method embodiment.

[0627] An embodiment of the present application further provides a computer-readable storage medium storing a computer program or instructions, which implements the steps described in the above method embodiment when executed.

[0628] An embodiment of the present application further provides a computer program product, including a computer program or instructions, which implement the steps described in the above method embodiment when executed.

[0629] An embodiment of the present application also provides a communication system, including the above-mentioned terminal device and the above-mentioned network device.

[0630] It should be noted that, for the above-mentioned various embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. Those skilled in the art should know that this application is not limited by the order of the actions described, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0631] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0632] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and storage medium can also be present in a terminal device or a management device as discrete components.

[0633] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part 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, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. 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 via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0634] The modules / units included in the devices and products described in the above embodiments may be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least part of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as chip, circuit module, etc.) or different components of the chip module, or at least part of the modules / units may be It is implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0635] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only a specific implementation method of the embodiments of the present application and is not intended to limit the scope of protection of the embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of protection of the embodiments of the present application.

Claims

1. A communication method, characterized in that, Including: Determining a grouping of first input information of an artificial intelligence first AI model, or determining channel state information CSI reporting of the first input information and / or first processing information; The first AI model is used for CSI compression, and the first processing information is information obtained by inputting the first input information into the first AI model or information obtained after further processing of the information obtained by inputting the first input information into the first AI model.

2. The method according to claim 1, characterized in that, The first AI model is used for performing CSI compression on the first input information and using first historical information to perform CSI compression on non-first input information; The first historical information includes at least one of historical input information, historical processing information, or historical compression intermediate information. The historical processing information is information obtained by inputting the historical input information into the first AI model or information obtained after further processing of the information obtained by inputting the historical input information into the first AI model. The historical compression intermediate information is information generated by the first AI model during the process of compressing the historical input information.

3. The method according to claim 1, wherein The historical input information within a grouping participates in the CSI compression of non-first input information within the same grouping, and all input information in a grouping does not participate in the CSI compression of any input information in other groupings.

4. The method according to claim 1, wherein The first input information is among the input information corresponding to at least one CSI report, and the time domain behavior of the at least one CSI report is at least one of periodic, semi-persistent, or aperiodic; Or, The first input information is among the input information corresponding to at least one measurement resource; The time domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

5. The method according to claim 4, characterized in that, The input information corresponding to the at least one CSI report is input into the first AI model in the order of the time domain positions of the CSI reports or in the order of the magnitudes of the identification IDs of the CSI reports; or, The input information corresponding to the at least one measurement resource is input into the first AI model in the order of the time domain positions of the measurement resources or in the order of the magnitudes of the IDs of the measurement resources.

6. The method according to any one of claims 1-5, characterized in that, The determining of the grouping of the first input information of the first AI model includes: Receiving configuration information for configuring a time window; Determining the grouping of the first input information of the first AI model according to the time window.

7. The method according to claim 6, wherein If the first input information is among the input information corresponding to at least one CSI report and the time domain position of the at least one CSI report is within the time window, then The input information corresponding to the at least one CSI report belongs to the same grouping.

8. The method according to claim 6, characterized in that, If the first input information is among the input information corresponding to at least one measurement resource and the time domain position of the at least one measurement resource is within the time window or the time domain position of the CSI report associated with the at least one measurement resource is within the time window, then The input information corresponding to the at least one measurement resource belongs to the same grouping.

9. The method according to any one of claims 6-8, characterized in that, The configuration information includes at least one of length information, start information, or period information; The length information is used for configuring the length of the time window; The starting information is used to configure the starting position of the time window; The period information is used to configure the period of the time window.

10. The method according to any one of claims 1-5, characterized in that, The grouping of the first input information for determining the first AI model includes: Receiving indication information, where the indication information is used to indicate the grouping of the first input information of the first AI model; Determining the grouping of the first input information according to the indication information.

11. The method according to any one of claims 6-10, characterized in that, It further includes: Sending first position information, where the first position information is used to indicate the position of the first input information in the grouping or the position of the first processing information in the grouping.

12. The method according to any one of claims 1-5, characterized in that, The CSI reporting for determining the first input information and / or the first processing information includes: If the first CSI report where the first input information and / or the first processing information is located fails to be reported, then sending a second CSI report, where the second CSI report includes the first input information and / or the first processing information; or, If the first CSI report where the first input information and / or the first processing information is located fails to be reported, then sending the first input information and / or the first processing information at an available time domain position after the time domain position of the first CSI report.

13. The method according to any one of claims 1-5, characterized in that, The CSI reporting for determining the first input information and / or the first processing information includes: If the first CSI report where the first input information and / or the first processing information is located fails to be reported, then sending a second CSI report, where the second CSI report includes the first input information and / or the first processing information, as well as the second input information and / or the second processing information; The second processing information is the information obtained by inputting the second input information into the first AI model or the information obtained by further processing the information obtained by inputting the second input information into the first AI model; The first input information and the second input information are different input information.

14. The method according to claim 13, wherein The first input information and the second input information are in the same grouping or different groupings; if the first input information and the second input information are in different groupings, then the second input information is the first input information in the grouping.

15. The method according to any one of claims 12 - 14, characterized in that, It further includes: Sending postponement information, where the postponement information is used to indicate that the first input information and / or the first processing information is a postponed report of the first CSI report.

16. The method according to any one of claims 1-5, characterized in that, The CSI reporting for determining the first input information and / or the first processing information includes: If the first CSI report where the first input information and / or the first processing information is located fails to be reported, then no longer sending the first input information and / or the first processing information, and sending a third CSI report, where the third CSI report includes the third input information and / or the third processing information; The third processing information is the information obtained by inputting the third input information into the first AI model or the information obtained by further processing the information obtained by inputting the third input information into the first AI model; The first input information and the third input information are different input information.

17. The method according to claim 16, wherein The first input information and the third input information are in different groupings, and the third input information is the first input information in the grouping.

18. A communication method, characterized in that, It includes: Send configuration information, where the configuration information is used to configure a time window, and the time window is used to determine the grouping of the first input information of the first AI model; Or, Send indication information, where the indication information is used to indicate the grouping of the first input information of the first AI model; The first AI model is used for channel state information (CSI) compression.

19. The method according to claim 18, wherein The first AI model is used to perform CSI compression on the first input information and use first historical information to perform CSI compression on non-first input information; The first historical information includes at least one of historical input information, historical processing information, or historical compression intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained by further processing the information obtained by inputting the historical input information into the first AI model. The historical compression intermediate information is the information generated by the first AI model during the process of compressing the historical input information.

20. The method according to claim 18, characterized in that, The historical input information within a group participates in the CSI compression of the non-first input information within the same group, and all the input information in a group does not participate in the CSI compression of any input information in other groups.

21. The method according to any one of claims 18 - 20, characterized in that If the first input information of the first AI model is among the input information corresponding to at least one CSI report and the time domain position of the at least one CSI report is within the time window, then the input information corresponding to the at least one CSI report belongs to the same group; or, If the first input information is among the input information corresponding to at least one measurement resource and the time domain position of the at least one measurement resource is within the time window or the time domain position of the CSI report associated with the at least one measurement resource is within the time window, then the input information corresponding to the at least one measurement resource belongs to the same group.

22. The method according to any one of claims 18 - 21, characterized in that, The configuration information includes at least one of length information, start information, or period information; The length information is used to configure the length of the time window; The start information is used to configure the start position of the time window; The period information is used to configure the period of the time window.

23. A communication method, characterized in that, Include: If the first CSI report where the first input information and / or the first processing information of the first AI model is located fails to be reported, then receive a second CSI report, where the second CSI report contains the first input information and / or the first processing information, or the second CSI report contains the first input information and / or the first processing information and the second input information and / or the second processing information, and the first input information and the second input information are different input information; Or, If the first CSI report where the first input information and / or the first processing information of the first AI model is located fails to be reported, then receive the first input information and / or the first processing information at an available time domain position after the time domain position of the first CSI report; Or, If the first CSI report in which the first input information and / or the first processing information of the first AI model is located fails to be reported, then a third CSI report is received, where the third CSI report includes third input information and / or third processing information, and the first input information and the third input information are different input information; The first AI model is used for CSI compression. The first processing information is the information obtained by inputting the first input information into the first AI model or the information obtained by further processing the information obtained by inputting the first input information into the first AI model. The second processing information is the information obtained by inputting the second input information into the first AI model or the information obtained by further processing the information obtained by inputting the second input information into the first AI model. The third processing information is the information obtained by inputting the third input information into the first AI model or the information obtained by further processing the information obtained by inputting the third input information into the first AI model.

24. The method according to claim 23, wherein The first input information and the second input information are in the same packet or different packets; if the first input information and the second input information are in different packets, then the second input information is the first input information in the packet. Or, The first input information and the third input information are in different packets, and the third input information is the first input information in the packet.

25. The method according to claim 23 or 24, characterized in that, It further includes: Receiving delay information, where the delay information is used to indicate that the first input information and / or the first processing information is a postponed report of the first CSI report.

26. A communication device, characterized in that, Includes: A determination unit, which is used to determine the packet of the first input information of the first AI model, or determine the channel state information CSI report of the first input information and / or the first processing information; The first AI model is used for CSI compression. The first processing information is the information obtained by inputting the first input information into the first AI model or the information obtained by further processing the information obtained by inputting the first input information into the first AI model.

27. The device according to claim 26, characterized in that, The first AI model is used to perform CSI compression on the first input information and use the first historical information to perform CSI compression on non-first input information; The first historical information includes at least one of historical input information, historical processing information, or historical compression intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained by further processing the information obtained by inputting the historical input information into the first AI model. The historical compression intermediate information is the information generated by the first AI model during the process of compressing the historical input information.

28. The device according to claim 26, wherein The historical input information within a packet participates in the CSI compression of non-first input information within the same packet, and all input information in a packet does not participate in the CSI compression of any input information in other packets.

29. The device according to claim 26, characterized in that, The first input information is among the input information corresponding to at least one CSI report, and the time-domain behavior of the at least one CSI report is at least one of periodic, semi-persistent, or aperiodic; Or, The first input information is among the input information corresponding to at least one measurement resource; The time-domain behavior of the at least one measurement resource is at least one of periodic, semi-persistent, or aperiodic.

30. The device according to claim 29, characterized in that, The input information corresponding to the at least one CSI report is input into the first AI model in the order of the time-domain positions of the CSI reports or in the order of the magnitudes of the identification IDs of the CSI reports; or, The input information corresponding to the at least one measurement resource is input into the first AI model in the order of the time-domain positions of the measurement resources or in the order of the magnitudes of the IDs of the measurement resources.

31. The device according to any one of claims 26-30, characterized in that, In the determination of the grouping of the first input information of the first AI model, the determination unit is configured to: Receive configuration information for configuring a time window; Determine the grouping of the first input information of the first AI model according to the time window.

32. The device according to claim 31, characterized in that, If the first input information is among the input information corresponding to at least one CSI report and the time-domain position of the at least one CSI report is within the time window, then The input information corresponding to the at least one CSI report belongs to the same group.

33. The device according to claim 31, characterized in that, If the first input information is among the input information corresponding to at least one measurement resource and the time-domain position of the at least one measurement resource is within the time window or the time-domain position of the CSI report associated with the at least one measurement resource is within the time window, then The input information corresponding to the at least one measurement resource belongs to the same group.

34. The device according to any one of claims 31 to 33, characterized in that, The configuration information includes at least one of length information, start information, or period information; The length information is used to configure the length of the time window; The start information is used to configure the start position of the time window; The period information is used to configure the period of the time window.

35. The device according to any one of claims 26 - 30, characterized in that, In the determination of the grouping of the first input information of the first AI model, the determination unit is configured to: Receive indication information for indicating the grouping of the first input information of the first AI model; Determine the grouping of the first input information according to the indication information.

36. The device according to any one of claims 31-35, characterized in that, It further includes a sending unit; The sending unit is configured to send first position information for indicating the position of the first input information in the group or the position of the first processing information in the group.

37. The device according to any one of claims 26 - 30, characterized in that, In the determination of the CSI reporting of the first input information and / or the first processing information, the determination unit is configured to: If the first CSI report in which the first input information and / or the first processing information is located fails to be reported, send a second CSI report including the first input information and / or the first processing information; Or, If the first CSI report in which the first input information and / or the first processing information is located fails to be reported, send the first input information and / or the first processing information at an available time-domain position after the time-domain position of the first CSI report.

38. The device according to any one of claims 26-30, characterized in that, In the determination of the CSI reporting of the first input information and / or the first processing information, the determination unit is configured to: If the first CSI report in which the first input information and / or the first processing information is located fails to be reported, then a second CSI report is sent, and the second CSI report includes the first input information and / or the first processing information, as well as the second input information and / or the second processing information; The second processing information is the information obtained by inputting the second input information into the first AI model or the information obtained after further processing the information obtained by inputting the second input information into the first AI model; The first input information and the second input information are different input information.

39. The device according to claim 38, wherein The first input information and the second input information are in the same group or different groups; if the first input information and the second input information are in different groups, then the second input information is the first input information in the group.

40. The device according to any one of claims 37 - 39, characterized in that, It further includes a sending unit; The sending unit is used to send delay information, and the delay information is used to indicate that the first input information and / or the first processing information is a delayed report of the first CSI report.

41. The device according to any one of claims 26 - 30, characterized in that, In the CSI reporting for determining the first input information and / or the first processing information, the determining unit is used for: If the first CSI report in which the first input information and / or the first processing information is located fails to be reported, then the first input information and / or the first processing information is no longer sent, and a third CSI report is sent, and the third CSI report includes the third input information and / or the third processing information; The third processing information is the information obtained by inputting the third input information into the first AI model or the information obtained after further processing the information obtained by inputting the third input information into the first AI model; The first input information and the third input information are different input information.

42. The device according to claim 41, characterized in that, The first input information and the third input information are in different groups, and the third input information is the first input information in the group.

43. A communication device, characterized in that, It includes: A sending unit, which is used to send configuration information, and the configuration information is used to configure a time window, and the time window is used to determine the group of the first input information of the first AI model; or, it is used to send indication information, and the indication information is used to indicate the group of the first input information of the first AI model; The first AI model is used for channel state information (CSI) compression.

44. The device according to claim 43, wherein, The first AI model is used to perform CSI compression on the first input information and use the first historical information to perform CSI compression on non-first input information; The first historical information includes at least one of historical input information, historical processing information, or historical compression intermediate information. The historical processing information is the information obtained by inputting the historical input information into the first AI model or the information obtained after further processing the information obtained by inputting the historical input information into the first AI model. The historical compression intermediate information is the information generated by the first AI model during the process of compressing the historical input information.

45. The device according to claim 43, characterized in that, The historical input information within a group participates in the CSI compression of the non-first input information within the same group, and all the input information in a group does not participate in the CSI compression of any input information in other groups.

46. The device according to any one of claims 43 to 45, characterized in that, If the first input information is among the input information corresponding to at least one CSI report, and the time domain position of the at least one CSI report is within the time window, then the input information corresponding to the at least one CSI report belongs to the same group; or, If the first input information is among the input information corresponding to at least one measurement resource, and the time domain position of the at least one measurement resource is within the time window or the time domain position of the CSI report associated with the at least one measurement resource is within the time window, then the input information corresponding to the at least one measurement resource belongs to the same group.

47. The device according to any one of claims 43-46, characterized in that, The configuration information includes at least one of length information, start information, or period information; The length information is used to configure the length of the time window; The start information is used to configure the start position of the time window; The period information is used to configure the period of the time window.

48. A communication device, characterized in that, It includes a receiving unit, and the receiving unit is used for: If the first CSI report where the first input information and / or the first processing information of the first AI model are located fails to be reported, receive a second CSI report, the second CSI report includes the first input information and / or the first processing information, or the second CSI report includes the first input information and / or the first processing information and the second input information and / or the second processing information, and the first input information and the second input information are different input information; Or, If the first CSI report where the first input information and / or the first processing information of the first AI model are located fails to be reported, receive the first input information and / or the first processing information at an available time domain position after the time domain position of the first CSI report; Or, If the first CSI report where the first input information and / or the first processing information of the first AI model are located fails to be reported, receive a third CSI report, the third CSI report includes the third input information and / or the third processing information, and the first input information and the third input information are different input information; The first AI model is used for CSI compression, the first processing information is the information obtained by inputting the first input information into the first AI model or the information obtained by further processing the information obtained by inputting the first input information into the first AI model, the second processing information is the information obtained by inputting the second input information into the first AI model or the information obtained by further processing the information obtained by inputting the second input information into the first AI model, and the third processing information is the information obtained by inputting the third input information into the first AI model or the information obtained by further processing the information obtained by inputting the third input information into the first AI model.

49. The device according to claim 48, characterized in that, The first input information and the second input information are in the same group or different groups; if the first input information and the second input information are in different groups, then the second input information is the first input information in the group; Or, The first input information and the third input information are in different groups, and the third input information is the first input information in the group.

50. The device according to claim 48 or 49, characterized in that, Further included: Receiving postponement information, where the postponement information is used to indicate that the first input information and / or the first processing information is a postponed report of the first CSI report.

51. A terminal device, comprising a processor, a memory, and a computer program or instruction stored on the memory, characterized in that, The processor executes the computer program or instruction to implement the steps of the method according to any one of claims 1-17.

52. A network device, comprising a processor, a memory, and a computer program or instruction stored on the memory, characterized in that, The processor executes the computer program or instruction to implement the steps of the method according to any one of claims 18-22 or 23-25.

53. A chip, comprising a processor and a communication interface, characterized in that, The processor executes the steps of the method according to any one of claims 1-25 through the communication interface.

54. A computer-readable storage medium, characterized in that, It stores a computer program or instruction, and when the computer program or instruction is executed, the steps of the method according to any one of claims 1-25 are executed.

Images