COMMUNICATION METHOD, APPARATUS, AND SYSTEM

Abstract

A communication method, apparatus, and system are provided, which are applicable to the field of communication technology. The method includes the steps of: a second device transmitting instruction information to a first device, the instruction information indicating a manner of determining transmission parameters of a first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of a second transmission, the determining manner including an artificial intelligence (AI)-based determination manner or a non-AI-based determination manner; and a step of the second device determining performance corresponding to the manner of determining transmission parameters of the first transmission based on the instruction information and at least one transmission from the second device, the at least one transmission including the first transmission and / or the second transmission. According to the above method, the performance of the artificial intelligence can be monitored.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to Chinese Patent Application No. 202310156244.8, entitled "Communication Method and Apparatus," filed with the State Intellectual Property Office of the People's Republic of China on February 16, 2023, which is incorporated herein by reference in its entirety.

[0002] The present application relates to the field of communications technology, and more particularly to communications methods, devices, and systems. [Background technology]

[0003] In wireless communication networks, e.g., mobile communication networks, the services supported by the network are becoming increasingly diverse, and therefore the requirements that need to be met are also becoming increasingly diverse. For example, networks need to be able to support ultra-high data rates, ultra-low latency, and / or massive connectivity. These characteristics make network planning, network configuration, and / or resource scheduling even more complex. These new requirements, new scenarios, and new features pose unprecedented challenges to network planning, maintenance, and efficient operation. To address these challenges, artificial intelligence techniques can be introduced into wireless communication networks to achieve network intelligence. For example, one specific application of introducing artificial intelligence techniques into wireless communication networks is using artificial intelligence (AI) models for channel state information (CSI) feedback.

[0004] In the context of introducing artificial intelligence into wireless communication networks, model monitoring is required to monitor the performance of AI models. How to effectively implement artificial intelligence in networks, including how to monitor the performance of artificial intelligence, is currently a topic worthy of consideration. Summary of the Invention [Means for solving the problem]

[0005] The present application provides a communication method, apparatus, and system for monitoring the performance of artificial intelligence.

[0006] According to a first aspect, a communication method is provided, which is applied to a first device. In the case of downlink transmission, the first device is a terminal side device, and the second device is a network side device. In the case of uplink transmission, the first device is a network side device, and the second device is a terminal side device. The terminal side device in this application may be a terminal device, or a chip, unit, or module within a terminal device. Alternatively, the terminal side device may be a communication device having a terminal device function, or a chip, unit, or module within a communication device having a terminal device function. The network side device in this application may be a network device, or a chip, unit, or module within a network device. Alternatively, the network side device may be a communication device having a network device function, or a chip, unit, or module within a communication device having a network device function.

[0007] The method includes a step of: a first device receiving instruction information from a second device, the instruction information indicating a manner of determining transmission parameters of a first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of a second transmission, the determining manner including an AI-based determination manner or a non-AI-based determination manner. The first device determines performance corresponding to the manner of determining transmission parameters of the first transmission based on the instruction information and at least one transmission from the second device, the at least one transmission including the first transmission and / or the second transmission.

[0008] The second device transmits a method for determining transmission parameters of the first transmission to the first device by using the instruction information, so that the first device can know the method for determining transmission parameters of the first transmission and further determine the performance corresponding to the determination method based on the reception status of the transmission, thereby performing model monitoring. Based on the model monitoring result, relevant measures can be taken to improve system performance. A CSI feedback scenario is used as an example. After obtaining the model monitoring result based on the above procedure, the first device may compare the performance corresponding to the AI-based CSI feedback method with the performance corresponding to the non-AI-based CSI feedback method to monitor the AI ​​model. For example, the performance corresponding to the AI ​​model-based CSI feedback method is compared with the performance corresponding to the non-AI-based CSI feedback method. If the performance corresponding to the AI ​​model-based CSI feedback method is better, this indicates that the performance of the AI ​​model meets the requirements. Otherwise, this indicates that the performance of the AI ​​model does not meet the requirements, and an operation such as switching the CSI feedback method or replacing or updating the AI ​​model may be performed.

[0009] In a possible implementation, the transmission parameters include one or more of precoding, beams, modulation and coding scheme (MCS), amount of transport streams, and resource allocation.

[0010] In a possible implementation, the manner of determining the transmission parameters of the first transmission is different from the manner of determining the transmission parameters of the second transmission, i.e., for multiple transmissions having an association relationship, the manners of determining the transmission parameters of the multiple transmissions are different.

[0011] In a possible implementation, the AI-based judgment method includes at least a first AI model-based judgment method and a second AI model-based judgment method. In this implementation, the AI-based judgment method may be further subdivided into judgment methods based on different AI models, so that more sophisticated model monitoring can be implemented.

[0012] Optionally, the functionality of the first AI model is the same as the functionality of the second AI model. For example, both the first AI model and the second AI model are used to determine CSI feedback information. In another example, both the first AI model and the second AI model are used to perform beam prediction. The structures of the first AI model and the second AI model are different. For example, the depth (number of layers) and / or width (number of neurons) of the neural network are different. Alternatively, the coefficients of the first AI model and the second AI model are different. Alternatively, the structures and coefficients of the first AI model and the second AI model are different.

[0013] In a possible implementation, the AI-based decision scheme includes one of an AI-based CSI feedback scheme, an AI-based CSI compression scheme, an AI-based CSI reconstruction scheme, an AI-based CSI prediction scheme, and an AI-based beam prediction scheme. The non-AI-based decision scheme includes one of a non-AI-based CSI feedback scheme, a non-AI-based CSI compression scheme, a non-AI-based CSI reconstruction scheme, a non-AI-based CSI prediction scheme, and a non-AI-based beam prediction scheme.

[0014] In a possible implementation, the first transmission includes one transmission, multiple transmissions, or transmissions within a first period. In this manner, a determination manner of transmission parameters for the multiple transmissions can be indicated by using the indication information.

[0015] Optionally, if the first transmission includes multiple transmissions, the indication indicates a manner of determining transmission parameters of each of the multiple transmissions.

[0016] In a possible implementation, receiving the indication information from the second device includes receiving downlink control information from the second device, where the downlink control information indicates a manner of determining transmission parameters for a first transmission, and the first transmission is a transmission scheduled by using the downlink control information, or receiving higher layer signaling from the second device, where the higher layer signaling indicates a manner of determining transmission parameters for the first transmission.

[0017] In a possible implementation, the instruction information indicates a first transmission pattern including a first determination scheme corresponding to N transmissions, the N transmissions including a first transmission, the first determination scheme being a scheme for determining transmission parameters of the first transmission, and N being a positive integer.

[0018] The N transmissions may include N1 transmissions and N2 transmissions. If N1 is greater than 1, the N1 transmissions may be N1 consecutive transmissions. If N2 is greater than 1, the N2 transmissions may be N2 consecutive transmissions. The first transmission pattern may indicate only the transmission amount of the N1 transmissions or may indicate a first determination method corresponding to the transmission amount. Similarly, the first transmission pattern may indicate only the transmission amount of the N2 transmissions or may indicate a second determination method corresponding to the transmission amount. In this way, when the first transmission pattern is transmitted by using the first indication information, signaling overhead can be reduced. N, N1, and N2 are all positive integers.

[0019] In a possible implementation, the instruction information indicates a second transmission pattern including a first determination method corresponding to a transmission within a first period, the transmission within the first period including a first transmission, and the first determination method being a method for determining a transmission parameter of the first transmission.

[0020] The first period may include one or more transmissions. When the first period includes multiple transmissions, the second transmission pattern may indicate a corresponding determination scheme for only the first period, so that signaling overhead can be reduced when the second transmission pattern is transmitted by using the first indication information.

[0021] In a possible implementation, the instruction information includes index information of a method for determining the transmission parameters of the first transmission, or the instruction information includes type information of the first transmission, and the method for determining the transmission parameters of the first transmission corresponds to the type of the first transmission.

[0022] Optionally, type division may be performed on the transmission in terms of whether the transmission is used for model monitoring and whether the transmission parameters are determined based on an AI model, so that the type of the transmission can correspond to the manner of determination of the transmission parameters of the transmission.

[0023] In a possible implementation, the indication information includes indication information for the first transmission and indication information for the second transmission, or the indication information indicates the transmission time points of the first transmission and the second transmission.

[0024] In a possible implementation, the indication information for the first transmission includes an index of the first transmission and / or time-frequency resource indication information for the first transmission, and the indication information for the second transmission includes an index of the second transmission and / or time-frequency resource indication information for the second transmission.

[0025] In a possible implementation, determining a performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information and the at least one transmission from the second device includes determining a performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information from the second device and the at least one transmission within each period after the indication information is received. Since the indication information may be periodic, signaling overhead can be reduced.

[0026] Optionally, the instruction information may further indicate one or more of a start time of a period, an end time of a period, or a duration of a period. It will be understood that one or more of a start time of a period, an end time of a period, or a duration of a period that is not indicated may be predefined, for example, protocol predefined, or may be obtained based on the indicated information and / or predefined information.

[0027] In a possible implementation, the method further includes transmitting first information to the second device, where the first information includes performance or the first information indicates one or more of the following: performance of at least one determination scheme among the plurality of determination schemes, a determination scheme corresponding to optimal performance among the performances corresponding to the plurality of determination schemes, a determination scheme corresponding to performance higher than a threshold among the performances corresponding to the plurality of determination schemes, a determination scheme corresponding to performance lower than a threshold among the performances corresponding to the plurality of determination schemes, and a determination scheme recommended by the terminal device among the performances corresponding to the plurality of determination schemes. The plurality of determination schemes includes a scheme for determining transmission parameters of each of the at least one transmission sent by the second device.

[0028] Optionally, the performance includes one or more of the following: throughput, spectral efficiency, transmission rate, block error rate (BLER), expected BLER, hybrid automatic repeat request (HARQ) acknowledgment / negative acknowledgment (ACK / NACK), and signal to interference plus noise ratio (SINR), and reference signal received power (RSRP).

[0029] According to a second aspect, a communication method is provided, which is applied to a second device. In the case of downlink transmission, the first device is a terminal side device, and the second device is a network side device. In the case of uplink transmission, the first device is a network side device, and the second device is a terminal side device. The terminal side device in this application may be a terminal device, or a chip, unit, or module within a terminal device. Alternatively, the terminal side device may be a communication device having a terminal device function, or a chip, unit, or module within a communication device having a terminal device function. The network side device in this application may be a network device, or a chip, unit, or module within a network device. Alternatively, the network side device may be a communication device having a network device function, or a chip, unit, or module within a communication device having a network device function.

[0030] The method includes a step of: the second device sending instruction information to the first device, the instruction information indicating a manner of determining transmission parameters of the first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of the second transmission, the determining manner including an AI-based determination manner or a non-AI-based determination manner. The second device sends at least one transmission to the first device, the at least one transmission including the first transmission and / or the second transmission.

[0031] In a possible implementation, the AI-based decision-making scheme includes at least a first AI model-based decision-making scheme and a second AI model-based decision-making scheme.

[0032] In a possible implementation, the AI-based decision scheme includes one of an AI-based CSI feedback scheme, an AI-based CSI compression scheme, an AI-based CSI reconstruction scheme, an AI-based CSI prediction scheme, and an AI-based beam prediction scheme. The non-AI-based decision scheme includes one of a non-AI-based CSI feedback scheme, a non-AI-based CSI compression scheme, a non-AI-based CSI reconstruction scheme, a non-AI-based CSI prediction scheme, and a non-AI-based beam prediction scheme.

[0033] In possible implementations, the first transmission includes one transmission, multiple transmissions, or transmissions within a first period of time.

[0034] In a possible implementation, the step of sending the indication information to the first device includes a step of sending downlink control information to the first device, where the downlink control information indicates a manner of determining transmission parameters of the first transmission, and the first transmission is a transmission scheduled by using the downlink control information, or a step of sending upper layer signaling to the first device, where the upper layer signaling indicates a manner of determining transmission parameters of the first transmission.

[0035] In a possible implementation, the instruction information indicates a first transmission pattern including a first determination scheme corresponding to N transmissions, where the N transmissions include the first transmission and the first determination scheme is a scheme for determining transmission parameters of the first transmission, where N is a positive integer, or the instruction information indicates a second transmission pattern including a first determination scheme corresponding to transmissions within a first period, where the transmissions within the first period include the first transmission and the first determination scheme is a scheme for determining transmission parameters of the first transmission.

[0036] In a possible implementation, the instruction information includes index information of a method for determining the transmission parameters of the first transmission, or the instruction information includes type information of the first transmission, and the method for determining the transmission parameters of the first transmission corresponds to the type of the first transmission.

[0037] In a possible implementation, the indication information includes indication information for the first transmission and indication information for the second transmission, or the indication information indicates the transmission time points of the first transmission and the second transmission.

[0038] In a possible implementation, the indication information for the first transmission includes an index of the first transmission and / or time-frequency resource indication information for the first transmission, and the indication information for the second transmission includes an index of the second transmission and / or time-frequency resource indication information for the second transmission.

[0039] In a possible implementation, after the step of sending at least one transmission to the first device, the method further includes a step of receiving first information from the first device, the first information including a performance corresponding to a manner of determining transmission parameters of the first transmission and determined by the first device based on the instruction information and the at least one transmission sent by the second device, or the first information indicates one or more of the following: a performance of at least one determination method among the plurality of determination methods; a determination method corresponding to optimal performance among the performances corresponding to the plurality of determination methods; a determination method corresponding to performance higher than a threshold among the performances corresponding to the plurality of determination methods; a determination method corresponding to performance lower than a threshold among the performances corresponding to the plurality of determination methods; and a determination method recommended by the terminal device among the performances corresponding to the plurality of determination methods, wherein the plurality of determination methods include a method of determining transmission parameters of each of the at least one transmission sent by the second device.

[0040] In a possible implementation, the first device is a terminal device, the second device is a network device, and the first transmission is a downlink transmission, or the first device is a network device, the second device is a terminal device, and the first transmission is an uplink transmission.

[0041] According to a third aspect, a communication device is provided. The communication device may perform the functions performed by the first device in the first aspect. The communication device includes a processing unit and a transceiver unit. The transceiver unit is configured to receive instruction information from a second device, the instruction information indicating a manner of determining transmission parameters for a first transmission, or the instruction information indicating that the manner of determining transmission parameters for the first transmission is the same as the manner of determining transmission parameters for a second transmission, the determining manner including an AI-based determination manner or a non-AI-based determination manner. The processing unit is configured to determine performance corresponding to the manner of determining transmission parameters for the first transmission based on the instruction information and at least one transmission from the second device, the at least one transmission including the first transmission and / or the second transmission.

[0042] According to a fourth aspect, a communication device is provided. The communication device may perform the functions performed by the second device in the second aspect. The communication device includes a processing unit and a transceiver unit. The processing unit is configured to: send instruction information to the first device by using the transceiver unit, the instruction information indicating a manner of determining transmission parameters for a first transmission, or the instruction information indicating that the manner of determining transmission parameters for the first transmission is the same as a manner of determining transmission parameters for a second transmission, the determining manner including an AI-based determination manner or a non-AI-based determination manner; and send at least one transmission to the first device by using the transceiver unit, the at least one transmission including the first transmission and / or the second transmission.

[0043] According to a fifth aspect, there is provided a communications device including one or more processors and one or more memories, the one or more memories storing one or more computer programs, the programs, when executed by the one or more processors, causing the communications device to perform a method according to any one of the first aspect or any one of the second aspect.

[0044] According to a sixth aspect, a communication method is provided. The communication method includes a step of: a second device transmitting instruction information to a first device, the instruction information indicating a manner of determining transmission parameters of a first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as a manner of determining transmission parameters of a second transmission. The second device transmits at least one transmission to the first device, the at least one transmission including the first transmission and / or the second transmission. The first device determines performance corresponding to the manner of determining transmission parameters of the first transmission based on the instruction information and the at least one transmission from the second device.

[0045] In the case of downlink transmission, the first device is a terminal side device and the second device is a network side device. In the case of uplink transmission, the first device is a network side device and the second device is a terminal side device. The terminal side device in this application may be a terminal device, or a chip, unit, or module within a terminal device. Alternatively, the terminal side device may be a communication device having a terminal device function, or a chip, unit, or module within a communication device having a terminal device function. The network side device in this application may be a network device, or a chip, unit, or module within a network device. Alternatively, the network side device may be a communication device having a network device function, or a chip, unit, or module within a communication device having a network device function.

[0046] According to a seventh aspect, there is provided a communication system, the system including: a first device configured to perform a method according to any one of the first aspects; and a second device configured to perform a method according to any one of the second aspects.

[0047] According to an eighth aspect, there is provided a chip system, the chip system including at least one chip and a memory, wherein the at least one chip is configured to read and execute a program stored in the memory to perform the method according to any one of the first aspect or the method according to any one of the second aspect.

[0048] According to a ninth aspect, there is provided a readable storage medium, the readable storage medium including a program, which, when executed on an apparatus, causes the apparatus to perform a method according to any one of the first aspect or any one of the second aspect.

[0049] According to a tenth aspect, there is provided a program product, the program product when running on an apparatus causing the apparatus to perform a method according to any one of the first aspect or any one of the second aspect.

[0050] For the effects of the solutions provided in any one of the second to tenth aspects, please refer to the corresponding description of the first aspect. [Brief explanation of the drawings]

[0051] [Figure 1] 1 is a diagram of the architecture of a communication system to which an embodiment of the present application applies; [Figure 2] FIG. 1 is a diagram of a neuron structure according to an embodiment of the present application. [Figure 3] FIG. 2 is a diagram of layer relationships of a neural network according to an embodiment of the present application. [Figure 4] FIG. 1 is a diagram of an AI application framework according to an embodiment of the present application. [Figure 5a] FIG. 2 is a diagram of the structure of another communication system to which an embodiment of the present application is applied; [Figure 5b] FIG. 2 is a diagram of the structure of another communication system to which an embodiment of the present application is applied; [Figure 6] FIG. 1 is a diagram of a CSI feedback framework according to an embodiment of the present application. [Figure 7] 1 is a schematic flowchart of a communication method according to an embodiment of the present application; [Figure 8a] FIG. 2 is a diagram of a downlink transmission pattern according to an embodiment of the present application. [Figure 8b] FIG. 10 is a diagram of another downlink transmission pattern according to an embodiment of the present application. [Figure 9a] FIG. 10 is a diagram illustrating the validity time of the indication information according to an embodiment of the present application. [Figure 9b] FIG. 10 is another diagram of the validity time of the instruction information according to an embodiment of the present application. [Figure 9c] FIG. 10 is another diagram of the validity time of the instruction information according to an embodiment of the present application. [Figure 10] 4 is a schematic flowchart of another communication method according to an embodiment of the present application; [Figure 11] 1 is a schematic flowchart of a communication method in a CSI feedback scenario according to an embodiment of the present application; [Figure 12] 1 is a schematic flowchart of a communication method in a CSI prediction scenario according to an embodiment of the present application; [Figure 13] 1 is a schematic flowchart of a communication method in a beam prediction scenario according to an embodiment of the present application; [Figure 14] 1 is a diagram of a communication device according to an embodiment of the present application; [Figure 15] FIG. 1 is a diagram of another communication device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0052] To make the objectives, technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings.

[0053] In the following description of the present application, "at least one part (item)" refers to one part (item) or multiple parts (items). "Multiple (items)" refers to two (items) or more than two (items). The term "and / or" describes an association relationship for describing related objects and indicates that three relationships may exist. For example, A and / or B can represent the following three cases: when only A is present, when both A and B are present, and when only B is present. The character " / " generally indicates an "or" relationship between related objects. Furthermore, although terms such as "first," "second," etc. may be used to describe objects in the present application, it should be understood that these objects are not limited by these terms. These terms are used merely to distinguish objects from one another.

[0054] The terms "comprise," "have," and any other variations thereof referred to in the description of this application are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device comprising a series of steps or units is not limited to the listed steps or units, but may further optionally include other unlisted steps or units, or may further optionally include other inherent steps or units of the process, method, product, or device. It should be noted that in this application, terms such as "example" or "for example" are used to denote providing an example, illustration, or explanation. A method or design solution described in this application as an "example" or "for example" should not be described as preferred or advantageous over another method or design solution. Rather, terms such as "example" or "for example" are intended to present the relevant concept in a particular manner.

[0055] The technical solutions provided in the present application may be used in various communication systems, for example, fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems such as sixth generation (6G) mobile communication systems, or integrated systems of multiple systems. The technical solutions provided in the present application may further be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine type communication (MTC), internet of things (IoT) communication systems, or other communication systems.

[0056] A network element in a communication system can transmit a signal to or receive a signal from another network element. The signal may include information, signaling, data, etc. Alternatively, the network element may be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. In this application, a network element is used as an example for explanation. For example, a communication system may include at least one terminal device and at least one network device. The network device may transmit a downlink signal to the terminal device, and / or the terminal device may transmit an uplink signal to the network device. It will be understood that the terminal device in this application may be replaced by a first network element, and the network device may be replaced by a second network element, and the terminal device and the network device perform the corresponding communication method in this application.

[0057] FIG. 1 is an architecture diagram of a communication system 1000 to which an embodiment of the present application is applied. As shown in FIG. 1, the communication system includes a radio access network 100 and a core network 200. Optionally, the communication system 1000 may further include the Internet 300. The radio access network 100 may include at least one radio access network device (e.g., 110a and 110b in FIG. 1) and may further include at least one terminal (e.g., 120a to 120j in FIG. 1). The terminal is connected to the radio access network device in a wireless manner, and the radio access network device is connected to the core network in a wireless or wired manner. The core network device and the radio access network device may be separate and distinct physical devices, or the functions of the core network device and the logical functions of the radio access network device may be integrated into the same physical device, or some functions of the core network device and some functions of the radio access network device may be integrated into one physical device. A wired or wireless method may be used for the connection between the terminal and the radio access network device. FIG. 1 is merely an exemplary diagram. The communication system may further include other network devices, for example, wireless relay devices and wireless backhaul devices not shown in FIG.

[0058] The radio access network device may be a base station (BS), an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a fifth generation (5G) mobile communication system, a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, an access node in a Wi-Fi system, etc., or may be a module or unit that completes part of the functions of a base station, such as a central unit (CU) or a distributed unit (DU). The CU in this specification completes the functions of the radio resource control protocol and packet data convergence protocol (PDCP) of a base station and may further complete the functions of a service data adaptation protocol (SDAP). The DU completes the functions of the radio link control layer and medium access control (MAC) layer of a base station and may further complete some or all of the functions of the physical layer. For a specific description of the aforementioned protocol layers, please refer to the relevant technical specifications of the 3rd generation partnership project (3GPP). A base station including a CU and a DU may also be referred to as a base station with a separated CU and DU. For example, a base station includes a gNB-CU and a gNB-DU. The CU may be further separated into a CU control plane (CU-CP) and a CU user plane (CU-CP). For example, a base station includes a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.The radio access network device may be a macro base station (such as 110a in FIG. 1), or may be a micro base station or an indoor base station (such as 110b in FIG. 1), or may be a relay node, a donor node, or the like. The specific technology and the specific device form used by the radio access network device are not limited in the embodiments of the present application. For ease of explanation, the following description will be given using an example in which the network device is a radio access network device.

[0059] A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc., and may be a device with wireless transceiver functionality. The terminal may be an indoor device, an outdoor device, a handheld device, a wearable device, or a computing device and / or an in-vehicle device, deployed on land, on water (e.g., on a ship), or in the air (e.g., on an airplane, balloon, or satellite). The terminal may be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communications, machine-type communications (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, and smart city. For example, the terminal may be a mobile phone, a tablet computer, or a computer with wireless transceiver functionality. Alternatively, the terminal device may be a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, an industrial control wireless terminal, an autonomous driving wireless terminal, a remote medical care wireless terminal, a smart grid wireless terminal, a smart city wireless terminal, a smart home wireless terminal, etc. The specific technology and the specific device form used for the terminal are not limited to the embodiments of the present application.

[0060] The network devices and terminals may be in fixed locations or may be mobile. The network devices and terminals may be deployed on land, on the water surface, or on aircraft, balloons, and satellites, including indoor devices, outdoor devices, handheld devices, or vehicle-mounted devices. The application scenarios of the network devices and terminals are not limited in the embodiments of the present application.

[0061] The roles of network device and terminal may be relative. For example, helicopter or unmanned aerial vehicle 120i in FIG. 1 may be configured as a mobile network device. In the case of terminal 120j accessing wireless access network 100 via 120i, unmanned aerial vehicle 120i is a network device. However, in network device 110a, 120i is a terminal, i.e., 110a and 120i communicate with each other according to a wireless air interface protocol. Of course, 110a and 120i may alternatively communicate with each other according to an interface protocol between network devices. In this case, 120i is also a network device, compared to 110a. Therefore, both network devices and terminals may be collectively referred to as communication devices. 110a and 110b in FIG. 1 may be referred to as communication devices having the functionality of network devices, and 120a to 120j in FIG. 1 may be referred to as communication devices having the functionality of terminals.

[0062] The network devices and / or terminal devices may be deployed on land, water, or on aircraft, balloons, and airborne satellites, including indoor devices, outdoor devices, handheld devices, or vehicle-mounted devices. The scenarios in which the network devices and terminal devices are deployed are not limited in the embodiments of the present application. In addition, each of the terminal devices and network devices may be a hardware device, a software function running on dedicated hardware, a software function running on general-purpose hardware, for example, a virtualization function instantiated on a platform (e.g., a cloud platform), or an entity including dedicated or general-purpose hardware devices and software functions. The specific forms of the terminal devices and network devices are not limited in the present application.

[0063] Communications between network devices and terminals, between network devices, or between terminals may be performed over licensed spectrum, unlicensed spectrum, or both licensed and unlicensed spectrum. Communications may be performed over a spectrum below 6 gigahertz (GHz), or over a spectrum above 6 GHz. Alternatively, communications may be performed over both a spectrum below 6 GHz and a spectrum above 6 GHz. Spectral resources for wireless communications are not limited in the embodiments of the present application.

[0064] In an embodiment of the present application, the functions of a network device may alternatively be performed by a module (e.g., a chip) within the network device, or may be performed by a control subsystem including the functions of the network device. The control subsystem including the functions of the network device may be a control center in the above-mentioned application scenarios such as smart grid, industrial control, intelligent transportation, and smart city. The functions of a terminal may be performed by a module (e.g., a chip or modem) within the terminal, or may be performed by a device including the functions of the terminal.

[0065] In an embodiment of the present application, a network device transmits a downlink signal or downlink information to a terminal. The downlink information is carried on a downlink channel. The terminal transmits an uplink signal or uplink information to a base station. The uplink information is carried on an uplink channel. To communicate with a base station, the terminal needs to establish a wireless connection to a cell controlled by the base station. The cell that establishes a wireless connection to the terminal is called the serving cell of the terminal. When communicating with the serving cell, the terminal is further interfered with by signals from neighboring cells.

[0066] In the embodiments of the present application, the time-domain symbols may be orthogonal frequency division multiplexing (OFDM) symbols or Discrete Fourier transform-spread-OFDM (DFT-s-OFDM) symbols. Unless otherwise specified, the symbols in the embodiments of the present application are time-domain symbols.

[0067] It should be understood that the number and types of devices in the communication system shown in Figure 1 are used as an example only, and the present application is not limited thereto. In actual applications, the communication system may further include more terminal devices and more access network devices, or may further include other network elements, such as core network devices, network managers, and / or network elements configured to implement artificial intelligence functions.

[0068] The method provided in this application relates to AI. For ease of understanding, the following describes some terms of AI in this application. It will be understood that the description is not intended to limit the present application.

[0069] (1) Artificial Intelligence and Machine Learning Artificial intelligence (AI) refers to intelligence exhibited by machines created by humans. In general, AI is a technology that exhibits human intelligence through the use of conventional computer programs. AI may be defined as a machine or computer that mimics humans and possesses cognitive functions associated with human thinking, such as learning and problem-solving. AI can learn from past experiences, make rational decisions, and respond quickly. The goal of AI is to understand intelligence through symbolic reasoning, or by building computer programs for reasoning.

[0070] Machine learning is a method for achieving artificial intelligence, that is, solving problems in artificial intelligence by using machine learning as a tool. Machine learning theory is primarily concerned with designing and analyzing several algorithms that allow computers to automatically "learn." Machine learning algorithms are algorithms that automatically analyze data to obtain rules and then use those rules to predict unknown data. Because learning algorithms involve a large amount of statistical theory, machine learning is closely related to inferential statistics and is also called statistical learning theory.

[0071] (2) AI models and neural networks An AI model is a specific implementation of an AI technology function. An AI model describes the mapping relationship between the model's inputs and outputs. The type of AI model may be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or another machine learning (ML) model.

[0072] A neural network (NN) is a specific embodiment of AI or machine learning technology. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, giving it the ability to learn any mapping. Therefore, neural networks can accurately perform abstract modeling of complex, high-dimensional problems.

[0073] The concept of neural networks comes from the neuron structure of the brain. For example, each neuron performs a weighted sum operation on its input values ​​and outputs the weighted sum result as the operation result by using an activation function. Figure 2 shows the neuron structure. The input of a neuron is x=[x0,x1,...,x n ], and the weights corresponding to the inputs are w=[w0,w1,...,w n ] and w i is x i is used as the weight of x i Assume that the activation function is used to weight the inputs. The offset to perform a weighted sum on the inputs based on the weights is, for example, b. There can be multiple forms of activation functions. The activation function for a neuron is y=f(c)=max(0,c) (1) It is assumed that

[0074] The output of the neuron is

number

[0075] In another example, the activation function of a neuron is y=f(c)=c (3) is.

[0076] The output of the neuron is

number

[0077] where b, w i , and x i may have a variety of possible values, such as a decimal number, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network may be the same or different.

[0078] A neural network typically includes multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve the representation capability of the neural network and provide more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network may be the number of layers included in the neural network, and the number of neurons included in each layer may be referred to as the layer width. In one implementation, a neural network includes an input layer and an output layer. The input layer of a neural network performs neuronal processing on received input information and forwards the processing results to the output layer. The output layer obtains the output result of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. See FIG. 3. The input layer of a neural network performs neuronal processing on received input information and forwards the processing results to an intermediate hidden layer. The hidden layer performs calculations on the received processing results and obtains the calculation results. The hidden layer forwards the calculation results to the output layer or an adjacent hidden layer. Finally, the output layer obtains the output result of the neural network. A neural network may include one hidden layer or multiple hidden layers connected in series, but is not limited to this.

[0079] A loss function may be defined in the training process of an AI model (e.g., a neural network). The loss function describes the gap or difference between the output value of the AI ​​model and an ideal target value. The specific form of the loss function is not limited in the embodiments of the present application. The training process of the AI ​​model is a process in which model parameters of the AI ​​model are adjusted so that the value of the loss function is less than a threshold or so that the value of the loss function meets a target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the AI ​​model includes adjusting at least one of the number and width of layers of the neural network, the weights of neurons, or parameters of activation functions of neurons.

[0080] The inference data may be used as an input to a trained AI model and used for inference by the AI ​​model. During model inference, the inference data is input to the AI ​​model to obtain a corresponding output, i.e., an inference result.

[0081] (3) AI model design AI model design mainly includes a data collection phase (e.g., collecting training data and / or inference data), a model training phase, and a model inference phase, and may further include an inference result application phase. Figure 4 shows an AI application framework. In the data collection phase, a data source is used to provide a training dataset and inference data. In the model training phase, the training data provided by the data source is analyzed or trained to obtain an AI model. Obtaining an AI model by learning using a model training node is equivalent to obtaining a mapping relationship between the model's input and output by learning using the training data. In the model inference phase, the AI ​​model obtained by training in the model training phase is used to perform inference based on the inference data provided by the data source and obtain an inference result. This phase can also be understood as follows: inference data is input to the AI ​​model to obtain an output by using the AI ​​model. The output is the inference result. The inference result may indicate the configuration parameters used (executed) by the actor object and / or the operation performed by the actor object. The inference result is published in the inference result application phase. For example, the inference result may be planned by the same actor entity. For example, the actor entity may send the inference results to one or more actor objects (e.g., a core network device, an access network device, a terminal device, or a network manager) for execution. As another example, the actor entity may further feed back the model performance to a data source to facilitate subsequent model updates and training.

[0082] It will be understood that the communication system may include network elements having artificial intelligence capabilities. The aforementioned steps related to AI model design may be performed by one or more network elements having artificial intelligence capabilities. In a possible design, an AI function (e.g., an AI module or AI entity) may be configured in an existing network element in the communication system to perform AI-related operations, such as AI model training and / or inference. For example, the existing network element may be an access network device, a terminal device, a core network device, a network management system, etc. In another possible design, an independent network element may be introduced into the communication system to perform AI-related operations, such as AI model training. The independent network element may be referred to as an AI entity, an AI node, etc. The name is not limited in this application. The AI ​​entity may be directly connected to an access network device in the communication system or indirectly connected to the access network device through a third-party network element. The third-party network element may be a network element of a core network, such as an authentication management function (AMF) network element or a user plane function (UPF) network element, a network manager, a cloud server, or another network element. This is not limited thereto. For example, the independent AI network element may be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, the independent AI network element may be deployed on a cloud-side server.

[0083] 5a shows a communication system including an access network device 110, a terminal device 120, and a terminal device 130. The terminal devices 120 and 130 may access and communicate with the access network device 110. An AI function (e.g., a CSI reconstructor) may be configured in the access network device 110, and an AI function (e.g., a CSI generator) may also be configured in the terminal device 130 and the terminal device 120.

[0084] 5b shows another communication system. The communication system includes an access network device 210, a terminal device 220, and a terminal device 230, and further includes an AI entity 240. The terminal device 220 and the terminal device 230 may access and communicate with the access network device 210. The access network device 210 may forward data related to AI models and reported by the terminal device 220 and the terminal device 230 to the AI ​​entity 240. The AI ​​entity 240 performs AI-related operations, such as training dataset construction and model training, and forwards outputs of the AI-related operations, such as trained neural network models, model evaluation, and test results, to the terminal devices via the access network device 210.

[0085] Some embodiments of the present application relate to CSI feedback techniques. In the aforementioned communication systems, such as LTE or NR systems, an access network device needs to obtain CSI of a channel. For example, CSI of a downlink channel is used. Based on the CSI, the access network device may determine configurations such as resources, modulation and coding scheme (MCS), and precoding for scheduling a downlink data channel of a terminal device. It should be understood that CSI is channel information that can reflect channel characteristics and channel quality. The channel information may also be referred to as a channel response. For example, the CSI may be represented by a channel matrix, e.g., the CSI may include a channel matrix, or the CSI may include a channel eigenvector. In a frequency division duplex (FDD) communication scenario, the uplink channel and the downlink channel do not have reciprocity or the reciprocity between the uplink channel and the downlink channel cannot be guaranteed, so the access network device usually transmits a downlink reference signal to the terminal device. The terminal device performs channel measurement and interference measurement based on the received downlink reference signal to estimate downlink channel information. The downlink channel information includes CSI, which is then fed back to the access network device.

[0086] In a conventional CSI feedback scheme, a terminal device may generate a CSI report based on the estimated CSI in a predefined manner or a manner configured by the access network device, and feed the CSI report back to the access network device. The downlink reference signal includes a channel state information-reference signal (CSI-RS) or a synchronizing signal / physical broadcast channel block (SSB). The CSI report includes feedback quantities, such as a rank indicator (RI), a channel quality indicator (CQI), and a precoding matrix indicator (PMI). The RI indicates the number of downlink transport layers recommended by the terminal device, the CQI indicates the modulation and coding scheme that can be supported by the current channel conditions determined by the terminal device, and the PMI indicates the precoding recommended by the terminal device. The number of precoding layers indicated by the PMI corresponds to the RI.

[0087] AI is introduced into wireless communication networks, and an AI-based CSI feedback scheme is generated. As shown in FIG. 6, a CSI generator is deployed in a terminal device, and the CSI generator has compression and quantization functions. A CSI reconstructor is deployed on an access network device, and the CSI reconstructor has inverse quantization and decompression functions. Both the CSI generator and the CSI reconstructor are AI models. The CSI of measured and estimated downlink channel information is referred to as original CSI. The terminal device compresses and quantizes the original CSI by using the CSI generator and then transmits the compressed and quantized CSI to the access network device. The access network device inverse quantizes and decompresses the received compressed and quantized CSI by using the CSI reconstructor to obtain restored CSI.

[0088] As a data-based technology, AI models are sensitive to changes in scenarios. If the scenario in which the AI ​​model is deployed is significantly different from the scenario corresponding to the training data used to train the AI ​​model, the performance of the AI ​​model may deteriorate rapidly. In an AI model-based CSI feedback scenario, if the current communication environment is significantly different from the communication environment in which the AI ​​model is trained, the performance of the AI ​​model may deteriorate. The performance of the AI ​​model directly affects the accuracy of CSI feedback and restoration. How to monitor the performance of the AI ​​model is a problem worth considering.

[0089] Model monitoring can be used to determine the performance of an AI model. A model monitoring scheme, sometimes referred to as a final key performance indicator (KPI) monitoring scheme, may include monitoring performance indicators of a communication system in which the AI ​​model is used and determining whether the performance of the AI ​​model meets requirements based on whether the performance indicators meet the requirements. In the case of a wireless communication system, the performance indicators may include one or more of throughput, spectral efficiency, transmission rate, block error rate (BLER), hypothetical BLER, hybrid automatic repeat request (HARQ) feedback, etc. Another model monitoring scheme, sometimes referred to as an intermediate KPI monitoring scheme, may include monitoring the output of the AI ​​model and determining whether the performance of the AI ​​model meets requirements by comparing the difference between the output of the AI ​​model and a corresponding label or ground truth. In the intermediate KPI monitoring method, whether the AI ​​model meets the requirements may generally be determined based on one or more of indicators such as generalized cosine similarity (GCS), squared generalized cosine similarity (SGCS), normalized mean square error (NMSE), etc. Model monitoring may be performed by the terminal or by the network device.

[0090] In a wireless communication scenario, to monitor the performance of an AI model, a terminal needs to know how to determine transmission parameters for downlink transmission, for example, whether the transmission parameters are determined based on AI, and a network device needs to know how to determine transmission parameters for uplink transmission.

[0091] Therefore, an embodiment of the present application provides a communication method and a related device capable of implementing the method. The communication method is described by using a network-side device and a terminal-side device as examples for implementation. The network-side device in the embodiment of the present application may be a network device, or a chip, chip system, unit, or module within the network device. For example, the network-side device may be the access network device 110a or the access network device 110b in FIG. 1. Alternatively, the network-side device may be a communication device having a network device function, or a chip, chip system, unit, or module within the communication device having a network device function. The device may be mounted on the network device or used in cooperation with the network device. The terminal-side device in the embodiment of the present application may be a terminal, or a chip, chip system, unit, or module within the terminal, such as any terminal 120 shown in FIG. 1. Alternatively, the terminal-side device may be a communication device having a terminal function, or a chip, chip system, unit, or module within the communication device having a terminal function. The device may be mounted on the terminal or used in cooperation with the terminal. For ease of understanding, in the embodiments of the present application, an example is used for explanation in which the terminal side device is a terminal device or a chip, unit, or module within the terminal device, and the network side device is a network device or a chip, unit, or module within the network device.

[0092] To support machine learning functions in wireless networks, in embodiments of the present application, a dedicated AI entity or module may be further introduced into the network. When an AI entity is introduced, the AI ​​entity may correspond to an independent network element. When an AI module is introduced, the AI ​​module may be located in a network element, and the corresponding network element may be a terminal, a network device, etc.

[0093] In order to make the objectives, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the accompanying drawings. Certain operation methods in the method embodiments may also be applied to the device embodiments or system embodiments.

[0094] In embodiments of the present application, where there is no logical contradiction, the terms “channel state information” and “CSI” may be interchanged, and the terms “report,” “feedback,” and “transmission” may be interchanged.

[0095] Based on the network system architecture shown in FIG. 1, FIG. 5a, or FIG. 5b and the contents described in the above-mentioned related art, FIG. 7 is an example of a possible schematic flowchart of a communication method according to an embodiment of the present application. The solution in FIG. 7 is explained by using an example in which a first device and a second device interact with each other for implementation. For downlink transmission, the first device is a terminal-side device, and the second device is a network-side device. For uplink transmission, the first device is a network-side device, and the second device is a terminal-side device. For related descriptions of the network-side device and the terminal-side device, please refer to the above content. Details will not be described again. In the following embodiment, an example in which the network-side device is a network device and the terminal-side device is a terminal device is used for explanation.

[0096] See Figure 7. The method includes the following steps.

[0097] Step 701: The second device sends instruction information to the first device, and the first device receives the instruction information in response.

[0098] The indication information indicates a manner of determining a transmission parameter of the first transmission, and the determining manner includes an AI-based determining manner or a non-AI-based determining manner.

[0099] Optionally, the transmission parameters of the first transmission may include one or more of a precoding, a beam, an MCS, a number of transport streams, and a resource allocation of the first transmission.

[0100] In a downlink transmission scenario, the second device is a network device, e.g., a base station, the first device is a terminal, and the first transmission is a first downlink transmission, e.g., including one or more of a physical downlink shared channel (PDSCH), a physical downlink control channel (PDCCH), a channel state information-reference signal (CSI-RS), a demodulation reference signal (DMRS), a synchronization signal and a physical broadcast channel block (SSB), etc. In this scenario, the network device may determine transmission parameters of the first transmission (first downlink transmission) based on feedback information of the terminal (e.g., channel state information or other information that can represent channel quality), or the network device may determine transmission parameters of the first transmission.

[0101] In an uplink transmission scenario, the second device is a terminal, the first device is a network device, e.g., a base station, and the first transmission is a first uplink transmission, e.g., a sounding reference signal (SRS) or a tracking reference signal (TRS). In this scenario, the terminal may determine transmission parameters of the first transmission (first uplink transmission) based on feedback information (e.g., channel state information or other information that can represent channel quality) of the network device, or the terminal may determine the transmission parameters of the first transmission.

[0102] The determination manner of the transmission parameters of the first transmission may be an AI-based determination manner or a non-AI-based determination manner.

[0103] Determining the transmission parameters of the first transmission based on AI means that the transmission parameters of the first transmission (e.g., one or more of precoding, beam, MCS, number of transport streams, and resource allocation) are obtained through AI. The transmission parameters of the first transmission are generally determined based on channel measurements. There are various methods for determining the transmission parameters based on channel measurements, for example, for determining the transmission parameters based on an AI model or for determining the transmission parameters based on a non-AI algorithm. From channel measurements to transmission parameter determination may include one step, i.e., directly calculating the transmission parameters based on the channel measurements, or may include multiple steps, such as performing channel estimation based on the channel measurements to obtain CSI (which may be different representations of CSI, such as channel response, channel characteristics, and RSRP). If CSI is not obtained by the second device, CSI feedback needs to be further performed, and the second device determines the transmission parameters based on the obtained CSI. The AI-based determination method means that the steps from channel measurement to transmission parameter determination are completed by an AI model, or at least one of the steps from channel measurement to transmission parameter determination is completed by an AI model. For example, the channel estimation is AI-based channel estimation, or the CSI feedback is AI-based, or the CSI compression and / or CSI reconstruction in the CSI feedback is AI-based, or the CSI prediction is AI-based, or the beam prediction is AI-based, or determining transmission parameters based on the CSI is AI-based.

[0104] The AI-based determination method and the non-AI-based determination method are for the same step or multiple steps. The CSI feedback step in downlink transmission is used as an example. As shown in FIG. 6, determining transmission parameters for the first transmission based on AI means that, on the terminal side, a CSI generator compresses and quantizes the original CSI measured by the terminal, and, on the base station side, a CSI reconstructor dequantizes and decompresses the received compressed and quantized CSI to determine transmission parameters for downlink transmission based on the CSI output by the CSI reconstructor. Determining transmission parameters for the first transmission based on non-AI means, on the terminal side, compressing and quantizing CSI based on a codebook predefined in a protocol (e.g., 3GPP TS38.214), and, on the base station side, dequantizing and decompressing the received compressed and quantized CSI based on a corresponding codebook to obtain CSI by reconstruction. In this example, the AI-based determination method and the non-AI-based determination method are for the CSI feedback step. The method by which the base station determines the transmission parameters of the first transmission (e.g., one or more of precoding, beam, MCS, number of transport streams, and resource allocation) based on the recovered CSI is not limited, and may be an AI-based determination method or a non-AI-based determination method.

[0105] Optionally, for two transmissions having different determination methods of transmission parameters, the parameters of the two transmissions are the same or the method of determining parameters is the same, so as to prevent other unrelated factors from affecting the performance monitoring other than one or more specific steps corresponding to the determination method and / or in addition to one or more specific parameters corresponding to the determination method. A CSI feedback step is used as an example. For example, the parameters of the two transmissions are precoding determined based on AI CSI feedback and precoding determined based on non-AI CSI feedback, respectively. In this case, other parameters of the two transmissions are the same, for example, the multi-user pairing method is the same, the MCS is the same, the resource allocation is the same, or the determination method is the same, for example, the method for calculating precoding based on CSI is the same, and the channel estimation method is the same.

[0106] Optionally, the AI-based decision-making scheme may include a first AI model-based decision-making scheme and a second AI model-based decision-making scheme. It will be understood that more decision-making schemes, such as a decision-making scheme based on a third AI model, may also be included. In a possible implementation, the function of the first AI model is the same as the function of the second AI model. For example, both the first AI model and the second AI model are used for CSI feedback. Specifically, the first AI model and the second AI model may be used to perform CSI compression, or the first AI model and the second AI model may be used to perform CSI decompression. In another example, both the first AI model and the second AI model are used for beam prediction. The first AI model and the second AI model have different structures. For example, both the first AI model and the second AI model are implemented based on neural networks, but the depth (number of layers) and / or width (number of neurons) of the neural networks of the first AI model and the second AI model are different. In another possible implementation, the functionality of the first AI model is the same as the functionality of the second AI model, but the coefficients of the first AI model and the second AI model are different. In another possible implementation, the functionality of the first AI model is the same as the functionality of the second AI model, but the structures and coefficients of the first AI model and the second AI model are different.

[0107] The embodiments of the present application are applicable to the following possible scenarios:

[0108] Possible scenario 1 is CSI feedback scenario 1.

[0109] In CSI feedback scenario 1, in some cases, CSI compression (which may further include quantization) is completed by using an AI model (e.g., a CSI generator), and CSI decompression (also referred to as CSI reconstruction, which may further include dequantization) is completed by using an AI model (e.g., a CSI reconstructor). In other cases, CSI compression (which may further include quantization) is not completed based on an AI model, and CSI decompression (which may further include dequantization) is not completed based on an AI model. Specifically, CSI compression (which may further include quantization) and CSI decompression (which may further include dequantization) may be implemented using a codebook-based CSI feedback scheme, including, for example, one or more of a Release-15 (R15) type I codebook, an R15 type II codebook, an R16 type II codebook (or referred to as an extended type II codebook), an R16 port selection codebook, an R17 port selection codebook, an R18 codebook, etc.

[0110] Correspondingly, the manner of determining the transmission parameters of the first transmission includes:

[0111] Determination Scheme 1 is an AI-based CSI feedback scheme. In other words, for the CSI used to determine transmission parameters, CSI compression (which may further include quantization) is performed based on the AI ​​model, and CSI decompression (which may further include dequantization) is also performed based on the AI ​​model.

[0112] Optionally, the AI-based CSI feedback scheme may further include a first AI model-based CSI feedback scheme and a second AI model-based CSI feedback scheme, and it will be understood that more schemes, such as a third AI model-based CSI feedback scheme, may also be included.

[0113] Determination Scheme 2 is a non-AI-based CSI feedback scheme. In other words, for the CSI used to determine transmission parameters, CSI compression (which may further include quantization) is not performed based on an AI model, and CSI decompression (which may further include dequantization) is not performed based on an AI model.

[0114] For an example of an implementation of a CSI feedback scenario in this embodiment of the present application, please refer to the procedure shown in Figure 11 below.

[0115] Possible scenario 2 is CSI feedback scenario 2.

[0116] In CSI feedback scenario 2, in some cases, CSI compression (which may further include quantization) is completed by using an AI model (e.g., a CSI generator). In other cases, CSI compression (which may further include quantization) is not completed based on an AI model. Specifically, CSI compression (which may further include quantization) may be performed using a codebook-based CSI feedback scheme, including, for example, one or more of a Release-15 (R15) type I codebook, an R15 type II codebook, an R16 type II codebook (or referred to as an extended type II codebook), an R16 port selection codebook, an R17 port selection codebook, an R18 codebook, etc. CSI decompression (which may further include dequantization) may be completed using an AI scheme or a non-AI scheme. In other words, the implementation of CSI decompression (which may further include dequantization) may be fixed.

[0117] Correspondingly, the manner of determining the transmission parameters of the first transmission includes:

[0118] Determination Scheme 1 is an AI-based CSI compression scheme. In other words, for CSI used to determine transmission parameters, CSI compression (which may further include quantization) is performed based on an AI model, and CSI decompression (which may further include dequantization) is performed in a fixed manner, for example, in an AI manner or a non-AI manner.

[0119] Optionally, the AI-based CSI compression scheme may further include a first AI model-based CSI compression scheme and a second AI model-based CSI compression scheme, and it will be understood that more schemes, such as a third AI model-based CSI compression scheme, may also be included.

[0120] Determination Scheme 2 is a non-AI-based CSI compression scheme. In other words, for the CSI used to determine transmission parameters, CSI compression (which may further include quantization) is not performed based on an AI model, and CSI decompression (which may further include dequantization) is performed in a fixed manner, for example, in an AI manner or a non-AI manner.

[0121] Possible scenario 3 is CSI feedback scenario 3.

[0122] In CSI feedback scenario 3, in some cases, CSI decompression (which may further include dequantization) is completed by using an AI model (e.g., a CSI generator). In other cases, CSI decompression (which may further include dequantization) is not completed based on an AI model. Specifically, CSI decompression (which may further include dequantization) may be performed using a codebook-based CSI feedback scheme, including, for example, one or more of a Release-15 (R15) type I codebook, an R15 type II codebook, an R16 type II codebook (or referred to as an extended type II codebook), an R16 port selection codebook, an R17 port selection codebook, an R18 codebook, etc. CSI compression (which may further include quantization) may be completed using an AI scheme or a non-AI scheme. In other words, the implementation of CSI compression (which may further include quantization) may be fixed.

[0123] Correspondingly, the manner of determining the transmission parameters of the first transmission includes:

[0124] Determination Scheme 1 is an AI-based CSI reconstruction scheme. In other words, for the CSI used to determine transmission parameters, CSI decompression (which may further include inverse quantization) is performed based on an AI model, and CSI compression (which may further include quantization) is performed in a fixed manner, for example, in an AI manner or a non-AI manner.

[0125] Optionally, the AI-based CSI reconstruction scheme may further include a first AI model-based CSI reconstruction scheme and a second AI model-based CSI reconstruction scheme. It will be understood that more schemes, such as a third AI model-based CSI reconstruction scheme, may also be included.

[0126] Determination Scheme 2 is a non-AI-based CSI reconstruction scheme. In other words, for the CSI used to determine transmission parameters, CSI decompression (which may further include inverse quantization) is not performed based on an AI model, and CSI compression (which may further include quantization) is performed in a fixed manner, for example, in an AI manner or in a non-AI manner.

[0127] Possible scenario 4 is the CSI forecast scenario.

[0128] In a CSI prediction scenario, for a first transmission, the CSI used to determine transmission parameters (e.g., precoding) of the first transmission may be determined by the transmitting end of the first transmission (the second device in this embodiment) based on historical data (historical CSI) without waiting for the CSI fed back by the receiving end (the first device in this embodiment of the present application).

[0129] In another CSI prediction scenario, for a first transmission, the CSI used to determine transmission parameters (e.g., precoding) of the first transmission may be determined by the receiving end of the first transmission (the first device in this embodiment) based on historical data (historical CSI), and the predicted CSI is then fed back to the transmitting end of the first transmission (the second device in this embodiment) to determine transmission parameters of the first transmission.

[0130] In a CSI prediction scenario, the manner of determining transmission parameters for the first transmission may include:

[0131] Determination method 1 is an AI-based CSI prediction method. In other words, the CSI used to determine the transmission parameters is obtained by prediction based on an AI model.

[0132] Optionally, the AI-based CSI prediction scheme may further include a first AI model-based CSI prediction scheme and a second AI model-based CSI prediction scheme. It will be understood that more schemes, such as a third AI model-based CSI prediction scheme, may also be included.

[0133] Determination method 2 is a non-AI-based CSI prediction method. In other words, the CSI used to determine the transmission parameters is not obtained by prediction based on an AI model. For example, the CSI prediction method may be an autoregressive-based CSI prediction method.

[0134] Decision Scheme 3 is a non-CSI prediction scheme, which means that no CSI prediction is performed, i.e., the transmission parameters of the first transmission are determined by using the latest CSI measurement results.

[0135] For an example of an implementation of a CSI prediction scenario in this embodiment of the present application, please refer to the procedure shown in Figure 12 below.

[0136] Possible scenario 5 is the beam prediction scenario.

[0137] In a beam prediction scenario, beam prediction refers to predicting a beam to be used for uplink or downlink transmission based on CSI (which may be different representations of CSI, such as channel response, channel characteristics, and RSRP). Beam prediction may include spatial domain prediction and time domain prediction. Spatial domain prediction refers to predicting an optimal beam in an entire beam set based on CSI of a portion of the beam set. Time domain prediction refers to predicting a current or future optimal beam based on past CSI. For the first transmission, the determination scheme (or prediction scheme) of the beam to be used for the first transmission may include the following:

[0138] Decision Scheme 1 is an AI-based beam prediction scheme. In other words, the beam used for the first transmission is obtained based on an AI model.

[0139] Optionally, the AI-based beam prediction scheme may further include a first AI model-based beam prediction scheme and a second AI model-based beam prediction scheme. It will be understood that more schemes, such as a third AI model-based beam prediction scheme, may also be included.

[0140] Decision Method 2 is a non-AI-based beam prediction method. For example, the beam used for the first transmission is obtained by using a linear interpolation beam prediction method.

[0141] Decision Scheme 3 is a non-beam prediction scheme, which means that no beam prediction is performed, i.e., only the best beam from the measured beams is selected as the beam to be used for the first transmission.

[0142] For an example of an implementation of a beam prediction scenario in this embodiment of the present application, see the procedure shown in Figure 13 below.

[0143] It should be understood that the above only lists some possible scenarios as examples, and the embodiments of the present application may further be applied to other scenarios, which are not limited herein.

[0144] In a possible implementation, the indication information in the embodiments of the present application may indicate one transmission or multiple transmissions. Downlink transmission is used as an example. In a possible implementation, the indication information may indicate all possible downlink transmissions, including, for example, PDSCH, PDCCH, CSI-RS, DMRS, and SSB. Downlink transmission is still used as an example. In another possible implementation, the indication information may indicate only one or more specific downlink transmissions, for example, only PDSCH or CSI-RS. In another possible implementation, the indication information may indicate only transmissions for which model monitoring needs to be performed. For example, in the case of a PDSCH, the CSI used to determine the transmission parameters of the PDSCH may be obtained in an AI manner (e.g., CSI compression is implemented by using an AI model). The system may specify that model monitoring needs to be performed on the PDSCH to determine the performance of the AI ​​model. Optionally, one or more transmissions included in the first transmission indicated by the indication information may be pre-agreed or configured by the network side. For example, the downlink transmissions indicated by the indication information may be pre-agreed as all possible downlink transmissions, or the downlink transmissions indicated by the indication information may be pre-agreed as downlink transmissions for which model monitoring needs to be performed, or which downlink transmissions are downlink transmissions for which model monitoring needs to be performed may be pre-agreed or configured by the network side. Optionally, the indication information indicating a manner of determining transmission parameters of the multiple transmissions may be understood as the indication information indicating a manner of determining transmission parameters for each of the multiple transmissions.

[0145] Optionally, when the first transmission is repeated or retransmitted, the initial transmission and all repetitions or retransmissions of the first transmission may be considered as one transmission. In this scenario, the manner of determining transmission parameters for the initial transmission of the first transmission is the same as the manner of determining transmission parameters for each repetition (or retransmission) of the first transmission. Optionally, when the first transmission is repeated or retransmitted, the initial transmission of the first transmission may be considered as an independent transmission, or each repetition or retransmission of the first transmission may be considered as an independent transmission. In this scenario, the manner of determining transmission parameters for the initial transmission and each repetition (or retransmission) of the first transmission may be the same, or the manner of determining transmission parameters for the initial transmission and each repetition (or retransmission) of the first transmission may be different.

[0146] In a possible implementation, the indication information in the embodiment of the present application may indicate a transmission within a first period. It will be understood that the transmission within the first period may include one transmission or multiple transmissions. Optionally, the length of the first period may be expressed by the number of time units. The time unit may be, for example, one or more symbols, one or more slots, one or more minislots, or n milliseconds, where n is a positive integer, for example, n=1 or n=10. This is not limited in the embodiment of the present application.

[0147] In a possible implementation, the instruction information in the embodiment of the present application includes index information of a determination method for the transmission parameters of the first transmission. For example, each determination method may be pre-assigned a number as the index information for the determination method. In this way, the number of the determination method is indicated in the instruction information to indicate the determination method for the transmission parameters of the first transmission. In another possible implementation, the instruction information in the embodiment of the present application includes type information of the first transmission, and there is a correspondence between the type of the first transmission and the method for determining the transmission parameters of the first transmission. In this way, the type of the first transmission may indicate the method for determining the transmission parameters of the first transmission. Optionally, in the embodiment of the present application, type division may be performed on the transmission in terms of whether the transmission is used for model monitoring and whether the transmission parameters are determined based on an AI model. For example, multiple transmission types or scheduling types may be predefined, including: Type 1: transmission or scheduling used for normal data transmission (this type of transmission or transmission scheduled with this type is not used for model monitoring), Type 2: transmission or scheduling used for monitoring and based on an AI determination scheme (this type of transmission or transmission scheduled with this type may be further classified into transmissions based on determination schemes based on different AI models), and Type 3: transmission or scheduling used for monitoring and based on a non-AI determination scheme. The transmission type or scheduling type corresponds to a method of determining transmission parameters for the first transmission, and the indication information may indicate the method of determining transmission parameters for the first transmission by indicating the transmission type or scheduling type.

[0148] In a possible implementation, the instruction information may implicitly indicate a method for determining the transmission parameters of the first transmission. In other words, the instruction information does not directly indicate a method for determining the transmission parameters of the first transmission, but there is an association between the content indicated by the instruction information and the method for determining the transmission parameters of the first transmission. For example, there is a correspondence between the method for determining the transmission parameters of the first transmission and a reference signal corresponding to the transmission, and different methods for determining the transmission parameters of the first transmission correspond to different reference signal sequences or resource mapping patterns. In this case, the first device may determine the method for determining the transmission parameters of the first transmission based on the reference signal corresponding to the first transmission.

[0149] In a possible implementation, the indication information in the embodiment of the present application may indicate a first transmission pattern. The first transmission pattern includes a first determination scheme corresponding to N consecutive transmissions, where the N consecutive transmissions include a first transmission, and the first determination scheme is a scheme for determining transmission parameters of the first transmission, where N is a positive integer. This implementation may be applicable to a scenario in which multiple consecutive transmissions in time have the same determination scheme for transmission parameters. The first transmission pattern may indicate a determination scheme corresponding to multiple consecutive transmissions, a determination scheme corresponding to multiple subsequent consecutive transmissions, etc. Downlink transmission in a CSI feedback scenario is used as an example. As shown in FIG. 8a, the downlink transmission pattern may indicate that, starting from the effective time point of the downlink transmission pattern, the determination scheme for transmission parameters of the first N1 downlink transmissions is CSI feedback scheme 1, the determination scheme for transmission parameters of the subsequent N2 downlink transmissions is CSI feedback scheme 2, and the determination scheme for transmission parameters of the subsequent N3 downlink transmissions is CSI feedback scheme 3. CSI feedback scheme 1, CSI feedback scheme 2, and CSI feedback scheme 3 may be, for example, any three of an AI-based CSI feedback scheme, a non-AI-based CSI feedback scheme, an AI-based CSI compression scheme, a non-AI-based CSI compression scheme, an AI-based CSI reconstruction scheme, and a non-AI-based CSI reconstruction scheme. See the above for a description of the three schemes. Correspondingly, the downlink transmission pattern may be {CSI feedback scheme 1: N1, CSI feedback scheme 2: N2, CSI feedback scheme 3: N3}. Optionally, the downlink transmission pattern may further include some empty bits. The empty bits indicate that the determination scheme of the transmission parameters of these downlink transmissions is not indicated. Correspondingly, model monitoring does not need to be performed for these downlink transmissions.For example, the format of the downlink transmission pattern may be {CSI feedback scheme 1: N1, idle bits: K1, CSI feedback scheme 2: N2, idle bits: K2, CSI feedback scheme 3: N3}. "Idle bits: K1" indicates that the determination scheme of the transmission parameters for K1 downlink transmissions after N1 downlink transmissions is not indicated. N1, N2, and N3 may all be 1. Thus, this implementation is not limited to scenarios in which the determination scheme of the transmission parameters for multiple consecutive transmissions in time is the same.

[0150] In a possible implementation, the indication information in the embodiment of the present application may indicate a second transmission pattern including a first determination scheme corresponding to a transmission within a first period, where the transmission within the first period includes a first transmission, and the first determination scheme is a scheme for determining transmission parameters for the first transmission. This implementation may be applicable to a scenario in which multiple transmissions within a certain period have the same determination scheme for transmission parameters. The second transmission pattern may indicate a determination scheme corresponding to a transmission within a period, a determination scheme corresponding to a transmission within a subsequent period, etc. Downlink transmission in a CSI feedback scenario is used as an example. As shown in FIG. 8b, the downlink transmission pattern indicates that the determination scheme for transmission parameters for downlink transmissions within the first M1 time periods (e.g., M1 time units, specifically, M1 slots) is CSI feedback scheme 1, the determination scheme for transmission parameters for downlink transmissions within the subsequent M2 time periods is CSI feedback scheme 2, and the determination scheme for transmission parameters for downlink transmissions within the subsequent M3 time periods is CSI feedback scheme 3. Correspondingly, the specific format of the downlink transmission pattern may be {CSI feedback scheme 1: M1, CSI feedback scheme 2: M2, CSI feedback scheme 3: M3}. Optionally, the downlink transmission pattern may further include some empty bits. The empty bits indicate that the determination scheme of the transmission parameters of these downlink transmissions within a time period is not indicated. For example, the format of the downlink transmission pattern may be {CSI feedback scheme 1: M1, empty bit: K1, CSI feedback scheme 2: M2, empty bit: K2, CSI feedback scheme 3: M3}. "Empty bit: K1" indicates that the determination scheme of the transmission parameters of downlink transmissions within K1 time periods is not indicated. M1, M2, and M3 may all be 1. Therefore, this implementation is not limited to scenarios in which the determination scheme of the transmission parameters of multiple transmissions within a time period is the same.

[0151] Optionally, the network side may pre-configure or pre-define multiple transmission patterns, and the second device may indicate or activate one of the multiple transmission patterns by using the indication information, or may indicate or activate one of the multiple transmission patterns by using an index of the transmission pattern, for example.

[0152] In a possible implementation, the indication information in the embodiment of the present application may be dynamic signaling, for example, downlink control information (DCI). In this case, the first transmission indicated by the DCI is a transmission scheduled by using the DCI. In other words, the manner of determining transmission parameters of the first transmission may be indicated by using the DCI used to schedule the first transmission. In another possible implementation, the indication information in the embodiment of the present application is a MAC control element (CE). In another possible implementation, the indication information may be semi-static. For example, the indication information is higher layer signaling, for example, radio resource control (RRC) signaling. The higher layer signaling may indicate the manner of determining transmission parameters of multiple transmissions, or the manner of determining transmission parameters of transmissions within a first period. In addition, the indication information may alternatively be a combination of higher layer signaling and lower layer signaling. For example, the RRC signaling indicates a determination scheme for transmission parameters of multiple transmissions, and the DCI or MAC signaling activates (indicates) one of the determination schemes for transmission parameters of multiple transmissions.

[0153] In an embodiment of the present application, the instruction information may be periodic. In other words, within the validity period of the instruction information, the transmission parameter determination manner indicated by the instruction information is periodically repeated until the next instruction information (the instruction information indicates a transmission parameter determination manner for one or more transmissions) is received, or until the instruction information indicating to stop model monitoring is received, or until the validity period of the instruction information expires.

[0154] Optionally, the effective time of the indication information (e.g., the effective time of a downlink transmission pattern indicated by using the indication information) may be after time t1 as shown in FIG. 9a, or the effective time is after moment t1 and before moment t2 as shown in FIG. 9b. Here, t1 may be t3+Δt1, where t3 is a reference time point, for example, the time point when the indication information is received. Optionally, the indication information may be used to activate the transmission pattern. In this case, t3 is the time point when the transmission pattern is activated by using the indication information, and Δt1 is a time offset relative to the reference time point, which is predefined or configured by the network side, and Δt1 is equal to or greater than 0. Similarly, t2 may be t4+Δt2, where t4 is a reference time point, for example, the time point when the indication information is received. Optionally, the indication information may be used to deactivate the transmission pattern. In this case, t4 is the time point at which the transmission pattern is deactivated by using the indication information, t4 and t3 may be the same time point, and Δt2 is a time offset relative to a reference time point predefined or configured by the network side, and Δt2 is greater than or equal to 0. Alternatively, as shown in Figure 9c, t2 may be t1 + Δt, where Δt is a validity period predefined or configured by the network side, and Δt is greater than 0.

[0155] If the indication information is periodic, the period T may be predefined or configured by the base station. In particular, the period T may be equal to the duration of the downlink transmission pattern by default. For example, if the first transmission pattern indicated by the indication information includes a first determination scheme corresponding to N consecutive transmissions, the period T may be a duration corresponding to N transmissions. In another example, if the second transmission pattern indicated by the indication information includes a first determination scheme corresponding to transmissions within a first period, the period T may be a duration of the first period.

[0156] The indication information in the embodiment of the present application may alternatively be aperiodic. Compared with periodic, aperiodic means that the determination manner indicated by the indication information is for the transmission parameters of the first transmission and is valid only once. For example, the indication information indicates a manner for determining the transmission parameters of the downlink transmission within a first period, and the indication information is valid only within the first period. In the case of aperiodic indication information, such as a downlink transmission pattern, the downlink transmission pattern is valid once from time t1. For the definition of t1, please refer to the above description.

[0157] Step 702: The second device sends at least one transmission to the first device, where the at least one transmission includes the first transmission. In response, the first device receives the at least one transmission sent by the second device.

[0158] In this embodiment of the present application, the first device may receive at least one transmission on a time-frequency resource corresponding to the at least one transmission.

[0159] Step 703: The first device determines, based on the indication information and at least one transmission from the second device, a capability corresponding to a manner of determining a transmission parameter of the first transmission.

[0160] Optionally, the performance may include one or more of the following: throughput, spectral efficiency, transmission rate, BLER, hypothetical BLER, SINR, RSRP, HARQ feedback (e.g., including HARQ ACK / NACK), generalized cosine similarity (GCS), squared generalized cosine similarity (SGCS), mean square error (MSE), normalized mean square error (NMSE), etc. This is not limited in the embodiments of the present application.

[0161] In an embodiment of the present application, after determining the method for determining the transmission parameters of the first transmission based on the instruction information, the first device may determine performance based on the reception status on the time-frequency resources of the first transmission, and use the determined performance as the performance corresponding to the determination method. If the first device determines based on the instruction information that the transmission parameters of N transmissions (N is an integer greater than 1) are all determined using the same method, the first device may determine performance based on the reception status on the time-frequency resources corresponding to the N transmissions. The performance is determined based on the reception status of the transmissions using the same method for determining the N transmission parameters. BLER is used as an example. BLER is the average block error rate of N transmissions. Throughput is used as an example. Throughput is the total throughput of the N transmissions.

[0162] Optionally, the first device may calculate performance corresponding to each determination scheme based on each determination scheme indicated by the indication information.

[0163] Optionally, if the instruction information is periodic, in each period after the instruction information is received, the first device may determine a performance corresponding to a manner of determining a transmission parameter of the first transmission based on the instruction information and at least one transmission from the second device within the period.

[0164] Optionally, the first device may perform some operations based on the model monitoring results to improve system performance. A CSI feedback scenario is used as an example. If the first device determines that the manner of determining transmission parameters of the first transmission is an AI model-based CSI feedback scheme and the performance corresponding to the AI ​​model-based CSI feedback scheme does not meet system requirements (e.g., the BLER is greater than a specified threshold or the throughput rate is less than a specified threshold), the first device may switch the manner of determining transmission parameters of the first transmission from the AI ​​model-based CSI feedback scheme to a non-AI model-based CSI feedback scheme, replace the AI ​​model used for CSI compression and decompression, or update the AI ​​model used for CSI compression and decompression (e.g., retrain the AI ​​model and replace the original AI model with the trained AI model).

[0165] Optionally, the first device may further transmit first information to the second device, the first information being of a transmission parameter of the first transmission and including performance corresponding to the determination method determined by the first device. In other words, the first device may transmit the determined performance to the second device as a monitoring result.

[0166] Optionally, the first device may further transmit first information to the second device, and the first information may include one or more of the following: performance of at least one determination scheme among the plurality of determination schemes; a determination scheme corresponding to optimal performance among the performances corresponding to the plurality of determination schemes; a determination scheme corresponding to performance higher than a threshold among the performances corresponding to the plurality of determination schemes; a determination scheme corresponding to performance lower than a threshold among the performances corresponding to the plurality of determination schemes; and a determination scheme recommended by the terminal device among the performances corresponding to the plurality of determination schemes. The plurality of determination schemes include a scheme for determining transmission parameters of each of the at least one transmission transmitted by the second device. In other words, the first device may transmit the above information to the second device as a model monitoring result.

[0167] Optionally, the first device may alternatively report the model monitoring results to the network management system. For the content of the model monitoring results, please refer to the above description.

[0168] In the procedure shown in FIG. 7, the second device transmits to the first device, by using the indication information, a method for determining transmission parameters of one or more transmissions. The first device can then learn the method for determining transmission parameters of the associated transmissions and determine the corresponding performance of each method based on the reception status of the corresponding transmissions, thereby performing model monitoring. A CSI feedback scenario is used as an example. After obtaining the model monitoring results based on the aforementioned procedure, the first device may compare the performance corresponding to the AI-based CSI feedback method with the performance corresponding to the non-AI-based CSI feedback method to monitor the AI ​​model. For example, the performance corresponding to the AI ​​model-based CSI feedback method is compared with the performance corresponding to the non-AI-based CSI feedback method. If the performance corresponding to the AI ​​model-based CSI feedback method is better, this indicates that the performance of the AI ​​model meets the requirements. Otherwise, this indicates that the performance of the AI ​​model does not meet the requirements, and an operation such as switching the CSI feedback method or replacing or updating the AI ​​model may be performed.

[0169] Based on the network system architecture shown in FIG. 1, FIG. 5a, or FIG. 5b and the contents described in the above-mentioned related art, FIG. 10 is an example of a possible schematic flowchart of another communication method according to an embodiment of the present application. The solution of FIG. 10 is explained by using an example in which a first device and a second device interact with each other. For downlink transmission, the first device is a terminal-side device, and the second device is a network-side device. For uplink transmission, the first device is a network-side device, and the second device is a terminal-side device. For related descriptions of the network-side device and the terminal-side device, please refer to the above content. Details will not be described again. In the following embodiment, an example in which the network-side device is a network device and the terminal-side device is a terminal device is used for explanation.

[0170] See Figure 10. The method includes the following steps.

[0171] Step 1001: The second device sends instruction information to the first device, and the first device receives the instruction information in response.

[0172] The instruction information indicates that the manner of determining the transmission parameters of the first transmission is the same as the manner of determining the transmission parameters of the second transmission, and the determining manner includes an AI-based determining manner or a non-AI-based determining manner. For related descriptions of the AI-based determining manner or the non-AI-based determining manner, please refer to the relevant content of Figure 7.

[0173] It will be understood that the indication information may indicate that there is an association between the first transmission and the second transmission. The association relationship is defined in terms of a determination method of a transmission parameter. For example, in the case of multiple transmissions having the same determination method of a transmission parameter, the multiple transmissions may be said to have an association relationship. In this way, when performing a model monitoring process of multiple transmissions having the same determination method of a transmission parameter based on the indication information, the first device may comprehensively consider the reception status of these downlink transmissions to determine performance. Therefore, performance corresponding to the determination method of the transmission parameter of these transmissions can be obtained.

[0174] In another possible implementation, when multiple transmissions (e.g., two transmissions) have different determination methods of transmission parameters, the multiple transmissions may also be referred to as having an association relationship. For example, the indication information indicates that there is an association relationship between the first transmission and the second transmission. The first device may separately determine performances of the first transmission and the second transmission based on the indication information, and compare the performance corresponding to the determination method of the transmission parameters of the first transmission with the performance corresponding to the determination method of the transmission parameters of the second transmission.

[0175] In a possible implementation, the first device only needs to know the determination methods of the transmission parameters for the same or different transmissions, and does not need to know whether the determination methods of the transmission parameters for these transmissions are AI-based or non-AI-based. In this case, the second device does not need to indicate the specific determination methods of the transmission parameters for these transmissions, and the first device only needs to monitor the performance corresponding to the different determination methods of the transmission parameters corresponding to these transmissions, for example, the performance of the first determination method and the performance of the second determination method.

[0176] It should be understood that "first" and "second" are virtual identifiers of the determination schemes (e.g., the determination schemes corresponding to the first performance and the second performance are different, and therefore the determination scheme corresponding to the first performance may be identified by using the number "first," and the determination scheme corresponding to the second performance may be identified by using the number "second").

[0177] Optionally, the first device and the second device may agree on a numbering convention corresponding to the virtual identifiers. For example, in a scheme for determining transmission parameters of a first downlink transmission after the indication information, the virtual identifier of the determination scheme may be set to "first" or "scheme A," etc. In another scheme for determining transmission parameters of a downlink transmission after the indication information, the virtual identifier of the determination scheme may be set to "second" or "scheme B."

[0178] Optionally, the first device may feed back performance monitoring results of the multiple determination schemes to the second device, and the monitoring results may include one or more of the following: performance of at least one determination scheme among the multiple determination schemes, a determination scheme corresponding to optimal performance among the performances corresponding to the multiple determination schemes, a determination scheme corresponding to performance higher than a threshold among the performances corresponding to the multiple determination schemes, a determination scheme corresponding to performance lower than a threshold among the performances corresponding to the multiple determination schemes, and a determination scheme recommended by the terminal device among the performances corresponding to the multiple determination schemes. If the second device knows a specific determination scheme corresponding to each virtual identifier (e.g., a determination scheme distinguished by using the number “first” or “second” as described above), e.g., AI-based, non-AI-based, or AI model-based), the second device may determine the performance corresponding to each specific determination scheme.

[0179] In another possible implementation, the second device may associate the first transmission and / or the second transmission with a downlink transmission for which a method for determining transmission parameters is known to the first device (i.e., the method for determining the transmission parameters of the downlink transmission is known). In this case, the first device may determine a specific method for determining the transmission parameters of the downlink transmission, the first transmission, and / or the second transmission based on the known method for determining the transmission parameters. For example, the specific method for determining the transmission parameters may be AI-based, non-AI-based, or based on which AI model. For example, the downlink transmission for which the method for determining transmission parameters is known to the first device may be a downlink transmission used for normal data transmission (e.g., the normal data transmission may be data transmission that does not require model monitoring). The first device knows the specific method for determining the transmission parameters of the downlink transmission in another procedure. For example, in a procedure such as model selection, model switching, or model activation, the first device knows whether the downlink transmission used for normal data transmission is AI-based, non-AI-based, or based on which AI model. It will be appreciated that the above implementations may also be used for uplink transmissions.

[0180] In another possible implementation, the second device may indicate to the first device a manner for determining transmission parameters of at least one reference downlink transmission, and associate the first transmission and / or the second transmission with the at least one reference downlink transmission. In this case, the first device may know a specific manner for determining the transmission parameters of the first transmission and / or the second transmission, for example, whether the specific determination manner is AI-based, non-AI-based, or based on an AI model. It will be understood that the above implementation may also be used for uplink transmission.

[0181] In a possible implementation, the indication information may include indication information of the first transmission and indication information of the second transmission, or may indicate the first transmission and the second transmission having an association relationship, to indicate that there is an association relationship between the first transmission and the second transmission. Optionally, the indication information of the first transmission may be an index of the first transmission and / or time-frequency resource indication information of the first transmission. The indication information of the second transmission may be an index of the second transmission and / or time-frequency resource indication information of the second transmission. Optionally, when the first transmission is scheduled, the second transmission having an association relationship with the scheduled first transmission may be indicated in the scheduling signaling (e.g., the indication information in this embodiment of the present application), for example, the indication information of the second transmission is included. It will be understood that the scheduling signaling includes the indication information of the first transmission. For a specific implementation form of determining performance corresponding to a method for determining transmission parameters of the first transmission and / or a method for determining transmission parameters of the second transmission based on an association relationship between the first transmission and the second transmission, please refer to the above description.

[0182] In a possible implementation, the indication information may include a transmission time point of the first transmission and a transmission time point of the second transmission, or may indicate the first transmission and the second transmission having an association relationship, to indicate that there is an association relationship between the first transmission and the second transmission. Optionally, when the first transmission is scheduled, the second transmission having an association relationship with the scheduled first transmission may be indicated in the scheduling signaling (e.g., the indication information in this embodiment of the present application), for example, including the transmission time point of the second transmission. It will be understood that the scheduling signaling further indicates the transmission time point of the first transmission.

[0183] In a possible implementation, the indication information in this embodiment of the present application may be dynamic signaling, for example, DCI. In this case, the first transmission indicated by the DCI is a transmission scheduled by using the DCI and may include indication information (for example, an index) of the second transmission or indicate the transmission time point of the second transmission. In other words, the second transmission having an association relationship with the first transmission may be indicated by using the DCI used to schedule the first transmission. In another possible implementation, the indication information in this embodiment of the present application is MAC CE. In another possible implementation, the indication information may be semi-static. For example, the indication information is higher layer signaling, for example, RRC signaling.

[0184] The indication information may be periodic or aperiodic, see above for related explanations.

[0185] Step 1002: The second device sends at least one transmission to the first device, where the at least one transmission includes the first transmission and / or the second transmission. In response, the first device receives the at least one transmission sent by the second device.

[0186] In this embodiment of the present application, the first device may receive at least one transmission on a time-frequency resource corresponding to the at least one transmission.

[0187] Step 1003: The first device determines, based on the indication information and at least one transmission from the second device, a capability corresponding to a manner of determining a transmission parameter of the first transmission or the second transmission.

[0188] For a specific implementation of step 1003, please refer to the related description of FIG.

[0189] In a possible implementation, when the transmission parameter determination schemes of the first transmission and the second transmission are different (e.g., as described above, an association relationship is defined as multiple transmissions having an association relationship having different transmission parameter determination schemes), the first device may separately determine performance corresponding to the transmission parameter determination schemes of the first transmission and the second transmission, compare the performance corresponding to the transmission parameter determination scheme of the first transmission with the performance corresponding to the transmission parameter determination scheme of the second transmission, determine which determination scheme corresponds to better performance, and determine whether the determination scheme needs to be switched or whether the AI ​​model needs to be replaced or updated. In a downlink transmission scenario, the terminal may alternatively transmit the determined performance to the network device, and the network device may perform the above-mentioned determination and decision.

[0190] The procedure shown in FIG. 10 may be applied to a CSI feedback scenario, a CSI compression scenario, a CSI reconstruction scenario, a CSI prediction scenario, a beam prediction scenario, an SRS transmission scenario, a phase-tracking reference signal (PTS) transmission scenario, etc.

[0191] The procedure shown in Figure 10 may be applied to downlink transmission. In this case, the first device may be a terminal, the second device may be a network device, and the first transmission and the second transmission are downlink transmissions. The procedure shown in Figure 10 may also be applied to uplink transmission. In this case, the first device is a network device, the second device is a terminal, and the first transmission and the second transmission are uplink transmissions.

[0192] In the procedure shown in FIG. 10 , the second device sends the association relationship between two or more transmissions to the first device by using the indication information, so that the first device can know the method of determining the transmission parameters of the transmissions, and may determine the corresponding performance for each determination method based on the receiving status of the corresponding transmission, thereby implementing model monitoring.

[0193] The following provides some application examples of downlink transmission based on the procedures shown in Figure 7 or Figure 10. For the application of uplink transmission, it should be understood to refer to the application examples of downlink transmission.

[0194] Based on the procedures shown in FIG. 7 or FIG. 10, an example of a CSI feedback scenario may be shown in FIG. 11. As shown in FIG. 11, at 1101, a network device (e.g., a base station) transmits indication information to a terminal device, where the indication information indicates a CSI feedback scheme for transmission parameters of one or more downlink transmissions, or indicates that the CSI feedback scheme for transmission parameters of a first downlink transmission is the same as the CSI feedback scheme for transmission parameters of a second downlink transmission. At 1102, the network device transmits one or more downlink transmissions to the terminal device. At 1103, after receiving the one or more downlink transmissions, the terminal obtains the CSI feedback scheme for the transmission parameters of the one or more downlink transmissions based on the indication information. For each CSI feedback scheme, the terminal determines performance corresponding to the CSI feedback scheme based on the reception status of the downlink transmission corresponding to the CSI feedback scheme to obtain a model monitoring result. The terminal may also perform operations such as model switching or updating based on the model monitoring result. Furthermore, at 1104, the terminal may transmit the model monitoring result to the base station. For details of specific implementations of the above procedures, please refer to the relevant descriptions of FIG. 7 or FIG.

[0195] Based on the procedures shown in FIG. 7 or FIG. 10, an example of a CSI prediction scenario may be shown in FIG. 12. As shown in FIG. 12, at 1201, a network device (e.g., a base station) transmits indication information to a terminal device, where the indication information indicates a CSI prediction scheme for transmission parameters of one or more downlink transmissions, or indicates that the CSI prediction scheme for transmission parameters of a first downlink transmission is the same as the CSI prediction scheme for a second downlink transmission. At 1202, the network device transmits one or more downlink transmissions to the terminal device. At 1203, after receiving the one or more downlink transmissions, the terminal obtains the CSI prediction scheme for transmission parameters of the one or more downlink transmissions based on the indication information. For each CSI prediction scheme, the terminal determines performance corresponding to the CSI prediction scheme based on the reception status of the downlink transmission corresponding to the CSI prediction scheme to obtain a model monitoring result. The terminal may also perform an operation such as model switching or updating based on the model monitoring result. Furthermore, at 1204, the terminal may transmit the model monitoring result to the base station. For details of specific implementations of the above procedures, please refer to the relevant descriptions of FIG. 7 or FIG.

[0196] Based on the procedures shown in FIG. 7 or 10, an example of a beam prediction scenario may be shown in FIG. 13. As shown in FIG. 13, at 1301, a network device (e.g., a base station) transmits instruction information to a terminal device, where the instruction information indicates a beam prediction scheme for transmission parameters of one or more downlink transmissions, or indicates that the beam prediction scheme for transmission parameters of a first downlink transmission is the same as the beam prediction scheme for transmission parameters of a second downlink transmission. At 1302, the network device transmits one or more downlink transmissions to the terminal device. At 1303, after receiving one or more downlink transmissions, the terminal obtains the beam prediction scheme for transmission parameters of the one or more downlink transmissions based on the instruction information. For each beam prediction scheme, the terminal determines the performance corresponding to the beam prediction scheme based on the reception status of the downlink transmission corresponding to the beam prediction scheme to obtain a model monitoring result. The terminal may also perform operations such as model switching or updating based on the model monitoring result, or may transmit the model monitoring result to the base station. For details of specific implementation forms of the above procedures, please refer to the relevant description of FIG. 7 or 10.

[0197] It can be understood that although the foregoing embodiments of the present application are described by using the final KPI model monitoring method as an example, those skilled in the art can understand that based on the same principle, the foregoing embodiments of the present application can also be applied to the intermediate KPI model monitoring method.

[0198] It can be understood that to implement the functions in the above-described embodiments, the network devices and terminals include corresponding hardware structures and / or software modules for performing each function. Those skilled in the art will easily recognize that the present application can be implemented by using hardware or a combination of hardware and computer software, in combination with the units and method steps in the examples described in the embodiments disclosed in the present application. Whether the functions are performed by hardware or by hardware driven by computer software depends on the specific application scenario and design constraints of the technical solution.

[0199] 14 and 15 are diagrams of possible communication device structures according to embodiments of the present application. These communication devices may be configured to implement the functions of the terminals or network devices in the above-described method embodiments, and thus may also implement the beneficial effects of the above-described method embodiments. In this embodiment of the present application, the communication device may be one of the terminals 120a to 120j shown in FIG. 1, or may be the base station 110a or 110b shown in FIG. 1, or may be a module (such as a chip) used in the terminal or base station.

[0200] 14, the communication device 1400 includes a processing unit 1410 and a transceiver unit 1420. The communication device 1400 is configured to perform the functions of the first device or the second device in any of the method embodiments shown in FIGS. 7 and 10-13.

[0201] 7, the transceiver unit 1420 is configured to receive instruction information from the second device, the instruction information indicating a manner of determining transmission parameters of the first transmission, the determination manner including an AI-based determination manner or a non-AI-based determination manner. The processing unit 1410 is configured to determine performance corresponding to the manner of determining transmission parameters of the first transmission based on the instruction information from the second device and the at least one transmission, the at least one transmission including the first transmission.

[0202] When the communication apparatus 1400 is configured to perform the functions of the second device in the method embodiment shown in FIG. 7, the transceiver unit 1420 is configured to send instruction information to the first device via the transceiver unit 1420, where the instruction information indicates a manner of determining transmission parameters of the first transmission, where the determination manner includes an AI-based determination manner or a non-AI-based determination manner; and send at least one transmission to the first device via the transceiver unit 1420, where the at least one downlink transmission includes the first transmission.

[0203] 10 , the transceiver unit 1420 is configured to receive instruction information from the second device, the instruction information indicating that a manner of determining transmission parameters of the first transmission is the same as a manner of determining transmission parameters of the second transmission, the determination manner including an AI-based determination manner or a non-AI-based determination manner. The processing unit 1410 is configured to determine performance corresponding to the manner of determining transmission parameters of the first transmission or the second transmission based on the instruction information and the at least one transmission from the second device, the at least one transmission including the first transmission and / or the second transmission.

[0204] When the communications apparatus 1400 is configured to perform the functions of the second device in the method embodiment shown in FIG. 10 , the processing unit 1410 is configured to send instruction information to the first device via the transceiver unit 1420, where the instruction information indicates that a manner of determining transmission parameters of the first transmission is the same as a manner of determining transmission parameters of the second transmission, where the determination manner includes an AI-based determination manner or a non-AI-based determination manner, and to send at least one transmission to the first device via the transceiver unit 1420, where the at least one downlink transmission includes the first transmission and / or the second transmission.

[0205] For a more detailed description of the processing unit 1410 and the transceiver unit 1420, please directly refer to the relevant descriptions of the method embodiments shown in Figures 7 and 10. The details will not be described again here.

[0206] 15, the communication device 1500 includes a processor 1510 and an interface circuit 1520. The processor 1510 and the interface circuit 1520 are coupled to each other. It may be understood that the interface circuit 1520 may be a transceiver or an input / output interface. Optionally, the communication device 1500 may further include a memory 1530 configured to store instructions to be executed by the processor 1510, to store input data required by the processor 1510 to execute the instructions, or to store data generated after the processor 1510 executes the instructions.

[0207] When the communications device 1500 is configured to perform the method shown in FIG. 7 or FIG. 10, the processor 1510 is configured to perform the functions of the processing unit 1410, and the interface circuit 1520 is configured to perform the functions of the transceiver unit 1420.

[0208] When the communication device is a chip used in a terminal, the chip in the terminal implements the functions of the terminal in the above-mentioned method embodiment. The chip in the terminal receives information from another module (e.g., a radio frequency module or an antenna) in the terminal, and the information is transmitted to the terminal by the network device. Alternatively, the chip in the terminal transmits information to another module (e.g., a radio frequency module or an antenna) in the terminal, and the information is transmitted to the network device by the terminal.

[0209] When the communication device is a module used in a network device, the module in the network device implements the functions of the network device in the above-described method embodiments. The module in the network device receives information from another module (e.g., a radio frequency module or an antenna) in the network device, and the information is transmitted to the network device by a terminal. Alternatively, the module in the network device transmits information to another module (e.g., a radio frequency module or an antenna) in the network device, and the information is transmitted to the terminal by the network device. The network device module in this specification may be a baseband chip of the network device, or may be a DU or another module. The DU in this specification may be a DU in an open radio access network (O-RAN) architecture.

[0210] It will be understood that the processor in embodiments of the present application may be a Central Processing Unit (CPU), or may be another 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. The general-purpose processor may be a microprocessor or any conventional processor.

[0211] The present application further provides another example of an apparatus. The communication apparatus includes at least one processor and at least one memory. The at least one processor is coupled to the at least one memory. The at least one memory is configured to store instructions. When the instructions are executed by the at least one processor, the communication apparatus is enabled to perform the method of the aforementioned embodiment. For example, the communication apparatus includes a processor and a memory. As shown in FIG. 15, the communication apparatus 1500 includes a processor 1510 and a memory 1530. The processor 1510 is coupled to the memory 1530. The memory 1530 stores instructions. When the instructions stored in the memory 1530 are executed by the processor 1510, the communication apparatus 1500 performs the method performed by the network device in the aforementioned embodiment.

[0212] The method steps in the embodiments of the present application may be implemented in hardware or software instructions that can be executed by a processor. The software instructions may include corresponding software modules. The software modules may be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well known in the art. For example, the storage medium is coupled to the processor such that the processor can read information from and write information to the storage medium. The storage medium may alternatively be components of the processor. The processor and the storage medium may be located in an ASIC. In addition, the ASIC may be located in a network device or a terminal. The processor and the storage medium may alternatively reside in the network device or terminal as discrete components.

[0213] All or part of the above-described embodiments may be implemented by software, hardware, firmware, or any combination thereof. When software is used to implement an embodiment, all or part of the embodiment may be implemented in the form of a computer program product. This computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded into a computer and executed, all or part of the procedures or functions of the embodiments of the present application are executed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user terminal, or another programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via wired or wireless communication. The computer-readable storage medium may be any available medium or data storage device that can be accessed by a computer, such as a server or data center that integrates one or more available media. The available media may be magnetic media such as floppy disks, hard disks, or magnetic tape, or optical media such as digital video disks, or semiconductor media such as solid-state drives. The computer-readable storage medium may be volatile or nonvolatile storage media, or may include both volatile and nonvolatile storage media.

[0214] In various embodiments of the present application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions in different embodiments are consistent and can be cross-referenced, and the technical features in different embodiments can be combined based on their internal logical relationships to form new embodiments.

[0215] In this application, "at least one" means one or more, and "more" means two or more. The term "and / or" describes an association relationship for describing related objects and represents three possible relationships. For example, A and / or B may represent the following three cases: when only A is present, when both A and B are present, and when only B is present, and A and B may be singular or plural. In the text description of this application, the character " / " represents an "or" relationship between related objects. In the formulas of this application, the character " / " represents a "divide" relationship between related objects. "Comprising at least one of A, B, and C" may represent including A, including B, including C, including A and B, including A and C, including B and C, and including A, B, and C.

[0216] It can be understood that various numbers in the embodiments of the present application are only used for distinction to facilitate description, and are not used to limit the scope of the embodiments of the present application. The sequence numbers of the above processes do not imply the execution order, and the execution order of the processes should be determined based on the functions and internal logic of the processes. [Explanation of symbols]

[0217] 100 Wireless Access Network 110 Access Network Devices 110a, 110b Radio access network device, base station 120 Terminal Devices 120a~120j terminals 120i helicopter or unmanned aerial vehicle 130 Terminal Devices 200 Core Network 210 Access Network Devices 220 Terminal Devices 230 Terminal Devices 240 AI entities 300 Internet 1000 Communication Systems 1400 Communication Equipment 1410 Processing Unit 1420 Transceiver Unit 1500 Communication Equipment 1510 processor 1520 Interface Circuit 1530 memory

Claims

1. A communication method applied to a first device, comprising: receiving instruction information from a second device, the instruction information indicating a manner of determining transmission parameters of a first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of a second transmission, and the determining manner includes an artificial intelligence (AI)-based determination manner or a non-AI-based determination manner; determining a performance corresponding to the manner of determining a transmission parameter of the first transmission based on the indication information and at least one transmission from the second device, the at least one transmission including the first transmission and / or the second transmission; A method comprising:

2. The AI-based judgment method is at least First AI model-based judgment method and second AI model-based judgment method 2. The method of claim 1, comprising:

3. The AI-based determination method is as follows: AI-based CSI feedback method, AI-based CSI compression method, AI-based CSI reconstruction method, AI-based CSI prediction method, and AI-based beam prediction method wherein the non-AI-based determination method comprises one of the following: Non-AI-based CSI feedback methods, Non-AI-based CSI compression methods, Non-AI based CSI reconstruction methods, Non-AI-based CSI prediction methods, and Non-AI based beam prediction method The method of claim 2, comprising one of:

4. The method of claim 1 , wherein the first transmission comprises one transmission or multiple transmissions or transmissions within a first period of time.

5. The step of receiving the instruction information from the second device includes: receiving downlink control information from the second device, the downlink control information indicating a manner of the determination of the transmission parameters of the first transmission, the first transmission being a transmission scheduled by using the downlink control information; or receiving higher layer signaling from the second device, the higher layer signaling indicating a manner of the determination of the transmission parameters of the first transmission; 5. The method of claim 1, comprising:

6. The indication information indicates a first transmission pattern including a first determination manner corresponding to N transmissions, the N transmissions including the first transmission, the first determination manner being the manner of determination of the transmission parameters of the first transmission, and N being a positive integer; or 6. The method according to claim 1, wherein the instruction information indicates a second transmission pattern including a first determination scheme corresponding to the transmission within the first period, the transmission within the first period including the first transmission, and the first determination scheme is a scheme for determining the transmission parameters of the first transmission.

7. The indication information includes index information of the manner of determining the transmission parameters of the first transmission; or 7. The method according to claim 1, wherein the instruction information includes type information of the first transmission, and the manner of determining the transmission parameters of the first transmission corresponds to the type of the first transmission.

8. 8. The method according to claim 1, wherein the instruction information includes instruction information for the first transmission and instruction information for the second transmission, or indicates transmission time points of the first transmission and the second transmission, or indicates that a manner of determining the transmission parameters for the first transmission is the same as a manner of determining the transmission parameters for the second transmission.

9. 9. The method of claim 8, wherein the indication information of the first transmission includes an index of the first transmission and / or time-frequency resource indication information of the first transmission, and the indication information of the second transmission includes an index of the second transmission and / or time-frequency resource indication information of the second transmission.

10. The step of determining the performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information and the at least one transmission from the second device includes: determining, within each period after the indication information is received, the performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information from the second device and the at least one transmission within the period; 10. The method of any one of claims 1 to 9, comprising:

11. transmitting first information to said second device, wherein said first information comprises said capability or said first information comprises the following: performance of at least one determination method among the plurality of determination methods; A judgment method corresponding to optimal performance among performances corresponding to a plurality of judgment methods; a determination method corresponding to a performance higher than a threshold value among the performances corresponding to the plurality of determination methods; a determination method corresponding to a performance lower than the threshold value among the performances corresponding to the plurality of determination methods; or indicating one or more of the determination methods recommended by the first device among the capabilities corresponding to the plurality of determination methods; The method of claim 1 , wherein the plurality of determination schemes includes a scheme for determining transmission parameters of each of the at least one transmission sent by the second device.

12. the first device is a terminal device, the second device is a network device, and the first transmission is a downlink transmission; or 12. The method of claim 1, wherein the first device is a network device, the second device is a terminal device, and the first transmission is an uplink transmission.

13. A communication method applied to a second device, comprising: sending instruction information to a first device, the instruction information indicating a manner of determining transmission parameters of a first transmission, or the instruction information indicating that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of a second transmission, and the determining manner includes an artificial intelligence (AI)-based determining manner or a non-AI-based determining manner; sending at least one transmission to the first device, the at least one transmission including the first transmission and / or the second transmission; A method comprising:

14. The AI-based judgment method is at least First AI model-based judgment method and second AI model-based judgment method 14. The method of claim 13, comprising:

15. The AI-based determination method is as follows: AI-based CSI feedback method, AI-based CSI compression method, AI-based CSI reconstruction method, AI-based CSI prediction method, and AI-based beam prediction method wherein the non-AI-based determination method comprises one of the following: Non-AI-based CSI feedback methods, Non-AI-based CSI compression methods, Non-AI based CSI reconstruction methods, Non-AI-based CSI prediction methods, and Non-AI based beam prediction method 15. The method of claim 14, comprising one of:

16. 16. The method of claim 13, wherein the first transmission comprises one transmission or multiple transmissions or transmissions within a first period of time.

17. The step of transmitting the instruction information to the first device includes:

17. The method according to claim 13, comprising: transmitting downlink control information to the first device, the downlink control information indicating a manner of determining the transmission parameters of the first transmission, the first transmission being a transmission scheduled by using the downlink control information; or transmitting higher layer signaling to the first device, the higher layer signaling indicating a manner of determining the transmission parameters of the first transmission.

18. The indication information indicates a first transmission pattern including a first determination manner corresponding to N transmissions, the N transmissions including the first transmission, the first determination manner being the manner of determination of the transmission parameters of the first transmission, and N being a positive integer; or 18. The method according to claim 13, wherein the instruction information indicates a second transmission pattern including a first determination scheme corresponding to the transmission within the first period, the transmission within the first period including the first transmission, and the first determination scheme is a scheme for determining the transmission parameters of the first transmission.

19. 19. The method according to claim 13, wherein the indication information includes index information of a manner of determining the transmission parameters of the first transmission, or the indication information includes type information of the first transmission, and the manner of determining the transmission parameters of the first transmission corresponds to the type of the first transmission.

20. 20. The method according to claim 13, wherein the indication information includes indication information for the first transmission and indication information for the second transmission, or the indication information indicates transmission time points of the first transmission and the second transmission.

21. 21. The method of claim 20, wherein the indication information of the first transmission includes an index of the first transmission and / or time-frequency resource indication information of the first transmission, and the indication information of the second transmission includes an index of the second transmission and / or time-frequency resource indication information of the second transmission.

22. The step of determining the performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information and the at least one transmission from the second device includes: determining, within each period after the indication information is received, the performance corresponding to the manner of determining the transmission parameters of the first transmission based on the indication information from the second device and the at least one transmission within the period; 22. The method of any one of claims 13 to 21, comprising:

23. receiving first information from the first device, wherein the first information corresponds to a manner of determining the transmission parameters of the first transmission and includes the capability determined by the first device based on the indication information and the at least one transmission sent by the second device, or the first information is one of the following: performance of at least one determination method among the plurality of determination methods; A judgment method corresponding to optimal performance among performances corresponding to a plurality of judgment methods; a determination method corresponding to a performance higher than a threshold value among the performances corresponding to the plurality of determination methods; a determination method corresponding to a performance lower than the threshold value among the performances corresponding to the plurality of determination methods; and and indicating one or more of the determination methods recommended by the terminal device among the capabilities corresponding to the plurality of determination methods; 23. The method of claim 13, wherein the plurality of determining schemes includes a scheme for determining transmission parameters of each of the at least one transmission sent by the second device.

24. the first device is a terminal device, the second device is a network device, and the first transmission is a downlink transmission; or 24. The method of any one of claims 13 to 23, wherein the first device is a network device, the second device is a terminal device, and the first transmission is an uplink transmission.

25. sending instruction information by the second device to the first device, wherein the instruction information indicates a manner of determining transmission parameters of the first transmission, or the instruction information indicates that the manner of determining transmission parameters of the first transmission is the same as the manner of determining transmission parameters of the second transmission; sending, by the second device, at least one transmission to the first device, the at least one transmission including the first transmission and / or the second transmission; determining, by the first device, a performance corresponding to the manner of determining a transmission parameter of the first transmission based on the indication information and the at least one transmission from the second device; A communication method including:

26. A communication system comprising a first device configured to perform the method of any one of claims 1 to 12 and a second device configured to perform the method of any one of claims 13 to 24.

27. A communication device comprising a unit or module configured to implement the method according to any one of claims 1 to 12 or comprising a unit or module configured to implement the method according to any one of claims 13 to 24.

28. A communications device comprising one or more processors and one or more memories, wherein the one or more memories store one or more computer programs that, when executed by the one or more processors, cause the communications device to perform the method of any one of claims 1 to 12 or any one of claims 13 to 24.

29. A chip system comprising at least one chip and a memory, wherein the at least one chip is configured to read and execute a program stored in the memory to perform the method of any one of claims 1 to 12 or the method of any one of claims 13 to 24.

30. 25. A readable storage medium, the readable storage medium comprising a program, which when executed on an apparatus causes the apparatus to carry out the method of any one of claims 1 to 12 or any one of claims 13 to 24.

31. A program product, which when running on an apparatus causes the apparatus to carry out the method of any one of claims 1 to 12 or the method of any one of claims 13 to 24.

Images