Communication method and device

Abstract

Provided are a communication method and apparatus, the method comprising: a terminal device obtaining first configuration information, the first configuration information comprising one or more of the following: a type of the first information, a quantization granularity of the first information, a feedback resource of the first information, a feedback period of the first information, and a measurement resource corresponding to the first information, a reference signal corresponding to the first information, and a mapping relationship between the reference signal corresponding to the first information and a measurement resource corresponding to the first information; the terminal equipment sends first information to the network equipment according to the first configuration information, and the first information is used for assisting an artificial intelligence AI model of the network equipment; and the network equipment assists the AI model of the network equipment according to the first information. According to the method provided by the invention, the terminal equipment can flexibly send the first information to the network equipment according to the first configuration information, so that the utilization efficiency of resources can be improved, and the spectrum utilization efficiency of a system is improved.

Description

Communication method and device Technical Field

[0001] The present application relates to the field of communications, and in particular, to a communication method and device. Background Art

[0002] Currently, terminal devices can report channel state information (CSI) to network devices. However, the configuration information related to CSI (for example, the configuration information includes feedback cycle, feedback resources, etc.) is relatively fixed. With the development of technologies such as artificial intelligence (AI) and perception, the integration of communication networks, perception networks, and computing power networks has become one of the trends in next-generation communication systems. The introduction of technologies such as AI and perception into communication systems will generate a variety of AI or perception-related information, and terminals may report various types of information to network devices. This information may be strongly related to the environment and have time-varying characteristics.

[0003] Therefore, the current relatively fixed configuration and reporting mechanism can no longer meet the needs.

[0004] Summary of the Invention

[0005] The present application provides a communication method and apparatus for solving the problem of a terminal device feeding back information to a network device based on relatively fixed configuration information.

[0006] In a first aspect, a communication method is provided, including: a terminal device obtains first configuration information, the first configuration information including one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; the terminal device sends the first information to a network device according to the first configuration information, and the first information is used to assist an artificial intelligence AI model of the network device.

[0007] According to the method of the present application, the terminal device can flexibly send the first information to the network device based on the first configuration information. Compared with the terminal device sending the first information based on the same configuration information, the method of the present application can improve resource utilization efficiency and improve the spectrum utilization efficiency of the system.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

[0009] In combination with the first aspect, in certain implementations of the first aspect, the terminal device obtains the first configuration information, including: the terminal device determines the quantization granularity of the first information based on the service quality requirements of the first information; and / or, the terminal device determines the feedback period of the first information based on the change frequency of the first information.

[0010] According to the method of the present application, the terminal device determines the first configuration information by itself, which can reduce the signaling interaction between the terminal device and the network device and save resources.

[0011] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the terminal device sending the quantization granularity of the first information and / or the feedback period of the first information to the network device.

[0012] In combination with the first aspect, in some implementations of the first aspect, the terminal device obtains the first configuration information, including: the terminal device obtains the first configuration information from predefined configuration information.

[0013] According to the method of the present application, the terminal device obtains the first configuration information from the predefined configuration information, which can reduce the signaling interaction between the terminal device and the network device and save resources.

[0014] In combination with the first aspect, in some implementations of the first aspect, the terminal device obtains the first configuration information, including: the terminal device obtains the first configuration information from the network device.

[0015] In combination with the first aspect, in some implementations of the first aspect, the method also includes: the terminal device obtains a mapping relationship between the index and the configuration information, and the mapping relationship between the index and the configuration information includes a first mapping relationship between the first index and the first configuration information; the terminal device obtains the first configuration information, including: the terminal device obtains the first configuration information based on the mapping relationship and the first index.

[0016] According to the method of the present application, the terminal device can obtain the first configuration information through the first index, which can reduce resource consumption compared to directly sending the specific content of the first configuration information to the terminal device.

[0017] In combination with the first aspect, in some implementations of the first aspect, the mapping relationship between the index and the configuration information is predefined.

[0018] In combination with the first aspect, in some implementations of the first aspect, the terminal device obtains the mapping relationship between the index and the configuration information, including: the terminal device obtains the mapping relationship between the index and the configuration information from the network device.

[0019] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the terminal device obtains second configuration information, the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0020] According to the method of the present application, when one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perceived network of the terminal device, and the channel status between the terminal device and the network device are updated, the terminal device updates the first configuration information. The updated first configuration information will be better adapted to the AI ​​model of the network device, the AI ​​model of the terminal device, the channel status between the terminal device and the network device, or the perceived network of the terminal device, thereby ensuring the effectiveness of the first information measurement and feedback process.

[0021] According to a second aspect, a communication method is provided, including: a network device receives first information from a terminal device, the first information is used to assist an artificial intelligence (AI) model of the network device, the first information corresponds to first configuration information, and the first configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; the network device assists the AI ​​model of the network device according to the first information.

[0022] According to the method of the present application, the terminal device can flexibly send the first information to the network device based on the first configuration information. Accordingly, the network device can assist the AI ​​model of the network device based on the first information.

[0023] In combination with the second aspect, in certain implementations of the second aspect, the quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

[0024] In combination with the second aspect, in some implementations of the second aspect, the method further includes: the network device determining the first configuration information; and the network device sending the first configuration information to the terminal device.

[0025] In combination with the second aspect, in some implementations of the second aspect, the method also includes: the network device sends a mapping relationship between an index and configuration information to the terminal device, and the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; the network device sends the first index to the terminal device.

[0026] According to the method of the present application, the network device can send a first index to the terminal device to indicate the first configuration information, which can reduce resource consumption compared to directly sending the specific content of the first configuration information to the terminal device.

[0027] In combination with the second aspect, in some implementations of the second aspect, the method also includes: if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel status between the terminal device and the network device are updated, the network device sends second configuration information to the terminal device, and the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0028] On the third aspect, a communication device is provided, which can be used in the terminal device of the first aspect, or can be a device in the terminal device (for example, a chip, or a chip system, or a circuit), or can be a device that can be used in combination with the terminal device.

[0029] In one possible implementation, the communication device may include a module or unit corresponding to the method / operation / step / action described in the first aspect. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0030] In one possible implementation, the communication device includes: a transceiver unit and a processing unit connected to the transceiver unit. The transceiver unit or the processing unit is used to obtain first configuration information, where the first configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; the transceiver unit is used to send the first information to a network device according to the first configuration information, where the first information is used to assist an artificial intelligence (AI) model of the network device.

[0031] In combination with the third aspect, in certain implementations of the third aspect, the quantization granularity of the first information is related to the service quality requirements of the first information, the feedback cycle of the first information is related to the change frequency of the first information, the feedback resources of the first information are related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resources corresponding to the first information are related to the type of the first information.

[0032] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is used to determine the quantization granularity of the first information based on the service quality requirements of the first information; and / or the processing unit is used to determine the feedback period of the first information based on the change frequency of the first information.

[0033] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is configured to send the quantization granularity of the first information and / or the feedback period of the first information to the network device.

[0034] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is configured to obtain the first configuration information from predefined configuration information.

[0035] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is configured to obtain the first configuration information from the network device.

[0036] In combination with the third aspect, in certain implementations of the third aspect, the transceiver unit is used to obtain a mapping relationship between an index and configuration information, wherein the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; the transceiver unit is used to obtain the first configuration information based on the mapping relationship and the first index.

[0037] In combination with the third aspect, in certain implementations of the third aspect, the mapping relationship between the index and the configuration information is predefined.

[0038] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is configured to obtain a mapping relationship between the index and the configuration information from the network device.

[0039] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit or the processing unit is used to obtain second configuration information, where the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0040] In a fourth aspect, a communication device is provided, which can be used in the network device of the second aspect, or can be a device in the network device (for example, a chip, or a chip system, or a circuit), or can be a device that can be used in conjunction with the network device.

[0041] In one possible implementation, the communication device may include a module or unit corresponding to the method / operation / step / action described in the second aspect. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0042] In a possible implementation, the communication device includes: a transceiver unit and a processing unit connected to the transceiver unit.

[0043] A transceiver unit is used to receive first information from a terminal device, where the first information is used to assist an artificial intelligence (AI) model of the network device, where the first information corresponds to first configuration information, and the first configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; a processing unit is used to assist the AI ​​model of the network device based on the first information.

[0044] In combination with the fourth aspect, in certain implementations of the fourth aspect, the quantization granularity of the first information is related to the service quality requirement of the first information, the feedback cycle of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

[0045] In combination with the fourth aspect, in some implementations of the fourth aspect, the processing unit is used to determine the first configuration information; and the transceiver unit is used to send the first configuration information to the terminal device.

[0046] In combination with the fourth aspect, in certain implementations of the fourth aspect, the transceiver unit is used to send a mapping relationship between an index and configuration information to the terminal device, wherein the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; the transceiver unit is used to send the first index to the terminal device.

[0047] In combination with the fourth aspect, in certain implementations of the fourth aspect, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel status between the terminal device and the network device are updated, the transceiver unit is used to send second configuration information to the terminal device, and the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0048] In a fifth aspect, a communication device is provided, comprising a communication interface and a processor, wherein the communication interface is used to output and / or input signals, and the processor is used to execute a computer program or instruction stored in a memory, so that the communication device executes the method in any possible implementation manner in the first aspect; or, the communication device executes the method in any possible implementation manner in the second aspect.

[0049] Optionally, the memory may be included in the communication device. As one approach, the memory may be provided separately from the processor; as another approach, the memory may be located in the processor and integrated with the processor.

[0050] Optionally, the memory may also be outside the communication device and coupled to the processor.

[0051] In a sixth aspect, a computer-readable storage medium is provided, comprising a computer program, which, when executed on a computer, enables the computer to execute the method in any possible implementation of the first to second aspects.

[0052] In a seventh aspect, a chip or chip system is provided, comprising a processing circuit and an input / output interface, wherein the processing circuit is configured to execute the method of any possible implementation of the first aspect; or the processing circuit is configured to execute the method of any possible implementation of the second aspect. The input / output interface is configured to input and / or output signals.

[0053] In an eighth aspect, a computer program product is provided, which includes: a computer program (also referred to as code, or instructions), which, when the computer program is run, enables the computer to execute the method in any possible implementation of the first aspect; or, enables the computer to execute the method in any possible implementation of the second aspect.

[0054] In a ninth aspect, a communication system is provided, comprising a terminal device and a network device. The terminal device is configured to execute the method in any possible implementation of the first aspect. The network device is configured to execute the method in any possible implementation of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] FIG1 shows a communication system to which the present application is applicable.

[0056] FIG2 is a schematic interaction diagram of an example of the method proposed in this application.

[0057] FIG3 is a schematic interaction diagram of an example of the method proposed in this application.

[0058] FIG4 is a schematic interaction diagram of an example of the method proposed in this application.

[0059] FIG5 is a schematic interaction diagram of an example of the method proposed in this application.

[0060] FIG6 is a schematic interaction diagram of an example of the method proposed in this application.

[0061] FIG7 is a schematic block diagram of a communication device provided in this application.

[0062] FIG8 is a schematic block diagram of a communication device provided in this application. DETAILED DESCRIPTION

[0063] The technical solutions of the embodiments of the present application can be applied to various third-generation partnership project (3GPP) communication systems, such as: long term evolution (LTE) systems, for example, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, fifth generation (5G) communication systems, also known as new radio (NR) communication systems, future evolved communication systems, such as: sixth generation (6G) communication systems, etc.

[0064] It should be understood that the term "and / or" as used herein is merely a description of an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the symbol " / " used in this application can represent "and / or," for example, A / B represents A and / or B.

[0065] It should be understood that in the embodiments of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0066] The term "plurality" used in the embodiments of the present application refers to two or more.

[0067] The first, second, etc. descriptions appearing in the embodiments of this application are only used for illustration and distinction of the described objects. There is no order, nor does it indicate any special limitation on the number of described objects in the embodiments of this application, and cannot constitute any limitation on the embodiments of this application.

[0068] Figure 1 shows a communication system to which this application is applicable, which includes a terminal device, an AI model for the terminal device, a perception network for the terminal device, a network device, an AI model for the network device, and a perception network for the network device.

[0069] In this application, terminal devices can be various devices that provide voice and / or data connectivity to users, and can also be referred to as terminals, user equipment (UE), mobile stations, mobile terminals, etc. Terminal devices can be widely used in various scenarios, such as customer-premises equipment (CPE), smart point of sale (POS), device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), Internet of Things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, drone, vehicle-mounted equipment, aerospace equipment, etc. In the embodiments of this application, the chip used in the above-mentioned devices can also be referred to as a terminal.

[0070] The network device in the embodiment of the present application may be an access network device such as a base station, and the base station may be an evolutionary nodeB (eNB or eNodeB) in an LTE system, a next generation NodeB (gNB) in a fifth generation (5G) mobile communication system, a next generation base station in a communication system that evolves after 5G, such as a sixth generation (6G) mobile communication system, etc. The embodiment of the present application does not limit the specific technology and specific device form adopted by the network device, for example, it may be: a macro base station, a micro base station (also known as a small station), a relay station, an access point, a transmission point (TRP), a transmitting point (TP), a mobile switching center, a network device in a non-terrestrial network (NTN) communication system (i.e., it can be deployed on a high-altitude platform or satellite), and a device that assumes the base station function in D2D, V2X, and MTC communications. The network device may be a module or unit that performs part of the functions of a base station, for example, it may be a centralized unit (CU) or a distributed unit (DU). The CU and DU each implement a portion of the base station's protocol stack functions. Furthermore, the CU's functions can be implemented by multiple entities. For example, the CU's control plane (CP) and user plane (UP) functions can be separated to form the CU control plane (CU-CP) and CU user plane (CU-UP). For example, the CU-CP and CU-UP can be implemented by different functional entities and connected via an E1 interface. The CU-CP and CU-UP can also be coupled to the DU.

[0071] For easier understanding, some terms in this application are explained below.

[0072] (1) Channel related information:

[0073] Channel-related information includes but is not limited to one or more of the following:

[0074] Rank indicator (RI), precoding matrix indicator (PMI), channel quality information (CQI), CSI-RS resource indicator (CRI), synchronization signal (SS) / physical layer broadcast channel (PBCH) resource block indicator (SS / PBCH resource block indicator, SSRBI), layer indicator (LI), layer 1-reference signal receiving power (L1-RSRP), signal to noise ratio (SNR), signal to interference plus noise ratio (SINR), and complete channel information, such as channel amplitude and channel phase, where the channel phase includes angle of arrival (AoA) and angle of departure (AoD).

[0075] Exemplarily, the channel-related information may be CSI.

[0076] (2) Information about the AI ​​model of the terminal device:

[0077] Information related to the AI ​​model of the terminal device includes, but is not limited to, one or more of the following:

[0078] AI model accuracy, AI model loss value, mean square error, mean absolute error, mean bias error, cross entropy loss, gradients, and the correlation between the base station AI model and the terminal device AI model.

[0079] (3) Relevant information of the perception network:

[0080] Related information about the sensory network includes, but is not limited to, one or more of the following:

[0081] The number of multipath paths, the distance of each path, Doppler shift, Doppler spread, fading rate, level cross rate (LCR), average fading duration (AFD), multipath delay, average delay, delay spread, and perceived environmental information (for example, weather information such as temperature and humidity).

[0082] (4) System performance related information:

[0083] Information related to system performance includes, but is not limited to, one or more of the following:

[0084] Block error rate (BLER), bit error rate (BER), code block group error ratio (COGER), throughput, and latency.

[0085] The relevant information of the above system performance can be obtained through the AI ​​model or independently (not through the AI ​​model).

[0086] (5) AI-assisted information:

[0087] AI-assisted information is used to assist the AI ​​model of the network device, for example, to assist the AI ​​model in training, inference, verification, testing, and other operations. AI-assisted information can serve as an input parameter for training, inference, verification, or testing the AI ​​model. For example, AI-assisted information can be training data for the AI ​​model of the network device.

[0088] AI-assisted information includes but is not limited to one or more of the following:

[0089] CSI, information related to the AI ​​model of the terminal device, information related to the perception network of the terminal device, and information related to system performance.

[0090] In other words, AI-assisted information may also include other types of information. For example, the training data of the AI ​​model of a network device may also include other types of information.

[0091] The solution of this application is introduced below.

[0092] FIG2 shows a method 200 proposed in this application, which includes:

[0093] S201: The terminal device obtains first configuration information. The first configuration information is associated with the type of the first information.

[0094] Specifically, the terminal device obtains the first configuration information in the following ways: the terminal device determines the first configuration information by itself, the terminal device obtains the first configuration information from predefined configuration information according to a protocol, or the terminal device obtains the first configuration information from a network device. For detailed processes, please refer to the following methods 300 to 600.

[0095] The first configuration information includes one or more of the following:

[0096] The type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0097] It should be understood that the first information in this application can be understood as a certain type of information.

[0098] Exemplarily, the feedback resources of the first information and the measurement resources corresponding to the first information include time domain resources, frequency domain resources, code domain resources, density, sequence, etc.

[0099] For example, the type of the first information includes but is not limited to one or more of the following:

[0100] CSI, information related to the AI ​​model of the terminal device, information related to the perception network of the terminal device, and information related to system performance.

[0101] In one possible implementation, the first information needs to be obtained through measurement of a reference signal, and the first configuration information includes one or more of the measurement resources corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resources corresponding to the first information, wherein the measurement resources corresponding to the first information are the resources occupied by the reference signal corresponding to the first information.

[0102] Exemplarily, the reference signal corresponding to the first information may include but is not limited to one or more of the following: the type of the reference signal corresponding to the first information, the generation sequence of the reference signal corresponding to the first information, and the generation criteria of the reference signal corresponding to the first information.

[0103] It should also be understood that the quantization granularity can represent how many bits are used to indicate a certain information. For example, the larger the quantization granularity of the first information, the fewer bits the terminal device can use to transmit the first information.

[0104] In one possible implementation, the quantization granularity of the first information is related to the quality of service requirements (e.g., reliability requirements) of the first information, the feedback period of the first information is related to the frequency of change of the first information, the feedback resource of the first information is related to the adjustment range of the AI ​​model of the network device, and the measurement resource corresponding to the first information is related to the type of the first information. This will be described in detail later.

[0105] The feedback period (or reporting period) of the first information may be a period for the terminal device to feed back / report the first information to the network device.

[0106] S202: The terminal device sends first information to the network device according to the first configuration information. Correspondingly, the network device receives the first information from the terminal device.

[0107] The first information is used to assist the AI ​​model of the network device. That is, the first information is AI auxiliary information. As can be seen from the above, the type of the first information includes but is not limited to one or more of the following:

[0108] CSI, information related to the AI ​​model of the terminal device, information related to the perception network of the terminal device, and information related to system performance.

[0109] The following describes the process in different situations.

[0110] Case 1:

[0111] The first information is obtained by measuring a reference signal (for example, the type of the first information is CSI or related information of a perception network).

[0112] The network device may send a reference signal to the terminal device on the measurement resource corresponding to the first information. Accordingly, the terminal device may receive the reference signal from the network device based on the reference signal corresponding to the first information (e.g., a sequence corresponding to the reference signal) and the measurement resource corresponding to the first information, measure the reference signal to obtain the first information, and further send the first information to the network device based on the feedback resource and feedback period of the first information.

[0113] In a possible implementation, the terminal device may generate the first information according to the quantization granularity of the first information during the process of obtaining the first information through measurement.

[0114] For example, the terminal device determines to carry the first information in 3 bits based on the quantization granularity of the first information. Then, in the process of generating the first information, the terminal device indicates the first information with 3 bits.

[0115] Case 2:

[0116] The first information does not need to be obtained through reference signal measurement. In this case, the network device does not need to send a reference signal, and the terminal device does not need to measure the reference signal. The terminal device can directly obtain the first information and send the first information to the network device based on the feedback resource and feedback period of the first information.

[0117] In addition, when the terminal device directly obtains the first information, the first information can be generated according to the quantization granularity of the first information.

[0118] S203: The network device assists the AI ​​model of the network device according to the first information.

[0119] During this process, the network device can use the first information as input to assist the AI ​​model in training, deduction, verification, testing and other operations.

[0120] The following are a few examples to illustrate this process:

[0121] Example 1:

[0122] The first information includes first CSI. The network device can use the first CSI as input to train an AI model of the network device. The AI ​​model of the network device can be used to predict second CSI. The first CSI and the second CSI are CSI at different times or on different ports.

[0123] As a possible scenario, the prediction process may include the following steps:

[0124] Step 1: The network device sends a CSI-RS to the terminal device via a downlink channel at the first moment.

[0125] Step 2: The terminal device measures the CSI-RS and obtains the first CSI of the downlink channel at the first moment.

[0126] Step 3: The terminal device sends the first CSI of the downlink channel at the first moment to the network device.

[0127] Step 4: The network device uses the AI ​​model to predict the second CSI of the downlink channel at the second moment based on the first CSI of the downlink channel at the first moment.

[0128] For example, the network device may make predictions based on a deep neural network model, or based on a Kalman prediction model, or based on a Prony method, or based on a linear or nonlinear prediction algorithm, and this application is not limited thereto. The methods or models used by the network device for prediction are not described in detail below.

[0129] As another example, the prediction process may include the following steps:

[0130] Step 1: The network device sends a CSI-RS to the terminal device through the first port at the first moment.

[0131] Step 2: The terminal device measures the CSI-RS and obtains the first CSI of the first port at the first moment.

[0132] Step 3: The terminal device sends the first CSI of the first port at the first moment to the network device.

[0133] Step 4: The network device uses the AI ​​model to predict the second CSI of the second port at the first moment based on the CSI of the first port at the first moment.

[0134] Example 2:

[0135] The first information includes a BLER at a first moment, and the network device may use the BLER at the first moment as input to train an AI model of the network device. The AI ​​model may be used to predict the BLER at a second moment.

[0136] Example 3:

[0137] The first information includes the location information of the terminal device at a first moment. The network device can use the location information of the terminal device at the first moment as input to train an AI model of the network device. The AI ​​model can be used to predict the location information of the terminal device at a second moment.

[0138] According to the method of the present application, a terminal device may send first information to a network device based on first configuration information. The first configuration information includes the type of the first information and may also include other configuration information in addition to the type, such as the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0139] Therefore, the terminal device can flexibly send the first information based on the first configuration information. For example, different types of first information can be sent, and the configuration information of each type of first information can be different. For example, the feedback resources of different types of first information can be different. In addition, the configuration information for the same type of first information can also be different. For example, the relevant information of the AI ​​model of the terminal device can be fed back using different cycles or resources. Compared with the terminal device sending the first information based on the same configuration information, the method of the present application can improve the utilization efficiency of resources and improve the spectrum utilization efficiency of the system.

[0140] Optionally, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel state between the terminal device and the network device are updated, the method further includes:

[0141] S204: The terminal device obtains second configuration information.

[0142] Specifically, the terminal device acquires the second configuration information in the following manner: the terminal device determines the second configuration information by itself, or the terminal device acquires the second configuration information from the network device. Detailed processes can be referred to methods 300 to 600 below.

[0143] The second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0144] Specifically, the second configuration information is used to update one or more of the following in the first configuration information:

[0145] The type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0146] For example, before S204 , the quantization granularity of the first information is M1 bits, and in S204 , the quantization granularity of the first information is updated to M2 bits.

[0147] For another example, before S204, the feedback cycle of the first information is a single feedback, and in S204, the feedback cycle of the first information is updated to N times with T as a period.

[0148] For another example, before S204, the terminal device needs to feed back CSI to the network device; in S204, the terminal device no longer feeds back CSI to the network device according to the second configuration information.

[0149] According to the method of the present application, when one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel status between the terminal device and the network device are updated, the first configuration information corresponding to the first information is also updated accordingly. The updated first configuration information will be better adapted to the AI ​​model of the network device, the AI ​​model of the terminal device, the channel status between the terminal device and the network device, or the perception network of the terminal device, thereby ensuring the effectiveness of the first information measurement and feedback process.

[0150] The method 200 is further described below with reference to FIG. 3 to FIG. 6 .

[0151] FIG3 shows a method 300. In the method 300, the terminal device obtains the first configuration information corresponding to the first information in the following manner: the terminal device determines the first configuration information by itself. Specifically, the method 300 includes:

[0152] S301: The terminal device determines first configuration information corresponding to the first information. For a description of the first configuration information, refer to S201.

[0153] Specifically, the terminal device may determine some parameters in the first configuration information according to the type of the first information. In other words, some parameters in the first configuration information are related to the type of the first information.

[0154] In a possible implementation, the terminal device may determine the quantization granularity of the first information according to a quality of service requirement of the first information.

[0155] Exemplarily, if the service quality requirement of the first information is lower than a first threshold, the terminal device determines that the first information corresponds to a first quantization granularity; if the service quality requirement of the first information is greater than or equal to the first threshold, the terminal device determines that the first information corresponds to a second quantization granularity; the second quantization granularity is smaller than the first quantization granularity.

[0156] Therefore, according to the method of the present application, if the quality of service requirement of the first information is low, the first information can be transmitted based on a larger quantization granularity (fewer bits), thereby saving resources.

[0157] In a possible implementation, the terminal device may determine the feedback period of the first information according to the change frequency of the first information.

[0158] Exemplarily, if the frequency of change of the first information is greater than a second threshold (in other words, the first information has a time-varying characteristic), the terminal device determines that the first information corresponds to a first feedback cycle; if the frequency of change of the first information is less than or equal to the second threshold (in other words, the first information has a slowly varying characteristic), the terminal device determines that the first information corresponds to a second feedback cycle; the second feedback cycle is greater than the first feedback cycle.

[0159] For example, for block error rate, bit error rate, error block group rate, terminal device location, terminal device speed, surrounding environment information, etc., the terminal device can use a longer feedback cycle for feedback, or the terminal device can only feedback to the network device once (equivalent to an infinite feedback cycle); for channel-related information (for example, CSI), the terminal device can use a shorter feedback cycle for feedback.

[0160] Therefore, according to the method of the present application, if the first information has a time-varying characteristic, the feedback cycle of the first information is shorter, thereby avoiding the occurrence of untimely feedback; if the first information has a slowly varying characteristic, the feedback cycle of the first information is longer, thereby saving resources.

[0161] In a possible implementation, the terminal device may determine the feedback resource of the first information from multiple feedback resources configured by the network device.

[0162] Exemplarily, the network device pre-configures a first feedback resource and a second feedback resource for the terminal device. The terminal device may determine the feedback resource for the first information from the two feedback resources.

[0163] For example, the terminal device may determine the feedback resource of the first information from the two feedback resources according to the data size of the first information. The data size of the first information is the number of data included in the first information, such as the number of bits or bytes included in the first information.

[0164] Specifically, if the data amount of the first information is greater than the third threshold, the terminal device selects the feedback resource with a larger number of time slots, symbols, resource elements (RE) or resource blocks (RB) from the above two feedback resources; if the data amount of the first information is less than or equal to the third threshold, the terminal device selects the feedback resource with a smaller number of slots, symbols, RE or RB from the above two feedback resources.

[0165] For another example, the network device may send adjustment amplitude information of the AI ​​model of the network device to the terminal device, and the terminal device may determine the feedback resource of the first information from the above two feedback resources based on the adjustment amplitude information of the AI ​​model of the network device.

[0166] Specifically, if the adjustment amplitude of the AI ​​model of the network device is greater than the fourth threshold, the terminal device selects the feedback resource with a larger number of slots, symbols, REs or RBs from the above two feedback resources; if the adjustment amplitude of the AI ​​model of the network device is less than or equal to the fourth threshold, the terminal device selects the feedback resource with a smaller number of slots, symbols, REs or RBs from the above two feedback resources.

[0167] Therefore, according to the method of the present application, the terminal device can flexibly determine the feedback resources of the first information to avoid waste of resources.

[0168] In a possible implementation, the terminal device may determine the measurement resource corresponding to the first information from multiple measurement resources configured by the network device.

[0169] Exemplarily, the network device pre-configures measurement resource #1 and measurement resource #2 for the terminal device. The terminal device can determine the measurement resource corresponding to the first information from the two measurement resources.

[0170] For example, the terminal device may determine the measurement resource corresponding to the first information based on the type of the first information. When the type of the first information is related information of the perception network, such as the number of multipaths, the distance of each path, Doppler shift, or Doppler spread, obtaining the first information requires more measurement resources. The terminal device may select the measurement resource with a larger number of slots, symbols, REs, or RBs from the above two measurement resources.

[0171] Therefore, according to the method of the present application, the terminal device can flexibly determine the measurement resources corresponding to the first information to avoid waste of resources.

[0172] Optionally, as a method, the terminal device may also independently determine the mapping relationship between the reference signal corresponding to the first information, the reference signal corresponding to the first information, and the measurement resource corresponding to the first information.

[0173] As an implementation method, the terminal device can generate a pseudo-random sequence based on a base sequence, where the pseudo-random sequence includes some parameters that are related to the configuration of the terminal device (e.g., the number of symbols, the configuration of the frame structure, and the scrambling identification (ID) of the terminal device). Furthermore, the terminal device determines a generation sequence of a reference signal corresponding to the first information from the pseudo-random sequence. Further, the terminal device determines, based on a preconfigured rule or algorithm, measurement resources (e.g., time domain resources, frequency domain resources, code domain resources) corresponding to different symbols in the generation sequence.

[0174] Alternatively, as another method, the network device may configure the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information to the terminal device. In other words, the terminal device may not be able to determine this information on its own.

[0175] In addition, the above-mentioned possible implementations are not isolated and can be combined with each other.

[0176] S302: The terminal device sends first configuration information to the network device. Correspondingly, the network device receives the first configuration information from the terminal device.

[0177] That is, the terminal device sends the first configuration information determined by itself in S301 to the network device.

[0178] For example, the terminal device reports the quantization granularity corresponding to the first information and / or the feedback period of the first information determined by itself to the network device.

[0179] For another example, the terminal device reports the measurement resources corresponding to the first information determined by itself and / or the reference signal corresponding to the first information to the network device, and the network device can send the reference signal determined by the terminal device on the measurement resources determined by the terminal device.

[0180] It should be understood that if the first information does not need to be obtained through reference signal measurement, the terminal device may not send the measurement resource corresponding to the first information and / or the reference signal corresponding to the first information to the network device. That is, S302 is an optional step.

[0181] S303: The terminal device sends first information to the network device according to the first configuration information. Correspondingly, the network device receives the first information from the terminal device.

[0182] This process may refer to S202.

[0183] S304: The network device assists the AI ​​model of the network device according to the first information.

[0184] This process may refer to S203.

[0185] According to the method of the present application, a terminal device can determine different first configuration information based on different types of first information, and then send the first information to the network device based on the first configuration information. Compared to a terminal device sending multiple types of first information based on the same configuration information, the method of the present application can improve resource utilization efficiency and improve the spectrum utilization efficiency of the system.

[0186] Optionally, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel state between the terminal device and the network device are updated, the method further includes:

[0187] S305: The terminal device determines second configuration information. The second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0188] In one possible implementation, the network device sends first indication information to the terminal device, where the first indication information is used to instruct the network device to update its AI model, and the terminal device determines the second configuration information based on the first indication information.

[0189] For example, the first indication information indicates that the adjustment range of the AI ​​model of the network device is updated from less than the fourth threshold to greater than the fourth threshold, and the terminal device re-determines the feedback resource of the first information.

[0190] For another example, if the AI ​​model of the network device before the update has the ability to predict the terminal device's location, and the first indication information indicates that the AI ​​model of the network device after the update no longer has the ability to predict the terminal device's location, the terminal device updates the type of the first information, and the updated first information type no longer includes the terminal device's location. In other words, the terminal device no longer feeds back its location information to the network device.

[0191] In one possible implementation, the terminal device determines that the AI ​​model of the terminal device is updated, and the terminal device determines the second configuration information based on the updated AI model of the terminal device.

[0192] For example, before the update, the gradient of the AI ​​model on the terminal device side changes relatively slowly, and the terminal device feeds back the gradient of the AI ​​model of the terminal device to the network device based on a longer feedback cycle; after the update, the gradient of the AI ​​model of the terminal device changes more frequently, and the terminal device feeds back the gradient of the AI ​​model of the terminal device to the network device based on a shorter feedback cycle.

[0193] In a possible implementation, the terminal device determines that the perception network of the terminal device is updated, and the terminal device determines the second configuration information according to the updated perception network of the terminal device.

[0194] For example, before the update, the perception network output result of the terminal device is the ambient temperature, and the terminal device feeds back the ambient temperature to the network device based on a longer feedback cycle; after the update, the perception network output result of the terminal device is the speed of the terminal device, and the terminal device feeds back the speed of the terminal device to the network device based on a shorter feedback cycle.

[0195] In one possible implementation, the terminal device determines that the channel state between the terminal device and the network device is updated, and if the updated channel state does not match the first configuration information, the terminal device determines the second configuration information based on the updated channel state.

[0196] For example, the terminal device determines the channel state update based on the CSI obtained by measurement, and the updated channel state does not match at least one of the feedback resources of the first information, the feedback period of the first information, and the measurement resources corresponding to the first information in the first configuration information, then the terminal device determines the second configuration information.

[0197] According to the method of the present application, when one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perceived network of the terminal device, and the channel status between the terminal device and the network device are updated, the terminal device updates the first configuration information. The updated first configuration information will be better adapted to the AI ​​model of the network device, the AI ​​model of the terminal device, the channel status between the terminal device and the network device, or the perceived network of the terminal device, thereby ensuring the effectiveness of the first information measurement and feedback process.

[0198] FIG4 shows a method 400. In the method 400, the terminal device obtains the first configuration information corresponding to the first information in the following manner: the terminal device obtains the first configuration information from the network device. Specifically, the method 400 includes:

[0199] S401: A network device determines first configuration information corresponding to first information.

[0200] For example, the network device may determine that the type of the first information is one or more of CSI, relevant information of the AI ​​model of the terminal device, relevant information of the perception network of the terminal device, and relevant information of system performance.

[0201] The following describes a process in which a network device determines the first configuration information through several possible implementations:

[0202] In one possible implementation, if the service quality requirement of the first information is lower than a first threshold, the network device determines that the first information corresponds to a first quantization granularity; if the service quality requirement of the first information is greater than or equal to the first threshold, the network device determines that the first information corresponds to a second quantization granularity; the second quantization granularity is smaller than the first quantization granularity.

[0203] In one possible implementation, if the frequency of change of the first information is greater than a second threshold (in other words, the first information has a time-varying characteristic), the network device determines that the first information corresponds to a first feedback cycle; if the frequency of change of the first information is less than or equal to the second threshold (in other words, the first information has a slowly varying characteristic), the network device determines that the first information corresponds to a second feedback cycle; the second feedback cycle is greater than the first feedback cycle.

[0204] In one possible implementation, the network device may determine the feedback resource of the first information based on the adjustment range of the AI ​​model of the network device.

[0205] Specifically, if the adjustment range of the AI ​​model of the network device is greater than the fourth threshold, the feedback resources allocated by the network device include a larger number of slots, symbols, REs or RBs; if the adjustment range of the AI ​​model of the network device is less than or equal to the fourth threshold, the feedback resources allocated by the network device include a smaller number of slots, symbols, REs or RBs.

[0206] In a possible implementation, the network device may determine the measurement resource corresponding to the first information according to the type of the first information.

[0207] Exemplarily, when the type of the first information is relevant information of the perception network, such as the number of multipaths, the distance of each path, Doppler shift or Doppler spread, obtaining the first information requires more measurement resources, and the network device can allocate measurement resources including a larger number of slots, symbols, REs or RBs.

[0208] In addition, the above-mentioned possible implementations are not isolated and can be combined with each other.

[0209] S402: The network device sends first configuration information to the terminal device. Correspondingly, the terminal device receives the first configuration information from the network device.

[0210] Exemplarily, the first configuration information includes one or more of the following:

[0211] The type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0212] It should be understood that the network device may send the first configuration information to the terminal device via one or more messages, and this application is not limited to this. If the network device sends the first configuration information to the terminal device via multiple messages, each of the multiple messages may include one or more of the following configuration information: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0213] The first configuration information may be carried by high-layer or physical layer signaling. The high-layer signaling may include, for example, radio resource control (RRC) signaling, medium access control (MAC) control element (CE), radio link control (RLC) signaling, etc. The physical layer signaling may include, for example, physical downlink control information (DCI), signaling transmitted through a downlink physical layer channel, etc. The downlink physical layer channel may be, for example, a physical downlink control channel (PDCCH) or a physical downlink shared channel (PDSCH).

[0214] S403: The terminal device sends first information to the network device according to the first configuration information. Correspondingly, the network device receives the first information from the terminal device.

[0215] This process may refer to S202.

[0216] S404: The network device assists the AI ​​model of the network device according to the first information.

[0217] This process may refer to S203.

[0218] According to the method of the present application, a terminal device can obtain first configuration information from a network device. For different types of first information, the corresponding first configuration information can also be different. Therefore, the terminal device can flexibly send multiple types of first information based on multiple types of first configuration information. Compared to a terminal device sending multiple types of first information based on the same configuration information, the method of the present application can improve resource utilization efficiency and improve the spectrum utilization efficiency of the system.

[0219] Optionally, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel state between the terminal device and the network device are updated, the method further includes:

[0220] S405: The network device sends second configuration information to the terminal device. Correspondingly, the terminal device receives the second configuration information. The second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0221] The following describes a process in which the network device determines the second configuration information.

[0222] In one possible implementation, the network device determines that an AI model of the network device is updated, and the network device determines the second configuration information based on the updated AI model of the network device.

[0223] For example, if the adjustment range of the AI ​​model of the network device is updated from less than the fourth threshold to greater than the fourth threshold, the network device updates one or more of the feedback cycle of the first information, the feedback resources of the first information, and the measurement resources corresponding to the first information.

[0224] For another example, if the AI ​​model of the network device before the update has the ability to predict the terminal device's location, but after the update the AI ​​model of the network device no longer has the ability to predict the terminal device's location, the network device updates the type of the first information, and the updated first information type no longer includes the terminal device's location. In other words, based on the second configuration information, the terminal device no longer feeds back its location information to the network device.

[0225] In one possible implementation, the terminal device sends second indication information to the network device, where the second indication information is used to instruct the terminal device to update its AI model, and the network device determines the second configuration information based on the second indication information.

[0226] For example, if the gradient of the AI ​​model of the terminal device changes slowly before the update, the feedback cycle of the gradient is longer; if the second indication information indicates that the gradient of the AI ​​model of the terminal device changes frequently after the update, the feedback cycle of the gradient is shorter.

[0227] In one possible implementation, the terminal device sends third indication information to the network device, where the third indication information is used to indicate that the terminal device's perception network is updated, and the network device determines the second configuration information based on the third indication information.

[0228] For example, if the perception network output result of the terminal device before the update is the ambient temperature, the feedback cycle of the ambient temperature is longer; if the third indication information indicates that the perception network output result of the terminal device after the update is the speed of the terminal device, the feedback cycle of the speed of the terminal device is shorter.

[0229] In one possible implementation, the network device determines that the channel state between the terminal device and the network device is updated, and if the updated channel state does not match the first configuration information, the network device determines the second configuration information based on the updated channel state.

[0230] For example, the network device determines the channel state update based on the CSI feedback from the terminal device, and the updated channel state does not match at least one of the feedback resources of the first information, the feedback period of the first information, and the measurement resources corresponding to the first information in the first configuration information, then the network device determines the second configuration information.

[0231] According to the method of the present application, when one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perceived network of the terminal device, and the channel status between the terminal device and the network device are updated, the network device updates the first configuration information. The updated first configuration information will be better adapted to the AI ​​model of the network device, the AI ​​model of the terminal device, the channel status between the terminal device and the network device, or the perceived network of the terminal device, thereby ensuring the effectiveness of the first information measurement and feedback process.

[0232] FIG5 shows a method 500. In the method 500, the terminal device obtains the first configuration information corresponding to the first information in the following manner: the terminal device obtains the first configuration information according to the mapping relationship between the index and the configuration information and the first index. Specifically, the method 500 includes:

[0233] S501: The terminal device obtains a mapping relationship between an index and configuration information.

[0234] For ease of description, the mapping relationship between the index obtained by the terminal device and the configuration information is recorded as mapping relationship #A. Mapping relationship #A includes a first mapping relationship between the first index and the first configuration information.

[0235] As a method, the network device may send the mapping relationship #A to the terminal device, and accordingly, the terminal device receives the mapping relationship #A.

[0236] The mapping relationship #A can be carried by high-layer signaling or physical layer signaling. For the relevant introduction of the high-layer signaling and physical layer signaling, please refer to the above.

[0237] As another approach, the mapping relationship #A may also be predefined in the protocol.

[0238] For example, mapping relationship #A is shown in Table 1. In Table 1, the same type of first information can correspond to multiple different other configuration information, and the other configuration information includes one or more of the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0239] In addition, if one or more of the quantization granularity of the first information, the feedback resources of the first information, the feedback period of the first information, the measurement resources corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resources corresponding to the first information are not included in the mapping relationship #A, then this information can be predefined.

[0240] Table 1

[0241]

[0242] In Table 1, the first information type belongs to some subcategories within certain major categories, for example, the number of multipaths belongs to information related to the perception network. Alternatively, as shown in Table 1-2, the first information type can be certain major categories; as shown in Table 1-2-1, the first information type belongs to some subcategories within information related to the AI ​​model; and as shown in Table 1-2-2, the first information type belongs to some subcategories within information related to the perception network.

[0243] Table 1-2

[0244]

[0245]

[0246] Table 1-2-1

[0247]

[0248] Table 1-2-2

[0249]

[0250] For another example, mapping relationship #A includes mapping relationship #A1 and mapping relationship #A2. As shown in Table 2, mapping relationship #A1 is a mapping relationship between an index and a type of first information. As shown in Table 3, mapping relationship #A2 is a mapping relationship between a type of first information and other configuration information.

[0251] Table 2

[0252] Index Type of first information 1 Number of multipaths 2 Doppler information (accuracy level 1) 3 Doppler information (accuracy level 2) 4 Complete channel information …………

[0253] Table 3

[0254]

[0255] It should be understood that Table 2 and Table 3 should be used in conjunction with each other.

[0256] S502: The network device sends a first index to the terminal device. Correspondingly, the terminal device receives the first index.

[0257] Illustratively, the network device also stores the information in Table 1 above; or, stores the information in Table 2 and Table 3.

[0258] The first index is one of the multiple indexes in S501, and the first index is associated with the first configuration information. As an implementation manner, the network device may send a DCI to the terminal device, where the DCI includes the first index.

[0259] Exemplarily, as shown in Table 1, in order to send configuration information corresponding to the "number of multipaths" to the terminal device, the first index may indicate "1"; in order to send configuration information corresponding to the "gradient of the AI ​​model of the terminal device" to the terminal device, the first index may indicate "2".

[0260] For example, as shown in Table 2, in order to send configuration information corresponding to the "number of multipaths" to the terminal device, the first index may indicate "1"; in order to send configuration information corresponding to the "complete channel information" to the terminal device, the first index may indicate "4".

[0261] S503: The terminal device obtains first configuration information according to the first index and the mapping relationship #A received in S501.

[0262] S504: The terminal device sends first information to the network device according to the first configuration information. Correspondingly, the network device receives the first information from the terminal device.

[0263] This process may refer to S202.

[0264] S505: The network device assists the AI ​​model of the network device according to the first information.

[0265] This process may refer to S203.

[0266] According to the method of the present application, the terminal device obtains the first configuration information based on the mapping relationship #A and the first index. For different types of first information, the corresponding first configuration information may also be different. Therefore, the terminal device can flexibly send multiple types of first information based on multiple types of first configuration information. Compared to a terminal device sending multiple types of first information based on the same configuration information, the method of the present application can improve resource utilization efficiency and improve the spectrum utilization efficiency of the system.

[0267] Optionally, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel state between the terminal device and the network device are updated, the method further includes:

[0268] S506: The network device sends a second index to the terminal device. Correspondingly, the terminal device receives the second index. The mapping relationship #A includes a second mapping relationship between the second index and the second configuration information.

[0269] Optionally, if the network device determines that the mapping relationship #A in S501 does not include the second mapping relationship, the network device may also directly send the second configuration information to the terminal device.

[0270] The following describes a process in which the network device determines the second index by taking the mapping relationship #A in S501 including the second mapping relationship as an example.

[0271] In one possible implementation, the network device determines that the AI ​​model of the network device is updated, and the network device determines the second configuration information based on the updated AI model of the network device, and then determines the second index.

[0272] For example, if the adjustment range of the AI ​​model of the network device is updated from less than the fourth threshold to greater than the fourth threshold, the network device determines the second configuration information from the mapping relationship #A, and then determines the second index. The second configuration information is applicable to the AI ​​model of the updated network device.

[0273] In one possible implementation, the terminal device sends a second indication message to the network device, where the second indication message is used to indicate that the AI ​​model of the terminal device is updated. The network device determines the second configuration information from the mapping relationship #A based on the second indication message, and then determines the second index. The second configuration information is applicable to the AI ​​model of the terminal device after the update.

[0274] In one possible implementation, the terminal device sends a third indication message to the network device, and the third indication message is used to indicate that the terminal device's perception network is updated. The network device determines the second configuration information from the mapping relationship #A based on the third indication message, and then determines the second index. The second configuration information is applicable to the perception network of the terminal device after the update.

[0275] In one possible implementation, the network device determines that the channel status between the terminal device and the network device is updated, and the updated channel status does not match the first configuration information. The network device then determines the second configuration information from the mapping relationship #A based on the updated channel status, and then determines the second index. The second configuration information is applicable to the updated channel status.

[0276] The beneficial effects of S506 can be found in the above text and will not be elaborated here.

[0277] FIG6 shows a method 600. In the method 600, the terminal device obtains the first configuration information corresponding to the first information in the following manner: the terminal device obtains the first configuration information from predefined configuration information. Specifically, the method 600 includes:

[0278] S601: The terminal device obtains first configuration information from predefined configuration information.

[0279] For the related description of the first configuration information, please refer to S201.

[0280] It should be understood that the terminal device and the network device may follow the same communication protocol, in which the configuration information is predefined.

[0281] As a method, the predefined configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and the mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information.

[0282] Exemplarily, the predefined configuration information may be as shown in Table 3 in S501.

[0283] In one possible implementation, the terminal device obtains configuration information corresponding to the CSI from predefined configuration information.

[0284] In one possible implementation, the terminal device obtains configuration information corresponding to the relevant information of the AI ​​model from predefined configuration information.

[0285] In a possible implementation, the terminal device obtains configuration information corresponding to the relevant information of the perception network from predefined configuration information.

[0286] In a possible implementation, the terminal device obtains configuration information corresponding to the relevant information of the system performance from predefined configuration information.

[0287] It should be understood that the above possible implementations are not isolated and can be combined with each other. For example, if the type of the first information includes CSI and related information of the perception network, the terminal device obtains the configuration information corresponding to the CSI and the configuration information corresponding to the related information of the perception network from the predefined configuration information.

[0288] S602: The terminal device sends first information to the network device according to the first configuration information. Correspondingly, the network device receives the first information from the terminal device.

[0289] This process may refer to S202.

[0290] S603: The network device assists the AI ​​model of the network device according to the first information.

[0291] This process may refer to S203.

[0292] According to the method of the present application, a terminal device can obtain first configuration information from predefined configuration information. For different types of first information, the corresponding first configuration information can also be different. Therefore, the terminal device can flexibly send multiple types of first information based on multiple types of first configuration information. Compared to a terminal device sending multiple types of first information based on the same configuration information, the method of the present application can improve resource utilization efficiency and improve the spectrum utilization efficiency of the system.

[0293] Optionally, if one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel state between the terminal device and the network device are updated, the method further includes:

[0294] S604: The terminal device obtains second configuration information. The second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

[0295] Optionally, as a method, the terminal device can determine the second configuration information by itself. The specific process can be referred to S305 and will not be described in detail here.

[0296] Alternatively, as another method, the terminal device may obtain the second configuration information from the network device. For the specific process, please refer to S405 and will not be described in detail here.

[0297] The beneficial effects of S604 can be found in the above text and will not be elaborated here.

[0298] According to the aforementioned method, FIG7 is a communication device provided in an embodiment of the present application, which includes a transceiver unit 701 and a processing unit 702 .

[0299] The transceiver unit 701 can be used to implement corresponding information transceiver functions. The transceiver unit 701 can also be called a communication interface or a communication unit. The processing unit 702 can be used to perform processing operations.

[0300] Exemplarily, the device also includes a storage unit, which can be used to store instructions and / or data. The processing unit 702 can read the instructions and / or data in the storage unit so that the device can implement the actions of the device in the aforementioned various method embodiments.

[0301] As a first implementation, the apparatus may be the network device described in the aforementioned embodiments, or a component of the network device (e.g., a chip). The transceiver unit and the processing unit may be used to implement the relevant operations of the network device described in each of the above method embodiments. For example, the transceiver unit is used to implement S402, and the processing unit is used to implement S203, S304, S404, S505, or S603.

[0302] As a second implementation, the apparatus may be a terminal device in the aforementioned embodiment, or a component (such as a chip) of the terminal device. The transceiver unit and the processing unit may be used to implement the relevant operations of the terminal device in each of the above method embodiments. For example, the transceiver unit is used to implement S202, S302, S303, S403, S504, or S602, and the processing unit is used to implement S301.

[0303] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0304] It should also be understood that the device here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merged logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device may be specifically the first network element in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the first network element in the above-mentioned method embodiments, or the device may be specifically the network management network element in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the network management network element in the above-mentioned method embodiments. To avoid repetition, it will not be described here.

[0305] The above-mentioned communication device has the function of implementing the corresponding steps performed by the device in the above-mentioned method. The function can be implemented by hardware, or the corresponding software implementation can be executed by hardware. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

[0306] In addition, the transceiver unit 701 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

[0307] It should be noted that the device in FIG7 can be the device in the aforementioned method embodiment, or it can be a chip or chip system, such as a system on chip (SoC). The transceiver unit can be an input / output circuit or a communication interface; the processing unit can be a processor, microprocessor, or integrated circuit integrated on the chip. This is not limited here.

[0308] The present application also provides a communication device, as shown in FIG8 , comprising: a processor 801 and a communication interface 802 . The processor 801 is configured to execute computer programs or instructions stored in a memory 803 , or read data stored in the memory 803 , to perform the methods described in the above method embodiments. Exemplarily, there are one or more processors 801 . The communication interface 802 is configured to receive and / or transmit signals. For example, the processor 801 is configured to control the communication interface 802 to receive and / or transmit signals.

[0309] For example, as shown in FIG8 , the communication device may further include a memory 803 for storing computer programs, instructions, and / or data. The memory 803 may be integrated with the processor 801, or may be separately provided. Of course, the communication device may also not include the memory 803, and the memory 803 may be provided externally to the communication device. For example, there may be one or more memories 803.

[0310] Illustratively, processor 801, communication interface 802, and memory 803 are interconnected via bus 804; bus 804 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Bus 804 may be divided into an address bus, a data bus, and a control bus. For ease of illustration, FIG8 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0311] For example, the processor 801 is configured to execute computer programs or instructions stored in the memory 803 .

[0312] As a first implementation, the device can be the network device in the aforementioned embodiment, or a component of the network device (such as a chip). The communication interface and processor can be used to implement the relevant operations of the network device in each of the above method embodiments. For example, the communication interface is used to implement S402, and the processor is used to implement S203, S304, S404, S505, or S603.

[0313] As a second implementation, the device can be the terminal device in the aforementioned embodiment, or a component of the terminal device (such as a chip). The communication interface and the processor can be used to implement the relevant operations of the terminal device in each of the above method embodiments. For example, the communication interface is used to implement S202, S302, S303, S403, S504, or S602, and the processor is used to implement S301.

[0314] It should be understood that the processor (such as processor 801) mentioned in the embodiments of the present application can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The processor can further include a hardware chip. The above-mentioned hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0315] It should also be understood that the memory (such as memory 803) mentioned in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache.

[0316] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0317] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0318] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0319] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0320] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0321] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The present application provides a computer-readable storage medium including a computer program that, when executed on a computer, causes the computer to perform any possible implementation of the above method embodiments.

[0322] The technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. A computer program product is provided, which includes: a computer program (also referred to as code, or instructions), which, when executed, causes a computer to perform any possible implementation of the above-mentioned method embodiments. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application.

[0323] The aforementioned storage media include: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0324] The contents of the various embodiments of this application can refer to each other. If there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0325] It is understood that in the embodiments of the present application, the UE and / or the base station may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples. In the embodiments of the present application, other operations or variations of various operations may also be performed. In addition, the various steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

Claims

1. A communication method, characterized in that: include: The terminal device obtains first configuration information, where the first configuration information includes one or more of the following: type of the first information, quantization granularity of the first information, feedback resource of the first information, feedback period of the first information, measurement resource corresponding to the first information, reference signal corresponding to the first information, and a mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; The terminal device sends the first information to the network device based on the first configuration information, and the first information is used to assist the artificial intelligence AI model of the network device.

2. The method according to claim 1, characterized in that The quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

3. The method according to claim 1 or 2, characterized in that The terminal device obtains the first configuration information, including: The terminal device determines the quantization granularity of the first information according to the quality of service requirement of the first information; and / or, The terminal device determines a feedback period of the first information according to a frequency of change of the first information.

4. The method according to claim 3, characterized in that The method further comprises: The terminal device sends the quantization granularity of the first information and / or the feedback period of the first information to the network device.

5. The method according to claim 1 or 2, characterized in that The terminal device obtains the first configuration information, including: The terminal device obtains the first configuration information from predefined configuration information.

6. The method according to claim 1 or 2, characterized in that The terminal device obtains the first configuration information, including: The terminal device obtains the first configuration information from the network device.

7. The method according to claim 1 or 2, characterized in that The method further comprises: The terminal device obtains a mapping relationship between an index and configuration information, where the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; The terminal device obtains the first configuration information, including: The terminal device obtains the first configuration information according to the mapping relationship and the first index.

8. The method according to claim 7, characterized in that The mapping relationship between the index and the configuration information is predefined.

9. The method according to claim 7, characterized in that The terminal device obtains a mapping relationship between the index and the configuration information, including: The terminal device obtains the mapping relationship between the index and the configuration information from the network device.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: The terminal device obtains second configuration information, where the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

11. A communication method, characterized in that: include: The network device receives first information from the terminal device, where the first information is used to assist an artificial intelligence (AI) model of the network device. The first information corresponds to first configuration information, and the first configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and a mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; The network device assists the AI ​​model of the network device according to the first information.

12. The method according to claim 11, characterized in that The quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

13. The method according to claim 11 or 12, characterized in that The method further comprises: The network device determines the first configuration information; The network device sends the first configuration information to the terminal device.

14. The method according to claim 11 or 12, characterized in that The method further comprises: The network device sends a mapping relationship between an index and configuration information to the terminal device, where the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; The network device sends the first index to the terminal device.

15. The method according to any one of claims 11 to 14, characterized in that The method further comprises: If one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel status between the terminal device and the network device are updated, the network device sends second configuration information to the terminal device, and the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

16. A communication device, characterized in that: including a transceiver unit and a processing unit; The transceiver unit or the processing unit is configured to obtain first configuration information, where the first configuration information includes one or more of the following: type of the first information, quantization granularity of the first information, feedback resource of the first information, feedback period of the first information, measurement resource corresponding to the first information, reference signal corresponding to the first information, and a mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; The transceiver unit is used to send the first information to the network device according to the first configuration information, and the first information is used to assist the artificial intelligence AI model of the network device.

17. The communication device according to claim 16, wherein: The quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

18. The communication device according to claim 16 or 17, characterized in that: the processing unit is configured to determine a quantization granularity of the first information according to a quality of service requirement of the first information; and / or, The processing unit is configured to determine a feedback period of the first information according to a frequency of change of the first information.

19. The communication device according to claim 18, wherein: The transceiver unit is configured to send the quantization granularity of the first information and / or the feedback period of the first information to the network device.

20. The communication device according to claim 16 or 17, characterized in that The transceiver unit is used for the terminal device to obtain the first configuration information from predefined configuration information.

21. The communication device according to claim 16 or 17, characterized in that The transceiver unit is configured to obtain the first configuration information from the network device.

22. The communication device according to claim 16 or 17, characterized in that: The transceiver unit is configured to obtain a mapping relationship between an index and configuration information, where the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; The transceiver unit is configured to obtain the first configuration information according to the mapping relationship and the first index.

23. The communication device according to claim 22, wherein: The mapping relationship between the index and the configuration information is predefined.

24. The communication device according to claim 22, wherein: The transceiver unit is configured to obtain a mapping relationship between the index and the configuration information from the network device.

25. The communication device according to any one of claims 16 to 24, characterized in that: The transceiver unit is used to obtain second configuration information, where the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

26. A communication device, characterized in that: include: transceiver unit and processing unit; The transceiver unit is configured to receive first information from a terminal device, where the first information is used to assist an artificial intelligence (AI) model of the network device, where the first information corresponds to first configuration information, and the first configuration information includes one or more of the following: the type of the first information, the quantization granularity of the first information, the feedback resource of the first information, the feedback period of the first information, the measurement resource corresponding to the first information, the reference signal corresponding to the first information, and a mapping relationship between the reference signal corresponding to the first information and the measurement resource corresponding to the first information; The processing unit is used to assist the AI ​​model of the network device according to the first information.

27. The communication device according to claim 26, characterized in that The quantization granularity of the first information is related to the service quality requirement of the first information, the feedback period of the first information is related to the change frequency of the first information, the feedback resource of the first information is related to the adjustment amplitude of the AI ​​model of the network device, or the measurement resource corresponding to the first information is related to the type of the first information.

28. The communication device according to claim 26 or 27, characterized in that The processing unit is configured to determine the first configuration information; The transceiver unit is used to send the first configuration information to the terminal device.

29. The communication device according to claim 26 or 27, characterized in that The transceiver unit is configured to send a mapping relationship between an index and configuration information to the terminal device, where the mapping relationship between the index and the configuration information includes a first mapping relationship between a first index and the first configuration information; The transceiver unit is used to send the first index to the terminal device.

30. The communication device according to any one of claims 26 to 29, characterized in that: If one or more of the AI ​​model of the network device, the AI ​​model of the terminal device, the perception network of the terminal device, and the channel status between the terminal device and the network device are updated, the transceiver unit is used to send second configuration information to the terminal device, and the second configuration information is used to update the first configuration information, and the first configuration information is different from the second configuration information.

31. A communication device, characterized in that: include: A communication interface and a processor, the communication interface being used to output and / or input signals, the processor being used to execute a computer program or instruction stored in a memory, so that the communication device performs the method according to any one of claims 1 to 10; or, the communication device performs the method according to any one of claims 11 to 15.

32. The communication device according to claim 31, wherein: The communication device further includes the memory.

33. A computer-readable storage medium, characterized in that The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 10; or causes the computer to execute the method according to any one of claims 11 to 15.

34. A computer program product, characterized in that The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 10; or cause the computer to execute the method according to any one of claims 11 to 15.

35. A communication system, characterized in that: The communication system includes a terminal device and a network device, wherein the terminal device is used to execute the method according to any one of claims 1 to 10, and the network device is used to execute the method according to any one of claims 11 to 15.

Images