Communication method and device, and storage medium

Abstract

The present application provides a communication method and device, and a storage medium. The method comprises: a terminal device receives configuration information sent by a network device, wherein the configuration information is used for instructing the terminal device to send channel state information (CSI); the terminal device performs CSI measurement on the basis of the configuration information, wherein the CSI comprises first CSI obtained by measurement based on the assumption of an artificial intelligence (AI) receiver and / or second CSI obtained by measurement based on the assumption of a non-AI receiver.

Description

Communication method, device and storage medium Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and specifically to a communication method, device, and storage medium. Background Art

[0002] In related technologies, terminal devices typically measure and report channel state information (CSI) based on the assumption of a non-artificial intelligence (AI) receiver. In this case, network devices are configured with a downlink transmission solution corresponding to a non-AI receiver. However, network devices may also introduce a downlink transmission solution corresponding to an AI receiver. In this case, how terminal devices measure the corresponding CSI is an urgent issue that needs to be addressed.

[0003] Summary of the Invention

[0004] Embodiments of the present application provide a communication method, device, and storage medium.

[0005] The communication method provided in the embodiment of the present application includes:

[0006] The terminal device receives configuration information sent by the network device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0007] The terminal device measures CSI based on the configuration information, where the CSI includes a first CSI measured based on an artificial intelligence (AI) receiver assumption and / or a second CSI measured based on a non-AI receiver assumption.

[0008] The communication method provided in the embodiment of the present application includes:

[0009] The network device sends configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0010] The network device receives the CSI sent by the terminal device, where the CSI includes a first CSI obtained based on an artificial intelligence (AI) receiver hypothesis measurement and / or a second CSI obtained based on a non-AI receiver hypothesis measurement.

[0011] The terminal device provided in the embodiment of the present application includes:

[0012] A first communication unit is configured to receive configuration information sent by a network device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0013] A measuring unit is configured to measure CSI based on the configuration information, where the CSI includes a first CSI measured based on an artificial intelligence (AI) receiver hypothesis and / or a second CSI measured based on a non-AI receiver hypothesis.

[0014] The network device provided in the embodiment of the present application includes:

[0015] A second communication unit is configured to send configuration information to a terminal device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0016] The second communication unit is further configured to receive the CSI sent by the terminal device, where the CSI includes a first CSI obtained by measurement based on an artificial intelligence (AI) receiver hypothesis and / or a second CSI obtained by measurement based on a non-AI receiver hypothesis.

[0017] The communication device provided in an embodiment of the present application may be a terminal device or a network device in the above-mentioned solution, and the communication device includes a processor and a memory. The memory is used to store a computer program, and the processor is used to call and execute the computer program stored in the memory to perform the above-mentioned communication method.

[0018] The chip provided in the embodiment of the present application is used to implement the above-mentioned communication method.

[0019] Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned communication method.

[0020] The computer-readable storage medium provided in an embodiment of the present application is used to store a computer program, which enables a computer to execute the above-mentioned communication method.

[0021] The computer program product provided in the embodiments of the present application includes computer program instructions, which enable a computer to execute the above-mentioned communication method.

[0022] The computer program provided in the embodiment of the present application, when executed on a computer, enables the computer to execute the above-mentioned communication method.

[0023] An embodiment of the present application provides a communication method in which a terminal device can receive configuration information sent by a network device, the configuration information being used to instruct the terminal device to transmit CSI. The terminal device then measures CSI based on the configuration information, where the CSI includes a first CSI measured based on an AI receiver assumption and / or a second CSI measured based on a non-AI receiver assumption. In this manner, when the first CSI is measured based on the AI ​​receiver assumption and the second CSI is measured based on the non-AI receiver assumption, the terminal device can measure the first CSI and / or the second CSI, thereby improving CSI measurement accuracy and facilitating receiver gain. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] FIG1 is a schematic diagram of a communication architecture;

[0026] FIG2 is a schematic diagram of a CSI reporting method of a terminal device;

[0027] Figure 3 is a schematic diagram of a neuron structure;

[0028] FIG4 is a schematic diagram of a neural network structure;

[0029] FIG5 is a flow chart of a communication method according to an embodiment of the present application;

[0030] FIG6 is a second flow chart of a communication method provided in an embodiment of the present application;

[0031] FIG7 is a third flow chart of a communication method provided in an embodiment of the present application;

[0032] FIG8 is a fourth flow chart of a communication method provided in an embodiment of the present application;

[0033] FIG9 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0034] FIG10 is a schematic diagram of the structure of a network device provided in an embodiment of the present application;

[0035] FIG11 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0036] FIG12 is a schematic structural diagram of a chip provided in an embodiment of the present application;

[0037] FIG13 is a schematic block diagram of a communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0039] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application.

[0040] As shown in Figure 1, a communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0041] It should be understood that the embodiments of the present application are only illustrative of the communication system 100, but the embodiments of the present application are not limited thereto. That is, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Internet of Things (IoT) system, Narrow Band Internet of Things (NB-IoT) system, enhanced Machine-Type Communications (eMTC) system, 5G communication system (also known as New Radio (NR) communication system), or future communication systems.

[0042] In the communication system 100 shown in Figure 1, the network device 120 may be an access network device that communicates with the terminal device 110. The access network device may provide communication coverage for a specific geographical area and may communicate with the terminal device 110 located within the coverage area.

[0043] The network device 120 may be an evolved Node B (eNB or eNodeB) in an LTE system, or a Next Generation Radio Access Network (NG RAN) device, or a base station (gNB) in an NR system, or a wireless controller in a Cloud Radio Access Network (CRAN), or the network device 120 may be a relay station, an access point, a vehicle-mounted device, a wearable device, a hub, a switch, a bridge, a router, or a network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0044] The terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wireless connection.

[0045] For example, the terminal device 110 may refer to an access terminal, user equipment (UE), a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus. The access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolution network, etc.

[0046] The terminal device 110 can be used for device-to-device (D2D) communication.

[0047] FIG1 exemplarily shows a network device and two terminal devices. Optionally, the communication system 100 may include multiple network devices and each network device may include another number of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0048] It should be noted that FIG1 is only an example of a system to which this application is applicable. Of course, the method shown in the embodiment of this application can also be applied to other systems. In addition, the terms "system" and "network" are often used interchangeably in this article.

[0049] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0050] It should also be pointed out that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0051] In addition, the term "and / or" in the embodiments of this application is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0052] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0053] It should also be understood that the "correspondence" mentioned in the embodiments of the present application may indicate a direct or indirect correspondence between the two, or an association between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0054] It should also be understood that the “predefined”, “protocol agreement”, “predetermined” or “predefined rules” mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, a terminal device), and the present application does not limit its specific implementation method. For example, predefined can refer to what is defined in the protocol. It should also be understood that in the embodiments of the present application, the “protocol” may refer to a standard protocol in the field of communications, such as the Long Term Evolution (LTE) protocol, the New Radio (NR) protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0055] The technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict. In the description of the present application, "multiple" means two or more, unless otherwise clearly defined.

[0056] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0057] In order for network equipment to perform reasonable scheduling, terminal devices need to report CSI, so that the network equipment can determine the scheduling information of the terminal devices, such as the number of transmission layers, precoding matrix, transmit beam, modulation and coding method, etc.

[0058] It should be noted that the CSI reporting of the terminal device can be performed based on the CSI reporting configuration indicated by the network device. The uplink resources used by the terminal device to report the CSI and the downlink reference signal used for CSI measurement can be indicated by the CSI reporting configuration; wherein, each CSI reporting configuration corresponds to a CSI report, and each CSI report may include different information such as channel state information-reference signal resource indication (Channel State Information-Reference Signal Resource Indicator, CRI), rank indication (Rank Indicator, RI), precoding matrix indication (Precoding Matrix Indicator, PMI), and channel quality indication (Channel Quality Indicator, CQI).

[0059] Furthermore, the information included in the CSI report can be determined by the reporting quantity information (ReportQuantity) in the CSI reporting configuration. The reporting quantity information can indicate one or more of the following reporting quantities:

[0060] The CRI is used to determine the CSI-RS resource currently used for channel measurement and the Interference Measurement Resource (IMR) currently used for interference measurement from multiple CSI-RS resources.

[0061] RI is used to report the recommended number of transmission layers;

[0062] PMI is used to determine the recommended precoding matrix from a predefined codebook;

[0063] CQI is used to report the current channel quality;

[0064] The Reference Signal Received Power (RSRP) is used to report the RSRP of the Synchronization Signal / PBCH Block (SSB) or CSI-RS corresponding to the feedback index, so that the network equipment side can determine the beam used for downlink transmission.

[0065] The layer indicator (LI) is used to report the index of the transmission layer associated with the phase tracking reference signal (PTRS).

[0066] Among them, one or more of RI, PMI, and CQI can be determined based on the Signal to Interference Plus Noise Ratio (SINR) estimated by the terminal device. The channel part of the SINR is determined based on the non-zero power CSI-RS configured by the network device for channel measurement, and the interference part is determined based on the Channel State Information-Interference Measurement (CSI-IM) or non-zero power CSI-RS configured by the network device for interference measurement. The calculation of the detected SINR can generally be based on the Minimum Mean Square Error (MMSE) receiver assumption or the Minimum Mean Square Error-Interference Rejection Combining (MMSE-IRC) receiver assumption. CQI can be obtained by calculating the corresponding SINR based on the estimated RI and PMI.

[0067] Figure 2 is a schematic diagram of a CSI reporting method of a terminal device. As shown in Figure 2, the CSI reporting method of the terminal device may include: periodic CSI reporting, quasi-continuous CSI reporting, and aperiodic CSI reporting. These three CSI reporting methods are described below.

[0068] Periodic CSI can be transmitted on the Physical Uplink Control Channel (PUCCH), and its CSI reporting configuration can be configured by Radio Resource Control (RRC) signaling. After receiving the corresponding RRC configuration, the terminal device can periodically report CSI.

[0069] Quasi-persistent CSI can be transmitted on the PUCCH. Its CSI reporting configuration is pre-configured by RRC signaling and activated or deactivated by Media Access Control Element (MAC CE) signaling. After receiving activation or indication signaling configured by the network equipment, the terminal device periodically reports CSI on the PUCCH until it receives deactivation signaling and stops reporting CSI.

[0070] Quasi-persistent CSI can also be transmitted on the Physical Uplink Shared Channel (PUSCH), and its CSI reporting configuration can be dynamically indicated (activated or deactivated) through Downlink Control Information (DCI) signaling. After receiving the activation or indication signaling configured by the network device and at a certain offset interval, the terminal device can periodically report CSI on the PUSCH until it receives the deactivation signaling and stops reporting.

[0071] The CSI reporting configuration corresponding to aperiodic CSI reporting can also be pre-configured through RRC signaling: some of the configurations can be activated through MAC CE signaling, and the CSI reporting configuration used for CSI reporting can be indicated through CSI trigger signaling in the DCI. After receiving the CSI trigger signaling and after a certain offset, the terminal device can report the corresponding CSI on the scheduled PUSCH in one go according to the indicated CSI reporting configuration.

[0072] AI models are capable of handling a variety of tasks. They possess the ability to self-learn and adapt, dynamically adjusting and making decisions based on environmental changes. AI models can also be referred to as machine learning (ML) models; the two are equivalent or interchangeable.

[0073] In practical applications, AI models can be constructed using neural networks. A neural network is a computational model consisting of multiple interconnected neuron nodes. The connections between nodes represent weighted values ​​from input signals to output signals, called weights. Each node performs a weighted summation of different input signals and outputs the result through a specific activation function. Refer to the neuron structure diagram shown in Figure 3, where a1, a2, ..., an, and 1 are neuron inputs, w1, w2, ..., wn, and b represent weights, Sum represents the summation function, f represents the activation function, and t represents the output result.

[0074] A simple neural network, shown in Figure 4, consists of an input layer, hidden layers, and an output layer. By varying the connections, weights, and activation functions of multiple neurons, different outputs can be generated, thereby fitting the mapping from input to output. Each node in the previous level is connected to all of its next-level nodes. This fully connected model is also called a deep neural network (DNN).

[0075] An AI model can be trained and obtained through the process of dataset construction, training, verification, and testing. Training can be divided into offline and online training. Network devices can obtain static training results through offline training of datasets, which is referred to as offline training. As network devices or terminal devices use AI models, as terminal devices further measure and / or report, network devices can continue to collect more data and conduct real-time online training to optimize AI model parameters and achieve better inference and prediction results. After obtaining the AI ​​model, the corresponding model output can be inferred by inputting the current information into the AI ​​model.

[0076] In order to achieve different functions, different AI models can be introduced to define corresponding inputs and outputs. For example, when the AI ​​model is used for CSI feedback, the channel information (such as eigenvectors, beam information, delay information, etc.) obtained based on the reference signal measurement can be used as the input of the AI ​​model to infer the corresponding CSI quantization bits. There will be a corresponding AI model on the network device side, which uses the CSI quantization bits as input to infer the corresponding channel information.

[0077] For example, when an AI model is used for data detection, that is, when an AI receiver is used to detect downlink signals, the terminal device can use the received signal (and some additional information such as the pilot sequence) as input for the AI ​​model to perform inference, thereby outputting the detected soft bit symbols (i.e., constellation points). In addition, the AI ​​model can also be used for other processes such as positioning, channel coding, channel decoding, beam management, and channel estimation.

[0078] Terminal devices typically measure and report CSI based on non-AI receiver assumptions (such as the MMSE receiver assumption). In this case, the network device is configured with a downlink transmission scheme corresponding to a non-AI receiver. However, if the terminal device uses the AI ​​receiver assumption, it may obtain a higher SINR than the non-AI receiver assumption. At this time, if the terminal device still calculates CSI based on the non-AI receiver assumption, it will result in inaccurate CSI measurement, making it difficult to obtain the gain of the AI ​​receiver. Therefore, when the network device introduces a downlink transmission scheme corresponding to the AI ​​receiver, how the terminal device measures the corresponding CSI is an urgent problem that needs to be solved.

[0079] Based on this, an embodiment of the present application provides a communication method, in which a terminal device can receive configuration information sent by a network device, the configuration information being used to instruct the terminal device to send CSI; the terminal device measures CSI based on the configuration information, where the CSI includes a first CSI measured based on an AI receiver assumption and / or a second CSI measured based on a non-AI receiver assumption. In this way, when the first CSI is measured based on the AI ​​receiver assumption and the second CSI is measured based on the non-AI receiver assumption, the terminal device can measure the first CSI and / or the second CSI, thereby improving the CSI measurement accuracy and facilitating the acquisition of receiver gain.

[0080] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0081] FIG5 is a flow chart of a communication method provided in an embodiment of the present application. As shown in FIG5 , the method may include the following steps.

[0082] S510. The network device sends configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send CSI.

[0083] Correspondingly, the terminal device receives the configuration information sent by the network device.

[0084] It should be noted that the configuration information may be a CSI reporting configuration.

[0085] In some embodiments, the configuration information may be used to indicate information used for CSI reporting. For example, the configuration information may be used to indicate time-frequency resources used for CSI reporting.

[0086] S520. The terminal device measures the CSI based on the configuration information, where the CSI includes a first CSI measured based on an AI receiver assumption and / or a second CSI measured based on a non-AI receiver assumption.

[0087] In some embodiments, the terminal device may send the CSI to a network device.

[0088] Correspondingly, the network device may receive the CSI sent by the terminal device.

[0089] It's important to note that the receiver assumption can be understood as the receiver used by the terminal device during measurements. The receiver is used to receive signals. When performing measurements, the terminal device doesn't need to use the receiver to receive the measured signal. Instead, the received signal information is input into the assumed receiver to simulate the reception conditions during signal transmission.

[0090] The receiver includes an AI receiver and a non-AI receiver. Accordingly, the receiver hypothesis includes an AI receiver hypothesis and a non-AI receiver hypothesis. The AI ​​receiver hypothesis is a hypothetical AI receiver to measure the signal reception situation in the case of an AI receiver, and the non-AI receiver hypothesis is a hypothetical non-AI receiver to measure the signal reception situation in the case of a non-AI receiver.

[0091] The AI ​​receiver hypothesis may be an AI receiver assumed by the terminal device. The terminal device may measure the first CSI based on the assumed AI receiver, thereby directly outputting the first CSI. For example, the terminal device may measure the first CSI based on a first AI model used by the AI ​​receiver hypothesis to obtain the first CSI.

[0092] The non-AI receiver assumption may be a non-AI receiver assumed by the terminal device. The terminal device may measure the second CSI based on the assumed non-AI receiver, thereby directly outputting the second CSI.

[0093] It should be understood that after the network device receives the CSI sent by the terminal device, it can perform scheduling based on the CSI, thereby achieving a higher downlink transmission rate.

[0094] Exemplarily, the network device performing scheduling based on the CSI may include: the network device adjusting one or more of the following based on the CSI:

[0095] Modulation and Coding Scheme (MCS), such as increasing the MCS level;

[0096] Number of transmission layers;

[0097] Precoding matrix.

[0098] It should be noted that the first CSI or the second CSI may include information such as RI, PMI, and CQI.

[0099] It should also be noted that the measurement based on the AI ​​receiver assumption can be based on the first AI model. That is, the terminal device assumes that the first AI model is used as the AI ​​receiver to calculate the corresponding CSI. Unlike linear receivers based on linear algorithms (such as MMSE and MMSE-IRC), AI receivers are nonlinear receivers.

[0100] In some embodiments, the non-AI receiver hypothesis may include one or more of the following: MMSE-IRC receiver hypothesis, MMSE receiver hypothesis, maximum likelihood receiver hypothesis.

[0101] For example, the second CSI may be measured based on relevant protocols and implementations. For example, the second CSI may be measured based on an MMSE-IRC receiver assumption; for another example, the second CSI may be measured based on an MMSE receiver assumption; for another example, the second CSI may be measured based on a maximum likelihood receiver assumption.

[0102] In some embodiments, a rank corresponding to the RI included in the first CSI is lower than a first threshold; and / or a CQI included in the first CSI is lower than a second threshold.

[0103] It should be noted that there is an upper limit to the rank and / or modulation and coding scheme supported by the AI ​​receiver. Within the upper limit, the first CSI can be measured based on the AI ​​receiver assumption. If the rank and / or modulation and coding scheme exceeds the rank and / or modulation and coding scheme supported by the AI ​​receiver, the CSI measured by the terminal device is based on the non-AI receiver assumption.

[0104] Exemplarily, the first threshold value may be pre-defined in the protocol, or may be indicated by the network device to the terminal device, which is not limited in the embodiments of the present application.

[0105] Exemplarily, the second threshold value may be pre-defined in the protocol, or may be indicated by the network device to the terminal device, which is not limited in the embodiments of the present application.

[0106] Through this method, the terminal device can measure the first CSI based on the AI ​​receiver assumption, and the rank corresponding to the RI contained in the first CSI is lower than the first threshold value; and / or the CQI contained in the first CSI is lower than the second threshold value, thereby improving the measurement accuracy of the first CSI and facilitating obtaining the gain of the AI ​​receiver.

[0107] In some embodiments, the rank corresponding to the RI included in the second CSI is not lower than the first threshold value; and / or the CQI included in the second CSI is not lower than the second threshold value, that is, the second CSI measured by the terminal device is based on the non-AI receiver assumption.

[0108] It should also be noted that in this embodiment of the present application, "not less than" can be understood as "greater than or equal to." For example, if the rank corresponding to the RI included in the second CSI is not less than the first threshold, it can be understood that the rank corresponding to the RI included in the second CSI is greater than or equal to the first threshold.

[0109] Through this method, the terminal device can measure the second CSI based on the non-AI receiver assumption, and the rank corresponding to the RI contained in the second CSI is not lower than the first threshold value; and / or the CQI contained in the second CSI is not lower than the second threshold value, thereby improving the measurement accuracy of the second CSI and facilitating obtaining the gain of the non-AI receiver.

[0110] The following describes the synchronization method between the terminal device and the network device based on the receiver assumption that CSI is based on, in combination with Method #A, Method #B and Method #C.

[0111] Method #A: The network device configures the receiver assumptions based on the CSI for the terminal device.

[0112] In some embodiments, the configuration information may include first information, where the first information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0113] Exemplarily, the receiver configured by the network device may be assumed to be a receiver corresponding to a transmission scheme that the network device is prepared to configure for the terminal device.

[0114] For example, when the first information indicates that the receiver assumption on which the CSI is based is an AI receiver assumption, it can be considered that the transmission scheme to be subsequently configured by the network device corresponds to the AI ​​receiver.

[0115] For another example, when the first information indicates that the receiver assumption on which the CSI is based is a non-AI receiver assumption, it can be considered that the transmission scheme to be subsequently configured by the network device corresponds to a non-AI receiver.

[0116] Further, when the first information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or, when the first information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0117] Exemplarily, when the first information indicates that the CSI is based on the AI ​​receiver assumption, the terminal device may measure the first CSI.

[0118] Exemplarily, when the first information indicates that the CSI is based on a non-AI receiver assumption, the terminal device may measure the second CSI.

[0119] This method allows network devices to flexibly configure the receiver assumptions underlying CSI, allowing subsequent network devices to use downlink transmission schemes corresponding to different receivers for downlink data transmission, thereby improving the downlink transmission rate. For example, for AI receivers, network devices can use a method of superimposing data and pilot signals for downlink data transmission; for non-AI receivers, network devices can use a method of time-frequency multiplexing of data and pilot signals for downlink data transmission.

[0120] Method #B: The network device receives the receiver hypothesis reported by the terminal device.

[0121] In some embodiments, the terminal device may send second information to the network device, where the second information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0122] Correspondingly, the network device can receive the second information sent by the terminal device.

[0123] Exemplarily, the receiver hypothesis sent by the terminal device to the network device may be the currently optimal receiver hypothesis.

[0124] For example, when the second information indicates that the receiver hypothesis on which the CSI is based is the AI ​​receiver hypothesis, it can be considered that the AI ​​receiver hypothesis is the current optimal receiver hypothesis.

[0125] For another example, when the second information indicates that the receiver hypothesis on which the CSI is based is a non-AI receiver hypothesis, it can be considered that the non-AI receiver hypothesis is the current optimal receiver hypothesis.

[0126] Further, when the second information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or, when the second information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0127] Exemplarily, the terminal device measures the first CSI, and accordingly, the second information may indicate that the first CSI is based on the AI ​​receiver hypothesis.

[0128] Exemplarily, the terminal device measures the second CSI, and accordingly, the second information may indicate that the second CSI is based on a non-AI receiver assumption.

[0129] Through this method, the terminal device can send the receiver hypothesis based on the CSI to the network device. After receiving the receiver hypothesis based on the CSI, the network device can subsequently use the downlink transmission scheme corresponding to the receiver for downlink data transmission, thereby improving the downlink transmission rate. For example, for an AI receiver, the network device can use the data and pilot superposition method for downlink data transmission; for another example, for a non-AI receiver, the network device can use the data and pilot time-frequency multiplexing method for downlink data transmission.

[0130] Method #C: The network device determines the receiver assumption on which the CSI is based based on the received CSI.

[0131] In some embodiments, when the rank corresponding to the RI included in the CSI is lower than a first threshold value, and / or the CQI included in the CSI is lower than a second threshold value, the CSI is measured based on an AI receiver hypothesis;

[0132] When the rank corresponding to the RI included in the CSI is not lower than a first threshold value, and / or the CQI included in the CSI is not lower than a second threshold value, the CSI is measured based on a non-AI receiver assumption.

[0133] That is, the network device may determine, based on the values ​​of the RI and / or CQI included in the CSI, whether the receiver assumption on which the CSI is based is the AI ​​receiver assumption or the non-AI receiver assumption.

[0134] Exemplarily, the receiver hypothesis determined by the network device may be the current optimal receiver hypothesis.

[0135] For example, when the network device determines that the receiver hypothesis on which the CSI is based is the AI ​​receiver hypothesis, it can be considered that the AI ​​receiver hypothesis is the current optimal receiver hypothesis.

[0136] For another example, when the receiver assumption based on which the CSI determined by the network device is based is a non-AI receiver assumption, it can be considered that the non-AI receiver assumption is the current optimal receiver assumption.

[0137] Further, when the CSI includes the first CSI, the network device may determine that the first CSI is based on the AI ​​receiver assumption; or, when the CSI includes the second CSI, the network device may determine that the second CSI is based on the non-AI receiver assumption.

[0138] This method allows network devices to determine the receiver assumptions underlying CSI. This allows them to use the downlink transmission scheme corresponding to the receiver for downlink data transmission, thereby increasing the downlink transmission rate. For example, for AI receivers, network devices can use a method of superimposing data and pilot signals for downlink data transmission; for non-AI receivers, network devices can use a method of time-frequency multiplexing of data and pilot signals for downlink data transmission.

[0139] In an embodiment of the present application, the terminal device can determine by itself whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0140] In some embodiments, the terminal device may measure the first CSI based on the AI ​​receiver assumption and the second CSI based on the non-AI receiver assumption. The terminal device may select the optimal CSI and its corresponding receiver assumption from the first CSI and the second CSI based on the measurement results.

[0141] Exemplarily, after measuring the first CSI based on the AI ​​receiver hypothesis and the second CSI based on the non-AI receiver hypothesis, the terminal device can select the second CSI and its corresponding non-AI receiver hypothesis; wherein the second CSI is the optimal CSI.

[0142] Exemplarily, after measuring the first CSI based on the AI ​​receiver hypothesis and measuring the second CSI based on the non-AI receiver hypothesis, the terminal device can select the first CSI and its corresponding AI receiver hypothesis; wherein the first CSI is the optimal CSI.

[0143] Through this method, the terminal device can determine the receiver hypothesis on which the CSI is based by itself, so that the terminal device can subsequently send the receiver hypothesis on which the CSI is based to the network device, so that after the network device receives the receiver hypothesis on which the CSI is based, it can adopt the downlink transmission scheme corresponding to the receiver for downlink data transmission, thereby improving the downlink transmission rate. For example, for an AI receiver, the network device can adopt a data and pilot superposition transmission method for downlink data transmission; for another example, for a non-AI receiver, the network device can adopt a data and pilot time-frequency multiplexing method for downlink data transmission.

[0144] In the embodiment of the present application, the first CSI may be represented in the following two ways.

[0145] Case #1: The first CSI may include the second CSI and a first offset value, and the first offset value may be obtained based on an AI receiver hypothesis measurement.

[0146] Through this method, the terminal device can send the second CSI and the first offset value to the network device, and the network device can receive the second CSI and the first offset value. Because the terminal device simultaneously sends the second CSI and the first offset value corresponding to the AI ​​receiver, the network device can simultaneously obtain CSI under two receiver assumptions, allowing for more flexible scheduling and thereby improving the downlink transmission rate.

[0147] Exemplarily, the network device performing scheduling based on the first CSI may include: the network device may further adjust one or more of the following based on the scheduling result based on the second CSI according to the first offset value:

[0148] MCS, such as increasing the MCS level;

[0149] Number of transmission layers;

[0150] Precoding matrix.

[0151] In some embodiments, the first offset value may represent an SINR offset or a CQI offset between the first CSI and the second CSI, or the first offset value may represent an SINR offset or a CQI offset between a non-AI receiver and an AI receiver.

[0152] In some embodiments, the first offset value may be obtained by comparing detection SINRs of an AI receiver and a non-AI receiver.

[0153] Exemplarily, the terminal device can use an AI receiver and a non-AI receiver to receive the same downlink signal and perform detection, and output their respective detection SINRs; after multiple detections and statistics (such as multiple detections and averaging the detection SINRs output by each), the first offset value can be determined by comparing their final detection SINRs (such as their averaged detection SINRs).

[0154] Among them, for non-AI receivers, the terminal device can calculate the detection SINR of each transmission layer based on the downlink channel information (channel covariance matrix) and the non-AI receiver assumption.

[0155] Among them, for the AI ​​receiver, the terminal device can directly output the detection SINR from the AI ​​receiver.

[0156] In some other embodiments, the first offset value may be obtained by comparing a first curve and a second curve, wherein the first curve represents the detection performance of the AI ​​receiver and the second curve represents the detection performance of the non-AI receiver.

[0157] For example, the first curve can be a block error rate (BLER)-SINR curve for an AI receiver under various modulation and coding schemes, and the second curve can be a BLER-SINR curve for a non-AI receiver under various modulation and coding schemes. By comparing the BLER-SINR curves of the AI ​​and non-AI receivers under various modulation and coding schemes, the SINR offset between the two at a certain MCS can be found, which can be used as the first offset value at that MCS.

[0158] In some embodiments, the first offset value may be calculated for one or more of the following:

[0159] a CQI in the second CSI;

[0160] The MCS used for data transmission;

[0161] The modulation method used for data transmission;

[0162] Number of transmission layers;

[0163] Transmission method.

[0164] Exemplarily, different CQIs may correspond to different first offset values, and the terminal device may calculate different first offset values ​​for different CQIs, so that when the terminal device subsequently sends the first offset value, different first offset values ​​may be sent for different CQIs.

[0165] For example, different MCSs used for data transmission may correspond to different first offset values, and the terminal device may calculate different first offset values ​​for different MCSs used for data transmission, so that when the terminal device subsequently sends the first offset value, different first offset values ​​may be sent for different MCSs used for data transmission.

[0166] For example, different modulation modes used for data transmission may correspond to different first offset values. The terminal device may calculate different first offset values ​​for different modulation modes used for data transmission, so that when the terminal device subsequently sends the first offset value, it may send different first offset values ​​for different modulation modes used for data transmission. For example, the terminal device may send a first offset value for each supported modulation mode. If the network device uses the modulation mode during scheduling, it may adjust the MCS based on the first offset value corresponding to the modulation mode.

[0167] Exemplarily, the number of transmission layers may be: the number of transmission layers reported by the terminal, or the number of transmission layers used for data transmission. Different numbers of transmission layers may correspond to different first offset values. The terminal device may calculate different first offset values ​​for different numbers of transmission layers, so that when the terminal device subsequently sends the first offset value, different first offset values ​​may be sent for different numbers of transmission layers.

[0168] Exemplarily, different transmission modes may correspond to different first offset values, and the terminal device may calculate different first offset values ​​for different transmission modes, so that when the terminal device subsequently sends the first offset value, different first offset values ​​may be sent for different transmission modes.

[0169] In some embodiments, a reporting period of the first offset value is greater than a reporting period of the second CSI.

[0170] It should be noted that since the size of the first offset value is associated with the first AI model used by the AI ​​receiver, the terminal device can update the first offset value when updating the first AI model. Therefore, the first offset value does not need to be frequently reported (i.e., sent). For example, the reporting of the first offset value can be triggered by the terminal device, and the terminal device can report the first offset value once after updating the first AI model.

[0171] Through this method, when the reporting period of the first offset value is greater than the reporting period of the second CSI, the terminal device does not need to frequently report the first offset value, thereby saving signaling overhead.

[0172] Case #2: The first CSI may be measured based on a first AI model, where the first AI model is a model used for an AI receiver of the terminal device.

[0173] It should be noted that the first AI model can be used for both terminal device-side data detection and output of the detected SINR or directly output of the CSI estimated based on the receiver and the received signal. In this way, the first AI model simultaneously implements the two related functions of data detection and measurement, reducing the complexity of the first AI model management and training.

[0174] Through this method, the terminal device can send the first CSI to the network device, so that after the network device receives the first CSI, it can perform scheduling based on the first CSI to increase the downlink transmission rate.

[0175] Exemplarily, the network device performing scheduling based on the first CSI may include: the network device adjusting one or more of the following based on the first CSI:

[0176] MCS, such as increasing the MCS level;

[0177] Number of transmission layers;

[0178] Precoding matrix.

[0179] There are two possible implementation methods for the terminal device to obtain the first AI model.

[0180] In some embodiments, the terminal device can train and maintain the first AI model by itself.

[0181] In other words, the first AI model is determined by the terminal device itself. The terminal device can obtain the first AI model through training and maintain the first AI model.

[0182] In some embodiments, the configuration information may include third information, and the third information may be used to indicate a second AI model used in the AI ​​receiver assumption.

[0183] Furthermore, in some embodiments, the third information may indicate the second AI model to the terminal device by indicating the model ID or model function of the second AI model.

[0184] It should be noted that the first AI model and the second AI model may be the same AI model; or, the first AI model and the second AI model may be different AI models.

[0185] That is, the network device may indicate the second AI model to the terminal device, and the terminal device may use the second AI model to measure the first CSI. The second AI model assumed / used by the terminal device when measuring the first CSI may be different from the first AI model used for detection.

[0186] An embodiment of the present application provides a communication method in which a terminal device can receive configuration information sent by a network device, the configuration information being used to instruct the terminal device to transmit CSI. The terminal device then measures CSI based on the configuration information, where the CSI includes a first CSI measured based on an AI receiver assumption and / or a second CSI measured based on a non-AI receiver assumption. In this manner, when the first CSI is measured based on the AI ​​receiver assumption and the second CSI is measured based on the non-AI receiver assumption, the terminal device can measure the first CSI and / or the second CSI, thereby improving CSI measurement accuracy and facilitating receiver gain.

[0187] The technical solutions provided by the embodiments of the present application are further described below in conjunction with the processes of the communication method shown in Figures 6 to 8. It should be understood that the technical solutions provided by the embodiments of the present application may include but are not limited to the following.

[0188] FIG6 is a second flow chart of a communication method provided in an embodiment of the present application. As shown in FIG6 , the method may include the following steps:

[0189] S610. The network device sends configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send CSI. The configuration information includes first information, where the first information is used to indicate whether a receiver assumption based on the CSI is an AI receiver assumption or a non-AI receiver assumption.

[0190] S620: When the first information indicates that the CSI is based on the AI ​​receiver assumption, the terminal device measures and sends the first CSI based on the configuration information, where the first CSI is measured based on the AI ​​receiver assumption; or

[0191] When the first information indicates that the CSI is based on a non-AI receiver assumption, the terminal device measures and sends the second CSI based on the configuration information, and the second CSI is measured based on the non-AI receiver assumption.

[0192] FIG7 is a flow chart of a communication method provided in an embodiment of the present application. As shown in FIG7 , the method may include the following steps.

[0193] S710. The network device sends configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send CSI.

[0194] S720: The terminal device measures the first CSI and the second CSI based on the configuration information, where the first CSI is measured based on an AI receiver assumption, and the second CSI is measured based on a non-AI receiver assumption.

[0195] S730. The terminal device sends the best CSI and second information of the first CSI and the second CSI to the network device, where the second information is used to indicate whether the receiver assumption based on the CSI is an AI receiver assumption or a non-AI receiver assumption.

[0196] FIG8 is a fourth flow chart of a communication method provided in an embodiment of the present application. As shown in FIG8 , the method may include the following steps.

[0197] S810. The network device sends configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send CSI.

[0198] S820. The terminal device measures a first CSI and a second CSI based on the configuration information, where the first CSI is measured based on an AI receiver assumption, and the second CSI is measured based on a non-AI receiver assumption.

[0199] S830. The terminal device sends the best CSI between the first CSI and the second CSI to the network device.

[0200] S840: When the rank corresponding to the RI included in the CSI is lower than the first threshold and / or the CQI included in the CSI is lower than the second threshold, the network device determines that the CSI is measured based on the AI ​​receiver hypothesis;

[0201] When the rank corresponding to the RI included in the CSI is not lower than the first threshold value and / or the CQI included in the CSI is not lower than the second threshold value, the network device determines that the CSI is measured based on the non-AI receiver assumption.

[0202] The communication method provided in the embodiment of the present application is described in detail below in conjunction with specific application scenarios.

[0203] The embodiment of the present application provides a CSI reporting method, in which the terminal device can calculate the SINR and report the corresponding CSI based on the receiver assumption, so that the network device can schedule the downlink transmission scheme based on the receiver based on the CSI reported by the terminal device to obtain a higher transmission rate.

[0204] Based on the two ways of receiver assumptions on which the terminal device obtains CSI, the technical solutions provided in the embodiments of the present application may mainly include the following two embodiments.

[0205] Embodiment 1: A network device configures a receiver assumption based on which CSI is configured for a terminal device.

[0206] 1. The network device sends configuration information to the terminal device, which is used to instruct the terminal device to report CSI.

[0207] 2. The terminal device receives configuration information sent by the network device, which is used to instruct the terminal device to report CSI.

[0208] (1) The configuration information may be a CSI reporting configuration, which is used to indicate information used for CSI reporting.

[0209] (2) The configuration information includes first information, where the first information is used to indicate whether the receiver assumption based on which the CSI reporting is based is an AI receiver assumption or a non-AI receiver assumption (such as an MMSE receiver assumption or a maximum likelihood receiver assumption). For example, the first information is used to indicate that the receiver assumption based on which the CSI reporting is based is an AI receiver assumption; or, the first information is used to indicate that the receiver assumption based on which the CSI reporting is based is a non-AI receiver assumption.

[0210] (3) An AI receiver is one that detects downlink data based on a first AI model. This means that the terminal device can use the received signal (and some additional information such as the pilot sequence) as input to the first AI model for inference, thereby outputting the detected soft bit symbols (i.e., constellation points) for subsequent demodulation. Unlike linear receivers based on linear algorithms (such as MMSE or MMSE-IRC), AI receivers are nonlinear receivers.

[0211] The following description takes the example of a network device instructing a first CSI report to be performed based on the AI ​​receiver assumption.

[0212] 3. The terminal device measures and reports the first CSI based on the configuration information.

[0213] (1) The CSI may include a first CSI, and the first CSI is measured based on an AI receiver assumption.

[0214] (2) The first CSI may include the second CSI and a first offset value, where the first offset value is obtained based on the AI ​​receiver hypothesis measurement. In the embodiment of the present application, the first CSI and the second CSI contain similar information content. For example, the first CSI or the second CSI may include information such as RI, PMI, and CQI.

[0215] a. In some embodiments, the first offset value may represent an SINR offset or a CQI offset based on the first CSI and the second CSI; or, the first offset value may represent an SINR offset or a CQI offset between a non-AI receiver (such as a linear receiver) and an AI receiver.

[0216] b. In some embodiments, after receiving the first offset value, the network device may adjust the MCS used for downlink transmission based on the AI ​​receiver based on the scheduling result of the second CSI in combination with the first offset value. For example, if the network device schedules downlink transmission based on a non-AI receiver, it may schedule based on the second CSI (e.g., determine the number of transmission layers, precoding matrix, and MCS); if the network device schedules downlink transmission based on an AI receiver (e.g., superimposes data and pilot signals), it may further adjust the MCS based on the scheduling result based on the second CSI (e.g., increase the MCS level) based on the first offset value, thereby achieving a higher transmission rate.

[0217] c. In some embodiments, the first offset value can be obtained by comparing the detection SINR of the AI ​​receiver and the non-AI receiver. For example, the terminal device can use different receivers to receive the same downlink signal and perform detection, output their respective detection SINRs, and determine the first offset value through multiple detections and statistics (for example, multiple measurements and averaging). For a non-AI receiver, the terminal device can calculate the detection SINR of each transmission layer based on the downlink channel information (channel covariance matrix) and the non-AI receiver assumption; for an AI receiver, the terminal device can directly output the detection SINR from the AI ​​receiver.

[0218] d. In other embodiments, the first offset value can be obtained by comparing the detection performance curves of an AI receiver and a non-AI receiver. For example, by comparing the BLER-SINR curves of an AI receiver and a non-AI receiver under various modulation and coding schemes, the SINR offset value of the two at a certain MCS can be found, which can be used as the first offset value at that MCS.

[0219] e. In some embodiments, the first offset value may be associated with the CQI in the second CSI, or the first offset value may be associated with the modulation mode corresponding to the CQI in the second CSI. That is, different CQI values ​​may correspond to different first offset values, or different modulation modes may correspond to different offset values. When the terminal device reports the first offset value, different first offset values ​​may be reported for different CQI values ​​or different modulation modes. For example, the terminal device reports a first offset value for each supported modulation mode. If the network device uses this modulation mode during scheduling, the MCS may be adjusted based on the first offset value.

[0220] f. In other embodiments, the first offset value may also be reported separately for different numbers of transmission layers and / or different transmission modes. For example, the terminal device may report a first offset value for each Rank value; or the terminal may report a first offset value separately for different transmission modes.

[0221] g. In some embodiments, the reporting period of the first offset value may be longer than the reporting period of the second CSI. Because the size of the first offset value is related to the first AI model used by the AI ​​receiver, the terminal device can update the first offset value when the first AI model is updated, thus eliminating the need to frequently report the first offset value. For example, the reporting of the first offset value may be triggered by the terminal device. After updating the first AI model, the terminal device may report the first offset value once.

[0222] h. In some embodiments, the second CSI may be measured based on a non-AI receiver assumption. For example, the second CSI may be measured based on a linear receiver assumption; or the second CSI may be measured based on an MMSE receiver assumption. In other words, the second CSI is reported based on protocol and implementation measurements.

[0223] (3) The Rank value corresponding to the RI included in the first CSI is lower than the first threshold value, and / or the CQI included in the first CSI is lower than the second threshold value.

[0224] In other words, there is an upper limit on the Rank values ​​and modulation and coding schemes that an AI receiver can support. Within this upper limit, the reported CSI is based on the AI ​​receiver's hypothetical measurements. The first and second thresholds can be pre-defined in the protocol or indicated to the terminal device by the network device.

[0225] b. If the Rank value corresponding to the RI included in the CSI is not lower than the first threshold, and / or the CQI included in the CSI is not lower than the second threshold, the CSI is not measured based on the AI ​​receiver assumption.

[0226] c. Based on the RI and CQI values ​​reported by the terminal device, the network device can determine whether the currently reported CSI is measured based on the AI ​​receiver hypothesis or the non-AI receiver hypothesis, so that the network device can perform corresponding downlink scheduling based on the CSI.

[0227] 4. The network device receives the CSI reported by the terminal device.

[0228] Based on the technical solution of Example 1, the network device can flexibly configure the receiver assumptions underlying the terminal device's CSI reporting, thereby obtaining CSI under different receiver assumptions for downlink scheduling and improving the downlink transmission rate. In addition, the terminal device may simultaneously report the second CSI and the first offset value corresponding to the AI ​​receiver. The network device can simultaneously obtain CSI under both receiver assumptions, allowing for more flexible scheduling.

[0229] Embodiment 2: The terminal device itself determines the receiver assumption based on which the CSI is based.

[0230] 1. The network device sends configuration information to the terminal device, which is used to instruct the terminal device to report CSI.

[0231] 2. The terminal device receives configuration information sent by the network device, which is used to instruct the terminal device to report CSI.

[0232] 3. The terminal device measures and reports CSI based on the configuration information.

[0233] (1) The terminal device may report second information to the network device, where the second information is used to indicate that the receiver assumption on which the reported CSI is based is an AI receiver assumption or a non-AI receiver assumption (such as an MMSE receiver assumption, or a maximum likelihood receiver assumption). For example, the second information is used to indicate that the receiver assumption on which the CSI report is based is an AI receiver assumption, or the second information is used to indicate that the receiver assumption on which the CSI report is based is a non-AI receiver assumption. The terminal device may calculate the CSI corresponding to the AI ​​receiver assumption and the non-AI receiver assumption respectively, and thereby report the optimal CSI and the corresponding receiver assumption to the network device, and the network device may adopt the downlink transmission scheme corresponding to the receiver. For example, for an AI receiver, the network device may adopt a downlink transmission scheme in which data and pilot signals are superimposed and sent; for a non-AI receiver, the network device may adopt a downlink transmission scheme in which data and pilot signals are time-frequency multiplexed.

[0234] (2) When the receiver assumption reported by the terminal device is a non-AI receiver assumption, the terminal device reports the second CSI; when the receiver assumption reported by the terminal device is an AI receiver assumption, the terminal device reports the first CSI.

[0235] a. The second CSI can be measured based on a non-AI receiver assumption. For example, the second CSI can be measured based on a linear receiver assumption; or the second CSI can be measured based on an MMSE receiver assumption. In other words, the second CSI is reported based on protocol and implementation measurements.

[0236] b. The first CSI can be measured and reported in two ways:

[0237] Method 1: The first CSI includes the second CSI and a first offset value, where the first offset value is measured based on an AI receiver assumption. The first offset value can represent an SINR offset or CQI offset based on the first CSI and the second CSI; alternatively, the first offset value can represent an SINR offset or CQI offset between a non-AI receiver (such as a linear receiver) and an AI receiver. For a detailed description of the first offset value, please refer to the description in Example 1 and will not be repeated here.

[0238] Method 2: The first CSI can be directly measured based on the first AI model, which is the model used for the AI ​​receiver of the terminal device. In other words, the first AI model is used for both terminal-side data detection and output of the detected SINR or directly outputs the first CSI estimated based on the AI ​​receiver and the received signal. In this way, the two related functions of data detection and measurement are simultaneously implemented through a single first AI model, reducing the complexity of managing and training the first AI model. The first AI model can be indicated to the terminal device by the network device or trained and maintained by the terminal device itself.

[0239] c. The first CSI and the second CSI contain similar information. For example, the first CSI or the second CSI may contain information such as RI, PMI, and CQI.

[0240] (3) In some embodiments, the second AI model used in the AI ​​receiver assumption may be indicated to the terminal device via the network device. For example, the configuration information may include third information indicating the second AI model used in the AI ​​receiver assumption. The terminal device may measure and obtain the first CSI based on the second AI model. Furthermore, the network device may indicate the second AI model to the terminal device by indicating a model ID or a model function of the AI ​​model.

[0241] 4. The network device receives the CSI reported by the terminal device.

[0242] Based on the technical solution of Example 2, the terminal device can report the recommended (i.e., optimal) CSI and the receiver hypothesis corresponding to the CSI to the network device based on the CSI calculated under different receiver assumptions. The network device can use the downlink transmission scheme corresponding to the receiver for downlink data transmission, thereby increasing the downlink transmission rate.

[0243] In the embodiments of the present application, the network device may configure or use the receiver assumption used by the terminal device to report CSI, so that the network device can use the CSI corresponding to the currently optimal receiver assumption for downlink scheduling. For example, compared to obtaining the second CSI based on a linear receiver assumption such as MMSE, the AI ​​receiver assumption may be used to obtain the first CSI, thereby achieving a higher Rank / MCS based on the first CSI, thereby achieving a higher downlink transmission rate.

[0244] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, the technical solution of the present application can be subjected to a variety of simple modifications, and these simple modifications all fall within the scope of protection of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present application will not further describe the various possible combinations. For another example, the various different embodiments of the present application can also be arbitrarily combined, as long as they do not violate the ideas of the present application, they should also be regarded as the contents disclosed in the present application. For another example, under the premise of no conflict, the various embodiments and / or the technical features in each embodiment described in the present application can be arbitrarily combined with the relevant technologies, and the technical solution obtained after the combination should also fall within the scope of protection of the present application.

[0245] It should also be understood that in the various method embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0246] FIG9 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. As shown in FIG9 , the terminal device 900 may include:

[0247] The first communication unit 910 is configured to receive configuration information sent by a network device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0248] The measuring unit 920 is configured to measure CSI based on the configuration information, where the CSI includes a first CSI measured based on an artificial intelligence (AI) receiver hypothesis and / or a second CSI measured based on a non-AI receiver hypothesis.

[0249] In some embodiments, the configuration information includes first information, where the first information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0250] In some embodiments, when the first information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or

[0251] In a case where the first information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0252] In some embodiments, the first communication unit 910 is further configured to send second information to the network device, where the second information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0253] In some embodiments, when the second information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or

[0254] In a case where the second information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0255] In some embodiments, the first CSI includes the second CSI and a first offset value, where the first offset value is measured based on an AI receiver hypothesis.

[0256] In some embodiments, the first offset value represents a signal-to-interference-plus-noise ratio (SINR) offset or a channel quality indicator (CQI) offset between the first CSI and the second CSI, or the first offset value represents an SINR offset or a CQI offset between a non-AI receiver and an AI receiver.

[0257] In some embodiments, the first offset value is obtained by comparing the detection SINR of an AI receiver and a non-AI receiver; or,

[0258] The first offset value is obtained by comparing a first curve and a second curve, where the first curve represents the detection performance of the AI ​​receiver and the second curve represents the detection performance of the non-AI receiver.

[0259] In some embodiments, the first offset value is calculated for one or more of the following:

[0260] a CQI in the second CSI;

[0261] The MCS used for data transmission;

[0262] The modulation method used for data transmission;

[0263] Number of transmission layers;

[0264] Transmission method.

[0265] In some embodiments, a reporting period of the first offset value is greater than a reporting period of the second CSI.

[0266] In some embodiments, the first CSI is measured based on a first AI model, where the first AI model is a model for an AI receiver of the terminal device.

[0267] In some embodiments, the configuration information includes third information, and the third information is used to indicate a second AI model used in the AI ​​receiver hypothesis.

[0268] In some embodiments, the rank corresponding to the RI included in the first CSI is lower than a first threshold value; and / or the CQI included in the first CSI is lower than a second threshold value.

[0269] In some embodiments, when the rank corresponding to the RI included in the CSI is lower than a first threshold value, and / or the CQI included in the CSI is lower than a second threshold value, the CSI is measured based on an AI receiver hypothesis;

[0270] When the rank corresponding to the RI included in the CSI is not lower than the first threshold value, and / or the CQI included in the CSI is not lower than the second threshold value, the CSI is measured based on the non-AI receiver assumption.

[0271] In some embodiments, the non-AI receiver hypothesis includes a minimum mean square error (MMSE) receiver hypothesis and / or a maximum likelihood receiver hypothesis.

[0272] An embodiment of the present application provides a terminal device that can receive configuration information sent by a network device, the configuration information being used to instruct the terminal device to send CSI. The terminal device measures CSI based on the configuration information, where the CSI includes first CSI measured based on an AI receiver assumption and / or second CSI measured based on a non-AI receiver assumption. In this way, when the first CSI is measured based on the AI ​​receiver assumption and the second CSI is measured based on the non-AI receiver assumption, the terminal device can measure the first CSI and / or the second CSI, thereby improving CSI measurement accuracy and facilitating receiver gain.

[0273] Those skilled in the art should understand that the relevant description of the above-mentioned terminal device in the embodiment of the present application can be understood with reference to the relevant description of the communication method in the embodiment of the present application.

[0274] FIG10 is a schematic diagram of the structure of a network device provided in an embodiment of the present application. As shown in FIG10 , the network device 1000 may include:

[0275] The second communication unit 1010 is configured to send configuration information to the terminal device, where the configuration information is used to instruct the terminal device to send channel state information CSI;

[0276] The second communication unit 1010 is further configured to receive the CSI sent by the terminal device, where the CSI includes a first CSI obtained based on an artificial intelligence (AI) receiver hypothesis measurement and / or a second CSI obtained based on a non-AI receiver hypothesis measurement.

[0277] In some embodiments, the configuration information includes first information, where the first information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0278] In some embodiments, when the first information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or

[0279] In a case where the first information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0280] In some embodiments, the second communication unit 1010 is further configured to receive second information sent by the terminal device, where the second information is used to indicate whether the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

[0281] In some embodiments, when the second information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or

[0282] In a case where the second information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

[0283] In some embodiments, the first CSI includes the second CSI and a first offset value, where the first offset value is measured based on an AI receiver hypothesis.

[0284] In some embodiments, the first offset value represents a signal-to-interference-plus-noise ratio (SINR) offset or a channel quality indicator (CQI) offset between the first CSI and the second CSI, or the first offset value represents an SINR offset or a CQI offset between a non-AI receiver and an AI receiver.

[0285] In some embodiments, the first offset value is obtained by comparing the detection SINR of an AI receiver and a non-AI receiver; or,

[0286] The first offset value is obtained by comparing a first curve and a second curve, where the first curve represents the detection performance of the AI ​​receiver and the second curve represents the detection performance of the non-AI receiver.

[0287] In some embodiments, the first offset value is calculated for one or more of the following:

[0288] a CQI in the second CSI;

[0289] The MCS used for data transmission;

[0290] The modulation method used for data transmission;

[0291] Number of transmission layers;

[0292] Transmission method.

[0293] In some embodiments, a reporting period of the first offset value is greater than a reporting period of the second CSI.

[0294] In some embodiments, the first CSI is measured based on a first AI model, where the first AI model is a model for an AI receiver of the terminal device.

[0295] In some embodiments, the configuration information includes third information, and the third information is used to indicate a second AI model used in the AI ​​receiver hypothesis.

[0296] In some embodiments, the rank corresponding to the RI included in the first CSI is lower than a first threshold value; and / or the CQI included in the first CSI is lower than a second threshold value.

[0297] In some embodiments, when the rank corresponding to the RI included in the CSI is lower than a first threshold value, and / or the CQI included in the CSI is lower than a second threshold value, the CSI is measured based on an AI receiver hypothesis;

[0298] When the rank corresponding to the RI included in the CSI is not lower than the first threshold value, and / or the CQI included in the CSI is not lower than the second threshold value, the CSI is measured based on the non-AI receiver assumption.

[0299] In some embodiments, the non-AI receiver hypothesis includes a minimum mean square error (MMSE) receiver hypothesis and / or a maximum likelihood receiver hypothesis.

[0300] An embodiment of the present application provides a network device that can send configuration information to a terminal device, the configuration information being used to instruct the terminal device to send channel state information (CSI); the network device can receive the CSI sent by the terminal device, where the CSI includes first CSI measured based on an artificial intelligence (AI) receiver hypothesis and / or second CSI measured based on a non-AI receiver hypothesis. In this way, when the first CSI is measured based on the AI ​​receiver hypothesis and the second CSI is measured based on the non-AI receiver hypothesis, the network device can receive the first CSI and / or the second CSI, thereby enabling scheduling based on the first CSI and / or the second CSI to increase the downlink transmission rate.

[0301] Those skilled in the art should understand that the relevant description of the above-mentioned network device in the embodiment of the present application can be understood with reference to the relevant description of the communication method in the embodiment of the present application.

[0302] Figure 11 is a schematic diagram of a communication device according to an embodiment of the present application. The communication device 1100 may be a terminal device or a network device. The communication device 1100 shown in Figure 11 includes a processor 1110, which may call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0303] In some embodiments, as shown in FIG11 , the communication device 1100 may further include a memory 1120. The processor 1110 may call and execute a computer program from the memory 1120 to implement the method in the embodiment of the present application.

[0304] The memory 1120 may be a separate device independent of the processor 1110 , or may be integrated into the processor 1110 .

[0305] In some embodiments, as shown in FIG11 , the communication device 1100 may further include a transceiver 1130 , and the processor 1110 may control the transceiver 1130 to communicate with other devices. Specifically, the transceiver 1130 may send information or data to other devices, or receive information or data sent by other devices.

[0306] The transceiver 1130 may include a transmitter and a receiver. The transceiver 1130 may further include an antenna, and the number of antennas may be one or more.

[0307] In some embodiments, the communication device 1100 may be a terminal device of an embodiment of the present application, and the communication device 1100 may implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0308] In some embodiments, the communication device 1100 may be a network device of an embodiment of the present application, and the communication device 1100 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0309] Figure 12 is a schematic structural diagram of a chip provided in an embodiment of the present application. The chip 1200 shown in Figure 12 includes a processor 1210, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0310] In some embodiments, as shown in FIG12 , the chip 1200 may further include a memory 1220. The processor 1210 may call and execute a computer program from the memory 1220 to implement the method in the embodiment of the present application.

[0311] The memory 1220 may be a separate device independent of the processor 1210 , or may be integrated into the processor 1210 .

[0312] In some embodiments, the chip 1200 may further include an input interface 1230. The processor 1210 may control the input interface 1230 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0313] In some embodiments, the chip 1200 may further include an output interface 1240. The processor 1210 may control the output interface 1240 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0314] In some embodiments, the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0315] In some embodiments, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0316] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0317] FIG13 is a schematic block diagram of a communication system provided in an embodiment of the present application. As shown in FIG13 , the communication system 1300 includes a terminal device 1310 and a network device 1320 .

[0318] Among them, the terminal device 1310 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 1320 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, they are not repeated here.

[0319] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0320] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may 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 may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0321] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0322] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0323] In some embodiments, the computer-readable storage medium can be applied to the terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0324] In some embodiments, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0325] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0326] In some embodiments, the computer program product can be applied to the terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0327] In some embodiments, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0328] The embodiment of the present application also provides a computer program.

[0329] In some embodiments, the computer program can be applied to the terminal device in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0330] In some embodiments, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0331] 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.

[0332] 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.

[0333] 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 the units is merely 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.

[0334] The units described as separate components may or may not be physically separate, and the 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.

[0335] 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.

[0336] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0337] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, the method comprising: A terminal device receives configuration information sent by a network device, the configuration information being used to instruct the terminal device to send channel state information CSI; The terminal device measures CSI based on the configuration information, the CSI including first CSI measured based on an artificial intelligence AI receiver hypothesis and / or second CSI measured based on a non-AI receiver hypothesis.

2. The method according to claim 1, wherein The configuration information includes first information, the first information being used to indicate that the receiver hypothesis on which the CSI is based is an AI receiver hypothesis or a non-AI receiver hypothesis.

3. The method according to claim 2, wherein, When the first information indicates that the CSI is based on an AI receiver hypothesis, the CSI includes the first CSI; or, When the first information indicates that the CSI is based on a non-AI receiver hypothesis, the CSI includes the second CSI.

4. The method according to claim 1, wherein, The method further comprises: The terminal device sends second information to the network device, the second information being used to indicate that the receiver hypothesis on which the CSI is based is an AI receiver hypothesis or a non-AI receiver hypothesis.

5. The method according to claim 4, wherein, When the second information indicates that the CSI is based on an AI receiver hypothesis, the CSI includes the first CSI; or, When the second information indicates that the CSI is based on a non-AI receiver hypothesis, the CSI includes the second CSI.

6. The method according to any one of claims 1 to 5, wherein The first CSI includes the second CSI and a first offset value, the first offset value being measured based on an AI receiver hypothesis.

7. The method according to claim 6, wherein, The first offset value characterizes the signal-to-interference-plus-noise ratio SINR offset or channel quality indicator CQI offset between the first CSI and the second CSI, or the first offset value characterizes the SINR offset or CQI offset between a non-AI receiver and an AI receiver.

8. The method according to claim 6 or 7, wherein, The first offset value is obtained by comparing the detected SINR of an AI receiver and a non-AI receiver; or, The first offset value is obtained by comparing a first curve and a second curve, the first curve characterizing the detection performance of an AI receiver, and the second curve characterizing the detection performance of a non-AI receiver.

9. The method according to any one of claims 6 to 8, wherein The first offset value is calculated separately for one or more of the following: The CQI in the second CSI; The MCS used for data transmission; The modulation method used for data transmission; The number of transmission layers; The transmission method.

10. The method according to any one of claims 6 to 9, wherein The reporting period of the first offset value is greater than the reporting period of the second CSI.

11. The method according to any one of claims 1 to 5, wherein The first CSI is measured based on a first AI model, the first AI model being a model for an AI receiver of the terminal device.

12. The method according to any one of claims 1 to 11, wherein The configuration information includes third information, the third information being used to indicate a second AI model used in the AI receiver hypothesis.

13. The method according to any one of claims 1 to 12, wherein, The rank corresponding to the RI included in the first CSI is lower than a first threshold; and / or, the CQI included in the first CSI is lower than a second threshold.

14. The method according to any one of claims 1, 6 to 13, wherein, when the rank corresponding to the RI included in the CSI is lower than a first threshold value, and / or when the CQI included in the CSI is lower than a second threshold value, the CSI is measured based on an AI receiver assumption; when the rank corresponding to the RI included in the CSI is not lower than the first threshold value, and / or when the CQI included in the CSI is not lower than the second threshold value, the CSI is measured based on a non-AI receiver assumption.

15. The method according to any one of claims 1 to 14, wherein The non-AI receiver assumption includes a minimum mean square error (MMSE) receiver assumption and / or a maximum likelihood receiver assumption.

16. A communication method, the method comprising: a network device sending configuration information to a terminal device, the configuration information being used to instruct the terminal device to send channel state information (CSI); the network device receiving the CSI sent by the terminal device, the CSI including a first CSI measured based on an artificial intelligence (AI) receiver assumption and / or a second CSI measured based on a non-AI receiver assumption.

17. The method according to claim 16, wherein The configuration information includes first information, the first information being used to indicate that the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

18. The method according to claim 17, wherein, when the first information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or, when the first information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

19. The method according to claim 16, wherein, The method further comprises: the network device receiving second information sent by the terminal device, the second information being used to indicate that the receiver assumption on which the CSI is based is an AI receiver assumption or a non-AI receiver assumption.

20. The method according to claim 19, wherein, when the second information indicates that the CSI is based on an AI receiver assumption, the CSI includes the first CSI; or, when the second information indicates that the CSI is based on a non-AI receiver assumption, the CSI includes the second CSI.

21. The method according to any one of claims 16 to 20, wherein The first CSI includes the second CSI and a first offset value, the first offset value being measured based on an AI receiver assumption.

22. The method according to claim 21, wherein, The first offset value represents a signal-to-interference-plus-noise ratio (SINR) offset or a channel quality indicator (CQI) offset between the first CSI and the second CSI, or the first offset value represents an SINR offset or a CQI offset between a non-AI receiver and an AI receiver.

23. The method according to claim 21 or 22, wherein, the first offset value is obtained by comparing the detected SINR of an AI receiver and a non-AI receiver; or, the first offset value is obtained by comparing a first curve and a second curve, the first curve representing the detection performance of an AI receiver, and the second curve representing the detection performance of a non-AI receiver.

24. The method according to any one of claims 21 to 23, wherein The first offset value is calculated separately for one or more of the following: the CQI in the second CSI; The MCS adopted for data transmission; The modulation method adopted for data transmission; The number of transmission layers; The transmission mode.

25. The method according to any one of claims 21 to 24, wherein The reporting period of the first offset value is greater than the reporting period of the second CSI.

26. The method according to any one of claims 16 to 20, wherein The first CSI is measured based on a first AI model, and the first AI model is a model for an AI receiver of the terminal device.

27. The method according to any one of claims 16 to 26, wherein, The configuration information includes third information, and the third information is used to indicate a second AI model used in an AI receiver hypothesis.

28. The method according to any one of claims 16 to 27, wherein, The rank of the RI included in the first CSI is lower than a first threshold; and / or, the CQI included in the first CSI is lower than a second threshold.

29. The method according to any one of claims 16, 21 to 28, wherein, When the rank of the RI included in the CSI is lower than a first threshold, and / or the CQI included in the CSI is lower than a second threshold, the CSI is measured based on an AI receiver hypothesis; When the rank of the RI included in the CSI is not lower than the first threshold, and / or the CQI included in the CSI is not lower than the second threshold, the CSI is measured based on a non-AI receiver hypothesis.

30. The method according to any one of claims 16 to 29, wherein, The non-AI receiver hypothesis includes a minimum mean square error (MMSE) receiver hypothesis and / or a maximum likelihood receiver hypothesis.

31. A terminal device, comprising: A first communication unit configured to receive configuration information sent by a network device, where the configuration information is used to instruct the terminal device to send channel state information (CSI); A measurement unit configured to measure CSI based on the configuration information, where the CSI includes a first CSI measured based on an artificial intelligence (AI) receiver hypothesis and / or a second CSI measured based on a non-AI receiver hypothesis.

32. A network device, comprising: A second communication unit configured to send configuration information to a terminal device, where the configuration information is used to instruct the terminal device to send channel state information (CSI); The second communication unit is further configured to receive the CSI sent by the terminal device, where the CSI includes a first CSI measured based on an artificial intelligence (AI) receiver hypothesis and / or a second CSI measured based on a non-AI receiver hypothesis.

33. A terminal device, comprising: A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 15.

34. A network device, comprising: A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 16 to 30.

35. A chip, comprising: A processor, used to call and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 1 to 15, or executes the method according to any one of claims 16 to 30.

36. A computer-readable storage medium for storing a computer program, the execution of which causes a computer to perform the method according to any one of claims 1 to 15, or to perform the method according to any one of claims 16 to 30.

37. A computer program product comprising computer program instructions, the execution of which causes a computer to perform the method according to any one of claims 1 to 15, or to perform the method according to any one of claims 16 to 30.

38. A computer program, the execution of which causes a computer to perform the method according to any one of claims 1 to 15, or to perform the method according to any one of claims 16 to 30.

Images