Performance determination method, apparatus, storage medium, and program product

Abstract

Embodiments of the present disclosure relate to the technical field of communications, and provide a performance determination method, an apparatus, a storage medium, and a program product. The method is applied to a first node. The method comprises: acquiring first channel state information and second channel state information, wherein the first channel state information is acquired on the basis of a plurality of first measurement resources, the second channel state information is acquired on the basis of a second measurement resource, and the first measurement resources and the second measurement resource are different in at least one of the following: a slot, a frequency-domain unit position, and a port resource; and determining a first performance indicator of the second channel state information on the basis of the first channel state information.

Description

Performance determination methods, apparatus, storage media and program products

[0001] This disclosure claims priority to Chinese patent application No. 202510389572.1, filed on March 28, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a performance determination method, apparatus, storage medium, and program product. Background Technology

[0003] Channel state information (CSI) technology based on artificial intelligence (AI) / machine learning (ML) generally requires monitoring the accuracy of model predictions to achieve lifecycle management of AI / ML models. Currently, AI / ML model monitoring can be based on performance metrics. Specifically, the terminal calculates a performance metric by combining measured ground truth data and the model's output, and sends this metric to the base station. The base station uses this performance metric to determine whether the prediction accuracy of the AI / ML model currently used by the terminal meets the current functional requirements, i.e., whether the performance of the AI / ML model currently used by the terminal meets the current functional requirements. Since the terminal needs to continuously calculate and report performance metrics to the base station during the detection process, reducing the computational overhead of performance metrics is an important goal for reducing terminal power consumption. Summary of the Invention

[0004] Firstly, a performance determination method is provided, applied to the first node, including:

[0005] First channel state information and second channel state information are obtained. Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain cell location, and port resources.

[0006] The first performance index for determining the second channel state information is based on the first channel state information.

[0007] Secondly, a performance determination method is provided, applied to the second node, including:

[0008] The first performance indicator is received from the first node. The first performance indicator is a first performance indicator of the second channel state information determined based on the first channel state information. Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0009] Thirdly, a performance determination method is provided, applied to the first node, including:

[0010] Receive first channel state information sent by the second node, the first channel state information being acquired based on multiple first measurement resources;

[0011] Send second channel state information to the second node. The second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain cell location, and port resources. The first channel state information is used to determine the first performance index of the second channel state information.

[0012] Fourthly, a performance determination method is provided, applied to the second node, including:

[0013] Send first channel state information to the first node. The first channel state information is acquired based on multiple first measurement resources.

[0014] The system receives second channel state information sent by the first node. The second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain cell location, and port resources.

[0015] The first performance index for determining the second channel state information is based on the first channel state information.

[0016] Fifthly, a communication device is provided for use in a first node, comprising:

[0017] The acquisition unit is used to acquire first channel state information and second channel state information. Here, the first channel state information is acquired based on multiple first measurement resources, and the second channel state information is acquired based on second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0018] The processing unit is used to determine a first performance index of the second channel state information based on the first channel state information.

[0019] Sixthly, a communication device is provided for use in a second node, comprising:

[0020] The receiving unit is used to receive the first performance index sent by the first node. The first performance index is a first performance index of the second channel state information determined based on the first channel state information. Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0021] A seventh aspect provides a communication device applied to a first node, comprising:

[0022] The receiving unit is used to receive first channel state information sent by the second node, the first channel state information being acquired based on multiple first measurement resources;

[0023] The transmitting unit is used to transmit second channel state information to the second node. The second channel state information is acquired based on second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain unit location, and port resources. The first channel state information is used to determine the first performance index of the second channel state information.

[0024] Eighthly, a communication device is provided for use in a second node, comprising:

[0025] The transmitting unit is used to transmit first channel state information to the first node. The first channel state information is acquired based on multiple first measurement resources.

[0026] The receiving unit is used to receive the second channel state information sent by the first node. The second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0027] The processing unit is used to determine a first performance index of the second channel state information based on the first channel state information.

[0028] A ninth aspect provides a communication device, comprising: a processor and a memory; the memory storing processor-executable instructions; when the processor is configured to execute the instructions, causing the communication device to implement any of the methods provided in any of the first to fourth aspects described above.

[0029] A tenth aspect provides a computer-readable storage medium, the computer-readable storage medium including a non-transitory computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform any method provided by any one of the first to fourth aspects.

[0030] Eleventhly, a computer program product comprising computer instructions is provided, which, when executed on a computer, causes the computer to perform any of the methods provided by any of the first to fourth aspects. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly described below. Obviously, the drawings described below are merely drawings of some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings.

[0032] Figure 1 is a structural diagram of a communication system provided according to an embodiment of the present disclosure.

[0033] Figure 2 is a flowchart of a performance determination method provided according to an embodiment of the present disclosure.

[0034] Figure 3 is a flowchart of another performance determination method provided according to an embodiment of the present disclosure.

[0035] Figure 4 is a flowchart of another performance determination method provided according to an embodiment of the present disclosure.

[0036] Figure 5 is a flowchart of another performance determination method provided according to an embodiment of the present disclosure.

[0037] Figure 6 is a block diagram of a communication device provided according to an embodiment of the present disclosure.

[0038] Figure 7 is a block diagram of another communication device provided according to an embodiment of the present disclosure.

[0039] Figure 8 is a block diagram of another communication device provided according to an embodiment of the present disclosure.

[0040] Figure 9 is a block diagram of another communication device provided according to an embodiment of the present disclosure.

[0041] Figure 10 is a block diagram of another communication device provided according to an embodiment of the present disclosure. Detailed Implementation

[0042] To enable those skilled in the art to better understand the technical solutions of the embodiments of this disclosure, the technical solutions of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0043] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and other forms such as the third-person singular "comprises" and the present participle "comprising" are interpreted as open-ended and encompassing, meaning "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiments," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this disclosure. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics mentioned may be included in any suitable manner in any one or more embodiments or examples.

[0044] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0045] In this disclosure, the terms "exemplarily" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplarily" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of the terms "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0046] In addition, the use of “based on” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0047] AI / ML model performance monitoring is a crucial support capability for future communication systems that natively support AI / ML functions. In AI / ML-based CSI monitoring, generalized cosine similarity or normalized mean square error can be used to compare the similarity between the model-predicted CSI and the terminal's actual measured CSI, thereby obtaining the AI / ML model performance. During model monitoring, it is necessary to ensure that the predicted CSI and the actual measured CSI correspond to the same channel state information reference signal (CSI-RS) at the same resource location; that is, the time slots, frequency domain units, and transmit / receive ports corresponding to the predicted CSI and the measured CSI must be completely identical. Based on this, the terminal uses the measured CSI matrix as the ground truth CSI, and each predicted CSI has a unique corresponding ground truth CSI. For a set of matrices consisting of a predicted CSI matrix and its corresponding ground truth CSI, the terminal can directly perform performance monitoring based on this set of CSI matrices, or it can preprocess this set of CSI matrices and then perform performance monitoring based on the preprocessed results.

[0048] The computational complexity of performance monitoring based on CSI matrices is generally directly related to the computational complexity of key performance indicators (KPIs). Furthermore, the computational complexity of performance monitoring directly based on the CSI matrix is ​​generally linearly related to the matrix's dimension. For example, the complexity of calculating an MxN-dimensional CSI matrix for a subband using normalized mean and variance is approximately O(MxN). The computational complexity of performance monitoring based on CSI matrix preprocessing results generally consists of two parts: the complexity of CSI matrix preprocessing and the computational complexity of the performance monitoring KPIs. For instance, considering the complexity of performance monitoring using the squared generalized cosine similarity of the singular vector corresponding to the largest singular value, this method first performs singular value decomposition on the MxN-dimensional CSI matrix, then selects the singular vector corresponding to the largest singular value for squared generalized cosine value calculation; the corresponding computational complexity is approximately O(MxN²).

[0049] Therefore, when designing a solution to reduce the computational complexity of AI / ML model performance monitoring, it is necessary to comprehensively consider the time-domain feedback period, frequency-domain granularity, and spatial-domain port number of the CSI matrix, and design a performance monitoring solution from multiple perspectives.

[0050] In some cases, AI / ML-based CSI prediction functions are implemented as follows:

[0051] (1) The base station configures a set of CSI-RS resources and informs the terminal of the reporting method for the set of CSI-RS through downlink control information (DCI) signaling.

[0052] (2) After receiving the DCI signaling, the terminal accepts the configured CSI-RS resources, determines the function that the base station wants the terminal to implement (i.e., CSI prediction) according to the configured reporting method, and calls the corresponding AI / ML model.

[0053] (3) The terminal uses an AI / ML model to predict the CSI of one or more future time slots. The specific number is configured by the CSI reporting and reported to the base station.

[0054] To enable model monitoring for AI / ML-based CSI prediction, the base station needs to configure an additional set of CSI-RS resources and send them to the terminal. Upon receiving the CSI-RS, the terminal measures the ground truth CSI and calculates the Key Performance Indicators (KPIs) for monitoring the AI / ML model based on the ground truth CSI and the previously configured predicted CSI. The terminal then reports the calculated KPIs to the base station. Based on the KPIs reported by the terminal, the base station determines whether the AI / ML model used for CSI prediction needs to be replaced.

[0055] The embodiments of this disclosure will now be described in conjunction with the accompanying drawings.

[0056] The technical solutions provided in this disclosure can be applied to various mobile communication networks, such as NR mobile communication networks using 5th generation mobile networks (5G), future mobile communication networks (such as 6G wireless communication systems), or multiple communication convergence systems, etc. This disclosure does not limit them.

[0057] In this disclosure, the mobile communication network (including but not limited to 3G, 4G, 5G, and future mobile communication networks, such as 6G) may include network-side devices (e.g., including but not limited to base stations) and receiving-side devices (e.g., including but not limited to terminals). It should be understood that, in this example, for instance, in the downlink, the first communication node (also referred to as the first communication node device, the first node) may be a base station-side device, and the second communication node (also referred to as the second communication node device, the second node) may be a terminal-side device. In some examples, such as in the uplink, the first communication node may also be a terminal-side device, and the second communication node may also be a base station-side device. In some examples, such as in device-to-device communication between the two communication nodes, both the first and second communication nodes may be base stations or terminals. Therefore, whether the first and second nodes are base stations or terminals needs to be determined based on the context.

[0058] Figure 1 is a structural diagram of a communication system provided according to an embodiment of the present disclosure. As shown in Figure 1, the communication system includes, but is not limited to, a first node 110 and a second node 120. Here, the first node 110 and the second node 120 can transmit and receive wireless signals and perform related interactions.

[0059] In a wireless communication scenario, the first node 110 and the second node 120 communicate via a wireless channel. For example, the first node 110 may be a terminal, and the second node 120 a base station; the terminal and the base station communicate via a wireless channel. Alternatively, the first node 110 may be a terminal, and the second node 120 a wireless router; the wireless router and the terminal communicate via a wireless channel. Another example is that the first node 110 may be a first base station, and the second node 120 a second base station; the first base station and the second base station communicate via a wireless channel. Yet another example is that the first node 110 may be a first terminal, and the second node 120 a second terminal; the first terminal and the second terminal communicate via a wireless channel. Finally, the first node 110 may be a repeater, and the second node 120 a base station; the base station and the repeater communicate via a wireless channel. Finally, the first node 110 may be a terminal, and the second node 120 a repeater; the repeater and the terminal communicate via a wireless channel. For example, node 110 is a first repeater, and node 120 is a second repeater; the first repeater and the second repeater communicate via a wireless channel. Alternatively, node 110 can be a base station, and node 120 a satellite; the satellite and the base station communicate via a wireless channel. Another example: node 110 can be a satellite, and node 120 a base station; the base station and the satellite communicate via a wireless channel. Yet another example: node 110 can be a terminal, and node 120 a satellite; the satellite and the terminal communicate via a wireless channel. Again, node 110 can be a satellite, and node 120 a terminal; the terminal and the satellite communicate via a wireless channel. Finally, node 110 can be ground equipment, and node 120 can be an aircraft; the aircraft and the ground equipment communicate via a wireless channel. Finally, node 110 can be a first aircraft, and node 120 a second aircraft; the first aircraft and the second aircraft communicate via a wireless channel.

[0060] Unless otherwise specified, the terms "first" node, "second" node, "first" method, "second" method, "first" approach, "second" approach, "first" matrix, "second" matrix, "first" part, and "second" part in this disclosure are used only for descriptive distinction and do not represent a sequential or chronological order.

[0061] In this disclosure, the base station can be a base station in Long Term Evolution (LTE), Long Term Evolution Advanced (LTEA), or an evolved Node B (eNB or eNodeB), a base station device in a 5G network, or a base station in a future communication system (such as 6G). The base station can include various macro base stations, micro base stations, home base stations, wireless remote extensions, reconfigurable intelligent surfaces (RISs), routers, wireless fidelity (WIFI) devices, or various network-side devices such as primary cells and secondary cells.

[0062] In this disclosure, a terminal is a device with wireless transceiver capabilities that can be deployed on land, including indoors or outdoors; on water (such as on ships); and in the air (such as on airplanes, balloons, and satellites). The terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. The embodiments of this disclosure do not limit the application scenarios. A terminal may also be referred to as a user, user equipment, access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication device, UE agent, or UE device, etc. The embodiments of this disclosure are not limited to these terms.

[0063] Figure 1 is an exemplary structural diagram. The number of devices included in the communication system shown in Figure 1 is not limited; for example, the number of first nodes and second nodes is not limited. Furthermore, in addition to the devices shown in Figure 1, the communication system shown in Figure 1 may include other devices, which are not limited thereto.

[0064] Next, as shown in Figure 2, this embodiment of the disclosure provides a performance determination method. This method is applied to a first node, which may be the first node 110 shown in Figure 1 above. The method may include the following steps:

[0065] S101. Obtain the first channel status information and the second channel status information.

[0066] Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain unit location, and port resources.

[0067] The first channel state information can be understood as the predicted value of the channel state information, and the second channel state information can be understood as the measured value of the channel state information. In other words, the first channel state information can be understood as the channel state information predicted based on the AI / ML model, and the second channel state information can be understood as the channel state information monitored at the prediction time corresponding to the first channel state information.

[0068] In some embodiments, the second channel state information corresponds to a second frequency domain resource, the first channel state information corresponds to a first frequency domain resource, and the second frequency domain resource is a subset of the first frequency domain resource; and / or,

[0069] The second channel state information corresponds to the second set of receiving ports, the first channel state information corresponds to the first set of receiving ports, and the second set of receiving ports is a subset of the first set of receiving ports.

[0070] In some embodiments, obtaining the first channel state information may include the following examples:

[0071] Example A1: Receive first measurement configuration information sent by the second node, the first measurement configuration information is used to configure the first measurement resource; measure the reference signal on the first measurement resource to obtain the fourth channel state information; obtain the first channel state information based on the fourth channel state information.

[0072] Here, the second node can be the second node 120 shown in Figure 1 above. For ease of description, the following embodiment uses a terminal as the first node and a base station as the second node to illustrate a performance determination method provided by this disclosure.

[0073] In other words, in some embodiments, the base station configures a set of CSI-RS (i.e., the first measurement resource) via signaling for the terminal's CSI prediction function based on an AI / ML model. After receiving the first measurement configuration information, the terminal measures the reference signal on the first measurement resource to obtain the fourth channel state information, and then uses the fourth channel state information to predict the first channel state information to obtain the first channel state information.

[0074] Example A2: Receives the first channel status information sent by the second node.

[0075] In some embodiments, the base station can use an AI / ML model to predict CSI groups (i.e., first channel state information) for the next N4 time points, with each CSI group containing K CSIs; then the base station indicates these N4 CSI groups to the terminal. This is equivalent to receiving the first channel state information sent by the second node.

[0076] In other words, the first channel state information can be determined by the first node, or it can be determined by the second node and then sent to the first node. Accordingly, the first node receives the first channel state information sent by the second node.

[0077] Example B1: Receive first channel state information sent by the second node; receive first indication information sent by the second node, the first indication information being used to indicate the channel state information monitoring set in the first channel state information; determine second channel state information from the first channel state information based on the first indication information.

[0078] Example B2: Receive second measurement configuration information sent by the second node, the second measurement configuration information being used to configure the second measurement resource; receive second indication information sent by the second node, the second indication information being used to indicate the frequency domain unit subset configuration and / or antenna port subset configuration; measure a reference signal on the second measurement resource to obtain the fifth channel state information; determine the second channel state information from the fifth channel state information based on the second indication information.

[0079] In some embodiments, the base station configures a set of CSI-RS (i.e., measurement resources) and instructs the terminal to monitor the performance of AI / ML models that predict the CSI set. In order to reduce the computational overhead of the terminal when performing model monitoring, the base station can reduce the monitoring overhead of the terminal at two granularities (i.e., Example B1 and Example B2 above).

[0080] For example B1 above, a CSI monitoring set is selected from all CSIs predicted by the base station, that is, a CSI monitoring set is selected from the first channel state information as the second channel state information.

[0081] On the one hand, the base station can indicate N4' CSI groups from the predicted N4 CSI groups, each group containing K' CSIs, forming a monitoring CSI set, which is also the second channel state information, where N4' <N4,K’<K。

[0082] On the other hand, the base station will indicate the CSI monitoring set to the terminal. The method for indicating the CSI group can be as follows:

[0083] The first indication information is used to indicate the number of CSI groups included in the monitoring CSI set and the first indication information is used to indicate the number of CSI groups included in each monitoring CSI set.

[0084] The first indication information indicates the indexes of the N4' CSI groups included in the monitoring CSI set, and the indexes of the K' CSIs included in a single monitoring CSI group; that is, the first indication information is used to indicate the indexes of the CSI groups included in the CSI monitoring set (i.e., the second channel state information), and to indicate the indexes of the CSIs included in each CSI group.

[0085] Alternatively, at least one set of CSI group indexes contained in a monitoring CSI set can be predefined, each set containing N4' CSI group indexes; and at least one set of CSI indexes contained in a single monitoring CSI set, each set containing K' CSI indexes, and indicating the sequence number of at least one CSI group index set and / or the sequence number of at least one CSI index set; or some sets of CSI group indexes and CSI indexes can be predefined, each set containing N4' CSI group indexes and K' CSI indexes, indicating the index of at least one of the above sets; here N4' <N4,K'<K。

[0086] For example B2 above, that is, selecting a subset of frequency domain elements or a subset of antenna ports from the CSI configured by the base station as the second channel state information, the steps are as follows:

[0087] The base station is configured with a CSI-RS (i.e., the second measurement resource) for the terminal to perform CSI monitoring within the CSI set. In other words, a set of measurement resources is configured for the terminal to measure channel state information. The terminal can measure the reference signal on this CSI-RS to obtain the fifth channel state information.

[0088] Taking the second indication information used to indicate a subset configuration of frequency domain units as an example, the base station indicates a subset configuration of a set of CSI-RS ports (i.e., an antenna port subset configuration). This CSI-RS port subset configuration includes a subset of transmitter ports and a subset of receiver ports, and the configuration of this port subset can be:

[0089] Indicates the number of ports included in the subset of transmit ports P', and indicates the number of ports included in the subset of receive ports M';

[0090] Indicates P' transmit port indices and M' receive port indices; or predefines at least one set of transmit port indices, each set containing P' transmit port indices, and at least one set of receive port indices, each set containing M' receive port indices, and indicates the sequence number of at least one set of transmit port indices and / or the sequence number of at least one set of receive port indices; or predefines some sets of transmit and receive port indices, each set containing P' transmit port indices and M' receive port indices, indicating at least one set of transmit and receive port indices;

[0091] Here, P' <P,M'<M。

[0092] If P' = P, the base station does not need to indicate the number of transmit ports or the subset of transmit ports as described above. If M' = M, the base station does not need to indicate the number of transmit ports or the subset of receive ports as described above.

[0093] The terminal measures the monitoring CSI-RS on N frequency domain units (i.e., measures the reference signal on the second measurement resource) according to the base station configuration to obtain the fifth channel state information, and selects the CSI-RS measurement results on these N' subcarriers as the true CSI matrix H according to the base station configuration (i.e., the second indication information). i That is, the CSI-RS measurement results on N' subcarriers in the fifth channel state information are selected as the second channel state information.

[0094] Taking the second indication information used to indicate an antenna port subset configuration as an example, the base station indicates a frequency domain subset configuration (i.e., frequency domain subset element configuration) of a CSI-RS. This frequency domain subset configuration of the CSI-RS can be:

[0095] The number of CSI-RS frequency domain units N' required when calculating performance indicators;

[0096] Indicates all N' CSI-RS frequency domain cell indices required for calculating performance metrics. The indication method is either to directly indicate all frequency domain cell indices; or, at least one set of frequency domain cell indices can be predefined, each set containing N' frequency domain cell indices, indicating at least one set of frequency domain cell indices.

[0097] Here, N' <N。

[0098] If N' = N, the base station does not need to indicate the number of frequency domain units or the frequency domain unit index as described above.

[0099] The terminal measures the full-port monitoring CSI-RS on N subcarriers according to the base station configuration, obtains an N×M port CSI matrix (i.e., fifth channel state information), and selects the N'×M' ports here as the true CSI matrix H for calculating the performance of the AI / ML model.i That is, the channel state information on port N'×M' in the fifth channel state information is selected as the second channel state information.

[0100] Taking the second indication information used to indicate the frequency domain element subset configuration and antenna port subset configuration as an example,

[0101] The terminal measures the full-port monitoring CSI-RS on N subcarriers according to the base station configuration, and selects the CSI-RS measurement results on N' subcarriers (i.e., frequency domain unit subsets) from the measured channel state information according to the base station configuration. Then, for each selected subcarrier, the terminal selects P'×M' ports (i.e., antenna port subsets) as the true CSI matrix H. i (That is, the second channel state information). In other words, the terminal measures the reference signal on the second measurement resource to obtain the fifth channel state information, and then selects the CSI-RS measurement results on N' subcarriers from the fifth channel state information based on the second indication information. Then, it selects the channel state information on the P'×M' port in the CSI matrix of each selected subcarrier as the second channel state information.

[0102] In some cases, the base station can use an AI / ML model to predict CSI groups for the next N4 time points, with each time point containing K CSIs; the base station then indicates these N4 CSI groups to the terminal, and the indication methods include, but are not limited to, the following:

[0103] (1) Channel matrix H.

[0104] (2) All left / right singular vectors of the channel matrix.

[0105] (3) The channel matrix corresponds to the left / right singular vectors of the first L largest singular values, where L≥1.

[0106] (4) All left / right singular vectors and singular values ​​of the channel matrix.

[0107] (5) The channel matrix corresponds to the top L largest singular values ​​and the corresponding left / right singular vectors, where L≥1.

[0108] (6) All left singular vectors, right singular vectors and singular values ​​of the channel matrix.

[0109] (7) The channel matrix corresponds to the first L largest singular values ​​and the corresponding left singular vector and right singular vector, L≥1.

[0110] In other words, receiving the first channel state information sent by the second node includes any of the following:

[0111] The channel matrix that receives the first channel state information sent by the second node;

[0112] All left / right singular vectors of the channel matrix that receives the first channel state information sent by the second node;

[0113] The left / right singular vectors corresponding to the top L largest singular values ​​of the channel matrix that receives the first channel state information sent by the second node, where L is a positive integer;

[0114] The channel matrix receiving the first channel state information sent by the second node contains all left / right singular vectors and singular values;

[0115] The top L largest singular values ​​and corresponding left / right singular vectors of the channel matrix corresponding to the first channel state information sent by the second node;

[0116] The channel matrix that receives the first channel state information sent by the second node contains all left singular vectors, right singular vectors, and singular values;

[0117] The first L largest singular values ​​of the channel matrix and the corresponding left and right singular vectors of the channel state information sent by the second node.

[0118] In some cases, the base station can use an AI / ML model to predict CSI groups for the next N4 time points, with each time point containing K CSIs; the base station then indicates these N4 CSI groups to the terminal, and the indication method includes, but is not limited to, the following:

[0119] (1) Indicator channel matrix H.

[0120] (2) Indicates all right singular vectors of the channel matrix.

[0121] (3) Indicates the right singular vector corresponding to the first L largest singular values ​​of the channel matrix.

[0122] (4) Indicates the spatial basis vector index of all right singular vectors of the channel matrix after quantization by a codebook (e.g., Type I codebook, Type II codebook, Enhanced Type II codebook, etc.).

[0123] (5) Indicates the spatial basis vector index of the right singular vector corresponding to the first L largest singular values ​​of the channel matrix after quantization by a codebook (e.g., Type I codebook, Type II codebook, Enhanced Type II codebook, etc.).

[0124] (6) Precoding matrix indicator (PMI) for indicating the channel matrix.

[0125] In other words, receiving the first channel state information sent by the second node also includes any of the following:

[0126] All right singular vectors of the channel matrix that receive the first channel state information sent by the second node.

[0127] The right singular vector corresponding to the top L largest singular values ​​of the channel matrix that receives the first channel state information sent by the second node.

[0128] The spatial basis vector index of all right singular vectors of the channel matrix that receive the first channel state information sent by the second node after codebook quantization.

[0129] The spatial basis vector index of the right singular vector corresponding to the top L singular values ​​of the channel matrix that receives the first channel state information sent by the second node after codebook quantization.

[0130] In some cases, base stations can use codebook quantization to reduce the indication overhead of the aforementioned CSI groups, that is, to reduce the overhead of transmitting the first channel state information. The generation and indication methods of the basis vector groups used in this quantization include, but are not limited to, the following:

[0131] 1. Quantization method based on discrete Fourier transform (DFT) basis vector groups. In this quantization method, the base station needs to specify a set of DFT basis vectors {u} used for quantizing CSI. m} and codeword {v l,m In related technologies, the basis vector {u} m} and codeword {v l,m The construction of} is shown in the following formula.

[0132] Here, N1, N2, O1, O2, l, and m are determined by parameters configured by the base station. In related technologies, these parameters are reported by the terminal to the base station in the PMI. In this embodiment of the present disclosure, in order to enable the base station to predict CSI and notify the terminal, the base station can also configure CSI and indicate it to the terminal, and the indication method includes at least PMI indication.

[0133] 2. Quantization method based on AI-generated basis vector sets. Under this quantization method, the base station can directly generate a set of basis vectors using an AI / ML model. The base station either explicitly notifies the terminal of this set of basis vectors, or it notifies the terminal of the AI / ML model that generated the basis vectors, and also notifies the terminal of the corresponding model input. When notifying the terminal of the basis vectors, the base station should also notify the terminal of the number of basis vectors in this set, and the indication method includes, but is not limited to, the following:

[0134] The base station notifies the number L of base vectors contained in the base vector group, and explicitly notifies the L base vectors generated by AI. The base station also notifies that the indices of this group of base vectors are arranged in ascending or descending order according to the order of notification.

[0135] The base station notifies the number L of basis vectors contained in the basis vector group, the AI / ML model used to generate the basis vectors, and the model input required for generating the basis vectors. The base station also notifies the terminals that the indices of this set of basis vectors are arranged in ascending or descending order based on the order of notification.

[0136] In other words, the first channel state information is obtained based on codebook quantization, and the codebook quantization method includes at least one of the following:

[0137] Quantization method based on DFT basis vector groups;

[0138] A quantization method based on AI-generated basis vector groups.

[0139] In some embodiments, the codebook quantization method is predefined or configured by signaling.

[0140] In some embodiments, the base station needs to agree on a base vector group with the terminal in advance. For example, the base station explicitly notifies the terminal via signaling of the base vector form used in predicting CSI (i.e., first channel state information), that is, the base station sends a third indication information to the terminal, which indicates the base vector group used for the first channel state information; the base station may also notify the terminal via signaling of receiving the CSI prediction result, whereby the base vector form is implicitly indicated by the signaling configuration terminal receiving the CSI prediction, that is, the base station sends an indication information to the terminal to instruct the terminal to receive the first channel state information, and the terminal can determine the base vector group used for the first channel state information based on this indication information.

[0141] The terminal uses the base vector set explicitly / implicitly indicated by the base station to determine the CSI indicated by the base station (that is, to determine the first channel state information).

[0142] The base station can configure a codebook for quantizing CSI using a pre-defined set of basis vectors. This codebook can contain all basis vectors from the set, or only a subset of them. The base station needs to indicate to the terminal via signaling the indices of all basis vectors contained in the codebook. This indication can be done in the following ways:

[0143] The base station configures a set of bit sequences to indicate the base vector indices contained in the codebook. This bit sequence has a length of at least L, and each bit indicates whether the base vector corresponding to that index is contained in the codebook. For example, this bit sequence can be represented as A = a0a1...a L-1 , here a i a indicates whether the basis vector at index i is included in the codebook. i =1 indicates that the basis vector is included in the codebook, a i =0 indicates that the basis vector is not included in the codebook. The base station can be configured to index the basis vectors in the codebook using one of the following two methods:

[0144] According to the original indexing method, the basis vector index is from 0 to L-1, regardless of whether the basis vector is contained in the codebook;

[0145] The index is determined by re-sorting the original indices of the basis vectors in the codebook from smallest to largest / from largest to smallest. That is, if the codebook contains L' basis vectors, the basis vectors in the codebook are sorted in ascending order of their original indices and then re-indexed according to the sequence numbers from 0 to L'.

[0146] When a base station uses basis vector quantization to indicate the first channel state information, it may adopt methods including but not limited to the following:

[0147] The spatial basis vector index of all right singular vectors of the channel matrix indicating the first channel state information after quantization by a codebook (e.g., Type I codebook, Type II codebook, Enhanced Type II codebook, AI-generated codebook, etc.).

[0148] The spatial basis vector index of the right singular vector corresponding to the first L largest singular values ​​of the channel matrix indicating the first channel state information, after being quantized by a codebook (e.g., Type I codebook, Type II codebook, Enhanced Type II codebook, AI-generated codebook, etc.), where L≧≥1.

[0149] The precoding matrix index of the channel matrix that indicates the first channel state information.

[0150] That is, receiving the first channel state information sent by the second node, including any one of the following:

[0151] The spatial basis vector index of all right singular vectors of the channel matrix that receive the first channel state information sent by the second node after codebook quantization.

[0152] The spatial basis vector index of the right singular vector corresponding to the top L singular values ​​of the channel matrix that receives the first channel state information sent by the second node after codebook quantization.

[0153] The precoding matrix index of the channel matrix that receives the first channel state information sent by the second node.

[0154] S102. Determine the first performance index of the second channel state information based on the first channel state information.

[0155] Here, the first performance metric is used to represent predictive performance, model monitoring performance, etc. Predictive performance is also the predictive performance of the AI / ML model.

[0156] In some embodiments, the first performance metric is a KPI.

[0157] As an example, based on the measurement configuration corresponding to the second channel state information, the third channel state information is determined from the first channel state information, and the third channel state information and the second channel state information are aligned on frequency domain resources and / or receiver ports; a first performance index of the second channel state information is determined based on the third channel state information.

[0158] The measurement configuration corresponding to the second channel state information includes frequency domain resource configuration and / or receiver port configuration.

[0159] Aligning the third channel state information with the second channel state information in the frequency domain resources and / or receiver ports eliminates the need to determine the first performance metric of the second channel state information based on all the first channel state information, thus reducing the computational overhead of performance metrics. Furthermore, aligning the third channel state information with the second channel state information in the frequency domain resources and / or receiver ports improves the accuracy of determining the first performance metric.

[0160] Combining the method of obtaining the second channel state information shown in Example B2 above, taking the second indication information used to indicate the antenna port subset configuration as an example, the terminal obtains the second channel state information H... i Subsequently, the terminal uses the predicted CSI matrix calculated by the model, corresponding to the arrival time of the N×M port and the subcarrier (physical resource block (PRB) / subband), to select the corresponding 8x2 port CSI as the H used to calculate the first performance indicator, according to the CSI port subset configuration configured by the base station. i That is, based on the receiving port configuration of the second channel state information, the third channel state information is determined from the first channel state information, and the third channel state information is aligned with the second channel state information on the receiving port. Then, N' groups of H... i and H i Based on the first performance index, that is, based on the third channel state information and the second channel state information, the first performance index is determined.

[0161] Taking the second indication information used to indicate the configuration of a subset of frequency domain units as an example, the terminal obtains the second channel state information H i Subsequently, the terminal calculates the predicted CSI (i.e., the first channel state information) based on the AI / ML model, which corresponds to the time-domain location and number of ports of the monitoring CSI-RS. It then selects the CSIs on the N' frequency domain units that are identical to the second channel state information as the H values ​​used to calculate the first performance indicator. i That is, based on the frequency domain resource allocation of the second channel state information, the third channel state information is determined from the first channel state information, and the third channel state information is aligned with the second channel state information in the frequency domain resources. Then, N' groups of H... i and H iBased on the first performance index, that is, based on the third channel state information and the second channel state information, the first performance index is determined.

[0162] Taking the second indication information used to indicate the frequency domain element subset configuration and antenna port subset configuration as an example, the terminal obtains the second channel state information H i Subsequently, the terminal calculates the predicted CSI corresponding to the frequency domain location and port number of the monitoring CSI-RS based on the AI / ML model, and selects the CSIs on the N' subcarriers that are identical to the second channel state information as H. i That is, based on the frequency domain resource configuration and antenna port configuration of the second channel state information, the third channel state information is determined from the first channel state information, and the third channel state information is aligned with the second channel state information in terms of frequency domain resources and antenna ports. Then, N' groups of H... i and H i Based on the first performance index, that is, based on the third channel state information and the second channel state information, the first performance index is determined.

[0163] In some embodiments, the method for determining the first performance indicator is predefined or configured by signaling. The first node may determine the first performance indicator based on the method for determining the first performance indicator, combined with first channel state information and second channel state information. Alternatively, the first node may determine the first performance indicator based on the method for determining the first performance indicator, combined with third channel state information and second channel state information.

[0164] Taking the method of determining the first performance indicator as an example, the first node receives signaling from the second node to configure the method for determining the first performance indicator. Then, the method for determining the first performance indicator is determined based on this signaling.

[0165] Currently, performance metrics used for monitoring AI / ML-based CSI prediction models are generally calculated using either square general cosine similarity (SGCS) or normalized mean square error (NMSE). As an example, the first performance metric can be determined using any of the following methods:

[0166] Method 1: Right singular vector based on codebook quantization.

[0167] The average SGCS of the spatial basis vectors obtained based on the first and second channel state information is determined as the first performance index. Alternatively, the average SGCS of the spatial basis vectors obtained based on the third and second channel state information is determined as the first performance index.

[0168] For example, if CSI is predicted on N frequency domain units (subband / PRB / subcarrier), N predicted CSI matrices are obtained. (i.e., the first channel state information). Simultaneously, the terminal measured the CSI-RS (i.e., the second measurement resource) on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i (i.e., second channel state information). After performing singular value decomposition (SVD) on the N predicted CSI matrices and N true CSI matrices, it is necessary to select N sets of corresponding right singular vectors and calculate the spatial basis vectors obtained by quantizing each set of right singular vectors using the codebook. and w i Calculate the SGCS of the spatial basis vectors, and define the mean SGCS of these N sets of spatial basis vectors as the KPI of the AI / ML model, i.e., the first performance index. The determination method can be shown in the following formula:

[0169] Method 2: Based on the right singular vector.

[0170] The average SGCS of the right singular vectors obtained based on the first and second channel state information is determined as the first performance metric. Alternatively, the average SGCS of the right singular vectors obtained based on the third and second channel state information is determined as the first performance metric.

[0171] For example, if CSI is predicted on N frequency domain units (subband / PRB / subcarrier), N predicted CSI matrices are obtained. Simultaneously, the terminal measured the CSI-RS on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i After performing SVD decomposition on N predicted CSI matrices and N true CSI matrices, it is necessary to select N sets of corresponding right singular vectors. and v i Calculate the SGCS of the right singular vectors, and define the mean SGCS of these N sets of right singular vectors as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0172] Method 3: Linear combination of row / column vectors based on the CSI matrix.

[0173] The average SGCS of the row / column vectors obtained based on the first channel state information and the second channel state information is determined as the first performance index; or, the average SGCS of the row / column vectors obtained based on the third channel state information and the second channel state information is determined as the first performance index.

[0174] For example, the terminal predicts the CSI on N frequency domain units (subband / PRB / subcarrier), resulting in N predicted CSI matrices. (i.e., the first channel state information). Simultaneously, the terminal measured the CSI-RS (i.e., the second measurement resource) on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i (i.e., second channel state information). The vector h corresponding to the N predicted CSI matrices and the N true CSI matrices. i and Calculate the SGCS and define the mean of the SGCS of these N corresponding vectors as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0175] Here, h i and The calculation method can be expressed as the following formula:

[0176] Alternatively, as shown in the following formula:

[0177] Here, c is the weight of the corresponding matrix selected from the CSI matrix.

[0178] If the weight c is chosen as the transmit port weight vector of CSI-RS (i.e., the second measurement resource), h i It can be directly provided by the signal from the receiving port, without needing to obtain the channel matrix H. i .

[0179] The above methods use SGCS to define the first performance metric, while the following implementation methods can use NMSE to define the first performance metric.

[0180] Method 4: Right singular vector based on codebook quantization.

[0181] The mean NMSE of the spatial basis vectors obtained based on the first channel state information and the second channel state information is determined as the first performance index; or, the mean NMSE of the spatial basis vectors obtained based on the third channel state information and the second channel state information is determined as the first performance index.

[0182] For example, if CSI is predicted on N frequency domain units (subband / PRB / subcarrier), N predicted CSI matrices are obtained. Simultaneously, the terminal measured the CSI-RS on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. iAfter performing SVD decomposition on N predicted CSI matrices and N true CSI matrices, it is necessary to select N sets of corresponding right singular vectors and calculate the spatial basis vectors obtained by quantizing each set of right singular vectors using the codebook. and w i Calculate the SGCS of the spatial basis vectors, and define the mean SGCS of these N sets of spatial basis vectors as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0183] Method 5: Based on the right singular vector.

[0184] The mean NMSE of the right singular vector obtained based on the first channel state information and the second channel state information is determined as the first performance index; or, the mean NMSE of the right singular vector obtained based on the third channel state information and the second channel state information is determined as the first performance index.

[0185] For example, if CSI is predicted on N frequency domain units (subband / PRB / subcarrier), N predicted CSI matrices are obtained. Simultaneously, the terminal measured the CSI-RS on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i After performing SVD decomposition on N predicted CSI matrices and N true CSI matrices, it is necessary to select N sets of corresponding right singular vectors. and v i Calculate the NMSE of the right singular vectors, and define the mean of the NMSEs of these N sets of right singular vectors as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0186] Method 6: Linear combination of row / column vectors based on the CSI matrix.

[0187] The mean NMSE of the row / column vectors obtained based on the first channel state information and the second channel state information is determined as the first performance index; or, the mean NMSE of the row / column vectors obtained based on the third channel state information and the second channel state information is determined as the first performance index.

[0188] For example, the terminal predicts the CSI on N frequency domain units (subband / PRB / subcarrier), resulting in N predicted CSI matrices. Simultaneously, the terminal measured the CSI-RS on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i For the vector h corresponding to N predicted CSI matrices and N true CSI matrices. i and Calculate the SGCS, and define the mean of the NMSEs of these N sets of corresponding vectors as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0189] Here, h i and The calculation method can be expressed as the following formula:

[0190] Alternatively, as shown in the following formula:

[0191] Here, c is the weight of the corresponding matrix selected from the CSI matrix.

[0192] If the weight c is chosen as the transmit port weight vector of CSI-RS (i.e., the second measurement resource), h i It can be directly provided by the signal from the receiving port, without needing to obtain the channel matrix H. i .

[0193] Method 7: Based on the CSI matrix.

[0194] The average NMSE between the first channel state information and the second channel state information is determined as the first performance indicator, or the average NMSE between the third channel state information and the second channel state information is determined as the first performance indicator.

[0195] For example, the terminal predicts the CSI on N frequency domain units (subband / PRB / subcarrier), resulting in N predicted CSI matrices. Simultaneously, the terminal measured the CSI-RS on the corresponding N frequency domain units (subband / PRB / subcarrier) and obtained N true CSI matrices H. i The terminal calculates the NMSE between the predicted CSI and the corresponding true CSI, and defines the mean of these N sets of NMSEs as the KPI of the AI / ML model. The determination method can be shown in the following formula:

[0196] Determining the first performance index based on the various methods of determining the first performance index shown in the above embodiments can reduce the computational overhead of the performance index.

[0197] Combining the above methods for determining the first performance indicator, the first performance indicator includes any one of the following:

[0198] The SGCS mean of the spatial basis vectors obtained based on the first channel state information and the second channel state information;

[0199] The SGCS mean of the right singular vector obtained based on the first channel state information and the second channel state information;

[0200] The mean SGCS of the row / column vectors obtained based on the first channel state information and the second channel state information;

[0201] The mean NMSE of the spatial basis vectors obtained based on the first channel state information and the second channel state information;

[0202] The mean NMSE of the right singular vector obtained based on the first channel state information and the second channel state information;

[0203] The mean NMSE of the row / column vectors obtained based on the first channel state information and the second channel state information;

[0204] The mean of NMSE between the first channel state information and the second channel state information.

[0205] Alternatively, the first performance metric may include any of the following:

[0206] The SGCS mean of the spatial basis vectors obtained based on the third channel state information and the second channel state information;

[0207] The SGCS mean of the right singular vector obtained based on the third channel state information and the second channel state information;

[0208] The mean SGCS of the row / column vectors obtained based on the third channel state information and the second channel state information;

[0209] The mean NMSE of the spatial basis vectors obtained based on the third channel state information and the second channel state information;

[0210] The mean NMSE of the right singular vector obtained based on the third channel state information and the second channel state information;

[0211] The mean NMSE of the row / column vectors obtained based on the third channel state information and the second channel state information;

[0212] The mean of NMSE between the third channel state information and the second channel state information.

[0213] In some embodiments, when the first node uses the above-described determination method 3 in a predefined manner or when the second node instructs the first node to use it, that is, when the first performance indicator is the SGCS mean of the row / column vectors obtained based on the first channel state information and the second channel state information, or when the first performance indicator is the SGCS mean of the row / column vectors obtained based on the third channel state information and the second channel state information, and when the first node determines that the row / column vector combination coefficient is the transmission port vector of the second measurement resource, the row / column vector corresponding to the second channel state information before the first node obtains the second channel state information will not be described in detail below.

[0214] In other words, under the above determination method 3, if the terminal knows that the row / column vector combination coefficient is the transmission port vector of the configured CSI-RS (i.e., the second measurement resource), then the terminal can obtain the row / column vector corresponding to the second channel state information, i.e., the power of the receiving port, before obtaining the second channel state information.

[0215] In some embodiments, when the first node uses the above-described determination method 6 in a predefined manner or when the second node instructs the first node to use it, that is, when the first performance indicator is the mean NMSE of the row / column vectors obtained based on the first channel state information and the second channel state information, or when the first performance indicator is the mean NMSE of the row / column vectors obtained based on the third channel state information and the second channel state information, and when the first node determines that the row / column vector combination coefficient is the transmission port vector of the second measurement resource, the first node obtains the row / column vector corresponding to the second channel state information before obtaining the second channel state information, which will not be elaborated further below.

[0216] In other words, under the above determination method 6, if the terminal knows that the row / column vector combination coefficient is the transmission port vector of the configured CSI-RS (i.e., the second measurement resource), then the terminal can obtain the row / column vector corresponding to the second channel state information, i.e., the power of the receiving port, before obtaining the second channel state information.

[0217] In some embodiments, when the first node determines the first performance index, it receives indication information sent by the second node to indicate the target determination method in the determination method of the first performance index, and then determines the target determination method used when determining the first performance index based on the indication information.

[0218] For example, a base station instructs a terminal to adopt a method for determining a first performance indicator via a set of signaling. This method can be one of the determination methods 1 to 7 mentioned above. When the base station instructs the method for determining the first performance indicator, it needs to match it with the first channel state information indicated by the base station. Specifically:

[0219] The base station uses a channel matrix H that indicates the first channel state information to indicate the predicted CSI (i.e., the first channel state information): the determination method can be one of the determination methods 1 to 7 mentioned above;

[0220] The base station uses all right singular vectors of the channel matrix that indicate the first channel state information to indicate the first channel state information: the determination method can be one of the determination methods 1, 2, 4 or 5 mentioned above;

[0221] The base station uses the right singular vector corresponding to the top N singular values ​​of the channel matrix that indicates the first channel state information: the determination method can be one of the determination methods 1, 2, 4 or 5 mentioned above;

[0222] The base station uses the spatial basis vector index of all right singular vectors of the indicator channel matrix that indicate the first channel state information after codebook quantization to indicate the first channel state information: the determination method can be the determination method 1 or 4 mentioned above.

[0223] The base station uses the spatial basis vector index of the right singular vector corresponding to the top N singular values ​​of the indication channel matrix that indicates the first channel state information after codebook quantization to indicate the first channel state information: the determination method can be the determination method 1 or 4 mentioned above.

[0224] The base station uses the PMI of the channel matrix that indicates the first channel state information: the determination method can be either determination method 1 or 4 mentioned above.

[0225] Based on the embodiment shown in Figure 2, a first performance index of the second channel state information is determined based on the first channel state information. The first channel state information can be understood as a predicted value of the channel state information, and the second channel state information can be understood as a measured value of the channel state information. Since the first channel state information is acquired based on multiple first measurement resources, and the second channel state information is acquired based on second measurement resources, and the first and second measurement resources differ in at least one of the following: time slot, frequency domain unit location, or port resources, the acquisition of the second channel state information is targeted and selective, and it is not necessary to process all possible channel state information data. Compared with comprehensively measuring and processing data to calculate performance indexes, the performance determination method provided by this disclosure embodiment reduces the amount of data processing, lowers computational overhead, and helps to achieve the goal of reducing terminal power consumption.

[0226] On the other hand, wireless channels are correlated to some extent. For example, channel state information may be similar in adjacent time slots, near frequency domain cell locations, or near the same port resources. Although the first measurement resource and the second measurement resource differ in at least one of the above, the second channel state information can still be inferred from the first channel state information based on this correlation. This eliminates the need for completely independent and detailed calculations of the second channel state information, reducing computational load and thus lowering computational overhead.

[0227] On the other hand, since measurement resources differ in terms of time slots, frequency domain cell locations, and port resources, it means that it is not necessary to perform measurements on all possible time slots, frequency domain cell locations, and port resources to obtain the second channel state information. Only the first channel state information and the differences between measurement resources need to be utilized, and certain algorithms or models can be used to deduce the performance indicators of the second channel state information, thereby reducing the number of actual measurement points and thus lowering computational overhead.

[0228] The following is an exemplary description of the embodiment shown in Figure 2. Taking the first performance indicator as KPI as an example, it may include the following examples.

[0229] Example 1: The second frequency domain resource is a subset of the first frequency domain resource.

[0230] In some cases, a base station can configure a CSI-RS (i.e., the first measurement resource) for the terminal to perform AI / ML-based CSI prediction. Simultaneously, the base station can configure another CSI-RS (i.e., the second measurement resource) for monitoring the performance of the AI / ML model. When configuring the CSI-RS for monitoring AI / ML model performance, the base station can simultaneously configure a signaling system to notify the terminal to select only the CSI matrix obtained from a subset of the frequency domain of the monitored CSI-RS for the aforementioned KPI calculation. Assuming the base station configures the CSI-RS for the terminal to contain N frequency domain elements (subband / PRB / subcarrier), the specific steps are as follows:

[0231] 1. The base station is configured with a CSI-RS for the terminal's CSI prediction function based on AI / ML models.

[0232] 2. The base station is equipped with a CSI-RS for monitoring the terminal's CSI prediction function based on AI / ML models.

[0233] The two sets of CSI-RS (i.e., the first measurement resource and the second measurement resource) can be indicated / configured by the same signaling or by different signaling. This embodiment of the present disclosure does not limit the indication / configuration method of the first measurement resource and the second measurement resource.

[0234] 3. The base station is configured with a signaling notification terminal that adopts a KPI determination method, which can be one of the determination methods 1-7 mentioned above.

[0235] 4. The base station indicates a frequency domain subset configuration of CSI-RS (i.e., the measurement configuration for the second channel state information). This frequency domain subset configuration of CSI-RS can be:

[0236] Indicates the number of CSI-RS frequency domain units N' required when calculating KPIs;

[0237] This indicates all N' CSI-RS frequency domain cell indices required for KPI calculation. The indication method is either to directly indicate all frequency domain cell indices; or, at least one set of frequency domain cell indices can be predefined, each set containing N' frequency domain cell indices, indicating at least one set of frequency domain cell indices. Here, N′ <N。

[0238] If N′=N, the base station does not need to indicate the number of transmission frequency domain units or the frequency domain unit index as described above.

[0239] 5. The terminal measures the monitoring CSI-RS on N frequency domain units according to the base station configuration, and selects the CSI-RS measurement results on N' subcarriers as the true CSI matrix H according to the base station configuration. i The terminal calculates the predicted CSI for the corresponding time-domain location and number of ports of the monitoring CSI-RS based on the AI / ML model, and selects the CSIs on the N' frequency domain units that are the same as the true CSIs as the predicted CSIs.

[0240] 6. The terminal determines the KPIs according to the method indicated by the base station, using N' groups of H. i and Based on this, calculate KPIs.

[0241] Example 2: The second set of receiving ports is a subset of the first set of receiving ports.

[0242] In some cases, a base station can configure a CSI-RS for the terminal to perform AI / ML-based CSI prediction. Simultaneously, the base station can configure another CSI-RS for the terminal to monitor the performance of the AI / ML model. When configuring the CSI-RS for monitoring AI / ML model performance, the base station can also configure a signaling system to notify the terminal to select only a subset of the CSI-RS ports for use in the aforementioned KPI calculation. The specific steps are as follows:

[0243] 1. The base station is configured with a CSI-RS for the terminal's CSI prediction function based on AI / ML models.

[0244] 2. The base station is equipped with a CSI-RS for monitoring the terminal's CSI prediction function based on AI / ML models.

[0245] 3. The base station is configured with a signaling notification terminal that adopts a KPI determination method, which can be one of the determination methods 1-7 mentioned above.

[0246] 4. The base station indicates a subset configuration of CSI-RS ports (i.e., the measurement configuration for the second channel state information). This subset configuration of CSI-RS ports includes a subset of transmitter ports and a subset of receiver ports, and the configuration of this subset of ports can be as follows:

[0247] Indicates the number of ports included in the subset of transmit ports P', and indicates the number of ports included in the subset of receive ports M';

[0248] Indicates P' transmit port indices and M' receive port indices; or predefines at least one set of transmit port indices, each set containing P' transmit port indices, and at least one set of receive port indices, each set containing M' receive port indices, and indicates the sequence number of at least one set of transmit port indices and / or the sequence number of at least one set of receive port indices; or predefines some sets of transmit and receive port indices, each set containing P' transmit port indices and M' receive port indices, indicating at least one set of transmit and receive port indices;

[0249] Here, P′ <P,M′<M。

[0250] If P′=P, the base station does not need to indicate the number of transmit ports or the subset of transmit ports as described above. If M′=M, the base station does not need to indicate the number of transmit ports or the subset of receive ports as described above.

[0251] 5. The terminal measures the monitoring CSI-RS of the complete port according to the base station configuration, obtains an N×M port CSI matrix, and selects the N′×M′ port here as the true CSI matrix H for calculating the performance of the AI / ML model. i The terminal uses the predicted CSI matrix calculated by the model, corresponding to the arrival time of the N×M port and the subcarrier (PRB / subband), to select the corresponding 8x2 port CSI as the basis for calculating the KPI, according to the CSI port subset configuration of the base station.

[0252] 6. The terminal determines the KPIs according to the method indicated by the base station, using N groups of H... i and Based on this, calculate KPIs.

[0253] Example 3: The second frequency domain resources are a subset of the first frequency domain resources, and the second set of receiving ports is a subset of the first set of receiving ports.

[0254] In some cases, the base station can configure a CSI-RS for the terminal to perform AI / ML-based CSI prediction. Simultaneously, the base station can configure a CSI-RS for the terminal to monitor the performance of the AI / ML model. To reduce the computational overhead of model monitoring on the terminal side, the base station can configure either Example 1 or Example 2 to notify the terminal, or the base station can configure a hybrid scheme of Example 1 and Example 2. The specific steps are as follows:

[0255] 1. The base station is configured with a CSI-RS for the terminal's CSI prediction function based on AI / ML models.

[0256] 2. The base station is equipped with a CSI-RS for monitoring the terminal's CSI prediction function based on AI / ML models.

[0257] 3. The base station is configured with a signaling notification terminal that adopts a KPI determination method, which can be one of the determination methods 1-7 mentioned above.

[0258] 4. The base station indicates a subset configuration of a set of CSI-RS ports (i.e., the measurement configuration of the second channel state information).

[0259] 5. The base station indicates a frequency domain subset configuration of CSI-RS (i.e., the measurement configuration of the second channel state information).

[0260] 6. The terminal measures the full-port monitoring CSI-RS on N subcarriers according to the base station configuration, and selects the CSI-RS measurement results on these N' subcarriers according to the base station configuration. In the CSI matrix of each selected subcarrier, the terminal selects port P′×M′ as the true CSI matrix H. i The terminal calculates the predicted CSI based on the AI / ML model, taking into account the frequency domain location and number of ports of the corresponding monitoring CSI-RS. It then selects the CSIs on the N' subcarriers that match the true CSIs as...

[0261] 7. The terminal determines the KPIs according to the method indicated by the base station, using N groups of H... i and Based on this, calculate KPIs.

[0262] The CSI-RS configured in the above base station may be a set of periodic or aperiodic CSI-RS, that is, the first measurement resource and the second measurement resource are periodic or aperiodic measurement resources.

[0263] In some embodiments, after determining a first performance metric for the second channel state information, the first node may feed back the first performance metric to the second node.

[0264] As an example, in order to reduce the number of times performance metrics are transmitted and thus reduce transmission overhead, the first node sends a first performance metric to the second node under the condition that preset conditions are met. The preset conditions include at least one of the following:

[0265] The first performance indicator is greater than the first threshold;

[0266] The number of times the first node has historically reported the first performance metric is less than or equal to the second threshold.

[0267] Here, the first and second thresholds are predefined or configured by signaling.

[0268] Taking the first and second thresholds as signaling configurations as an example, the base station can configure a set of parameters to control the way the terminal reports CSI. This set of parameters includes at least:

[0269] (1) A first threshold T. After the terminal calculates the KPI based on the true CSI and the predicted CSI obtained by monitoring the CSI-RS, the terminal needs to compare the KPI with the first threshold T. If the KPI is less than the first threshold T, the terminal needs to determine that this CSI prediction fails. If the KPI is greater than or equal to the first threshold T, the terminal needs to determine that this CSI prediction succeeds, and then report the result to the base station.

[0270] (2) A second threshold C0. A counter C is defined at the terminal side, with an initial value of 0. If the terminal determines that one CSI prediction fails, the counter C is incremented by 1.

[0271] (3) When the counter C < C0, the terminal reports the KPI and the counter status indicator bit according to the CSI reporting configuration indicated by the base station, and when C < C0, the counter status indicator bit is 0.

[0272] (4) When the counter C = C0, the terminal reports the KPI and the counter status indicator bit according to the CSI reporting configuration indicated by the base station, and when C = C0, the counter status indicator bit is 1.

[0273] (5) After the counter status indicator bit of the terminal is 1, the terminal will no longer measure or report the CSI-RS configured by the base station in the current round until the base station configures a new CSI-RS, that is, configures new measurement resources.

[0274] In some embodiments, in order to reduce the calculation overhead of performance indicators of the terminal and improve the calculation accuracy of performance indicators, after obtaining a first performance indicator, a first node obtains the first performance indicator corresponding to each of a plurality of time instants; determines a fused first performance indicator based on the first performance indicator corresponding to each of the plurality of time instants; and sends the fused first performance indicator to a second node.

[0275] Here, determining the fused first performance indicator based on the first performance indicator corresponding to each of the plurality of time instants includes: obtaining a weighting coefficient corresponding to each of the plurality of time instants; performing weighting calculation on the first performance indicator corresponding to each of the plurality of time instants based on the weighting coefficient corresponding to each of the plurality of time instants, to obtain the fused first performance indicator. Here, the weighting coefficient corresponding to each of the plurality of time instants is predefined or configured through signaling, which is not limited in the embodiments of the present disclosure.

[0276] That is, in order to reduce the calculation overhead of performance indicators of the terminal and improve the calculation accuracy of performance indicators, the base station may configure the terminal to perform weighted averaging on the first performance indicators obtained by calculating CSI of different time slots, and the solutions that can be adopted include at least one of the following:[*END]]

[0277] (1) The base station configures and indicates a time-domain weighted vector q, which is a 1xQ row vector, where Q is the number of time slots of CSIs in a set of CSI-RS configured by the base station that participate in the performance index calculation, and Q≧1;

[0278] (2) The base station is configured with a set of time-domain weighted vectors q and indicates the index of the weighted vectors in the set;

[0279] Here, the weighted vector q satisfies the following normalization condition:

[0280] The terminal calculates the weighted KPI of the CSI predicted by the model for the first Q time slots based on the received weighted vector q. q Let KPI be the KPI corresponding to the CSI of the i-th time slot. i The time-domain weighted KPI is defined as follows:

[0281] Here, KPI i The computational overhead can be reduced by following the methods shown in Examples 1 to 3 above.

[0282] In some embodiments, as shown in FIG3, this disclosure also provides another performance determination method, which is applied to a second node and may include the following steps:

[0283] S201, Receive the first performance index sent by the first node.

[0284] Here, the first performance index is the first performance index of the second channel state information determined based on the first channel state information. Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain unit location, and port resources.

[0285] The descriptions of the first channel state information, the second channel state information, the first measurement resource, the second measurement source, and the first performance index can be referred to the corresponding descriptions in the embodiments shown in Figure 2 above, and will not be repeated here.

[0286] In some embodiments, the second channel state information corresponds to a second frequency domain resource, the first channel state information corresponds to a first frequency domain resource, and the second frequency domain resource is a subset of the first frequency domain resource; and / or,

[0287] The second channel state information corresponds to the second set of receiving ports, the first channel state information corresponds to the first set of receiving ports, and the second set of receiving ports is a subset of the first set of receiving ports.

[0288] In some embodiments, the second node sends first measurement configuration information to the first node, the first measurement configuration information being used to configure first measurement resources;

[0289] In some embodiments, the second node sends first channel state information to the first node.

[0290] In some embodiments, the second node sends first indication information to the first node, the first indication information being used to indicate the channel state information monitoring set in the first channel state information;

[0291] In some embodiments, the second node sends second measurement configuration information to the first node, the second measurement configuration information being used to configure the second measurement resource;

[0292] In some embodiments, the second node sends second indication information to the first node, the second indication information being used to indicate the frequency domain unit subset configuration and / or antenna port subset configuration;

[0293] In some embodiments, the second node sends first channel state information, including any one of the following: the second node sends a channel matrix of the first channel state information;

[0294] All left / right singular vectors of the channel matrix that the second node transmits the first channel state information;

[0295] The left / right singular vectors corresponding to the top L largest singular values ​​of the channel matrix of the first channel state information sent by the second node, where L is a positive integer;

[0296] The second node transmits all left / right singular vectors and singular values ​​of the channel matrix that contains the first channel state information;

[0297] The first L largest singular values ​​and corresponding left / right singular vectors of the channel matrix corresponding to the first channel state information sent by the second node;

[0298] The second node transmits the channel matrix containing all left singular vectors, right singular vectors, and singular values ​​of the channel matrix for the first channel state information.

[0299] The second node transmits the first channel state information, including the first L largest singular values ​​of the channel matrix and the corresponding left and right singular vectors.

[0300] In some embodiments, the first performance metric includes any one of the following:

[0301] The mean SGCS of spatial basis vectors obtained based on the first and second channel state information; the mean SGCS of right singular vectors obtained based on the first and second channel state information; the mean SGCS of row / column vectors obtained based on the first and second channel state information; the mean NMSE of spatial basis vectors obtained based on the first and second channel state information; the mean NMSE of right singular vectors obtained based on the first and second channel state information; the mean NMSE of row / column vectors obtained based on the first and second channel state information; and the mean NMSE between the first and second channel state information. Alternatively, the third performance metric may include any of the following: the SGCS value of the spatial basis vectors obtained based on the third channel state information and the second channel state information; the mean SGCS value of the right singular vectors obtained based on the third channel state information and the second channel state information; the mean SGCS value of the row / column vectors obtained based on the third channel state information and the second channel state information; the mean NMSE value of the spatial basis vectors obtained based on the third channel state information and the second channel state information; the mean NMSE value of the right singular vectors obtained based on the third channel state information and the second channel state information; the mean NMSE value of the row / column vectors obtained based on the third channel state information and the second channel state information; and the mean NMSE value between the third channel state information and the second channel state information.

[0302] As an example, receiving a first performance indicator includes: receiving a first performance indicator sent by a first node under preset conditions. Here, the preset conditions include at least one of the following: the first performance indicator is greater than a first threshold; the number of times the first node has historically reported the first performance indicator is less than or equal to a second threshold.

[0303] As another example, receiving a first performance metric includes: receiving a fused first performance metric, where the fused first performance metric is obtained by fusing the first performance metrics corresponding to multiple time points. As another possible example, the fused first performance metric is obtained by weighting the first performance metrics corresponding to multiple time points using weighted coefficients.

[0304] The above embodiments are performed from the perspective of the first node to execute steps S101 and S102 to obtain the first performance indicator. It can be understood that the second node (i.e., the base station) can also execute steps S101 and S102 to obtain the first performance indicator. That is, the method shown in steps S101 and S102 can also be applied to the base station.

[0305] The above embodiments illustrate the determination of a first performance indicator by a first node (i.e., a terminal). In some embodiments, to reduce the computational overhead of the terminal, the base station can also calculate the performance indicator. Based on this, as shown in Figure 4, this disclosure also provides another performance determination method applied to a second node. This method may include the following steps:

[0306] S301, Send the first channel status information to the first node.

[0307] In some embodiments, the base station can use an AI / ML model to predict CSI groups for the next N4 time periods, with each CSI group containing K CSIs; the base station then indicates these N4 CSI groups to the terminal. That is, the second node predicts the first channel state information, which includes the CSI groups for the next N4 time periods, with each CSI group containing K CSIs, and then sends the first channel state information to the first node. Here, the first channel state information is acquired based on multiple first measurement resources.

[0308] The description of the first channel state information and the first measurement resource can be referred to the relevant description in the embodiment shown in Figure 2 above, and will not be repeated here.

[0309] In some embodiments, the second node indicates or transmits the first channel state information in a manner including, but not limited to, the following:

[0310] (1) Channel matrix H.

[0311] (2) All left / right singular vectors of the channel matrix.

[0312] (3) The channel matrix corresponds to the left / right singular vectors of the first L largest singular values, where L≥1.

[0313] (4) All left / right singular vectors and singular values ​​of the channel matrix.

[0314] (5) The channel matrix corresponds to the top L largest singular values ​​and the corresponding left / right singular vectors, where L≥1.

[0315] (6) All left singular vectors, right singular vectors and singular values ​​of the channel matrix.

[0316] (7) The channel matrix corresponds to the first L largest singular values ​​and the corresponding left singular vector and right singular vector, L≥1.

[0317] For descriptions of other methods by which the second node indicates or sends the first channel state information, please refer to the corresponding descriptions in the embodiments shown in Figure 2 above, and they will not be repeated here.

[0318] In some cases, the second node can use codebook quantization to reduce the indication overhead of the aforementioned CSI group, that is, to reduce the transmission overhead of sending the first channel state information.

[0319] The generation and indication methods of the basis vector set used in this quantization include, but are not limited to, the following:

[0320] 1. Quantization method based on DFT basis vector group.

[0321] 2. Quantization method based on AI-generated basis vector groups.

[0322] For a description of the two methods described above, please refer to the corresponding description in the embodiment shown in Figure 2 above, which will not be repeated here.

[0323] In some embodiments, the second node sends a third indication information to the first node, the third indication information being used to indicate the basis vector group used by the first channel state information.

[0324] S302, Receive the second channel status information sent by the first node.

[0325] Here, the second channel state information is obtained based on the second measurement resource, and the first measurement resource and the second measurement resource differ in at least one of the following: time slot, frequency domain cell location, and port resources.

[0326] The descriptions of the second channel state information and the second measurement resources can be found in the relevant descriptions in the embodiment shown in Figure 2 above, and will not be repeated here.

[0327] In some embodiments, to reduce the computational and feedback overhead of the first node, the second node can be configured with a set of monitoring CSI-RS for the first node to measure the true CSI at the resource location corresponding to the predicted CSI, and the terminal can be configured to report the true CSI, that is, to configure the reporting of the second channel state information. When configuring the reporting of the second channel state information, the base station can configure various reporting schemes, including but not limited to the following:

[0328] (1) Broadband PMI / CQI / RSRP / RSRQ;

[0329] (2) Subband PMI / CQI / RSRP / RSRQ;

[0330] (3) Specify the PMI / CQI / RSRP / RSRQ of one or more frequency domain units;

[0331] (4) Specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0332] (5) Specify the PMI / CQI / RSRP / RSRQ for one or more transceiver antenna ports;

[0333] (6) Specify the broadband PMI / CQI / RSRP / RSRQ for one or more transceiver antenna ports;

[0334] (7) Specify one or more subbands PMI / CQI / RSRP / RSRQ for the transmit and receive antenna ports;

[0335] (8) Specify one or more transmit and receive antenna ports, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ;

[0336] (9) Specify one or more transmit and receive antenna ports, and specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0337] (10) Specify one or more transmit and receive antenna ports, specify one or more time slots, and specify one or more frequency domain units of PMI / CQI / RSRP / RSRQ.

[0338] In other words, in some embodiments, the second node sends a fourth indication information to the first node. The fourth indication information is used to indicate the reporting method of channel state information, and the reporting method includes at least one of the following:

[0339] Broadband PMI / CQI / RSRP / RSRQ;

[0340] Sub-band PMI / CQI / RSRP / RSRQ;

[0341] Specify the PMI / CQI / RSRP / RSRQ of one or more frequency domain units;

[0342] Specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0343] Specify the PMI / CQI / RSRP / RSRQ for one or more transmit / receive antenna ports;

[0344] Specify one or more transmit / receive antenna ports for wideband PMI / CQI / RSRP / RSRQ;

[0345] Specify one or more sub-bands PMI / CQI / RSRP / RSRQ for transmit and receive antenna ports;

[0346] Specify one or more transmit / receive antenna ports, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ;

[0347] Specify one or more transmit and receive antenna ports, and specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0348] Specify one or more transmit / receive antenna ports, specify one or more time slots, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ.

[0349] When the first node sends the second channel status information, it can do so based on one of the reporting methods described above. Correspondingly, the second channel status information received by the second node can be second channel status information that satisfies the reporting method described above.

[0350] S303. Determine the first performance index of the second channel state information based on the first channel state information.

[0351] The description of step S303 is the same as that of step S102 described above, and will not be repeated here. The method for determining the first performance indicator shown above is also applicable to determining the first performance indicator on the second node side (i.e., the base station side).

[0352] In some cases, the base station configures a CSI reporting method for monitoring AI / ML model predictions and instructs it on the terminal. The CSI-RS resource location (time domain location, frequency domain location, port) indicated by the base station matches the CSI location predicted by the model. After receiving the CSI-RS from the base station, the terminal reports the CSI at a specified time. The base station monitors the performance of the CSI prediction model based on the CSI reported by the terminal. The KPIs selected by the base station for monitoring the performance of the CSI prediction model need to be consistent with the reporting method of the terminal's CSI reports.

[0353] The base station should convert the CSI predicted by the base station into a predicted quantity that is the same as the terminal feedback method, according to the CSI reporting method instructed by the base station. In other words, the first channel state information should be converted into the same form as the second channel state information.

[0354] For example, terminal feedback PMI: The base station sets the codebook for PMI reporting according to the configuration of the terminal, quantizes the predicted CSI into a corresponding set of spatial basis vectors, and compares them with the spatial basis vector set corresponding to the PMI reported by the terminal to determine the KPI. The determination method can be either method 1 or 4 mentioned above.

[0355] For example, regarding the terminal's feedback of right singular vectors: the base station configures the terminal's right singular vector reporting, quantizes the predicted CSI into a set of right singular vectors, and compares them with the right singular vector set reported by the terminal to determine the KPI. The determination method can be either method 2 or 5 described above.

[0356] For example, the terminal feedback channel matrix H: The base station configures the terminal to report the channel matrix H, compares the predicted CSI matrix with the channel matrix H, and determines the KPI. The determination method can be one of the methods 1-7 described above.

[0357] The base station can also convert the CSI feedback from the terminal into a CSI matrix and use this CSI matrix as the true CSI for performance monitoring.

[0358] Based on the embodiment shown in Figure 4, a first performance index of the second channel state information is determined based on the first channel state information. The first channel state information can be understood as a predicted value of the channel state information, and the second channel state information can be understood as a measured value of the channel state information. Since the first channel state information is acquired based on multiple first measurement resources, and the second channel state information is acquired based on second measurement resources, and the first and second measurement resources differ in at least one of the following: time slot, frequency domain unit location, or port resources, the acquisition of the second channel state information is targeted and selective, and it is not necessary to process all possible channel state information data. Compared with comprehensively measuring and processing data to calculate performance indexes, the performance determination method provided by this disclosure embodiment reduces the amount of data processing and lowers the computational overhead of performance indexes. Furthermore, the embodiment shown in Figure 4 migrates the calculation of performance indexes to the second node side (i.e., the base station side), which can reduce the computational overhead of the terminal for performance indexes and reduce the power consumption of the terminal.

[0359] In some embodiments, as shown in FIG5, this disclosure also provides another performance determination method applied to a first node, which may include the following steps:

[0360] S401, Receive the first channel status information sent by the second node.

[0361] In some embodiments, the base station can use an AI / ML model to predict CSI groups for the next N4 time periods, where each CSI group contains K CSIs; the base station then indicates these N4 CSI groups to the terminal. That is, the second node predicts the first channel state information, which includes the CSI groups for the next N4 time periods, where each CSI group contains K CSIs, and then sends the first channel state information to the first node. Correspondingly, the first node receives the first channel state information sent by the second node. Here, the first channel state information is acquired based on multiple first measurement resources.

[0362] The descriptions of the first channel state information and the first measurement resources can be found in the corresponding descriptions in the embodiment shown in Figure 2 above, and will not be repeated here.

[0363] Receive the first channel state information sent by the second node, including any one of the following:

[0364] The channel matrix that receives the first channel state information sent by the second node;

[0365] All left / right singular vectors of the channel matrix that receives the first channel state information sent by the second node;

[0366] The left / right singular vectors corresponding to the top L largest singular values ​​of the channel matrix that receives the first channel state information sent by the second node, where L is a positive integer;

[0367] The channel matrix receiving the first channel state information sent by the second node contains all left / right singular vectors and singular values;

[0368] The top L largest singular values ​​and corresponding left / right singular vectors of the channel matrix corresponding to the first channel state information sent by the second node;

[0369] The channel matrix that receives the first channel state information sent by the second node contains all left singular vectors, right singular vectors, and singular values;

[0370] The first L largest singular values ​​of the channel matrix and the corresponding left and right singular vectors of the channel state information sent by the second node.

[0371] S402, Send the second channel status information to the second node.

[0372] In some embodiments, after receiving the first channel state information, the first node can adjust its own measurement strategy (e.g., determine the second measurement resource) based on the first channel state information, and then measure the reference signal based on the adjusted measurement strategy to obtain the second channel state information, and then send the second channel state information to the second node.

[0373] Here, the second channel state information is acquired based on the second measurement resource. The first measurement resource and the second measurement resource differ in at least one of the following: time slot, frequency domain cell location, and port resources. The first channel state information is used to determine the first performance index of the second channel state information.

[0374] The first channel state information sent by the second node to the first node can assist the first node in measuring the reference signal, helping the first node to obtain a relatively reliable CSI estimate even in harsh environments.

[0375] In some embodiments, the first node receives fourth indication information sent by the second node. The fourth indication information is used to indicate the reporting method of channel state information. The reporting method includes at least one of the following: wideband precoding matrix indicator PMI / channel quality indicator CQI / reference signal received power RSRP / reference signal received quality RSRQ.

[0376] Sub-band PMI / CQI / RSRP / RSRQ;

[0377] Specify the PMI / CQI / RSRP / RSRQ of one or more frequency domain units;

[0378] Specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0379] Specify the PMI / CQI / RSRP / RSRQ for one or more transmit / receive antenna ports;

[0380] Specify one or more transmit / receive antenna ports for wideband PMI / CQI / RSRP / RSRQ;

[0381] Specify one or more sub-bands PMI / CQI / RSRP / RSRQ for transmit and receive antenna ports;

[0382] Specify one or more transmit / receive antenna ports, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ;

[0383] Specify one or more transmit and receive antenna ports, and specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0384] Specify one or more transmit / receive antenna ports, specify one or more time slots, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ.

[0385] When the first node sends the second channel status information, it can send the second channel status information based on the reporting method indicated by the fourth indication information.

[0386] In some embodiments, the first node receives third indication information sent by the second node. This third indication information indicates the basis vector group used by the first channel state information. A description of the third indication information can be found in the corresponding description in the above embodiments, and will not be repeated here.

[0387] The foregoing primarily describes the solution provided in this disclosure from the perspective of the interaction between various nodes. It is understood that each node, such as the first node or the second node, includes corresponding hardware structures and / or software modules to perform the aforementioned functions. Those skilled in the art should readily recognize that, based on the algorithmic steps of the examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0388] This disclosure embodiment can divide the first node or the second node into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one functional module. The integrated module can be implemented in hardware or software. The module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the example of dividing each functional module according to each function.

[0389] Figure 6 is a block diagram of a communication device according to an embodiment of the present disclosure. As shown in Figure 6, the communication device 50 includes an acquisition unit 501 and a processing unit 502. In some embodiments, the communication device 50 further includes a transmission unit 503.

[0390] The communication device 50 can be the first node or a chip within the first node. When the communication device 50 is used to implement the functions of the first node in the above embodiments, each unit is specifically used to implement the following functions.

[0391] The acquisition unit 501 is used to acquire first channel state information and second channel state information. Here, the first channel state information is acquired based on multiple first measurement resources, and the second channel state information is acquired based on second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0392] Processing unit 502 is used to determine a first performance index of the second channel state information based on the first channel state information.

[0393] In some embodiments, the processing unit 502 is specifically configured to determine third channel state information from the first channel state information based on the measurement configuration corresponding to the second channel state information, wherein the third channel state information and the second channel state information are aligned on frequency domain resources and / or receiving ports; and to determine a first performance index of the second channel state information based on the third channel state information.

[0394] In some embodiments, the acquisition unit 501 is specifically used to receive first measurement configuration information sent by the second node, the first measurement configuration information being used to configure the first measurement resource; to measure a reference signal on the first measurement resource to obtain fourth channel state information; and to obtain the first channel state information based on the fourth channel state information.

[0395] In some embodiments, the acquisition unit 501 is specifically used to receive the first channel state information sent by the second node.

[0396] In some embodiments, the acquisition unit 501 is specifically configured to receive first channel state information sent by the second node; receive first indication information sent by the second node, the first indication information being used to indicate the channel state information monitoring set in the first channel state information; and determine second channel state information from the first channel state information based on the first indication information.

[0397] In some embodiments, the acquisition unit 501 is specifically configured to receive second measurement configuration information sent by the second node, the second measurement configuration information being used to configure the second measurement resources; receive second indication information sent by the second node, the second indication information being used to indicate the configuration of frequency domain unit subsets and / or antenna port subsets; measure a reference signal on the second measurement resources to obtain fifth channel state information; and determine the second channel state information from the fifth channel state information based on the second indication information.

[0398] In some embodiments, the sending unit 503 is configured to send a first performance indicator to the second node when a preset condition is met. The preset condition includes at least one of the following: the first performance indicator is greater than a first threshold; the number of times the first node has historically reported the first performance indicator is less than or equal to a second threshold.

[0399] In some embodiments, the acquisition unit 501 is further configured to acquire the first performance index corresponding to each of the multiple time points;

[0400] The processing unit 502 is also used to determine the first performance index of fusion based on the first performance index corresponding to each of the multiple time points;

[0401] The sending unit 503 is used to send the first performance index of the fusion to the second node.

[0402] In some embodiments, the processing unit 502 is specifically used to obtain the weighting coefficients corresponding to each of the multiple time points; and to perform weighted calculation on the first performance index corresponding to each of the multiple time points based on the weighting coefficients corresponding to each of the multiple time points to obtain the fused first performance index.

[0403] Figure 7 is a block diagram of another communication device provided according to an embodiment of the present disclosure. As shown in Figure 7, the communication device 60 includes a receiving unit 601.

[0404] The communication device 60 can be the second node or a chip within the second node. When the communication device 60 is used to implement the functions of the second node in the above embodiments, each unit is specifically used to implement the following functions.

[0405] The receiving unit 601 is used to receive a first performance index sent by the first node. The first performance index is a first performance index of the second channel state information determined based on the first channel state information. Here, the first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0406] Figure 8 is a block diagram of a communication device according to an embodiment of the present disclosure. As shown in Figure 8, the communication device 70 includes a receiving unit 701 and a transmitting unit 702.

[0407] The communication device 70 can be the first node or a chip within the first node. When the communication device 70 is used to implement the functions of the first node in the above embodiments, each unit is specifically used to implement the following functions.

[0408] The receiving unit 701 is used to receive first channel state information sent by the second node, the first channel state information being acquired based on multiple first measurement resources;

[0409] The transmitting unit 702 is used to transmit second channel state information to the second node. The second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources. The first channel state information is used to determine the first performance index of the second channel state information.

[0410] In some embodiments, the receiving unit 701 is further configured to receive third indication information sent by the second node, the third indication information being used to indicate the base vector group used by the first channel state information.

[0411] In some embodiments, the receiving unit 701 is further configured to receive fourth indication information sent by the second node. The fourth indication information is used to indicate the reporting method of channel state information. The reporting method includes at least one of the following: wideband precoding matrix indicator PMI / channel quality indicator CQI / reference signal received power RSRP / reference signal received quality RSRQ.

[0412] Sub-band PMI / CQI / RSRP / RSRQ;

[0413] Specify the PMI / CQI / RSRP / RSRQ of one or more frequency domain units;

[0414] Specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0415] Specify the PMI / CQI / RSRP / RSRQ for one or more transmit / receive antenna ports;

[0416] Specify one or more transmit / receive antenna ports for wideband PMI / CQI / RSRP / RSRQ;

[0417] Specify one or more sub-bands PMI / CQI / RSRP / RSRQ for transmit and receive antenna ports;

[0418] Specify one or more transmit / receive antenna ports, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ;

[0419] Specify one or more transmit and receive antenna ports, and specify one or more time slots for PMI / CQI / RSRP / RSRQ;

[0420] Specify one or more transmit / receive antenna ports, specify one or more time slots, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ.

[0421] Figure 9 is a block diagram of another communication device provided according to an embodiment of the present disclosure. As shown in Figure 9, the communication device 80 includes a transmitting unit 801, a receiving unit 802, and a processing unit 803.

[0422] The communication device 80 can be the second node or a chip within the second node. When the communication device 80 is used to implement the functions of the second node in the above embodiments, each unit is specifically used to implement the following functions.

[0423] The transmitting unit 801 is used to transmit first channel state information to the first node, the first channel state information being acquired based on multiple first measurement resources;

[0424] The receiving unit 802 is used to receive the second channel state information sent by the first node. The second channel state information is obtained based on the second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

[0425] The processing unit 803 is used to determine a first performance index of the second channel state information based on the first channel state information.

[0426] The units in Figures 6 to 9 can also be called modules; for example, a transmitting unit can be called a transmitting module. Furthermore, in the embodiments shown in Figures 6 to 9, the names of the units may not be those shown in the figures; for example, a transmitting unit can also be called a communication unit, and a receiving unit can also be called a communication unit.

[0427] If the units in Figures 6 to 9 are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this disclosure, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this disclosure. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0428] In the case where any of the communication devices 50 to 80 described above implements the functions of the integrated module in hardware, a block diagram of another communication device is provided according to an embodiment of this disclosure. As shown in FIG10, the communication device 90 includes: a processor 902, a communication interface 903, and a bus 904. In some embodiments, the communication device 90 may further include a memory 901.

[0429] Processor 902 may implement or execute various exemplary logic blocks, modules, and circuits described in connection with embodiments of this disclosure. Processor 902 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in connection with embodiments of this disclosure. Processor 902 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a digital signal processor (DSP), and a microprocessor.

[0430] The communication interface 903 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0431] The memory 901 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0432] In some embodiments, the memory 901 may exist independently of the processor 902. The memory 901 may be connected to the processor 902 via a bus 904 and is used to store instructions or program code. When the processor 902 calls and executes the instructions or program code stored in the memory 901, it can implement the performance determination method provided in the embodiments of this disclosure.

[0433] In some embodiments, the memory 901 may also be integrated with the processor 902.

[0434] Bus 904 can be an extended industry standard architecture (EISA) bus, etc. Bus 904 can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in Figure 10, but this does not mean that there is only one bus or one type of bus.

[0435] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the first node or the second node can be divided into different functional modules to complete all or part of the functions described above.

[0436] This disclosure also provides a computer-readable storage medium, including a non-transitory computer-readable storage medium on which computer instructions are stored. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. These computer instructions can be stored in the aforementioned non-transitory computer-readable storage medium. When executed, the computer instructions can include the processes described in the above method embodiments. The aforementioned computer-readable storage medium can also be an external storage device for the aforementioned first node or second node, such as a pluggable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the aforementioned first node or second node. Further, the aforementioned computer-readable storage medium can also include both internal storage units of the aforementioned first node or second node and external storage devices. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the aforementioned first node or second node. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0437] This disclosure also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to perform any of the performance determination methods provided in the above embodiments.

[0438] Although this disclosure has been described herein in conjunction with various embodiments, those skilled in the art will understand and implement other variations of the disclosed embodiments by reviewing the accompanying drawings, the disclosure, and the appended claims in carrying out the claimed disclosure. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0439] Although this disclosure has been described in conjunction with specific features and embodiments, it will be apparent that various modifications and combinations can be made therein without departing from the spirit and scope of this disclosure. Accordingly, this specification and drawings are merely exemplary illustrations of the disclosure as defined by the appended claims and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this disclosure. It is obvious that those skilled in the art can make various alterations and modifications to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include any such modifications and modifications that fall within the scope of the claims of this disclosure and their equivalents.

[0440] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A performance determination method, wherein, Applied to the first node, the method includes: First channel state information and second channel state information are obtained. The first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain cell location, and port resources. A first performance index of the second channel state information is determined based on the first channel state information.

2. The method of claim 1, wherein, The second channel state information corresponds to the second frequency domain resource, the first channel state information corresponds to the first frequency domain resource, and the second frequency domain resource is a subset of the first frequency domain resource; And / or, The second channel state information corresponds to the second set of receiving ports, the first channel state information corresponds to the first set of receiving ports, and the second set of receiving ports is a subset of the first set of receiving ports.

3. The method of claim 2, wherein, The first performance metric for determining the second channel state information based on the first channel state information includes: Based on the measurement configuration corresponding to the second channel state information, third channel state information is determined from the first channel state information, and the third channel state information and the second channel state information are aligned in frequency domain resources and / or receiving ports; The first performance index of the second channel state information is determined based on the third channel state information.

4. The method of claim 1, wherein, The acquisition of the first channel state information includes: Receive first measurement configuration information sent by the second node, the first measurement configuration information being used to configure the first measurement resource; The reference signal is measured on the first measurement resource to obtain the fourth channel state information; The first channel state information is obtained based on the fourth channel state information.

5. The method of claim 1, wherein, The acquisition of the first channel state information includes: Receive the first channel status information sent by the second node.

6. The method of claim 1, wherein, Obtaining the second channel state information includes: Receive the first channel status information sent by the second node; Receive first indication information sent by the second node, the first indication information being used to indicate the channel state information monitoring set in the first channel state information; Based on the first indication information, the second channel state information is determined from the first channel state information.

7. The method of claim 1, wherein, Obtaining the second channel state information includes: Receive second measurement configuration information sent by the second node, the second measurement configuration information being used to configure the second measurement resource; Receive second indication information sent by the second node, the second indication information being used to indicate frequency domain unit subset configuration and / or antenna port subset configuration; The reference signal is measured on the second measurement resource to obtain the fifth channel state information; Based on the second indication information, the second channel state information is determined from the fifth channel state information.

8. The method of claim 6 or 7, wherein, The receipt of the first channel state information sent by the second node includes any one of the following: The channel matrix that receives the first channel state information sent by the second node; All left / right singular vectors of the channel matrix that receive the first channel state information sent by the second node; The left / right singular vectors corresponding to the top L largest singular values ​​of the channel matrix receiving the first channel state information sent by the second node, where L is a positive integer; The channel matrix receiving the first channel state information sent by the second node contains all left / right singular vectors and singular values. The top L largest singular values ​​and corresponding left / right singular vectors of the channel matrix corresponding to the first channel state information sent by the second node; The channel matrix receiving the first channel state information sent by the second node contains all left singular vectors, right singular vectors, and singular values. The first L largest singular values ​​of the channel matrix and the corresponding left and right singular vectors of the channel state information sent by the second node.

9. The method of claim 1, wherein, The first channel state information is obtained based on codebook quantization, and the codebook quantization method includes at least one of the following: Quantization method based on Discrete Fourier Transform (DFT) basis vector groups; A quantization method based on artificial intelligence (AI) to generate basis vector groups.

10. The method of claim 9, wherein, The codebook quantization method is predefined or configured by signaling.

11. The method of claim 1, wherein, The first performance indicator includes any one of the following: The mean of the generalized squared cosine similarity (SGCS) of the spatial basis vectors obtained based on the first channel state information and the second channel state information; The SGCS mean of the right singular vector obtained based on the first channel state information and the second channel state information; The mean SGCS of the row / column vectors obtained based on the first channel state information and the second channel state information; The mean normalized mean square error (NMSE) of the spatial basis vectors obtained based on the first channel state information and the second channel state information; The mean NMSE of the right singular vector obtained based on the first channel state information and the second channel state information; The mean NMSE of the row / column vectors obtained based on the first channel state information and the second channel state information; The mean NMSE between the first channel state information and the second channel state information.

12. The method of claim 11, wherein, The first performance metric is the SGCS mean of the row / column vectors obtained based on the first channel state information and the second channel state information. When the first node determines that the row / column vector combination coefficient is the transmission port vector of the second measurement resource, the first node obtains the row / column vector corresponding to the second channel state information before obtaining the second channel state information.

13. The method of claim 11, wherein, The first performance metric is the mean NMSE of the row / column vectors obtained based on the first channel state information and the second channel state information. When the first node determines that the row / column vector combination coefficient is the transmission port vector of the second measurement resource, the first node obtains the row / column vector corresponding to the second channel state information before obtaining the second channel state information.

14. The method of claim 1, wherein, The method further includes: Under preset conditions, the first performance indicator is sent to the second node, wherein the preset conditions include at least one of the following: The first performance indicator is greater than the first threshold; The number of times the first node has historically reported the first performance metric is less than or equal to the second threshold.

15. The method of claim 14, wherein, The first threshold and the second threshold are predefined or configured by signaling.

16. The method of claim 1, wherein, The method further includes: Obtain the first performance index corresponding to each of the multiple time points; Based on the first performance index corresponding to each of the multiple time points, the first performance index of fusion is determined. Send the first performance metric of the fusion to the second node.

17. The method of claim 16, wherein, The determination of the first performance index for fusion based on the first performance index corresponding to each of the multiple time points includes: Obtain the weighting coefficients corresponding to each of the multiple time points; Based on the weighting coefficients corresponding to each of the multiple time points, the first performance index corresponding to each of the multiple time points is weighted and calculated to obtain the fused first performance index.

18. The method of claim 1, wherein, The method for determining the first performance indicator is either predefined or configured via signaling.

19. A performance determination method, wherein, Applied to the second node, the method includes: The first performance indicator is received from the first node. The first performance indicator is a first performance indicator of the second channel state information determined based on the first channel state information. The first channel state information is obtained based on multiple first measurement resources, and the second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit position, and port resources.

20. A performance determination method, wherein, Applied to the first node, the method includes: Receive first channel state information sent by the second node, the first channel state information being acquired based on multiple first measurement resources; Send second channel state information to the second node. The second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources are different in at least one of the following: time slot, frequency domain unit location, and port resources. The first channel state information is used to determine the first performance index of the second channel state information.

21. The method of claim 20, wherein, The first channel state information received from the second node includes any one of the following: The channel matrix that receives the first channel state information sent by the second node; All left / right singular vectors of the channel matrix that receive the first channel state information sent by the second node; The left / right singular vectors corresponding to the top L largest singular values ​​of the channel matrix receiving the first channel state information sent by the second node, where L is a positive integer; The channel matrix receiving the first channel state information sent by the second node contains all left / right singular vectors and singular values. The top L largest singular values ​​and corresponding left / right singular vectors of the channel matrix corresponding to the first channel state information sent by the second node; The channel matrix receiving the first channel state information sent by the second node contains all left singular vectors, right singular vectors, and singular values. The first L largest singular values ​​of the channel matrix and the corresponding left and right singular vectors of the channel state information sent by the second node.

22. The method of claim 20, wherein, The first channel state information is obtained based on codebook quantization, and the codebook quantization method includes at least one of the following: Quantization method based on DFT basis vector groups; A quantization method based on AI-generated basis vector groups.

23. The method of claim 20, wherein, The method further includes: The third indication information sent by the second node is received, which is used to indicate the base vector group used by the first channel state information.

24. The method of claim 20, wherein, The method further includes: The system receives a fourth indication message sent by the second node, the fourth indication message indicating the reporting method of channel state information, the reporting method including at least one of the following: Wideband precoding matrix indicator PMI / Channel Quality Indicator CQI / Reference Signal Received Power RSRP / Reference Signal Received Quality RSRQ; Sub-band PMI / CQI / RSRP / RSRQ; Specify the PMI / CQI / RSRP / RSRQ of one or more frequency domain units; Specify one or more time slots for PMI / CQI / RSRP / RSRQ; Specify the PMI / CQI / RSRP / RSRQ for one or more transmit / receive antenna ports; Specify one or more transmit / receive antenna ports for wideband PMI / CQI / RSRP / RSRQ; Specify one or more sub-bands PMI / CQI / RSRP / RSRQ for transmit and receive antenna ports; Specify one or more transmit / receive antenna ports, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ; Specify one or more transmit and receive antenna ports, and specify one or more time slots for PMI / CQI / RSRP / RSRQ; Specify one or more transmit / receive antenna ports, specify one or more time slots, and specify one or more frequency domain elements for PMI / CQI / RSRP / RSRQ.

25. A performance determination method, wherein, Applied to the second node, the method includes: Send first channel state information to the first node, the first channel state information being acquired based on multiple first measurement resources; The system receives second channel state information sent by the first node. The second channel state information is obtained based on second measurement resources. The first measurement resources and the second measurement resources differ in at least one of the following: time slot, frequency domain cell location, and port resources. A first performance index of the second channel state information is determined based on the first channel state information.

26. A communications device, wherein include: Memory and processor; Memory and processor are coupled; The memory is used to store instructions that can be executed by the processor; When the processor executes the instructions, it performs the method as described in any one of claims 1 to 25.

27. A computer readable storage medium, wherein, The computer-readable storage medium includes a non-transitory computer-readable storage medium on which computer instructions are stored, which, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 25.

28. A computer program product, wherein, The computer program product includes computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 25.

Images