Data set acquisition method, resource configuration method, apparatus, and storage medium

Abstract

The present disclosure provides a data set acquisition method, a resource configuration method, an apparatus, and a storage medium. The data set acquisition method comprises: receiving a first channel measurement resource configured by a network device; and acquiring a training data set on the basis of the first channel measurement resource, wherein a frequency domain resource occupied by the first channel measurement resource is less than a transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission; and the training data set is used for training an AI model. In the foregoing embodiments, the frequency domain resource occupied by the first channel measurement resource received by the terminal is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission, that is to say, radio resources occupied by the first channel measurement resource are reduced, and after the training data set is acquired on the basis of the overhead-reduced channel measurement resource, the AI model may be trained, thereby reducing the overhead of measurement resources and improving the resource utilization rate.

Description

Dataset acquisition, resource configuration methods, devices, and storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to methods, apparatus, and storage media for acquiring and configuring data sets and resources. Background Technology

[0002] With the development and application of artificial intelligence (AI) technology, AI has been widely applied in the field of wireless communication technology. For example, terminals can use AI models to infer or predict channel information at future moments based on channel information at historical moments. Summary of the Invention

[0003] For situations where training datasets are obtained based on channel measurement resources, how to reduce the channel measurement resources used to train AI models has become an urgent problem to be solved.

[0004] This disclosure provides a method, apparatus, and storage medium for acquiring and configuring datasets and resources.

[0005] According to a first aspect of the embodiments of this disclosure, a dataset acquisition method is proposed, the method being executed by a terminal, the method comprising:

[0006] The network device receives a first channel measurement resource configured, wherein the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0007] A training dataset is obtained based on the first channel measurement resource. The training dataset is used to train the AI ​​model. The AI ​​model predicts the second CSI based on the first Channel State Information (CSI).

[0008] According to a second aspect of the present disclosure, a resource allocation method is provided, the method being executed by a network device, the method comprising:

[0009] Configure a first channel measurement resource for the terminal, the first channel resource is used by the terminal to acquire a training dataset, the frequency domain resource occupied by the first channel resource is less than the transmission bandwidth, and / or, the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0010] The training dataset is used to train the AI ​​model, which predicts the second CSI based on the first CSI.

[0011] According to a third aspect of the present disclosure, a communication device is provided for performing the method described in the first or second aspect.

[0012] According to a fourth aspect of the present disclosure, a communication device is provided, comprising:

[0013] A processing module is used to execute the method described in the first aspect or the second aspect.

[0014] According to a fifth aspect of the present disclosure, a terminal is provided, comprising: one or more processors; wherein the processors are configured to perform any of the methods described in the first aspect.

[0015] According to a sixth aspect of the present disclosure, a network device is provided, comprising: one or more processors; wherein the processors are configured to perform any of the methods described in the second aspect.

[0016] According to a seventh aspect of the present disclosure, a communication system is provided, comprising: a terminal and a network device, wherein the terminal is configured to implement the method of the first aspect, and the network device is configured to perform the method of the second aspect.

[0017] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions which, when executed on a communication device, cause the communication device to perform the method as described in any one of the first or second aspects.

[0018] In the above embodiments, the terminal obtains the training dataset through the first channel measurement resource, and the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. That is to say, the wireless resources occupied by the first channel measurement resource are reduced, and the AI ​​model can be trained based on the training dataset obtained by the channel measurement resource with reduced overhead, thereby reducing the overhead of measurement resources and improving resource utilization. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0020] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure;

[0021] Figures 1B to 1D are schematic diagrams illustrating observation windows and prediction windows according to embodiments of the present disclosure;

[0022] Figure 2A is an interactive schematic diagram of a resource configuration and dataset acquisition method according to an embodiment of the present disclosure;

[0023] Figures 2B to 2C are frequency domain structure diagrams illustrating embodiments of the present disclosure;

[0024] Figure 2D is a schematic diagram of the observation window and prediction window according to an embodiment of the present disclosure;

[0025] Figure 3 is a flowchart illustrating a resource configuration and dataset acquisition method according to an embodiment of the present disclosure;

[0026] Figure 4 is a flowchart illustrating a resource allocation method according to an embodiment of the present disclosure;

[0027] Figure 5A is a schematic diagram of the structure of the terminal proposed in an embodiment of this disclosure;

[0028] Figure 5B is a schematic diagram of the structure of the network device proposed in an embodiment of this disclosure;

[0029] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure;

[0030] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0031] This disclosure provides a method, apparatus, and storage medium for acquiring and configuring datasets and resources.

[0032] In a first aspect, embodiments of this disclosure propose a dataset acquisition method, the method being executed by a terminal, the method comprising:

[0033] The network device receives a first channel measurement resource configured, wherein the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0034] A training dataset is obtained based on the first channel measurement resources. The training dataset is used to train the AI ​​model. The AI ​​model predicts the second CSI based on the first channel state information (CSI).

[0035] In the above embodiments, the terminal obtains the training dataset through the first channel measurement resource, and the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. That is to say, the wireless resources occupied by the first channel measurement resource are reduced, and the AI ​​model can be trained based on the training dataset obtained by the channel measurement resource with reduced overhead, thereby reducing the overhead of measurement resources and improving resource utilization.

[0036] In conjunction with some embodiments of the first aspect, in some embodiments, the time-domain location and / or frequency-domain location of the first channel measurement resource at a given moment is determined based on a communication protocol, or the time-domain location and / or frequency-domain location of the first channel measurement resource at a given moment is configured by the network device.

[0037] In the above embodiments, the first channel measurement resources can be specified by a communication protocol or configured by a network device, which expands the configuration methods of the first channel measurement resources and improves the flexibility of the configuration of the first channel measurement resources.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the first channel measurement resource includes at least one of the following:

[0039] The transmission bandwidth includes a portion of the multiple subbands;

[0040] A portion of a resource block (RB) in any subband of the transmission bandwidth;

[0041] A portion of the multiple antenna ports used for transmission.

[0042] In the above embodiments, the first channel measurement resources can be configured in the frequency domain or the spatial domain, which can realize the diversity of configuration in the frequency domain or the spatial domain, thereby improving the flexibility of configuring the first channel measurement resources.

[0043] In conjunction with some embodiments of the first aspect, in some embodiments, different first channel measurement resources among a plurality of first channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-location (QCL) or power offset values ​​on the frequency domain resources occupied by the different first channel measurement resources are the same.

[0044] In the above embodiments, by setting the QCL or power offset values ​​of different first channel measurement resources to be the same in the frequency domain, it is possible to achieve the same large-scale parameters of different first channel measurement resources on the channel, thereby ensuring the reliability of data transmission through the channel.

[0045] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0046] The network device receives a second channel measurement resource configured, which includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

[0047] The AI ​​model is monitored based on the second channel measurement resources to obtain the monitoring results of the AI ​​model, which are used to indicate the performance of the AI ​​model when making predictions.

[0048] In the above embodiments, the wireless resources occupied by the second channel measurement resources used by the terminal are reduced, and the AI ​​model can also be monitored based on the reduced overhead channel measurement resources, thereby reducing the measurement resource overhead when monitoring the AI ​​model and improving resource utilization.

[0049] In conjunction with some embodiments of the first aspect, in some embodiments, at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at each time of the first type of time-domain position is determined based on a communication protocol, or at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at one time is configured by the network device;

[0050] Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

[0051] In the above embodiments, the second channel measurement resources can be specified by a communication protocol or configured by network devices, which expands the configuration methods of the second channel measurement resources and improves the configuration flexibility of the second channel measurement resources.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the second channel measurement resource includes at least one of the following:

[0053] The AI ​​model predicts a portion of the time interval of the second CSI;

[0054] The transmission bandwidth includes a portion of the multiple subbands;

[0055] A portion of RBs in any subband of the transmission bandwidth;

[0056] A portion of the multiple antenna ports used for data transmission.

[0057] In the above embodiments, the second channel measurement resources can be configured in the time domain, frequency domain, or spatial domain, which can realize the diversity of configuration in the frequency domain or spatial domain, thereby improving the flexibility of configuring the second channel measurement resources.

[0058] In conjunction with some embodiments of the first aspect, in some embodiments, a portion of the multiple antenna ports used for data transmission includes at least one of the following:

[0059] Antenna ports with the same polarization direction;

[0060] Predefined antenna ports.

[0061] In the above embodiments, by selecting antenna ports with the same polarization direction or predefined antenna ports, interference between antenna ports can be reduced, thereby improving the accuracy of training or inference of AI models based on antenna ports.

[0062] In conjunction with some embodiments of the first aspect, in some embodiments, different second channel measurement resources among a plurality of second channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by the different second channel measurement resources are the same.

[0063] In the above embodiments, by setting the QCL or power offset values ​​of different second channel measurement resources to be the same in the frequency domain, it is possible to achieve the same large-scale parameters of different second channel measurement resources on the channel, thereby ensuring the reliability of data transmission through the channel.

[0064] Secondly, embodiments of this disclosure provide a resource allocation method, which is executed by a network device, the method comprising:

[0065] Configure a first channel measurement resource for the terminal, the first channel resource is used by the terminal to acquire a training dataset, the frequency domain resource occupied by the first channel resource is less than the transmission bandwidth, and / or, the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0066] The training dataset is used to train the AI ​​model, which predicts the second CSI based on the first CSI.

[0067] In conjunction with some embodiments of the second aspect, in some embodiments, the time-domain position and / or frequency-domain position of the first channel measurement resource at a given moment are determined based on a communication protocol, or the time-domain position and / or frequency-domain position of the first channel measurement resource at a given moment are configured by the network device.

[0068] In conjunction with some embodiments of the second aspect, in some embodiments, the first channel measurement resource includes at least one of the following:

[0069] The transmission bandwidth includes a portion of the multiple subbands;

[0070] A portion of RBs in any subband of the transmission bandwidth;

[0071] A portion of the multiple antenna ports used for transmission.

[0072] In conjunction with some embodiments of the second aspect, in some embodiments, the frequency domain resources occupied by different first channel measurement resources among a plurality of first channel measurement resources are the same or different, and the QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

[0073] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0074] A second channel measurement resource is configured for the terminal, wherein the second channel measurement resource is used to monitor the AI ​​model and obtain the monitoring result of the AI ​​model. The monitoring result is used to indicate the performance of the AI ​​model when making predictions. The second channel measurement resource includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

[0075] In conjunction with some embodiments of the second aspect, in some embodiments, at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at each time of the first type of time-domain position is determined based on a communication protocol, or at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at one time is configured by the network device;

[0076] Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

[0077] In conjunction with some embodiments of the second aspect, in some embodiments, the second channel measurement resource includes at least one of the following:

[0078] The AI ​​model predicts a portion of the time interval of the second CSI;

[0079] The transmission bandwidth includes a portion of the multiple subbands;

[0080] A portion of RBs in any subband of the transmission bandwidth;

[0081] A portion of the multiple antenna ports used for data transmission.

[0082] In conjunction with some embodiments of the second aspect, in some embodiments, a portion of the antenna ports among the plurality of antenna ports for data transmission includes at least one of the following:

[0083] Antenna ports with the same polarization direction;

[0084] Predefined antenna ports.

[0085] In conjunction with some embodiments of the second aspect, in some embodiments, different second channel measurement resources among a plurality of second channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different second channel measurement resources are the same.

[0086] Thirdly, embodiments of this disclosure provide a communication device for performing the method described in the first or second aspect.

[0087] Fourthly, embodiments of this disclosure provide a communication device, which includes at least one of a transceiver module and a processing module; wherein the communication device is used to execute an optional implementation of the first aspect or the second aspect.

[0088] Fifthly, embodiments of this disclosure provide a terminal, including: one or more processors; wherein the processors are configured to perform the method described in any one of the first aspects.

[0089] In a sixth aspect, embodiments of this disclosure provide a network device, including: one or more processors; wherein the processors are configured to perform the method described in any one of the second aspects.

[0090] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of the first or second aspects.

[0091] Eighthly, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method as described in either the first or second aspect.

[0092] In a ninth aspect, embodiments of this disclosure provide a computer program that, when run on a communication device, causes the communication device to perform the method described in either the first or second aspect.

[0093] In a tenth aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described in either the first or second aspect.

[0094] It is understood that the aforementioned communication equipment, communication system, storage medium, program product, etc., are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0095] This disclosure provides a model training method, apparatus, system, storage medium, and program product. In some embodiments, the terms "model training method," "training method," "model processing method," and "model instruction method" can be used interchangeably.

[0096] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0097] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0098] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0099] In the embodiments disclosed herein, "multiple" refers to two or more.

[0100] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0101] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0102] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.

[0103] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "symbol," the ordinal number preceding "symbol" in "first symbol" and "second symbol" does not restrict the position or order of the "symbols." "First" and "second" do not restrict whether the "symbols" they modify are in the same message, nor do they restrict the order of "first symbol" and "second symbol." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, objects modified by different prefixes can be the same or different. For example, if the descriptive object is a "device," then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the descriptive object is "information," then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0104] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0105] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0106] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0107] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0108] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0109] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0110] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0111] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0112] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0113] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0114] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0115] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0116] Figure 1A is a schematic diagram of the architecture of a sensory system according to an embodiment of the present disclosure.

[0117] As shown in Figure 1A, the communication system 100 includes a terminal 101, an access network device 102, and a core network device 103.

[0118] In some embodiments, terminal 101 includes, for example, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home, but is not limited thereto.

[0119] In some embodiments, the access network device 102 may be a node or device that connects a terminal to a wireless network. The access network device may include at least one of the following in a 5G communication system: an evolved Node B (eNB), a next-generation eNB (ng-eNB), a next-generation Node B (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open RAN, a cloud RAN, a base station in other communication systems, and an access node in a Wi-Fi system, but is not limited thereto.

[0120] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0121] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0122] In some embodiments, the core network device 103 may be a single device, including a first network element 1031, a second network element 1032, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element 1031, the second network element 1032, etc. Network elements may be virtual or physical. The core network may include, for example, at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), Next Generation Core (NGC), and 6G Core Network (6GCN).

[0123] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0124] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0125] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other model training methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0126] In some embodiments, as shown in Figures 1B-1D, when the terminal makes predictions based on an AI model, it utilizes CSI data from multiple historical time points. The time range for estimating downlink channel information based on Channel State Information Reference Signals (CSI-RS) from multiple historical time points is called the observation window. Furthermore, it can predict CSI data from multiple future time points based on the CSI data from multiple historical time points; the time range for predicting CSI data from multiple future time points is called the prediction window. In the figures, N represents the N times when CSI-RS are transmitted within the observation window, M represents the interval between adjacent CSI-RS within the observation window, K represents the K times when CSI is predicted by the prediction window, and D represents the interval between adjacent CSI predicted by the prediction window. It should be noted that the length of the prediction window is the product of K and D.

[0127] Figure 2A is an interactive schematic diagram illustrating the resource configuration and dataset acquisition method according to an embodiment of the present disclosure. As shown in Figure 2A, the embodiments of the present disclosure relate to a model training method, which includes:

[0128] Step S2101: The network device configures the transmission bandwidth and / or the number of antenna ports for data transmission to the terminal.

[0129] In some embodiments, the terminal receives the transmission bandwidth and / or the number of antenna ports for data transmission configured by the network device.

[0130] Optionally, the transmission bandwidth refers to the bandwidth used for normal data transmission. For example, the transmission bandwidth includes three subbands, each of which includes four RBs. Optionally, the number of antenna ports used for data transmission refers to the actual number of antenna ports available for data transmission. For example, the number of antenna ports used for data transmission may be 4, 8, 16, or 32, or other values, which are not limited in the embodiments of this disclosure.

[0131] In some embodiments, the network device indicates the corresponding transmission bandwidth through this resource parameter. Additionally, the network device also indicates the corresponding number of antenna ports through a port parameter.

[0132] In this embodiment of the disclosure, the network device configures the transmission bandwidth and / or the number of antenna ports for data transmission to the terminal. After receiving the configuration from the network device, the terminal can determine the configured transmission bandwidth and / or the number of antenna ports for data transmission, and then perform data transmission based on the configured transmission bandwidth and / or the number of antenna ports for data transmission.

[0133] It should be noted that the transmission bandwidth and / or the number of antenna ports used for data transmission are used for AI model inference. In some embodiments, the network device can send a reference signal to the terminal through the configured frequency domain resources and / or the number of antenna ports. The terminal receives the reference signal sent by the network device based on the configured frequency domain resources and / or the number of antenna ports, measures the reference signal to obtain the measurement result, and then the AI ​​model can predict the measurement result at future times.

[0134] The reference signal can be CSI-RS, and the measurement result obtained by measuring the reference signal is CSI. It should be noted that the reference signal in this embodiment can also be other signals, and this embodiment does not limit them.

[0135] It should be noted that step S2101 in this embodiment is an optional step. In another embodiment, step S2101 may not be executed. The transmission bandwidth and / or the antenna port used for data transmission are predefined by the communication protocol or pre-configured, so it is not necessary to execute step S2101 before each execution of step S2102.

[0136] Step S2102: The network device configures the first channel measurement resources to the terminal.

[0137] In some embodiments, the terminal receives a first channel measurement resource configured by the network device.

[0138] The first channel measurement resource is used to acquire the training dataset. It should be noted that the name of the first channel measurement resource in this embodiment is not limited; it may be, for example, measurement resource, channel resource, etc.

[0139] Optionally, the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth, and / or, the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. For example, the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth. Another example, the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. Yet another example, the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth, and the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0140] In this embodiment of the disclosure, after the network device configures the first channel measurement resources to the terminal, the terminal receives the first channel measurement resources configured by the network device, and then executes the subsequent scheme of obtaining the training dataset based on the first channel measurement resources.

[0141] It should be noted that there can be multiple first channel measurement resources in this embodiment of the disclosure. That is, the network device can be configured with multiple first channel measurement resources. The frequency domain positions of different first channel measurement resources may be different, or the number of antenna ports may be different. This embodiment of the disclosure does not limit this.

[0142] In some embodiments, the first channel measurement resource includes at least one of the following:

[0143] (1) The transmission bandwidth includes a portion of the multiple subbands.

[0144] In this embodiment of the disclosure, the transmission bandwidth includes a large number of subbands. The network device can select a portion of the subbands as the first channel measurement resource, and then the terminal can obtain the training dataset on the selected portion of the subbands.

[0145] For example, as shown in Figure 2B, the transmission bandwidth includes three subbands, namely subband 1, subband 2 and subband 3, and each subband includes four RBs, and all four RBs of subband 2 can be activated.

[0146] The frequency domain location of the first channel measurement resource is based on the communication protocol or configured by the network device. This frequency domain location refers to the location of a portion of the sub-band. Additionally, the time domain location of the first channel measurement resource within a given moment is also based on the communication protocol or configured by the network device. For example, the time domain location at a given moment can be understood as the location of the OFDM symbol within a time slot.

[0147] (2) A portion of RB in any subband of the transmission bandwidth.

[0148] In this embodiment of the disclosure, the transmission bandwidth includes a large number of subbands, and each subband includes multiple RBs. Therefore, the network device can select a portion of RBs from any of the multiple subbands as the first channel measurement resource, and the terminal can obtain the training dataset on the selected portion of RBs.

[0149] For example, as shown in Figure 2C, the transmission bandwidth includes three subbands, namely subband 1, subband 2 and subband 3, and each subband includes four RBs, which can activate the first RB of subband 1.

[0150] The frequency domain location of the first channel measurement resource is based on the communication protocol or configured by the network device. This frequency domain location refers to the location of a portion of the redundancy blocks (RBs). Additionally, the time domain location of the first channel measurement resource within a given moment is based on the communication protocol or configured by the network device. For example, the time domain location at a given moment can be understood as the location of an Orthogonal Frequency Division Multiplexing (OFDM) symbol within a time slot.

[0151] (3) Some of the antenna ports among the multiple antenna ports used for transmission.

[0152] In this embodiment of the disclosure, there are multiple antenna ports for transmission. When training an AI model, not all antenna ports may be used for data transmission. Therefore, the network device can select some antenna ports from the multiple antenna ports as the first channel measurement resource, and the terminal can obtain the training dataset through the selected antenna ports.

[0153] In some embodiments, different first channel measurement resources among a plurality of first channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

[0154] Optionally, some of the antenna ports among the multiple antenna ports used for data transmission include at least one of the following: antenna ports with the same polarization direction; and predefined antenna ports. Here, antenna ports with the same polarization direction can also be understood as antenna ports with a single polarization direction among the multiple antenna ports. Furthermore, the predefined antenna ports can be antenna ports with all odd or all even indices. Alternatively, the predefined antenna ports can be the antenna ports remaining after removing the antenna ports corresponding to a certain row or column in the horizontal or vertical dimension of the two-dimensional antenna array.

[0155] It should be noted that the first channel measurement resource in this embodiment may include any one of (1)-(3) above, or may include multiple of (1)-(3) above. For example, the first channel resource includes (1) and (3) above: the first channel measurement resource includes a portion of a sub-band of a plurality of sub-bands included in the transmission bandwidth and a portion of an antenna port of a plurality of antenna ports used for transmission. Alternatively, the first channel resource includes (2) and (3) above: the first channel measurement resource includes a portion of an RB in any sub-band of the transmission bandwidth and a portion of an antenna port of a plurality of antenna ports used for transmission.

[0156] The following explanation uses the periodic CSI-RS resource as an example of the first channel measurement resource. The network device indicates the number of RBs occupied by the CSI-RS resource through the parameters included in the first channel measurement resource. When the number of occupied RBs is greater than 1, for example, if 4 RBs are configured, and the positions of the 4 RBs are continuous in the frequency domain, then only the starting position of the RBs needs to be configured, as shown in Figure 2B. If the positions of the 4 RBs are not continuous in the frequency domain, the position of each RB can be indicated through the frequency domain position parameters.

[0157] For example, suppose a network device is configured with multiple non-periodic CSI-RS resources. These multiple CSI-RS resources have frequency domain location, QCL, or power offset value factor of the configured channel measurement resources. They can be sent together after being triggered by a single signaling. The interval between each CSI-RS is d, and the value of d can be determined by predefinition or network device configuration.

[0158] For example, taking a network device with 32 antenna ports for data transmission as an example, the antennas are deployed as dual-polarized antennas, with 16 antenna ports in each polarization direction. Optionally, the configured CSI-RS resources only include ports with even-numbered antenna port indices. Furthermore, multiple CSI-RS resources can be configured, each containing different antenna ports. For instance, two CSI-RS resources can be configured: the first contains only an even number of antenna ports, and the second contains only an odd number of ports. These two CSI-RS resources are transmitted at adjacent times. These two CSI-RS resources also have frequency domain location, QCL, or power offset values ​​for the configured channel measurement resources.

[0159] It should be noted that the frequency domain position of the first channel measurement resource in step S2102 of this embodiment can be configured by the network device. That is, when the network device configures the first channel measurement resource, it will also configure the time domain position and / or frequency domain position of the first channel measurement resource at a certain moment. In another embodiment, the time domain position and / or frequency domain position of the first channel measurement resource at a certain moment is directly determined according to the communication protocol.

[0160] In step S2103, the network device sends a reference signal to the terminal based on the first channel measurement resources.

[0161] In this embodiment of the disclosure, after the network device completes the configuration of the first channel resources of the terminal, it can send a reference signal to the terminal based on the first channel measurement resources. This reference signal is CSI-RS, and the terminal can subsequently measure the CSI-RS to obtain the measurement result.

[0162] Step S2104: The terminal acquires the training dataset based on the first channel measurement resources.

[0163] In this embodiment of the disclosure, the terminal receives a reference signal sent by the network device based on the first channel measurement resource, then measures the reference signal to obtain a measurement result, uses the obtained measurement result as a training dataset, and subsequently trains the AI ​​model based on the obtained training dataset.

[0164] Step S2105: The terminal trains the AI ​​model based on the training dataset.

[0165] In some embodiments, the AI ​​model predicts a second CSI based on the first CSI.

[0166] In some embodiments, the measurement results obtained by the terminal include measurement results in different time domains, such as measurement results at historical moments and measurement results at future moments. It should be noted that the measurement results at historical moments and the measurement results at future moments in this embodiment are relative measurement results in the time domain, and are both measurement results actually obtained by the terminal. The terminal uses the AI ​​model to predict the measurement results at historical moments to obtain predicted measurement results at future moments, and then adjusts the AI ​​model based on the difference between the measurement results at future moments and the predicted measurement results at future moments. Here, the measurement result is called CSI, the measurement result at historical moments is the first CSI, and the predicted measurement result at future moments is the second CSI.

[0167] It should be noted that the above steps S2102-S2105 are the scheme for the terminal to train the AI ​​model. Steps S2102-S2105 in this embodiment can form a new embodiment on their own.

[0168] Step S2106: The network device configures the second channel measurement resources to the terminal.

[0169] In some embodiments, the terminal receives a second channel measurement resource configured by the network device.

[0170] The second channel measurement resource is used to monitor the AI ​​model. It should be noted that the name of the second channel measurement resource in this embodiment is not limited; it may be, for example, measurement resource, channel resource, etc.

[0171] In some embodiments, the second channel measurement resource includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

[0172] In this embodiment of the disclosure, after the network device configures the second channel measurement resources to the terminal, the terminal receives the second channel measurement resources configured by the network device, and then executes the subsequent monitoring AI model based on the second channel measurement resources.

[0173] It should be noted that there can be multiple second channel measurement resources in this embodiment of the disclosure. That is, the network device can be configured with multiple second channel measurement resources. The frequency domain positions of different second channel measurement resources may be different, or the number of antenna ports may be different. This embodiment of the disclosure does not limit this.

[0174] In some embodiments, the second channel measurement resource includes at least one of the following:

[0175] (1) A portion of the time intervals of the second CSI predicted by the AI ​​model.

[0176] In some embodiments of this disclosure, the time interval can be a time slot. For example, a portion of the time slot occupied by the second CSI predicted by the AI ​​model. Alternatively, the time interval in this disclosure can also be a time-domain resource of other granularities, which is not limited in this disclosure.

[0177] For example, as shown in Figure 2D, CSI occupies the second and third moments within the prediction window.

[0178] Among them, at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency domain position at each time of the first type of time-domain position is determined based on the communication protocol, or at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency domain position at one time is configured by the network device; wherein, the first type of time-domain position refers to the time occupied by the second channel measurement resource, and the second type of time-domain position refers to the time-domain position occupied within one time.

[0179] For example, let's take time slots as an example. If the first type of time domain location occupies two time slots of the second channel measurement resource, then for each time slot, the second type of time domain location will occupy a portion of the OFDM symbols in each time slot of the second channel measurement resource.

[0180] (2) The transmission bandwidth includes a portion of the multiple subbands.

[0181] In this embodiment, (2) is similar to (2) included in the first channel measurement resources in the above embodiment, and will not be repeated here.

[0182] (3) A portion of the resource block RB in any subband of the transmission bandwidth.

[0183] In this embodiment, (3) is similar to (3) included in the first channel measurement resources in the above embodiment, and will not be repeated here.

[0184] (4) Some of the antenna ports among the multiple antenna ports used for data transmission.

[0185] In this embodiment, (4) is similar to (4) included in the first channel measurement resources in the above embodiment, and will not be repeated here.

[0186] In some embodiments, different second channel measurement resources among a plurality of second channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-located QCL or power offset values ​​on the frequency domain resources occupied by the different second channel measurement resources are the same.

[0187] Optionally, some of the antenna ports among the multiple antenna ports used for data transmission include at least one of the following: antenna ports with the same polarization direction; and predefined antenna ports. Here, antenna ports with the same polarization direction can also be understood as antenna ports with a single polarization direction among the multiple antenna ports. Furthermore, the predefined antenna ports can be antenna ports with all odd or all even indices. Alternatively, the predefined antenna ports can be the antenna ports remaining after removing the antenna ports corresponding to a certain row or column in the horizontal or vertical dimension of the two-dimensional antenna array.

[0188] It should be noted that the second channel measurement resources in this embodiment may include any one of (1)-(4) above, or may include multiple of (1)-(4) above. For example, the second channel resources include (2) and (3) above: the second channel measurement resources include a portion of a sub-band among multiple sub-bands included in the transmission bandwidth and a portion of an antenna port among multiple antenna ports used for transmission. Or, the second channel resources include (3) and (4) above: the second channel measurement resources include a portion of an RB in any sub-band of the transmission bandwidth and a portion of an antenna port among multiple antenna ports used for transmission. The second channel resources include (1) and (2) above: the second channel measurement resources include a portion of the time occupied by the second CSI predicted by the AI ​​model and a portion of a sub-band among multiple sub-bands included in the transmission bandwidth. The above embodiments are all illustrative examples, and there may be other combinations, which are not limited in this embodiment.

[0189] The following explanation uses the periodic CSI-RS resource as an example to illustrate this. An AI model can predict CSI at one or more times. When predicting CSI at multiple times, the network device needs to configure multiple CSI-RS resources corresponding to each time point to measure the CSI at those times in order to calculate the performance index values. This increases pilot transmission overhead when the predicted time is large. Considering that the performance index at a finite number of times can also reflect the model's performance, the network device does not need to send CSI-RS at every time within the prediction window. For example, the network device only needs to send CSI-RS at a portion of the multiple times, and the terminal determines the model's performance based on the CSI-RS received at those portions. This approach not only reduces CSI-RS transmission overhead but also lowers the computational complexity of the terminal.

[0190] For example, the timing of CSI-RS transmission within the prediction window can be determined by predefinition or by the network device through Radio Resource Control (RRC) signaling. The predefinition method is also related to the number of predicted CSI times within the prediction window. Different numbers of predicted CSI times are associated with different predefined values. Optionally, the network device configures multiple CSI-RS resources via RRC signaling and additionally indicates the interval between CSI-RS resources or the slot offset of each resource relative to the CSI-RS resource set. For example, if a CSI-RS resource set containing two aperiodic CSI-RS resources is configured, and the resource set slot offset triggered by Downlink Control Information (DCI) is used as a reference time, the transmission times of these two CSI-RS resources are determined based on the offset values ​​of each resource relative to the reference time indicated by the Network Equipment (NW).

[0191] It should be noted that, in step S2102 of this embodiment, at least one of the first type of time-domain position, the second type of time-domain position, or the frequency domain position of the second channel measurement resource at multiple times can be configured by the network device. That is, when configuring the second channel measurement resource, the network device will also configure at least one of the first type of time-domain position, the second type of time-domain position, or the frequency domain position of the second channel measurement resource at multiple times. In another embodiment, at least one of the first type of time-domain position, the second type of time-domain position, or the frequency domain position of the second channel measurement resource at multiple times is directly determined according to the communication protocol.

[0192] In step S2107, the network device sends a reference signal to the terminal based on the second channel measurement resources.

[0193] In this embodiment of the disclosure, after the network device completes the configuration of the second channel resources of the terminal, it can send a reference signal to the terminal based on the second channel measurement resources. This reference signal is the CSI-RS, and the terminal can subsequently measure the CSI-RS to obtain the measurement result.

[0194] In step S2108, the terminal monitors the AI ​​model based on the second channel measurement resources and obtains the monitoring results of the AI ​​model.

[0195] In some embodiments, monitoring results are used to indicate the performance of the AI ​​model when making predictions.

[0196] In some embodiments, the second channel measurement resource includes second channel measurement resources at historical times and second channel measurement resources at future times. Specifically, the terminal measures the CSI-RS based on the second channel measurement resources at historical times to obtain a first CSI at that historical time, and then predicts the second CSI at the future time based on the first CSI using an AI model. Alternatively, the terminal can also measure the CSI-RS based on the second channel measurement resources at future times to obtain the actual CSI at the future time.

[0197] In this embodiment of the disclosure, the second CSI predicted by the model may differ from the actual CSI. In this case, the terminal can determine the performance index value of the model at each time step based on the difference between the predicted second CSI and the actual CSI.

[0198] In some embodiments, the names of performance metric values ​​are not limited in this disclosure. Examples include performance metric value, performance value, accuracy, etc.

[0199] In some embodiments, the terminal may use Gradient Cosine Similarity (GCS), SGCS, or NMSE to determine the performance metric value. Here, GCS represents cosine similarity, SGCS represents squared GCS, and NMSE represents normalized mean square error.

[0200] Alternatively, GCS can be calculated using the following formula:

[0201] Among them, w k Let w′ represent the feature vector of the actual CSI at time k. k This represents the eigenvector of the second CSI at time k.

[0202] Alternatively, SGCS can be calculated using the following formula:

[0203] Among them, w k Let w′ represent the feature vector of the actual CSI at time k. k This represents the eigenvector of the second CSI at time k.

[0204] Optionally, NMSE is calculated using the following formula:

[0205] Where w' refers to the feature vector of the second CSI, and w refers to the feature vector of the actual CSI.

[0206] In some embodiments, assuming that the network device and terminal determine the performance metric as Normalized Mean Square Error (NMSE) through a predefined method, the terminal's model can predict H′1, H′2, H′3, and H′4 at K = four future times. The network device transmits CSI-RS at these four times to measure its real-time channels H1, H2, H3, and H4. For each time point, the terminal can calculate the corresponding NMSE value according to a formula. Optionally, the terminal can also calculate the average of the NMSEs at these four times as the performance metric value of the model.

[0207] In order for the terminal to send the model's monitoring results, after calculating the NMSE value, the terminal also needs to determine the indicator threshold to determine the final monitoring result before sending it to the network device. A corresponding indicator threshold is defined for each of the four predicted time points. The terminal compares the calculated NMSE for each time point with the defined indicator threshold to determine the monitoring result for each time point.

[0208] In some embodiments, the monitoring result is used to indicate whether the model meets the prediction requirements when making predictions, or it can also be understood as the monitoring result being used to indicate whether the model's performance meets the prediction requirements.

[0209] In some embodiments, if the performance metric value is greater than or equal to the metric threshold, the model's performance is determined to meet the prediction requirements. Alternatively, if the performance metric value is less than the metric threshold, the model's performance is determined to not meet the prediction requirements.

[0210] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0211] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0212] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0213] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0214] The model training method disclosed herein may include at least one of steps S2101 to S2108. For example, at least one of steps S2101 to S2108 may be implemented as an independent embodiment.

[0215] In some embodiments, at least one of steps S2101 to S2108 is optional, and one or more of these steps may be omitted or substituted in different embodiments. In some embodiments, please refer to the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, which will not be repeated here.

[0216] Figure 3 is a flowchart illustrating the resource configuration and dataset acquisition method according to an embodiment of the present disclosure. As shown in Figure 3, the embodiments of the present disclosure involve a model training method, which includes:

[0217] Step S3101: The network device configures the first channel measurement resources to the terminal.

[0218] In some embodiments, the first channel resource is used by the terminal to acquire a training dataset, the frequency domain resource occupied by the first channel resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission; the training dataset is used to train an AI model, and the AI ​​model predicts a second CSI based on the first channel state information (CSI).

[0219] In some embodiments, the implementation of step S3101 can be referred to the implementation of step S2102 in FIG2A, and will not be repeated here.

[0220] In some embodiments, the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is determined based on a communication protocol, or the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is configured by the network device.

[0221] In some embodiments, the first channel measurement resource includes at least one of the following:

[0222] The transmission bandwidth includes a portion of the multiple subbands;

[0223] A portion of resource blocks RB in any subband of the transmission bandwidth;

[0224] A portion of the multiple antenna ports used for transmission.

[0225] In some embodiments, different first channel measurement resources among a plurality of first channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

[0226] In some embodiments, the method further includes:

[0227] A second channel measurement resource is configured for the terminal, wherein the second channel measurement resource is used to monitor the AI ​​model and obtain the monitoring result of the AI ​​model. The monitoring result is used to indicate the performance of the AI ​​model when making predictions. The second channel measurement resource includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

[0228] In some embodiments, at least one of the first type of time-domain location of the second channel measurement resource at multiple times, the second type of time-domain location at each time of the first type of time-domain location, or the frequency domain location is determined based on a communication protocol; or, at least one of the first type of time-domain location of the second channel measurement resource at multiple times, the second type of time-domain location at one time, or the frequency domain location is configured by the network device.

[0229] Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

[0230] In some embodiments, the second channel measurement resource includes at least one of the following:

[0231] The AI ​​model predicts a portion of the time interval of the second CSI;

[0232] The transmission bandwidth includes a portion of the multiple subbands;

[0233] A portion of resource blocks RB in any subband of the transmission bandwidth;

[0234] A portion of the multiple antenna ports used for data transmission.

[0235] In some embodiments, a portion of the plurality of antenna ports used for data transmission includes at least one of the following:

[0236] Antenna ports with the same polarization direction;

[0237] Predefined antenna ports.

[0238] In some embodiments, different second channel measurement resources among a plurality of second channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different second channel measurement resources are the same.

[0239] Step S3102: The terminal acquires the training dataset based on the first channel measurement resources.

[0240] In some embodiments, the frequency domain resources occupied by the first channel measurement resource are less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission.

[0241] In some embodiments, the implementation of step S3102 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0242] Step S3103: The terminal trains the AI ​​model based on the training dataset.

[0243] In some embodiments, the AI ​​model predicts a second CSI based on the first channel state information (CSI).

[0244] In some embodiments, the implementation of step S3103 can be referred to the implementation of step S2105 in FIG2A, and will not be repeated here.

[0245] In some embodiments, the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is determined based on a communication protocol, or the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is configured by the network device.

[0246] In some embodiments, the first channel measurement resource includes at least one of the following:

[0247] The transmission bandwidth includes a portion of the multiple subbands;

[0248] A portion of RBs in any subband of the transmission bandwidth;

[0249] A portion of the multiple antenna ports used for transmission.

[0250] In some embodiments, different first channel measurement resources among a plurality of first channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

[0251] In some embodiments, the method further includes:

[0252] The network device receives a second channel measurement resource configured, which includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

[0253] The AI ​​model is monitored based on the second channel measurement resources to obtain the monitoring results of the AI ​​model, which are used to indicate the performance of the AI ​​model when making predictions.

[0254] In some embodiments, at least one of the first type of time-domain location of the second channel measurement resource at multiple times, the second type of time-domain location at each time of the first type of time-domain location, or the frequency domain location is determined based on a communication protocol; or, at least one of the first type of time-domain location of the second channel measurement resource at multiple times, the second type of time-domain location at one time, or the frequency domain location is configured by the network device.

[0255] Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

[0256] In some embodiments, the second channel measurement resource includes at least one of the following:

[0257] The AI ​​model predicts a portion of the time interval of the second CSI;

[0258] The transmission bandwidth includes a portion of the multiple subbands;

[0259] A portion of RBs in any subband of the transmission bandwidth;

[0260] A portion of the multiple antenna ports used for data transmission.

[0261] In some embodiments, a portion of the plurality of antenna ports used for data transmission includes at least one of the following:

[0262] Antenna ports with the same polarization direction;

[0263] Predefined antenna ports.

[0264] In some embodiments, different second channel measurement resources among a plurality of second channel measurement resources occupy the same or different frequency domain resources, and the QCL or power offset values ​​on the frequency domain resources occupied by different second channel measurement resources are the same.

[0265] Figure 4 is a flowchart illustrating a resource allocation method according to an embodiment of the present disclosure. As shown in Figure 4, the embodiment of the present disclosure relates to a model training method, which includes:

[0266] Step S4101: The network device configures channel measurement resources for the terminal to generate training data collection.

[0267] Step S4101 is similar to step S2102 in the above embodiment. The channel measurement resources are similar to the first channel measurement resources in the above embodiment.

[0268] In some embodiments, Alt1: Channel measurement resources are configured in each sub-band portion RB across the entire bandwidth, or N across the entire bandwidth. <N tot Channel measurement resources are configured for some or all of the RBs within a sub-band. Among them, N tot This indicates the number of subbands for which channel measurement resources are configured.

[0269] In some embodiments, the frequency domain location of Alt1 can be indicated by predefined parameters or by network devices through higher-layer signaling configuration parameters to indicate the frequency domain location of channel measurement resources.

[0270] If multiple channel measurement resources are configured in Alt1, the frequency domain position, QCL, or power control offset factor of the configured channel measurement resources are the same as the configuration parameters powercontroloffset or powerControlOffsetSS.

[0271] In some embodiments, Alt2: Configure the number of channel measurement resource ports to P. c <P tot , where P c To configure the number of ports for channel measurement resources, P tot This represents the number of antenna ports actually transmitting data. The number of ports P configured for channel measurement resources. c This refers to the number of antenna ports including only a single polarization direction or a portion of a predefined first port number, where the first port number is less than the actual number of antenna ports used for transmission. For example, configuring the first port of the channel measurement resource to be the actual transmission antenna port P. tot The antenna port index is either an odd or even number corresponding to the number of ports, or the actual number of antenna ports minus the number of ports in a row or column of the horizontal or vertical dimension of the two-dimensional antenna array. The configured channel measurement resources include which ports through predefined or NW configuration.

[0272] Alternatively, Alt3: Channel measurement resources can also be configured based on a combination of the above Alt1 and Alt2 methods.

[0273] Step S4102, the network device configures channel measurement resources for the terminal to calculate monitoring information.

[0274] Among them, step S4102 is similar to step S2106 in the above embodiment. The channel measurement resources for calculating monitoring information are similar to the second channel measurement resources in the above embodiment.

[0275] In some embodiments, Option 1: When 1 < K, configure some moments within K′ < K prediction windows. When K = 4, configure K′ = 2 channel measurement resources. The NW sends a channel measurement reference signal based on the configured channel measurement resources. The transmission position of the channel measurement reference signal within the prediction window can be determined by predefined, configured by the NW through high-layer signaling, or indicated by UE reporting. For example, the moments corresponding to the red double-headed arrows in Figure 4 below are the transmission moments of the channel measurement reference signal.

[0276] Option 2: Configure K or K′ < K channel measurement resources for measuring future moments, with a lower frequency-domain density or within some subbands or fewer channel measurement resource ports within the prediction window of each channel measurement resource, as described in Alt1 / Alt2 / Alt3.

[0277] The frequency-domain positions of the K′ or K channel measurement resources described in Option 1 or Option 2 can be the same or different, and the QCL or the power control offset factor of the configured channel measurement resources, such as the configuration parameter powercontroloffset or powerControlOffsetSS, is the same.

[0278] If there is a UL / DL switch, and there is a UL slot at K moments within the prediction window, then the configured K′ < K resources are only transmitted on valid DL slots. If K resources are configured, then CSI-RS is not transmitted at the UL slot position.

[0279] Option 3: Determine the channel resource configuration by combining the methods of Option 1 and Option 2 above.

[0280] For example, assume that the NW configures a CSI-RS resource with a period of T1 and indicates the frequency-domain and time-domain positions of this resource within a time slot through RRC signaling. In addition, an additional parameter is also used to indicate the number of RBs occupied by the CSI-RS resource. When the number of occupied RBs is greater than 1, for example, 4 RBs are configured. If the positions of the 4 RBs are continuous in the frequency domain, then only the starting position of the RB needs to be configured; if the positions of the 4 RBs are discontinuous in the frequency domain, the NW can indicate the positions of each RB through frequency-domain position parameters.

[0281] Suppose the NW is configured with multiple aperiodic CSI-RS resources. These CSI-RS resources have frequency domain locations, QCLs, or power control offset factors such as the configuration parameters powercontroloffset or powerControlOffsetSS for the configured channel measurement resources. They can be transmitted together after a single signaling trigger, with an interval of d between each CSI-RS. The value of d can be determined by predefinition or NW configuration.

[0282] Assuming the number of antenna ports N=32 on the NW side for data transmission, and the antennas on the NW side are deployed as dual-polarized antennas, each polarization direction contains 16 ports. The corresponding polarization direction can be determined by a predefined first polarization direction. Optionally, the configured CSI-RS resources only include ports with even-numbered antenna port indices. Furthermore, multiple CSI-RS resources can be configured, each containing different ports. For example, two CSI-RS resources can be configured: the first contains only an even number of antenna ports, and the second contains only an odd number of ports. These two CSI-RS resources are transmitted at adjacent times. These two CSI-RS resources also have frequency domain positions, QCL, or power control offset factors for the configured channel measurement resources, such as the configuration parameters powercontroloffset or powerControlOffsetSS.

[0283] At any given time, even if the configured resources only include a portion of the antenna ports, CSI-RS can still be transmitted in the frequency domain at only one RB or a finite number of RB locations to further reduce CSI-RS resource overhead.

[0284] For example, a CSI prediction model can predict CSI at one or more times. When predicting CSI at multiple times, the NW needs to configure CSI-RS resources for multiple times to measure the CSI at each time in order to calculate the performance index value at each time. When the predicted time is large, this also increases the overhead of pilot transmission. Considering that the performance index at a finite number of times can also reflect the model performance, the NW does not need to send CSI-RS at every time within the prediction window. The NW only needs to send CSI-RS at two times, and the UE determines the model performance based on the CSI-RS received at these two times. This approach not only reduces CSI-RS transmission overhead but also reduces the computational complexity of the UE. Optionally.

[0285] The number of RBs or antenna ports occupied by the configured CSI-RS resources is as described in Example 1, in order to further reduce the transmission overhead of CSI-RS.

[0286] The timing of CSI-RS transmission within the prediction window can be determined through predefinition or by the NW (Network Controller) via RRC signaling. The predefinition method is also related to the number of predicted CSI times within the prediction window. Different numbers of predicted CSI times are associated with different predefined values. Optionally, the NW configures multiple CSI-RS resources via RRC signaling and further indicates the interval between CSI-RS resources or the slot offset of each resource relative to the CSI-RS resource set. For example, if a CSI-RS resource set containing two aperiodic CSI-RS resources is configured, using the resource set slot offset triggered by DCI as a reference time, the transmission times of these two CSI-RS resources are determined by the offset values ​​of each resource relative to the reference time indicated by the NW.

[0287] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0288] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0289] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0290] Figure 5A is a schematic diagram of the structure of a terminal proposed in an embodiment of this disclosure. Terminal 5100 is used to execute any of the above methods. In some embodiments, as shown in Figure 5A, terminal 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, processing module 5102 is used to acquire a training dataset based on a first channel measurement resource, wherein the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission; the training dataset is used to train the AI ​​model, and the AI ​​model predicts a second CSI based on a first CSI.

[0291] Figure 5B is a schematic diagram of the structure of a network device proposed in an embodiment of this disclosure. The network device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the network device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the transceiver module 5201 is used to configure a first channel measurement resource to a terminal, the first channel resource being used by the terminal to acquire a training dataset, the frequency domain resource occupied by the first channel resource being less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource being less than the number of antenna ports used for data transmission; the training dataset is used to train an AI model, the AI ​​model predicting a second CSI based on the first channel state information (CSI).

[0292] Optionally, the transceiver module described above is used to perform at least one of the communication steps such as sending and / or receiving performed by the terminal in any of the above methods, which will not be elaborated here. Optionally, the processing module described above is used to perform at least one of the other steps performed by the terminal in any of the above methods, which will not be elaborated here.

[0293] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a sensing function device, a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0294] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control sensing devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0295] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above-described method, and the processor 6101 performs at least one of the other steps. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0296] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In an optional embodiment, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6103 and can be used to receive data and / or instructions from the memory 6102 or other devices, and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6102 and send the data and / or instructions to the processor 6101.

[0297] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (6) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (7) others, etc.

[0298] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0299] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0300] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.

[0301] In some embodiments, the interface circuit 6202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the interface circuit 6202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the interface circuit 6202 performs data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of the other steps.

[0302] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0303] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0304] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0305] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0306] The terminal acquires the training dataset through the first channel measurement resource, and the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. In other words, the terminal uses fewer first channel measurement resources, and can also train the AI ​​model after acquiring the training dataset based on the reduced channel measurement resources, thereby reducing resource overhead and improving resource utilization.

Claims

1. A method for acquiring a dataset, wherein, The method is executed by a terminal, and the method includes: The network device receives a first channel measurement resource configured, wherein the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. A training dataset is obtained based on the first channel measurement resources. The training dataset is used to train the artificial intelligence (AI) model. The AI ​​model predicts the second CSI based on the first channel state information (CSI).

2. The method according to claim 1, wherein, The time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is determined based on the communication protocol, or the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is configured by the network device.

3. The method according to claim 1, wherein, The first channel measurement resource includes at least one of the following: The transmission bandwidth includes a portion of the multiple subbands; A portion of resource blocks RB in any subband of the transmission bandwidth; A portion of the multiple antenna ports used for transmission.

4. The method according to any one of claims 1 to 3, wherein, Among multiple first channel measurement resources, different first channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-address QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

5. The method according to any one of claims 1 to 3, wherein, The method further includes: The network device receives a second channel measurement resource configured, which includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model; the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth; and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission. The AI ​​model is monitored based on the second channel measurement resources to obtain the monitoring results of the AI ​​model, which are used to indicate the performance of the AI ​​model when making predictions.

6. The method according to claim 5, wherein, At least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at each time of the first type of time-domain position, is determined based on the communication protocol; or, at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at one time is configured by the network device. Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

7. The method according to claim 5, wherein, The second channel measurement resource includes at least one of the following: The AI ​​model predicts a portion of the time interval of the second CSI; The transmission bandwidth includes a portion of the multiple subbands; A portion of resource blocks RB in any subband of the transmission bandwidth; A portion of the multiple antenna ports used for data transmission.

8. The method according to claim 3 or 7, wherein, A portion of the multiple antenna ports used for data transmission includes at least one of the following: Antenna ports with the same polarization direction; Predefined antenna ports.

9. The method according to any one of claims 5 to 8, wherein, Among multiple second channel measurement resources, different second channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-address QCL or power offset values ​​on the frequency domain resources occupied by different second channel measurement resources are the same.

10. A resource allocation method, wherein, The method is performed by a network device, and the method includes: Configure a first channel measurement resource for the terminal, the first channel resource is used by the terminal to acquire a training dataset, the frequency domain resource occupied by the first channel resource is less than the transmission bandwidth, and / or, the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. The training dataset is used to train the AI ​​model, which predicts the second CSI based on the first channel state information (CSI).

11. The method according to claim 10, wherein, The time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is determined based on the communication protocol, or the time-domain and / or frequency-domain location of the first channel measurement resource at a given moment is configured by the network device.

12. The method according to claim 10, wherein, The first channel measurement resource includes at least one of the following: The transmission bandwidth includes a portion of the multiple subbands; A portion of resource blocks RB in any subband of the transmission bandwidth; A portion of the multiple antenna ports used for transmission.

13. The method according to any one of claims 10 to 12, wherein, Among multiple first channel measurement resources, different first channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-address QCL or power offset values ​​on the frequency domain resources occupied by different first channel measurement resources are the same.

14. The method according to any one of claims 10 to 12, wherein, The method further includes: Configure a second channel measurement resource for the terminal; wherein the second channel measurement resource is used to monitor the AI ​​model and obtain the monitoring result of the AI ​​model, the monitoring result is used to indicate the performance of the AI ​​model when making predictions, and the second channel measurement resource includes at least one of the following: the time occupied by the second channel measurement resource is less than the time occupied by the second CSI predicted by the AI ​​model, the frequency domain resource occupied by the second channel measurement resource is less than the transmission bandwidth, and the number of antenna ports of the second channel measurement resource is less than the number of antenna ports used for data transmission.

15. The method according to claim 14, wherein, At least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at each time of the first type of time-domain position, is determined based on the communication protocol; or, at least one of the first type of time-domain position of the second channel measurement resource at multiple times, the second type of time-domain position or frequency-domain position at one time is configured by the network device. Wherein, the first type of time-domain location refers to the time occupied by the second channel measurement resource, and the second type of time-domain location refers to the time-domain location occupied within a certain time.

16. The method of claim 14, wherein, The second channel measurement resource includes at least one of the following: The AI ​​model predicts a portion of the time interval of the second CSI; The transmission bandwidth includes a portion of the multiple subbands; A portion of resource blocks RB in any subband of the transmission bandwidth; A portion of the multiple antenna ports used for data transmission.

17. The method according to claim 12 or 16, wherein, A portion of the multiple antenna ports used for data transmission includes at least one of the following: Antenna ports with the same polarization direction; Predefined antenna ports.

18. The method according to any one of claims 14 to 17, wherein, Among multiple second channel measurement resources, different second channel measurement resources occupy the same or different frequency domain resources, and the quasi-co-address QCL or power offset values ​​on the frequency domain resources occupied by different second channel measurement resources are the same.

19. A dataset acquisition device, wherein, The device includes: The transceiver module is used to receive a first channel measurement resource configured by the network device, wherein the frequency domain resource occupied by the first channel measurement resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. The processing module is used to acquire a training dataset based on the first channel measurement resources. The training dataset is used to train an AI model. The AI ​​model predicts a second CSI based on the first channel state information (CSI).

20. A resource allocation device, wherein, The device includes: The transceiver module is configured to configure a first channel measurement resource to the terminal. The first channel resource is used by the terminal to acquire a training dataset. The frequency domain resource occupied by the first channel resource is less than the transmission bandwidth, and / or the number of antenna ports of the first channel measurement resource is less than the number of antenna ports used for data transmission. The training dataset is used to train the AI ​​model, which predicts the second CSI based on the first channel state information (CSI).

21. A communication device, wherein, The communication device is used to perform the method according to any one of claims 1 to 9 or any one of claims 10 to 18.

22. A communication system comprising a terminal and network equipment, wherein, The terminal is configured to implement the method as described in any one of claims 1 to 9; The network device is configured to implement the method as described in any one of claims 10 to 18.

23. A storage medium storing instructions, wherein, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1 to 9, or the method as described in any one of claims 10 to 18.

24. A program product comprising at least one of a program and instructions, wherein, When at least one of the programs or instructions is executed by a communication device, it implements the method as described in any one of claims 1 to 9 or any one of claims 10 to 18.

Images