Communication methods, terminals, network devices, system and storage medium

Abstract

The present disclosure relates to communication methods, terminals, network devices, a system, and a storage medium. A method comprises: sending first information to a network device by means of first signaling, the first information being used for indicating a first AI function or a first AI model supported by a terminal, and the first AI function or the first AI model being used for predicting channel state information (CSI) of the terminal. Thus, AI function or AI model identification for CSI prediction in a communication system is achieved, thereby reducing the complexity of AI model or AI function identification, improving the prediction precision of CSI, and reducing the signaling overhead in the CSI prediction process.

Description

Communication method, terminal, network device, system and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to a communication method, terminal, network device, system, and storage medium. Background Art

[0002] For terminals moving at medium to high speeds, using the existing Type II codebook to feed back CSI (Channel Status Information) can degrade communication system performance due to the rapid changes in channel information in the time domain. Related technologies use a new Type II codebook to predict future downlink channel information based on historical downlink channel information on the terminal side, improving communication system performance in medium to high speed mobility scenarios.

[0003] Summary of the Invention

[0004] To overcome the technical problem in related technologies of being unable to identify CSI prediction AI models or AI functions, the present disclosure provides a communication method, terminal, network device, system, and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a communication method is proposed, which is executed by a terminal. The method includes:

[0006] First information is sent to a network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

[0007] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a network device. The method includes:

[0008] First information sent by a terminal through first signaling is received, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0009] According to a third aspect of an embodiment of the present disclosure, a terminal is provided, including:

[0010] The first transceiver module is configured to send first information to the network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

[0011] According to a fourth aspect of an embodiment of the present disclosure, a network device is provided, including:

[0012] The second transceiver module is configured to receive first information sent by the terminal through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0013] According to a fifth aspect of an embodiment of the present disclosure, a terminal is provided, including:

[0014] one or more processors;

[0015] The terminal is used to execute the communication method described in any one of the first aspects of this disclosure.

[0016] According to a sixth aspect of an embodiment of the present disclosure, a network device is provided, including:

[0017] one or more processors;

[0018] The network device is used to execute the communication method described in any one of the second aspects of this disclosure.

[0019] According to the seventh aspect of an embodiment of the present disclosure, a communication system is proposed, comprising a terminal and a network device, wherein the terminal is configured to implement the communication method described in any one of the first aspects of the present disclosure, and the network device is configured to implement the communication method described in any one of the second aspects of the present disclosure.

[0020] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is proposed, which stores instructions. When the instructions are executed on a communication device, the communication device executes a communication method as described in any one of the first aspects of the present disclosure, or the communication device executes a communication method as described in any one of the second aspects of the present disclosure.

[0021] According to the ninth aspect of an embodiment of the present disclosure, a computer program product is proposed, comprising a computer program and / or instructions, which, when executed by a communication device, implement the communication method as described in any one of the first aspects of the present disclosure, or implement the communication method as described in any one of the second aspects of the present disclosure when the computer program and / or instructions are executed by a communication device.

[0022] In the above solution, first information is sent to a network device via first signaling. The first information indicates a first AI function or a first AI model supported by a terminal. The first AI function or model is used to predict the terminal's channel state information (CSI). This enables identification of the AI ​​function or model used for CSI prediction in the communication system, reduces the complexity of AI model or function identification, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0024] FIG1A is a schematic diagram showing the architecture of a communication system according to an embodiment of the present disclosure.

[0025] FIG1B is a schematic diagram showing an observation window and a prediction window according to an embodiment of the present disclosure.

[0026] FIG2A is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure.

[0027] FIG2B is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure.

[0028] FIG3A is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0029] FIG3B is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0030] FIG3C is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0031] FIG3D is a flow chart of a communication method according to an embodiment of the present disclosure.

[0032] FIG4A is a flow chart showing a communication method according to an embodiment of the present disclosure.

[0033] FIG4B is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0034] FIG4C is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0035] FIG4D is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0036] FIG5A is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure.

[0037] FIG5B is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure.

[0038] FIG6A is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0039] FIG6B is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0040] FIG6C is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0041] FIG6D is a flow chart illustrating a communication method according to an embodiment of the present disclosure.

[0042] FIG7 is a schematic diagram of the structure of a terminal proposed in an embodiment of the present disclosure.

[0043] FIG8 is a schematic diagram of the structure of a network device proposed in an embodiment of the present disclosure.

[0044] FIG9 is a schematic structural diagram of a communication device 9100 according to an embodiment of the present disclosure.

[0045] FIG10 is a schematic structural diagram of a chip 9200 according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The embodiments of the present disclosure provide a communication method, a terminal, a network device, a system, and a storage medium.

[0047] In a first aspect, an embodiment of the present disclosure provides a communication method, which is executed by a terminal. The method includes:

[0048] First information is sent to a network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

[0049] In conjunction with some embodiments of the first aspect, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0050] A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment;

[0051] A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window;

[0052] a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment;

[0053] a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window;

[0054] A fifth parameter is used to indicate the time domain range of the prediction window.

[0055] Through the above method, the AI ​​model or AI function is reported by reporting parameter information, thereby reducing the signaling overhead in the CSI prediction process and improving the CSI prediction performance in the communication system.

[0056] In conjunction with some embodiments of the first aspect, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0057] A sixth parameter, used to indicate a time domain channel attribute TDCP value of the terminal;

[0058] A seventh parameter is used to indicate capability information of the terminal.

[0059] In combination with some embodiments of the first aspect, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0060] In combination with some embodiments of the first aspect, the first information includes first AI model ID information of the first AI model.

[0061] In combination with some embodiments of the first aspect, the first signaling includes at least one of the following: radio resource control RRC message, medium access control layer-control unit MAC-CE information and uplink control information UCI.

[0062] In conjunction with some embodiments of the first aspect, the method further includes:

[0063] receiving second information sent by the network device through second signaling;

[0064] The first information is generated based on the second information.

[0065] In combination with some embodiments of the first aspect, the second signaling includes at least one of the following: RRC message, MAC-CE information and downlink control information DCI.

[0066] In conjunction with some embodiments of the first aspect, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0067] A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment;

[0068] A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window;

[0069] a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment;

[0070] a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window;

[0071] A fifth parameter is used to indicate the time domain range of the prediction window.

[0072] In combination with some embodiments of the first aspect, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0073] In combination with some embodiments of the first aspect, the second information includes a pilot signal resource, and generating the first information based on the second information includes:

[0074] Acquire AI model training data of the terminal based on the pilot signal resource in the second information;

[0075] Training the set AI model of the terminal according to the AI ​​model training data to generate the first AI model;

[0076] Generate the first information according to the first AI model.

[0077] In conjunction with some embodiments of the first aspect, the method further includes:

[0078] receiving third information sent by the network device, where the third information includes a pilot signal resource;

[0079] Acquire AI model training data of the terminal based on the pilot signal resource in the third information;

[0080] The set AI model of the terminal is trained according to the AI ​​model training data to generate a second AI model, where the second AI model is used to predict the CSI of the terminal.

[0081] In combination with some embodiments of the first aspect, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0082] In conjunction with some embodiments of the first aspect, the method further includes:

[0083] The second AI model ID information is used as the model ID of the second AI model.

[0084] In combination with some embodiments of the first aspect, the pilot signal resources include CSI-RS resources.

[0085] In this manner, first information is sent to a network device via first signaling. The first information indicates a first AI function or a first AI model supported by the terminal. The first AI function or model is used to predict the terminal's channel state information (CSI). This enables identification of the AI ​​function or model used for CSI prediction in the communication system, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process.

[0086] In a second aspect, an embodiment of the present disclosure provides a communication method, which is performed by a network device. The method includes:

[0087] First information sent by a terminal through first signaling is received, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0088] With reference to some embodiments of the second aspect, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0089] A first parameter, where the first parameter is used to indicate the number of CSI-RSs in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before a current moment;

[0090] A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window;

[0091] a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment;

[0092] a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window;

[0093] A fifth parameter is used to indicate the time domain range of the prediction window.

[0094] In conjunction with some embodiments of the second aspect, the first information includes second parameter information, including at least one of the following:

[0095] A sixth parameter, used to indicate a time domain channel attribute TDCP value of the terminal;

[0096] A seventh parameter is used to indicate capability information of the terminal.

[0097] In combination with some embodiments of the second aspect, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0098] In combination with some embodiments of the second aspect, the first information includes first AI model ID information of the first AI model.

[0099] In combination with some embodiments of the second aspect, the first signaling includes at least one of the following: RRC message, MAC-CE information and UCI.

[0100] In conjunction with some embodiments of the second aspect, the method further includes:

[0101] Second information is sent through second signaling, where the second information is used to instruct the terminal to report the first AI function or the first AI model based on the second information.

[0102] In combination with some embodiments of the second aspect, the second signaling includes at least one of the following: RRC message, MAC-CE information and DCI.

[0103] In conjunction with some embodiments of the second aspect, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0104] A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment;

[0105] A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window;

[0106] a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment;

[0107] a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window;

[0108] A fifth parameter is used to indicate the time domain range of the prediction window.

[0109] In combination with some embodiments of the second aspect, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0110] In combination with some embodiments of the second aspect, the second information includes pilot signal resources.

[0111] In conjunction with some embodiments of the second aspect, the method further includes:

[0112] Sending third information to the terminal, where the third information includes pilot signal resources.

[0113] In combination with some embodiments of the second aspect, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0114] In combination with some embodiments of the second aspect, the pilot signal resources include CSI-RS resources.

[0115] In this manner, a network device receives first information sent by a terminal via first signaling. The first information indicates a first AI function or a first AI model supported by the terminal, which is used to predict the terminal's CSI. This provides an AI function or model identification mechanism and process for CSI prediction, improving CSI prediction accuracy and reducing signaling overhead during the CSI prediction process.

[0116] In a third aspect, an embodiment of the present disclosure provides a terminal, including:

[0117] The first transceiver module is configured to send first information to the network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

[0118] In a fourth aspect, an embodiment of the present disclosure provides a network device, including:

[0119] The second transceiver module is configured to receive first information sent by the terminal through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0120] In a fifth aspect, an embodiment of the present disclosure provides a terminal, including:

[0121] one or more processors;

[0122] The terminal is used to execute the communication method described in any one of the first aspects of this disclosure.

[0123] In a sixth aspect, an embodiment of the present disclosure provides a network device, including:

[0124] one or more processors;

[0125] The network device is used to execute the communication method described in any one of the second aspects of this disclosure.

[0126] In a seventh aspect, an embodiment of the present disclosure provides a communication system, including:

[0127] The invention comprises a terminal and a network device, wherein the terminal is configured to implement the communication method described in any one of the first aspects of the present disclosure, and the network device is configured to implement the communication method described in any one of the second aspects of the present disclosure.

[0128] In an eighth aspect, an embodiment of the present disclosure proposes a storage medium storing instructions. When the instructions are executed on a communication device, the communication device executes a communication method as described in any one of the first aspects of the present disclosure, or the communication device executes a communication method as described in any one of the second aspects of the present disclosure.

[0129] In the ninth aspect, an embodiment of the present disclosure proposes a computer program product, comprising a computer program and / or instructions, which, when executed by a communication device, implement the communication method as described in any one of the first aspects of the present disclosure, or implement the communication method as described in any one of the second aspects of the present disclosure when the computer program and / or instructions are executed by a communication device.

[0130] In the above solution, first information is sent to a network device via first signaling. The first information indicates a first AI function or a first AI model supported by a terminal. The first AI function or model is used to predict the terminal's channel state information (CSI). This enables identification of the AI ​​function or model used for CSI prediction in the communication system, reduces the complexity of AI model or function identification, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process.

[0131] It is understandable that the above-mentioned terminals, network devices, communication systems, storage media, and computer programs are all used to execute the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods and will not be repeated here.

[0132] The present disclosure provides a communication method, terminal, network device, system, and storage medium. In some embodiments, the terms communication method and information processing method are interchangeable, the terms communication device and information processing device are interchangeable, and the terms information processing system and communication system are interchangeable.

[0133] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain 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 certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0134] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0135] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0136] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0137] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0138] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0139] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0140] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0141] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0142] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0143] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0144] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0145] In some embodiments, terms such as "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 less than", and "above" can be replaced with each other, and terms such as "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" can be replaced with each other.

[0146] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0147] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0148] 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", "bandwidth part (BWP)" and the like may be used interchangeably.

[0149] 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, client, etc. can be used interchangeably.

[0150] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0151] 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, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0152] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0153] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0154] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0155] FIG1A is a schematic diagram illustrating an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG1A , a communication system 100 includes a terminal 101 and a network device 102 .

[0156] In some embodiments, the terminal 101 includes, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0157] In some embodiments, the network device 102 is, for example, a node or device that accesses the terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (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 base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a Wi-Fi system, but is not limited thereto.

[0158] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0159] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0160] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0161] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1 , or a portion thereof, but are not limited thereto. The entities shown in FIG1 are illustrative only. The communication system may include all or part of the entities shown in FIG1 , or may include other entities outside of FIG1 . The number and form of the entities are arbitrary, and the entities may be physical or virtual. The connection relationships between the entities are illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0162] The embodiments of the present disclosure 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 (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (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 utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0163] In some embodiments, the new generation Type II codebook uses an autoregressive algorithm or LMMSE (Linear Minimum Mean Square Error) algorithm to predict future downlink channel information based on historical downlink channel information evaluated by the terminal side. The precoding information corresponding to the future time is then calculated based on the predicted downlink channel information. In medium- and high-speed mobility scenarios, the new generation Type II codebook can significantly improve system performance compared to the old generation Type II codebook.

[0164] In some embodiments, with the development of AI (Artificial Intelligence) technology, AI technology has been widely applied to the physical layer of wireless communications. The CSI prediction algorithm in the above example can also use an AI model for inference to predict channel information at future times. Furthermore, the CSI prediction performance of the AI ​​model is superior to that of non-AI algorithms.

[0165] In some embodiments, CSI prediction needs to use the CSI determined by measurements at multiple historical moments, and based on the CSI-RS (Channel State Information-Reference Signal) sent by the NW (Network Side) at multiple historical moments, predict the CSI at multiple future moments. The range of the CSI-RS at multiple historical moments in the time domain is the observation window, and the range of the CSI at multiple future moments in the time domain is the prediction window. For example, Figure 1B is a schematic diagram of the observation window and the prediction window shown in an embodiment of the present disclosure. As shown in Figure 1B, the time domain ranges of the observation window and the prediction window corresponding to different parameter configurations are different. The parameter N indicates that the CSI-RS is sent at N moments in the observation window, that is, there are N CSI-RS in the observation window, for example, N = {4, 5, 8, 10}; the parameter M indicates the time domain interval between adjacent CSI-RS in the observation window, for example, M = {2.5, 4, 5} (slots); the parameter K indicates the CSI predicted at K moments in the prediction window, that is, there are K predicted CSI in the prediction window, for example K = {1, 3, 4}; the parameter D indicates the time domain interval between the CSIs predicted at adjacent moments in the prediction window, for example D = {1, 2.5, 4, 5, 8} (slots); the parameter w d Represents the time domain range of the prediction window in the time domain. Based on the above parameters K and D, w d =K*D, that is, the time domain range of the prediction window in the time domain is the product of parameter K and parameter D.

[0166] It should be noted that in this embodiment, both historical moments and future moments are relative to the current moment. A historical moment can be any moment before the current moment, and a future moment can be any moment after the current moment. Therefore, a historical moment can also be referred to as a previous moment, a past moment, etc., and a future moment can also be referred to as a later moment, a future moment, etc., without limitation in this embodiment.

[0167] For example, different CSI prediction scenarios have different CSI prediction requirements, corresponding to different time intervals between multiple CSI predictions, and different CSI prediction algorithms or CSI prediction AI models. As shown in Figure 1B, these correspond to medium-speed, low-speed, and high-speed mobility scenarios, respectively.

[0168] In some embodiments, the UE (User Equipment) can report the supported AI functions to the NW by reporting capabilities. An AI function supported by the UE may include one or more AI / ML (Machine Learning) models. In the LCM (Life Cyclic Management) process based on function identification, the AI ​​model ID can also be used to report AI functions.

[0169] In some embodiments, the NW may identify the AI ​​model supported by the UE by reporting the AI ​​model ID, and the UE may indicate the supported AI model to the NW through the AI ​​model ID.

[0170] In some embodiments, before performing reasoning using an AI model, corresponding AI model identification needs to be completed first. AI model identification on the UE side includes the following methods:

[0171] (1) Identifying the NW and UE side models in an offline manner. For example, during the offline identification of the AI ​​model, a corresponding model ID can be assigned to the corresponding AI model to distinguish different AI models;

[0172] (2) AI model identification is realized through air interface signaling. For example, the UE can initiate the AI ​​model identification process, and the NW can assist in completing the remaining steps of AI model identification based on the interactive information. During the model identification period, a corresponding AI model ID can be assigned to the corresponding AI model. The NW can also initiate the AI ​​model identification process, and the UE can assist in completing the remaining steps of AI model identification based on the interactive information. During the model identification period, a corresponding AI model ID can also be assigned to the corresponding AI model.

[0173] FIG2A is a schematic diagram of an interaction process of a communication method according to an embodiment of the present disclosure. As shown in FIG2A , the embodiment of the present disclosure relates to a communication method, which is executed by a terminal and a network device, and the method includes:

[0174] In step S2101, the terminal sends first information to the network device via a first signaling.

[0175] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0176] For example, the terminal reports first information to the network device through first signaling. The first information is used to indicate a first AI function or a first AI model supported by the terminal. The first AI function or the first AI model configured in the terminal is used to predict CSI at a future time. By the terminal reporting the AI ​​function or AI model, AI function or AI model identification is implemented in the communication system.

[0177] In some embodiments, when some AI functions or AI models used for CSI prediction cannot be applied due to changes in the terminal's hardware conditions or external network environment, the terminal needs to report the available AI functions or AI models that support CSI prediction under the current network conditions (including hardware conditions and external network environment conditions) to the network device, thereby enabling AI function or AI model identification in the communication system. The terminal determines the available AI functions or AI models under the current network conditions based on channel measurement, performance monitoring, monitoring of its own hardware conditions, etc.

[0178] In some embodiments, the name of the first information is not limited, and it can be, for example, "capability reporting information", "AI parameter information", etc.

[0179] In some embodiments, the first signaling includes at least one of the following: an RRC message, MAC-CE information, and UCI (Uplink Control Information). For example, in this embodiment, the first information in the above embodiment can be carried by at least one of the RRC message, MAC-CE information, and UCI.

[0180] In some embodiments, the first information includes first parameter information. The first parameter information includes at least one of the following:

[0181] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0182] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0183] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0184] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0185] The fifth parameter is used to indicate the time domain range of the prediction window.

[0186] For example, the first information includes first parameter information, and the first parameter information is used to indicate the corresponding first AI function or first AI model. A mapping relationship between multiple parameter information and multiple AI models or multiple AI functions can be configured in the network device and the terminal. When the network environment in which the terminal is located changes, resulting in the inability to apply some AI functions or some AI models used for CSI prediction, and the AI ​​function or AI model needs to be replaced, the first AI function or first AI model that can be used for CSI prediction in the current network environment of the terminal is first determined, and then the first parameter information corresponding to the first AI function or first AI model is determined based on the mapping relationship. The first parameter information is reported to realize the identification of the AI ​​function or AI model.

[0187] Among them, the first parameter N represents the number of CSI-RS in the observation window, which can be a specific value or a range of values. For example, N = {4, 5, 8, 10}. The observation window is the first time domain window of the CSI-RS, and the first time domain window is the historical time domain window corresponding to one or more historical CSI-RS received before the current moment. Among them, the current moment is the moment when the terminal triggers the AI ​​function or AI model recognition. For example, when the terminal determines through data monitoring that the network environment in which the terminal is located has changed, or the corresponding hardware conditions of the terminal have changed, resulting in some AI functions or AI models being unable to be applied, the terminal actively triggers the recognition of the AI ​​function or AI model; optionally, the network device can also send a query signaling to trigger the terminal to perform AI function or AI model recognition.

[0188] The second parameter M represents the time interval between adjacent CSI-RSs within the observation window. The time interval can be a specific time length or a time length range. For example, in this embodiment, the time interval M between adjacent CSI-RSs within the observation window is the same, M = {2.5, 4, 5} (slots), where slots (time period) is a unit time interval;

[0189] The third parameter K represents the number of predicted CSIs within the prediction window. This number can be a specific value or a range of values. For example, K = {1, 3, 4}, where the prediction window is the second time domain window for predicting CSI, and the second time domain window is the future time domain window corresponding to the predicted CSI after the current moment. The predicted CSI is the CSI after the current moment predicted by the AI ​​model.

[0190] The fourth parameter D represents the time interval between predicted CSIs within the prediction window. The time interval can be a specific time length or a time length range. For example, in this embodiment, the time interval D between adjacent predicted CSIs within the prediction window is the same, D = {1, 2.5, 4, 5, 8} (slots).

[0191] The fifth parameter w d , represents the time domain range of the prediction window in the future time period, for example, w d =K*D.

[0192] It should be noted that, based on the above-mentioned first parameter information, different AI models can be distinguished by the presence or absence of part of the first parameter information, wherein the AI ​​models are all AI models for predicting CSI. For example, when applying AI model 1 for CSI prediction, the first parameter N and the second parameter M need to be applied; when applying AI model 2 for CSI prediction, the third parameter K and the fourth parameter D need to be applied. When the terminal uses AI model 1 to predict CSI at a historical moment, and at the current moment, due to changes in the network environment, AI model 1 cannot be applied and needs to be switched to AI model 2 for CSI prediction, the first information can be reported at the current moment to realize the identification of the AI ​​model, wherein the first information includes the third parameter K and the fourth parameter D corresponding to AI model 2.

[0193] Optionally, based on the first parameter information, different parameter values ​​can be set to correspond to different AI models. For example, the following AI model and parameter table 1:

[0194] As shown in Table 1 above, a mapping relationship is established between different parameter values ​​and different AI models. When the terminal reports the AI ​​model, it reports the parameter values ​​corresponding to the AI ​​model, and the network device determines the AI ​​model reported by the terminal based on the parameter values. For example, if the first parameter information includes N=4 and M=2, the network device determines that the AI ​​model reported by the terminal is AI model 2 based on the above table; if the first parameter information includes N=12, the network device determines that the AI ​​model reported by the terminal is AI model 4 based on the above table.

[0195] It should be noted that the first parameter information includes the first parameter N, the second parameter M, the third parameter K, the fourth parameter D and the fifth parameter wd One or more of them, so that the network device can confirm the corresponding AI model from the above mapping relationship based on the first parameter information, and the AI ​​model can be one or more.

[0196] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0197] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0198] The seventh parameter is used to indicate the capability information of the terminal.

[0199] For example, the sixth parameter, C, represents the TDCP value of the terminal. TDCP is measured by the terminal and reported to the network device. The TDCP value describes the current time domain channel changes of the terminal. TDCP values ​​range from 0 to 3. A higher value indicates that more time domain resources are required in the communication system to improve data transmission quality. TDCP = 0 indicates the lowest degree of spectrum resource compensation, while TDCP = 2 or 3 is generally used in harsh communication environments with poor connectivity.

[0200] The seventh parameter A is used to indicate characteristics related to terminal capabilities, such as the ability of the terminal's hardware or software to process AI models.

[0201] Optionally, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval or a phase value interval.

[0202] For example, the TDCP value may correspond to one or more amplitude values ​​or phase values, and may also correspond to one or more amplitude value intervals or phase value intervals.

[0203] In some embodiments, the first information includes first AI model ID information of the first AI model.

[0204] For example, the terminal reports the first AI model ID information, where the first AI model ID information is the model ID of the first AI model. The terminal indicates to the network device the AI ​​model currently available for CSI prediction by reporting the model ID.

[0205] For example, in this embodiment, taking AI functions as an example, the network device does not need to know which AI models are deployed on the terminal. After querying the terminal's capability information, it can determine which AI functions the terminal supports. Each AI function is associated with at least one or more of the following parameters, or each AI function is associated with at least a certain value or a certain range of values ​​for one or more of the following parameters. For example, the following Table 2 shows the different parameters corresponding to the four AI functions.

[0206] The parameter N represents one or more moments in the observation window when N CSI-RS are transmitted, and the corresponding observation window contains N CSI-RS;

[0207] Parameter M represents the time domain interval between adjacent CSI-RSs within the observation window;

[0208] Parameter K, indicates that there are K predicted CSIs in the prediction window;

[0209] The parameter D represents the time domain interval between the CSIs predicted at adjacent moments within the prediction window.

[0210] When the terminal moves at a high speed, the time domain channel experienced by the terminal changes rapidly. At this time, the prediction window w of the AI-based CSI prediction channel AI is d =The value of K*D needs to be smaller to obtain better prediction performance. If the larger prediction window originally used when the terminal's moving speed is slow (such as 3Km / h), such as using AI function 4 for reasoning, the prediction window length is 32, the CSI prediction accuracy that meets the requirements can be obtained with less signaling overhead. However, if the current terminal speed is (60Km / h), the UE still uses the model corresponding to AI function 4 for reasoning, which will result in a decrease in CSI prediction performance. Therefore, the terminal can actively send the AI ​​function that can be used on the terminal side in the current channel environment to the network device through L1 signaling such as UCI (Uplink Control Information). The network device determines the available AI functions in the terminal based on the indication information sent by the terminal, such as the available AI function 1 or function 2. The network device will reconfigure the relevant parameters based on the currently available AI function 1 or AI function 2. Based on the above process, the identification of the currently available AI model is achieved between the terminal and the network device.

[0211] Step S2102: The network device sends third information to the terminal based on the first information, where the third information includes pilot signal resources.

[0212] For example, in this embodiment, the terminal initiates the process of AI function and AI model identification. When the network device determines, based on the received first information, that there are multiple AI models that can be used for CSI prediction in the current terminal, it can configure corresponding pilot signal resources for the terminal and send the pilot signal resources to the terminal, where the pilot signal resources are used to assist the terminal in training or updating the AI ​​model.

[0213] Step S2103: The terminal obtains the AI ​​model training data of the terminal based on the pilot signal resources in the third information.

[0214] For example, the terminal obtains the AI ​​model training data of the terminal based on the pilot signal resource, trains the set AI model configured in the terminal through the AI ​​model training data, and uses the trained second AI model as the AI ​​model currently used for CSI prediction.

[0215] In step S2104, the terminal trains a set AI model of the terminal according to the AI ​​model training data to generate a second AI model. The second AI model is used to predict the CSI of the terminal.

[0216] For example, in this embodiment, the terminal initiates the AI ​​model identification process and sends first information to the network device. This first information indicates a first AI model or first AI function that can be used for CSI prediction under the terminal's current network environment. Optionally, the terminal may report first parameter information and / or second parameter information associated with the CSI prediction AI model. The terminal may also report the value of the first parameter information and / or the value of the second parameter information associated with the CSI prediction AI model.

[0217] The network device configures corresponding pilot signal resources based on the received first information and sends the pilot signal resources to the terminal. The terminal obtains AI model training data for the terminal based on the pilot signal resources, trains a preset AI model configured in the terminal using the AI ​​model training data, and uses the trained second AI model as the AI ​​model currently used for CSI prediction.

[0218] Optionally, in some embodiments, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0219] For example, in this embodiment, after receiving the first information reported by the terminal, the network device determines that the terminal currently has multiple AI models available for CSI prediction. Based on current network performance monitoring, the network device may determine a second AI model from the multiple AI models reported by the terminal as the AI ​​model for current CSI prediction. Optionally, the transmitted third information carries second AI model ID information and pilot signal resources for the AI ​​model. The pilot signal resources are used to instruct the terminal to collect data and train or update the AI ​​model based on the collected AI model data to obtain the second AI model. The second AI model ID information is the model ID assigned by the network device to the second AI model generated for training or updating. It should be noted that the second AI model ID information is associated with the first information, that is, there is a mapping relationship between the second AI model ID information and the first information. For example, referring to Table 1 above, if the first information includes first parameter information, and the first parameter information is N=8 and M=4, then the second AI model ID information associated with the first parameter information is AI model 3.

[0220] Optionally, in some embodiments, the method further comprises:

[0221] The terminal uses the second AI model ID information as the model ID of the second AI model.

[0222] For example, after the pre-set AI model in the terminal is trained to a second AI model based on pilot signal resources through the above embodiment, the second AI model ID information in the third information is used as the model ID of the second AI model, thereby defining the model ID of the trained or updated CSI prediction AI model as the model ID sent by the network device. In other words, when the third information includes a model ID, it indicates that the network device has assigned a corresponding model ID to the AI ​​model performing CSI prediction, and the terminal uses the model ID assigned by the network device as the model ID of the AI ​​model generated after training or updating.

[0223] In some embodiments, the pilot signal resources include CSI-RS resources.

[0224] For example, in this embodiment, the pilot signal resources are CSI-RS resources. For example, the pilot signal resources are the number of CSI-RS resources and the time interval parameters between each CSI-RS resource.

[0225] For example, the AI ​​model for CSI prediction may be associated with the first parameter information and / or the second parameter information. The definition of the first parameter information and / or the second parameter information may refer to the above embodiment and will not be repeated here. For example, four AI models for CSI prediction are trained in the terminal, as shown in Table 3 below:

[0226] (1) The terminal reports the first parameters N, M, K, and D corresponding to each of the four AI models in the table above to the network device. Optionally, the terminal may also report the second parameter information S, C, or A related to each AI model to the network device.

[0227] (2) The network device configures four CSI-RS resources for the terminal according to the received first parameter information and / or second parameter information, and the time domain interval between each CSI-RS resource is 1. Optionally, the network device further indicates the model ID of the AI ​​model as AI model 1.

[0228] (3) The terminal can determine that AI model 1 is recognized between the terminal and the network device based on the received CSI-RS resource configuration or AI model ID. Subsequently, the terminal and the network device can perform LCM of the AI ​​model based on AI model 1.

[0229] In this manner, a terminal sends first information to a network device via first signaling. The terminal then receives third information from the network device, which includes pilot signal resources. Based on the pilot signal resources in the third information, the terminal obtains AI model training data for the terminal. The terminal then trains its predefined AI model based on the AI ​​model training data to generate a second AI model, which is used to predict the terminal's CSI. This enables the identification of an AI function or AI model for CSI prediction in a communication system, reduces the complexity of identifying the AI ​​model or AI function, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process.

[0230] FIG2B is a schematic diagram of an interaction process of a communication method according to an embodiment of the present disclosure. As shown in FIG2B , the embodiment of the present disclosure relates to a communication method, which is executed by a terminal and a network device, and the method includes:

[0231] Step S2201: The network device sends second information through second signaling, where the second information includes pilot signal resources.

[0232] For example, in this embodiment, the network device triggers the AI ​​function or AI model identification process. Based on the performance detection results, the network device sends second information via second signaling. The second information is used to query the terminal for the AI ​​function or AI model currently supported by CSI prediction. The terminal receives the second information, determines a first AI model or first AI function that can be used for CSI prediction in the current network environment, and generates first information based on the first AI model or first AI function. The first information is used to indicate the first AI model or first AI function. Optionally, the first information is the AI ​​model ID of the first AI model or first AI function.

[0233] When a network device needs to call the AI ​​function or AI capability in the terminal, the network device detects the performance of the terminal and obtains the AI ​​function or AI model currently supported by the terminal through signaling query.

[0234] In some embodiments, the second signaling includes at least one of the following: an RRC message, MAC-CE information, and DCI (Downlink Control Information).

[0235] For example, in this embodiment, the network device carries the second information through at least one of an RRC message, MAC-CE information, and DCI.

[0236] Optionally, in some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0237] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0238] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0239] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0240] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0241] The fifth parameter is used to indicate the time domain range of the prediction window.

[0242] For example, the definitions of the first parameter, second parameter, third parameter, fourth parameter, and fifth parameter in this embodiment are the same as those in the above embodiment, and reference can be made to the above embodiment, and no further description is given here. The network device inquires the terminal about the AI ​​model or AI function that currently matches the first parameter information and / or the second parameter information by indicating the first parameter information and / or the second parameter information to the terminal.

[0243] In this embodiment, the network device initiates AI model identification, and the network device sends third information to the terminal, where the third information includes a first parameter. The terminal monitors the current network environment based on the first parameter and determines the currently available first AI model or first AI function based on the monitoring results.

[0244] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0245] For example, the eighth parameter S is used to indicate the channel scenario in which the terminal is currently located. For example, the Uma (Urban Macro) scenario is used to indicate that the terminal is in a channel scenario similar to an outdoor scenario, and the Indoor (indoor) scenario is used to indicate that the terminal is in a channel scenario covered by an indoor cell. Different channel scenarios are indicated by the network device, so that the terminal determines the first AI function or the first AI model for CSI prediction in the current network environment according to the eighth parameter S.

[0246] Step S2202: The terminal obtains the AI ​​model training data of the terminal based on the pilot signal resources in the second information.

[0247] The optional implementation of step S2202 can refer to the optional implementation of step S2203 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0248] In step S2203, the terminal trains a set AI model of the terminal according to the AI ​​model training data to generate a first AI model.

[0249] The optional implementation of step S2203 can refer to the optional implementation of step S2204 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0250] In step S2204, the terminal generates first information according to the first AI model, and sends the first information to the network device through the first signaling.

[0251] For example, the second information includes pilot signal resources. The terminal collects data based on the pilot signal resources to obtain the terminal's AI model training data, and then trains or updates the set AI model in the terminal based on the AI ​​model training data, thereby generating a first AI model for current CSI prediction. The first information is generated based on the first AI model, and the first information is reported to the network device. In the above manner, the network device sends the second information via the second signaling, and the second information includes pilot signal resources. The terminal obtains the terminal's AI model training data based on the pilot signal resources in the second information. The terminal trains the terminal's set AI model based on the AI ​​model training data to generate the first AI model. The terminal generates the first information based on the first AI model and sends the first information to the network device via the first signaling. This implements the AI ​​function or AI model recognition for CSI prediction in the communication system, reduces the complexity of AI model or AI function recognition, improves the CSI prediction accuracy, and reduces the signaling overhead in the CSI prediction process.

[0252] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0253] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" may be used interchangeably. For example, a codebook may be a collection of one or more codewords / precoding matrices.

[0254] In some embodiments, terms such as "uplink", "uplink", "physical uplink" can be interchangeable with each other, and terms such as "downlink", "downlink", "physical downlink" can be interchangeable with each other, and terms such as "side", "sidelink", "side communication", "sidelink communication", "direct connection", "direct link", "direct communication", "direct link communication" can be interchangeable with each other.

[0255] In some embodiments, the terms "downlink control information (DCI)", "downlink (DL) assignment", "DL DCI", "uplink (UL) grant", "UL DCI" and the like may be used interchangeably.

[0256] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, and terms such as "physical uplink shared channel (PUSCH)" and "UL data" can be used interchangeably.

[0257] In some embodiments, the terms "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based" and the like may be used interchangeably.

[0258] In some embodiments, terms such as "synchronization signal (SS)", "synchronization signal block (SSB)", "reference signal (RS)", "pilot", and "pilot signal" can be used interchangeably.

[0259] In some embodiments, terms such as "moment", "time point", "time", and "time position" can be replaced with each other, and terms such as "duration", "period", "time window", "window", and "time" can be replaced with each other.

[0260] In some embodiments, the terms "component carrier (CC)", "cell", "frequency carrier", "carrier frequency" and the like can be used interchangeably.

[0261] In some embodiments, terms such as "resource block (RB)", "physical resource block (PRB)", "sub-carrier group (SCG)", "resource element group (REG)", "PRB pair", "RB pair", "resource element (RE)", and "sub-carrier" can be used interchangeably.

[0262] In some embodiments, the terms "precoding", "precoder", "weight", "precoding weight", "quasi-co-location (QCL)", "transmission configuration indication (TCI) state", "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "the number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angular degree", "antenna", "antenna element", "panel" and the like can be used interchangeably.

[0263] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0264] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0265] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0266] In some embodiments, the determination or judgment can be performed by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values ​​(for example, comparison with a predetermined value), but is not limited thereto.

[0267] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data after receiving it; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the recipient to respond to the content sent.

[0268] The communication method involved in the embodiments of the present disclosure may include at least one of steps S2101 and S2102. For example, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, and step S2101 + step S2102 may be implemented as independent embodiments, but the present invention is not limited thereto.

[0269] In some embodiments, step S2102 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0270] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 .

[0271] FIG3A is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3A , the present disclosure embodiment relates to a communication method, which is executed by a terminal, and the method includes:

[0272] Step S3101: Send first information to a network device via a first signaling.

[0273] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0274] In some embodiments, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0275] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0276] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0277] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0278] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0279] The fifth parameter is used to indicate the time domain range of the prediction window.

[0280] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0281] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0282] The seventh parameter is used to indicate the capability information of the terminal.

[0283] In some embodiments, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0284] In some embodiments, the first information includes first AI model ID information of the first AI model.

[0285] In some embodiments, the first signaling includes at least one of the following: a radio resource control RRC message, a medium access control layer-element MAC-CE information and a UCI.

[0286] In some embodiments, the method further comprises:

[0287] receiving second information sent by the network device through second signaling;

[0288] Based on the second information, the first information is generated.

[0289] In some embodiments, the second signaling includes at least one of the following: an RRC message, MAC-CE information, and DCI.

[0290] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0291] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0292] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0293] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0294] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0295] The fifth parameter is used to indicate the time domain range of the prediction window.

[0296] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0297] In some embodiments, the second information includes a pilot signal resource, and generating the first information based on the second information includes:

[0298] Acquire AI model training data of the terminal based on the pilot signal resource in the second information;

[0299] Training a set AI model of the terminal according to the AI ​​model training data to generate a first AI model;

[0300] First information is generated according to the first AI model.

[0301] In some embodiments, the method further comprises:

[0302] receiving third information sent by the network device, where the third information includes a pilot signal resource;

[0303] Acquire AI model training data of the terminal based on the pilot signal resource in the third information;

[0304] The terminal's set AI model is trained according to the AI ​​model training data to generate a second AI model, which is used to predict the terminal's CSI.

[0305] In some embodiments, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0306] In some embodiments, the method further comprises:

[0307] The second AI model ID information is used as the model ID of the second AI model.

[0308] In some embodiments, the pilot signal resources include CSI-RS resources.

[0309] The optional implementation of step S3101 can refer to the optional implementation of step S2101 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0310] The optional implementation of step S3101 can also refer to the optional implementation of steps S2201-S2204 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0311] In this manner, the terminal uses first signaling to send first information to the network device. The first information indicates a first AI function or a first AI model supported by the terminal. The first AI function or model is used to predict the terminal's channel state information (CSI). This enables identification of the AI ​​function or model used for CSI prediction in the communication system, reduces the complexity of AI model or function identification, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process.

[0312] FIG3B is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3B , the present disclosure embodiment relates to a communication method, which is executed by a terminal and includes:

[0313] Step S3201: Receive second information sent by a network device through a second signaling.

[0314] For example, in this embodiment, the network device triggers the process of AI function or AI model identification. Based on the performance detection results, the network device sends second information through the second signaling. The second information is used to query the AI ​​function or AI model that the terminal currently supports for CSI prediction.

[0315] The optional implementation of step S3201 can refer to the optional implementation of step S2201 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0316] Step S3202: Generate first information based on the second information.

[0317] For example, the terminal receives the second information, determines a first AI model or a first AI function that can be used for CSI prediction in the current network environment, and generates first information based on the first AI model or the first AI function. The first information is used to indicate the first AI model or the first AI function.

[0318] Optionally, in some embodiments, the first information is an AI model ID of a first AI model or a first AI function.

[0319] The optional implementation of step S3202 can refer to the optional implementation of steps S2202 to S2204 in Figure 2B, and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0320] Step S3203: Send first information to the network device via first signaling.

[0321] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0322] For example, the terminal reports first information to the network device through first signaling. The first information is used to indicate a first AI function or a first AI model supported by the terminal. The first AI function or the first AI model configured in the terminal is used to predict CSI at a future time. By the terminal reporting the AI ​​function or AI model, AI function or AI model identification is implemented in the communication system.

[0323] The optional implementation of step S3203 can refer to the optional implementation of step S2204 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0324] Through the above method, the network device initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the CSI prediction accuracy, and reducing the signaling overhead in the CSI prediction process.

[0325] FIG3C is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3C , the present disclosure embodiment relates to a communication method, which is executed by a terminal and includes:

[0326] Step S3301: Send first information to a network device via a first signaling.

[0327] In some embodiments, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0328] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0329] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0330] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0331] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0332] The fifth parameter is used to indicate the time domain range of the prediction window.

[0333] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0334] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0335] The seventh parameter is used to indicate the capability information of the terminal.

[0336] The optional implementation of step S3301 can refer to the optional implementation of step S2101 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0337] Step S3302: Receive third information sent by the network device, where the third information includes pilot signal resources.

[0338] For example, the third information includes pilot signal resources. The terminal collects data based on the pilot signal resources to obtain AI model training data for the terminal. The terminal then trains or updates a preset AI model in the terminal based on the AI ​​model training data, thereby generating a first AI model for current CSI prediction. First information is generated based on the first AI model, and the first information is reported to the network device. Optionally, the first information includes model ID information of the first AI model.

[0339] The optional implementation of step S3302 can refer to the optional implementation of step S2102 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0340] Step S3303: Obtain the AI ​​model training data of the terminal based on the pilot signal resources in the third information.

[0341] The optional implementation of step S3303 can refer to the optional implementation of step S2103 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0342] Step S3304: Train the terminal's set AI model according to the AI ​​model training data to generate a second AI model.

[0343] In some embodiments, the second AI model is used to predict the CSI of the terminal.

[0344] The optional implementation of step S3304 can refer to the optional implementation of step S2104 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0345] Through the above method, the terminal initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the prediction accuracy of CSI, and reducing the signaling overhead in the CSI prediction process.

[0346] FIG3D is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG3D , the present disclosure embodiment relates to a communication method, which is executed by a terminal, and the method includes:

[0347] Step S3401: Receive second information sent by a network device through a second signaling.

[0348] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0349] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0350] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0351] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0352] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0353] The fifth parameter is used to indicate the time domain range of the prediction window.

[0354] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0355] The optional implementation of step S3401 can refer to the optional implementation of step S2201 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0356] Step S3402: Obtain the AI ​​model training data of the terminal based on the pilot signal resources in the second information.

[0357] The optional implementation of step S3402 can refer to the optional implementation of step S2202 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0358] Step S3403: Train the set AI model of the terminal according to the AI ​​model training data to generate a first AI model.

[0359] The optional implementation of step S3403 can refer to the optional implementation of step S2203 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0360] Step S3404: Generate first information based on the first AI model and send the first information to the network device.

[0361] The optional implementation of step S3404 can refer to the optional implementation of step S2204 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0362] Through the above method, the network device initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the CSI prediction accuracy, and reducing the signaling overhead in the CSI prediction process.

[0363] FIG4A is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4A , the present disclosure embodiment relates to a communication method, which is executed by a network device, and the method includes:

[0364] Step S4101: receiving first information sent by a terminal through a first signaling.

[0365] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

[0366] In some embodiments, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0367] A first parameter, which is used to indicate the number of CSI-RSs in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0368] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0369] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0370] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0371] The fifth parameter is used to indicate the time domain range of the prediction window.

[0372] In some embodiments, the first information includes second parameter information, including at least one of the following:

[0373] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0374] The seventh parameter is used to indicate the capability information of the terminal.

[0375] In some embodiments, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0376] In some embodiments, the first information includes first AI model ID information of the first AI model.

[0377] In some embodiments, the first signaling includes at least one of the following: an RRC message, MAC-CE information, and UCI.

[0378] In some embodiments, the method further comprises:

[0379] The second information is sent through the second signaling, where the second information is used to instruct the terminal to report the first AI function or the first AI model based on the second information.

[0380] In some embodiments, the second signaling includes at least one of the following: an RRC message, MAC-CE information, and DCI.

[0381] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0382] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0383] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0384] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0385] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0386] The fifth parameter is used to indicate the time domain range of the prediction window.

[0387] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0388] In some embodiments, the second information includes pilot signal resources.

[0389] In some embodiments, the method further comprises:

[0390] Sending third information to the terminal, where the third information includes pilot signal resources.

[0391] In some embodiments, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0392] In some embodiments, the pilot signal resources include CSI-RS resources.

[0393] The optional implementation of step S4101 can refer to the optional implementation of steps S2101 to S2104 in Figure 2A, and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0394] Through the above method, the network device receives and sends first information, where the first information is used to indicate a first AI function or a first AI model supported by the terminal. The first AI function or the first AI model is used to predict the terminal's channel state information (CSI). This enables identification of the AI ​​function or AI model used for CSI prediction in the communication system, reduces the complexity of AI model or AI function identification, improves CSI prediction accuracy, and reduces signaling overhead during the CSI prediction process.

[0395] FIG4B is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4B , the present disclosure embodiment relates to a communication method, which is executed by a network device, and the method includes:

[0396] Step S4201: sending the second information via the second signaling.

[0397] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0398] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0399] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0400] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0401] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0402] The fifth parameter is used to indicate the time domain range of the prediction window.

[0403] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0404] The optional implementation of step S4201 can refer to the optional implementation of step S2201 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0405] Step S4202: receiving first information sent by the terminal through first signaling.

[0406] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0407] The optional implementation of step S4202 can refer to the optional implementation of steps S2202 to S2204 in Figure 2B, and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0408] Through the above method, the network device initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the CSI prediction accuracy, and reducing the signaling overhead in the CSI prediction process.

[0409] FIG4C is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4C , the embodiment of the present disclosure relates to a communication method, which is executed by a network device. The method includes:

[0410] Step S4301: receiving first information sent by a terminal through a first signaling.

[0411] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0412] In some embodiments, the first information includes first parameter information. The first parameter information includes at least one of the following:

[0413] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0414] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0415] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0416] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0417] The fifth parameter is used to indicate the time domain range of the prediction window.

[0418] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0419] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0420] The seventh parameter is used to indicate the capability information of the terminal.

[0421] The optional implementation of step S4301 can refer to the optional implementation of step S2101 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0422] Step S4302: Send third information to the terminal, where the third information includes pilot signal resources.

[0423] For example, in this embodiment, the terminal initiates the AI ​​model identification process and sends first information to the network device. This first information indicates a first AI model or first AI function that can be used for CSI prediction under the terminal's current network environment. Optionally, the terminal may report first parameter information and / or second parameter information associated with the CSI prediction AI model. The terminal may also report the value of the first parameter information and / or the value of the second parameter information associated with the CSI prediction AI model.

[0424] The network device configures corresponding pilot signal resources based on the received first information and sends the pilot signal resources to the terminal. The terminal obtains AI model training data for the terminal based on the pilot signal resources, trains a preset AI model configured in the terminal using the AI ​​model training data, and uses the trained second AI model as the AI ​​model currently used for CSI prediction.

[0425] The optional implementation of step S4302 can refer to the optional implementation of steps S2102 to S2104 in Figure 2A, and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0426] Through the above method, the terminal initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the prediction accuracy of CSI, and reducing the signaling overhead in the CSI prediction process.

[0427] FIG4D is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG4D , the embodiment of the present disclosure relates to a communication method, which is executed by a network device. The method includes:

[0428] Step S4401: Send second information to the terminal through second signaling, where the second information includes pilot signal resources.

[0429] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0430] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0431] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0432] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0433] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0434] The fifth parameter is used to indicate the time domain range of the prediction window.

[0435] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0436] For example, the second information includes pilot signal resources. The terminal collects data based on the pilot signal resources to obtain AI model training data for the terminal. The terminal then trains or updates a preset AI model in the terminal based on the AI ​​model training data, thereby generating a first AI model for current CSI prediction. First information is generated based on the first AI model, and the first information is reported to the network device. Optionally, the first information includes model ID information of the first AI model.

[0437] The optional implementation of step S4401 can refer to the optional implementation of step S2201 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0438] Step S4402: Receive the first information sent by the terminal.

[0439] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0440] The optional implementation of step S4402 can refer to the optional implementation of steps S2202 to S2204 in Figure 2B, and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0441] Through the above method, the network device initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the CSI prediction accuracy, and reducing the signaling overhead in the CSI prediction process.

[0442] FIG5A is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure. As shown in FIG5A , the embodiment of the present disclosure relates to a communication method, which is executed by a network device and a terminal. The method includes:

[0443] Step S5101: The terminal sends first information to the network device through a first signaling.

[0444] In some embodiments, the first information is used to indicate a first AI function or a first AI model supported by the terminal, where the first AI function or the first AI model is used to predict the CSI of the terminal.

[0445] In some embodiments, the first information includes first parameter information. The first parameter information includes at least one of the following:

[0446] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0447] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0448] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0449] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0450] The fifth parameter is used to indicate the time domain range of the prediction window.

[0451] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0452] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0453] The seventh parameter is used to indicate the capability information of the terminal.

[0454] The optional implementation of step S5101 can refer to the optional implementation of step S2101 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0455] Step S5102: The network device configures pilot signal resources according to the first information and sends the pilot signal resources to the terminal.

[0456] The optional implementation of step S5102 can refer to the optional implementation of step S2102 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0457] In step S5103, the terminal obtains the AI ​​model training data of the terminal based on the pilot signal resources.

[0458] The optional implementation of step S5103 can refer to the optional implementation of step S2103 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0459] In step S5104, the terminal trains a set AI model of the terminal according to the AI ​​model training data to generate a first AI model.

[0460] The optional implementation of step S5104 can refer to the optional implementation of step S2104 in Figure 2A and other related parts in the embodiment involved in Figure 2A, which will not be repeated here.

[0461] Through the above method, the terminal initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the prediction accuracy of CSI, and reducing the signaling overhead in the CSI prediction process.

[0462] FIG5B is a schematic diagram of an interaction flow of a communication method according to an embodiment of the present disclosure. As shown in FIG5B , the embodiment of the present disclosure relates to a communication method, which is executed by a network device and a terminal. The method includes:

[0463] Step S5201: The network device sends second information to the terminal via second signaling.

[0464] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0465] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0466] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0467] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0468] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0469] The fifth parameter is used to indicate the time domain range of the prediction window.

[0470] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0471] The optional implementation of step S5201 can refer to the optional implementation of step S2201 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0472] Step S5202: The terminal obtains the AI ​​model training data of the terminal based on the pilot signal resources in the second information.

[0473] The optional implementation of step S5202 can refer to the optional implementation of step S2202 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0474] In step S5203, the terminal trains a set AI model of the terminal according to the AI ​​model training data to generate a first AI model.

[0475] The optional implementation of step S5203 can refer to the optional implementation of step S2203 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0476] In step S5204, the terminal generates first information according to the first AI model and sends the first information to the network device through the first signaling.

[0477] The optional implementation of step S5204 can refer to the optional implementation of step S2204 in Figure 2B and other related parts in the embodiment involved in Figure 2B, which will not be repeated here.

[0478] Through the above method, the network device initiates the identification process of the AI ​​function or AI model, thereby realizing the identification of the AI ​​function or AI model used for CSI prediction in the communication system, reducing the complexity of AI model or AI function identification, improving the CSI prediction accuracy, and reducing the signaling overhead in the CSI prediction process.

[0479] FIG6A is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG6A , the embodiment of the present disclosure relates to a communication method, which is executed by a network device. The method includes:

[0480] Step S6101: Send first information to the terminal via signaling.

[0481] For example, in this embodiment, the network device sends signaling to query the terminal for the AI ​​function or AI model currently supported by the CSI prediction. Based on the received signaling, the terminal reports the AI ​​function or AI model currently supported by the terminal to the network device, thereby completing the initial identification of the AI ​​function or AI model. When some AI functions or AI models used for CSI prediction in the terminal cannot be applied due to changes in the terminal's hardware conditions or channel environment, the terminal needs to report the currently supported AI functions that can be used for CSI prediction to the network device.

[0482] In some embodiments, the first information is used to instruct the terminal to report available AI functions or AI models to the network device.

[0483] In some embodiments, the network device sends first information to the terminal through at least one of RRC / MAC-CE / UCI signaling based on the results of performance monitoring, thereby instructing the terminal to report available AI functions or AI models, wherein the available AI functions or AI models are used for CSI prediction.

[0484] Through the above method, the network device initiates the CSI prediction AI function or the CSI prediction AI model identification process, which reduces the complexity of AI model or AI function identification, improves the accuracy of CSI prediction, and reduces the signaling overhead in the CSI prediction process.

[0485] FIG6B is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG6B , the embodiment of the present disclosure relates to a communication method, which is executed by a terminal. The method includes:

[0486] Step S6201: Send second information to the network device via signaling.

[0487] For example, in this embodiment, the terminal determines the available AI function or AI model based on the results of channel measurement, performance monitoring, hardware condition monitoring, etc., and reports the second information to the network device through at least one of RRC / MAC-CE / UCI signaling.

[0488] In some embodiments, the second information is used to indicate an AI function or AI model currently available to the terminal, where the AI ​​function or AI model is used to predict CSI.

[0489] In some embodiments, the second information includes configuration parameter information related to the currently available AI function or AI model of the terminal or model ID information of the AI ​​model.

[0490] Through the above method, the terminal initiates the identification process of the CSI prediction AI function or the CSI prediction AI model, which reduces the complexity of AI model or AI function identification, improves the accuracy of CSI prediction, and reduces the signaling overhead in the CSI prediction process.

[0491] FIG6C is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG6C , the embodiment of the present disclosure relates to a communication method, which is executed by a terminal and a network device. The method includes:

[0492] Step S6301: The terminal sends first parameter information and / or second parameter information.

[0493] In some embodiments, first parameter information associated with a CSI prediction AI model is defined, where the first parameter information includes at least one of the following:

[0494] The parameter N indicates that the CSI-RS is sent at N moments in the observation window;

[0495] Parameter M represents the time domain interval between adjacent CSI-RSs within the observation window;

[0496] The parameter K indicates that there are K predicted CSIs in the prediction window;

[0497] The parameter D represents the time domain interval between the CSIs predicted at adjacent moments within the prediction window.

[0498] In some embodiments, second parameter information associated with a CSI prediction AI model is defined, and the second parameter information includes at least one of the following:

[0499] Parameter C: represents the time domain channel correlation of the TDCP, which may correspond to one or more amplitude values ​​or phase values, or one or more amplitude value intervals or phase value intervals;

[0500] Parameter A: Indicates characteristics related to UE capabilities, for example, the ability of UE hardware or software to process AI models.

[0501] For example, the terminal reports first parameter information and / or second parameter information associated with the CSI prediction AI model.

[0502] In some embodiments, the first parameter information includes the value of the first parameter, and the second parameter information includes the value of the second parameter. The value may be a specific numerical value or a corresponding value range.

[0503] Step S6302: The network device configures corresponding pilot signal resources to the terminal according to the first parameter information and / or the second parameter information.

[0504] In some embodiments, the network device also sends the AI ​​model ID associated with the first parameter information and / or the second parameter information to the terminal.

[0505] In step S6303, the terminal collects data based on the pilot signal resources and implements CSI prediction model training based on the collected data.

[0506] In some embodiments, the terminal defines the model ID of the CSI prediction AI model generated by training or updating as the AI ​​model ID sent by the network device.

[0507] Through the above method, the terminal reports parameter information to the network device, and the CSI prediction AI model is trained or updated according to the pilot signal resources configured by the network device, thereby completing the identification of the CSI prediction AI model, reducing the complexity of AI model or AI function identification, improving the accuracy of CSI prediction, and reducing signaling overhead.

[0508] FIG6D is a flow chart of a communication method according to an embodiment of the present disclosure. As shown in FIG6D , the embodiment of the present disclosure relates to a communication method, which is executed by a terminal and a network device. The method includes:

[0509] Step S6401: The network device sends first parameter information and / or second parameter information.

[0510] In some embodiments, first parameter information associated with a CSI prediction AI model is defined, where the first parameter information includes at least one of the following:

[0511] The parameter N indicates that the CSI-RS is sent at N moments in the observation window;

[0512] Parameter M represents the time domain interval between adjacent CSI-RSs within the observation window;

[0513] The parameter K indicates that there are K predicted CSIs in the prediction window;

[0514] The parameter D represents the time domain interval between the CSIs predicted at adjacent moments within the prediction window.

[0515] In some embodiments, a second parameter information associated with a CSI prediction AI model is defined, and the second parameter information includes: a parameter S, which is used to indicate the channel scenario in which the terminal is currently located. For example: an Uma (Urban Macro) scenario is used to indicate that the terminal is in a channel scenario similar to an outdoor scenario, and an Indoor (indoor) scenario is used to indicate that the terminal is in a channel scenario covered by an indoor cell. Different channel scenarios are indicated by the network device, so that the terminal determines the first AI function or the first AI model for CSI prediction in the current network environment according to the parameter S.

[0516] In some embodiments, the terminal indicates the first parameter information and / or the second parameter information through a pilot signal resource.

[0517] Optionally, in some embodiments, the terminal sends the AI ​​model ID associated with the first parameter information and / or the second parameter information to the terminal.

[0518] In step S6402, the terminal collects data based on the received pilot signal resources, and implements CSI prediction model training based on the collected data.

[0519] Optionally, in some embodiments, the terminal defines the model ID of the trained or updated CSI prediction AI model as the AI ​​model ID sent by the network device.

[0520] Through the above method, the network device initiates the AI ​​model query, and the terminal implements the training or update of the CSI prediction AI model based on the pilot signal resources configured by the network device, thereby completing the identification of the CSI prediction AI model, reducing the complexity of AI model or AI function identification, improving the accuracy of CSI prediction, and reducing signaling overhead.

[0521] Figure 7 is a structural diagram of a terminal proposed in an embodiment of the present disclosure. As shown in Figure 7, the terminal 7100 may include: a first transceiver module 7101. In some embodiments, the first transceiver module 7101 is configured to send first information to a network device through a first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal. Optionally, the first transceiver module 7101 is used to perform at least one of the communication steps such as receiving and / or acquiring performed by the terminal 101 in any of the above methods, which will not be repeated here.

[0522] In some embodiments, the first transceiver module 7101 may include a receiving module and a sending module, and the receiving module and the sending module may be separate or integrated.

[0523] In some embodiments, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0524] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0525] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0526] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0527] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0528] The fifth parameter is used to indicate the time domain range of the prediction window.

[0529] In some embodiments, the first information includes second parameter information, and the second parameter information includes at least one of the following:

[0530] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0531] The seventh parameter is used to indicate the capability information of the terminal.

[0532] In some embodiments, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0533] In some embodiments, the first information includes first AI model ID information of the first AI model.

[0534] In some embodiments, the first signaling includes at least one of the following: a radio resource control RRC message, a medium access control layer-element MAC-CE information and uplink control information UCI.

[0535] In some embodiments, the terminal 7100 further includes:

[0536] A first receiving module is configured to receive second information sent by the network device through second signaling;

[0537] The first generating module is configured to generate first information based on second information.

[0538] In some embodiments, the second signaling includes at least one of the following: an RRC message, MAC-CE information, and downlink control information DCI.

[0539] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0540] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0541] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0542] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0543] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0544] The fifth parameter is used to indicate the time domain range of the prediction window.

[0545] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0546] In some embodiments, the second information includes a pilot signal resource, and the first generating module is configured to:

[0547] Acquire AI model training data of the terminal based on the pilot signal resource in the second information;

[0548] Training a set AI model of the terminal according to the AI ​​model training data to generate a first AI model;

[0549] First information is generated according to the first AI model.

[0550] In some embodiments, the terminal 7100 includes a second receiving module, which is configured to:

[0551] receiving third information sent by the network device, where the third information includes a pilot signal resource;

[0552] Acquire AI model training data of the terminal based on the pilot signal resource in the third information;

[0553] The terminal's set AI model is trained according to the AI ​​model training data to generate a second AI model, which is used to predict the terminal's CSI.

[0554] In some embodiments, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0555] In some embodiments, the terminal 7100 further includes a processing module, which is configured to:

[0556] The second AI model ID information is used as the model ID of the second AI model.

[0557] In some embodiments, the pilot signal resources include CSI-RS resources.

[0558] Figure 8 is a schematic diagram of the structure of a network device proposed in an embodiment of the present disclosure. As shown in Figure 8, the network device 8100 may include: a second transceiver module 8101. In some embodiments, the second transceiver module 8101 is configured to receive first information sent by the terminal through a first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal. Optionally, the second transceiver module 8101 is used to perform at least one of the communication steps such as receiving and / or acquiring performed by the network device 102 in any of the above methods, which will not be repeated here.

[0559] In some embodiments, the second transceiver module 8101 may include a receiving module and a sending module, and the receiving module and the sending module may be separate or integrated.

[0560] In some embodiments, the first information includes first parameter information, and the first parameter information includes at least one of the following:

[0561] A first parameter, which is used to indicate the number of CSI-RSs in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0562] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0563] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0564] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0565] The fifth parameter is used to indicate the time domain range of the prediction window.

[0566] In some embodiments, the first information includes second parameter information, including at least one of the following:

[0567] A sixth parameter is used to indicate a time domain channel attribute TDCP value of the terminal;

[0568] The seventh parameter is used to indicate the capability information of the terminal.

[0569] In some embodiments, the TDCP value includes: an amplitude value, a phase value, an amplitude value interval, or a phase value interval.

[0570] In some embodiments, the first information includes first AI model ID information of the first AI model.

[0571] In some embodiments, the first signaling includes at least one of the following: an RRC message, MAC-CE information, and UCI.

[0572] In some embodiments, the network device 8100 includes a first sending module, which is configured to:

[0573] The second information is sent through the second signaling, where the second information is used to instruct the terminal to report the first AI function or the first AI model based on the second information.

[0574] In some embodiments, the second signaling includes at least one of the following: an RRC message, MAC-CE information, and DCI.

[0575] In some embodiments, the second information includes first parameter information, and the first parameter information includes at least one of the following:

[0576] A first parameter, which is used to indicate the number of channel state information reference signals CSI-RS in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before the current moment;

[0577] A second parameter, the second parameter is used to indicate the time interval between adjacent CSI-RSs in the observation window;

[0578] A third parameter is used to indicate the number of predicted CSIs in a prediction window, where the prediction window is a second time domain window for predicting the CSI, and the second time domain window is a time domain window after the current moment;

[0579] A fourth parameter is used to indicate the time interval between adjacent predicted CSIs within the prediction window;

[0580] The fifth parameter is used to indicate the time domain range of the prediction window.

[0581] In some embodiments, the second information includes second parameter information, the second parameter information includes an eighth parameter, and the eighth parameter is used to indicate a channel scenario of the terminal.

[0582] In some embodiments, the second information includes pilot signal resources.

[0583] In some embodiments, the network device 8100 includes a second sending module, which is configured to:

[0584] Sending third information to the terminal, where the third information includes pilot signal resources.

[0585] In some embodiments, the third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

[0586] In some embodiments, the pilot signal resources include CSI-RS resources.

[0587] Figure 9 is a schematic diagram of the structure of a communication device 9100 according to an embodiment of the present disclosure. Communication device 9100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), or a chip, chip system, or processor that supports a network device in implementing any of the above methods. It can also be a chip, chip system, or processor that supports a terminal in implementing any of the above methods. Communication device 9100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0588] As shown in Figure 9, the communication device 9100 includes one or more third processors 9101. The third processor 9101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. Optionally, the communication device 9100 is used to perform any of the above methods. Optionally, one or more third processors 9101 are used to call instructions to cause the communication device 9100 to perform any of the above methods.

[0589] In some embodiments, the communication device 9100 further includes one or more third transceivers 9102. When the communication device 9100 includes one or more third transceivers 9102, the third transceiver 9102 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method, and the third processor 9101 performs at least one of the other steps. In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface may be interchangeable, the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be interchangeable, and the terms receiver, receiving unit, receiver, and receiving circuit may be interchangeable.

[0590] In some embodiments, the communication device 9100 further includes one or more third memories 9103 for storing data. Alternatively, all or part of the third memories 9103 may be located outside the communication device 9100. In an alternative embodiment, the communication device 9100 may include one or more first interface circuits 9104. Optionally, the first interface circuit 9104 is connected to the third memories 9103. The first interface circuit 9104 may be configured to receive data from the third memories 9103 or other devices, and to send data to the third processor 9101 or other devices. For example, the first interface circuit 9104 may read data stored in the third memories 9103 and send the data to the third processor 9101.

[0591] The communication device 9100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 9100 described in the present disclosure is not limited thereto, and the structure of the communication device 9100 may not be limited by FIG. 9 . The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0592] FIG10 is a schematic diagram of the structure of a chip 9200 according to an embodiment of the present disclosure. If the communication device 9100 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 9200 shown in FIG10 , but the present invention is not limited thereto.

[0593] The chip 9200 includes one or more fourth processors 9201. The chip 9200 is configured to execute any one of the above methods.

[0594] In some embodiments, the chip 9200 further includes one or more second interface circuits 9202. The terms interface circuit, interface, and transceiver pins are optionally interchangeable. In some embodiments, the chip 9200 further includes one or more fourth memories 9203 for storing data. Optionally, all or part of the fourth memories 9203 may be located external to the chip 9200. Optionally, the second interface circuit 9202 is connected to the fourth memory 9203. The second interface circuit 9202 can be used to receive data from the fourth memory 9203 or other devices, or to send data to the fourth memory 9203 or other devices. For example, the second interface circuit 9202 can read data stored in the fourth memory 9203 and send the data to the fourth processor 9201.

[0595] In some embodiments, the second interface circuit 9202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the second interface circuit 9202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the second interface circuit 9202 performs data exchange between the fourth processor 9201, the chip 9200, the fourth memory 9203, or the transceiver device. In some embodiments, the fourth processor 9201 performs at least one of the other steps.

[0596] The modules and / or devices described in various embodiments, such as virtual devices, physical devices, and chips, can be arbitrarily combined or separated according to circumstances. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0597] The present disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 9100, causes the communication device 9100 to execute 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 is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a temporary storage medium.

[0598] The present disclosure also provides a program product, which, when executed by the communication device 9100, enables the communication device 9100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0599] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

Claims

1. A communication method, characterized in that: Executed by a terminal, the method includes: First information is sent to a network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

2. The method according to claim 1, characterized in that The first information includes first parameter information, and the first parameter information includes at least one of the following: A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment; A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window; a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment; a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window; A fifth parameter is used to indicate the time domain range of the prediction window.

3. The method according to claim 1 or 2, characterized in that The first information includes second parameter information, and the second parameter information includes at least one of the following: A sixth parameter, used to indicate a time domain channel attribute TDCP value of the terminal; A seventh parameter is used to indicate capability information of the terminal.

4. The method according to claim 3, characterized in that The TDCP value includes: amplitude value, phase value, amplitude value interval or phase value interval.

5. The method according to claim 1, characterized in that The first information includes first AI model ID information of the first AI model.

6. The method according to any one of claims 1 to 5, characterized in that The first signaling includes at least one of the following: a radio resource control RRC message, a medium access control layer-control element MAC-CE information and uplink control information UCI.

7. The method according to claim 1, characterized in that The method further comprises: receiving second information sent by the network device through second signaling; The first information is generated based on the second information.

8. The method according to claim 7, characterized in that The second signaling includes at least one of the following: an RRC message, MAC-CE information and downlink control information DCI.

9. The method according to claim 7, characterized in that The second information includes first parameter information, and the first parameter information includes at least one of the following: A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment; A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window; a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment; a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window; A fifth parameter is used to indicate the time domain range of the prediction window.

10. The method according to claim 7 or 9, characterized in that The second information includes second parameter information, and the second parameter information includes an eighth parameter, where the eighth parameter is used to indicate a channel scenario of the terminal.

11. The method according to claim 10, characterized in that The second information includes a pilot signal resource, and generating the first information based on the second information includes: Acquire AI model training data of the terminal based on the pilot signal resource in the second information; Training the set AI model of the terminal according to the AI ​​model training data to generate the first AI model; Generate the first information according to the first AI model.

12. The method according to any one of claims 1 to 3, characterized in that The method further comprises: receiving third information sent by the network device, where the third information includes a pilot signal resource; Acquire AI model training data of the terminal based on the pilot signal resource in the third information; The set AI model of the terminal is trained according to the AI ​​model training data to generate a second AI model, where the second AI model is used to predict the CSI of the terminal.

13. The method according to claim 12, characterized in that The third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

14. The method according to claim 13, characterized in that The method further comprises: The second AI model ID information is used as the model ID of the second AI model.

15. The method according to claim 11 or 12, characterized in that The pilot signal resources include CSI-RS resources.

16. A communication method, characterized in that: Executed by a network device, the method includes: First information sent by a terminal through first signaling is received, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

17. The method according to claim 16, characterized in that The first information includes first parameter information, and the first parameter information includes at least one of the following: A first parameter, where the first parameter is used to indicate the number of CSI-RSs in an observation window, where the observation window is a first time domain window of the CSI-RS, and the first time domain window is a time domain window before a current moment; A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window; a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment; a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window; A fifth parameter is used to indicate the time domain range of the prediction window.

18. The method according to claim 16 or 17, characterized in that The first information includes second parameter information, including at least one of the following: A sixth parameter, used to indicate a time domain channel attribute TDCP value of the terminal; A seventh parameter is used to indicate capability information of the terminal.

19. The method according to claim 18, characterized in that The TDCP value includes: amplitude value, phase value, amplitude value interval or phase value interval.

20. The method according to claim 16, wherein The first information includes first AI model ID information of the first AI model.

21. The method according to any one of claims 16 to 20, characterized in that The first signaling includes at least one of the following: RRC message, MAC-CE information and UCI.

22. The method according to claim 16, wherein The method further comprises: Second information is sent through second signaling, where the second information is used to instruct the terminal to report the first AI function or the first AI model based on the second information.

23. The method according to claim 22, characterized in that The second signaling includes at least one of the following: RRC message, MAC-CE information and DCI.

24. The method according to claim 22, characterized in that The second information includes first parameter information, and the first parameter information includes at least one of the following: A first parameter, where the first parameter is used to indicate the number of channel state information reference signals (CSI-RSs) in an observation window, where the observation window is a first time domain window of the CSI-RSs, and the first time domain window is a time domain window before a current moment; A second parameter, where the second parameter is used to indicate a time interval between adjacent CSI-RSs in the observation window; a third parameter, the third parameter being used to indicate the amount of predicted CSI within a prediction window, the prediction window being a second time domain window of the predicted CSI, the second time domain window being a time domain window after the current moment; a fourth parameter, the fourth parameter being used to indicate a time interval between adjacent predicted CSIs within the prediction window; A fifth parameter is used to indicate the time domain range of the prediction window.

25. The method according to claim 22 or 24, characterized in that The second information includes second parameter information, and the second parameter information includes an eighth parameter, where the eighth parameter is used to indicate a channel scenario of the terminal.

26. The method according to claim 25, characterized in that The second information includes pilot signal resources.

27. The method according to any one of claims 16 to 18, characterized in that The method further comprises: Sending third information to the terminal, where the third information includes pilot signal resources.

28. The method according to claim 27, characterized in that The third information includes second AI model ID information, and the second AI model ID information is associated with the first information.

29. The method according to claim 26 or 27, characterized in that The pilot signal resources include CSI-RS resources.

30. A terminal, characterized in that: include: The first transceiver module is configured to send first information to the network device through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the channel state information CSI of the terminal.

31. A network device, characterized in that: include: The second transceiver module is configured to receive first information sent by the terminal through first signaling, where the first information is used to indicate a first AI function or a first AI model supported by the terminal, and the first AI function or the first AI model is used to predict the CSI of the terminal.

32. A terminal, characterized in that: include: one or more processors; The terminal is used to execute the communication method according to any one of claims 1 to 15.

33. A network device, characterized in that: include: one or more processors; The network device is used to execute the communication method according to any one of claims 16 to 29.

34. A communication system, characterized in that The invention comprises a terminal and a network device, wherein the terminal is configured to implement the communication method according to any one of claims 1 to 15, and the network device is configured to implement the communication method according to any one of claims 16 to 29.

35. A storage medium storing instructions, characterized in that: When the instruction is executed on a communication device, the communication device is caused to execute the communication method according to any one of claims 1 to 15, or the communication device is caused to execute the communication method according to any one of claims 16 to 29.

36. A computer program product comprising a computer program and / or instructions, characterized in that When the computer program and / or instruction is executed by a communication device, the communication method according to any one of claims 1 to 15 is implemented; or when the computer program and / or instruction is executed by a communication device, the communication method according to any one of claims 16 to 29 is implemented.

Images