Communication method, device, and system, storage medium, and program product

Abstract

The present disclosure provides a communication method, device, and system, a storage medium, and a program product. The method comprises: sending capability information to a network device, the capability information being used for indicating whether a terminal supports model transmission and / or supports a training mode for training an AI model, and the capability information being used by the network device to configure model transmission information for the terminal. In the above embodiment, a terminal may send to a network device capability information, which is used to indicate that the terminal supports model transmission and to indicate a training mode for an AI model supported by the terminal, thereby facilitating the network device in subsequently configuring model transmission information for the AI model for the terminal, ensuring that the terminal can acquire the configured AI model, improving the accuracy of AI model transmission, and ensuring the reliability of subsequent AI-model-based processing.

Description

Communication methods, devices, systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods, devices, systems, storage media, and program products. Background Technology

[0002] Artificial intelligence (AI) models are one of the most important methods for implementing artificial intelligence technology, and they can also be applied to mobile communication systems. AI models can perform functions such as encoding, decoding, and predicting data. Summary of the Invention

[0003] In situations where AI models need to be transmitted between network devices and terminals, how to transmit AI models becomes an urgent problem to be solved.

[0004] This disclosure provides a communication method, device, system, storage medium, and program product.

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

[0006] The network device sends capability information to the network device, the capability information being used to indicate whether the terminal supports model transmission and / or supports training methods for training AI models, wherein the capability information is used by the network device to configure model transmission information for the terminal.

[0007] According to a second aspect of the present disclosure, a communication method is provided, the method being performed by a network device, the method comprising:

[0008] The network device receives capability information sent by the terminal, which indicates whether the terminal supports model transmission and / or supports training methods for training AI models. The capability information is used by the network device to configure model transmission information for the terminal.

[0009] According to a third aspect of the present disclosure, a communication device is provided for performing the communication method described in the first or second aspect.

[0010] According to a fourth aspect of the present disclosure, a communication device is provided, comprising:

[0011] A processing module is used to execute the communication method described in the first or second aspect.

[0012] According to a fifth aspect of the present disclosure, a terminal is provided, comprising: one or more processors; wherein the processors are configured to perform any of the methods described in the first aspect.

[0013] According to a sixth aspect of the present disclosure, a network device is provided, comprising: one or more processors; wherein the processors are configured to perform any of the methods described in the second aspect.

[0014] According to a seventh aspect of the present disclosure, a communication system is provided, comprising: a terminal and a network device, wherein the terminal is configured to implement the communication method described in the first aspect, and the network device is configured to perform the method described in the second aspect.

[0015] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions which, when executed on a communication device, cause the communication device to perform the method as described in any one of the first or second aspects.

[0016] In the above embodiments, the terminal can send capability information to the network device, indicating that the terminal has the ability to support model transmission and the training method of the AI ​​model supported by the terminal, so that the network device can configure the model transmission information of the AI ​​model for the terminal, ensuring that the terminal can obtain the configured AI model, improving the accuracy of AI model transmission and ensuring the reliability of subsequent processing based on the AI ​​model. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0018] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure;

[0019] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure;

[0020] Figure 2B is a schematic diagram of the structure of the second instruction information according to an embodiment of the present disclosure;

[0021] Figure 2C is a schematic diagram of the structure of the second instruction information according to an embodiment of the present disclosure;

[0022] Figure 2D is a schematic diagram of the structure of the second instruction information according to an embodiment of the present disclosure;

[0023] Figure 3 is a flowchart illustrating a communication method according to an embodiment of the present disclosure;

[0024] Figure 4 is a flowchart illustrating a communication method according to an embodiment of the present disclosure;

[0025] Figure 5A is a schematic diagram of the structure of the terminal proposed in an embodiment of this disclosure;

[0026] Figure 5B is a schematic diagram of the structure of the network device proposed in an embodiment of this disclosure;

[0027] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure;

[0028] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0029] This disclosure provides a communication method, device, system, storage medium, and program product.

[0030] In a first aspect, embodiments of this disclosure provide a communication method, the method being executed by a terminal, the method comprising:

[0031] The network device sends capability information to the network device, the capability information being used to indicate whether the terminal supports model transmission and / or supports training methods for training AI models, wherein the capability information is used by the network device to configure model transmission information for the terminal.

[0032] In the above embodiments, the terminal can send capability information to the network device, indicating that the terminal has the ability to support model transmission and the training method of the AI ​​model supported by the terminal, so that the network device can configure the model transmission information of the AI ​​model for the terminal, ensuring that the terminal can obtain the configured AI model, improving the accuracy of AI model transmission and ensuring the reliability of subsequent processing based on the AI ​​model.

[0033] In conjunction with some embodiments of the first aspect, in some embodiments, the training method includes at least one of the following:

[0034] Training based on the dataset;

[0035] Training based on model parameters;

[0036] Training based on the dataset and the model parameters.

[0037] In the above embodiments, the terminal can support at least one of multiple training methods, which expands the types of training methods supported by the terminal and improves the flexibility of the terminal's reporting capabilities.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0039] The network device receives a first configuration message, which is used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier, and the first condition is used to indicate the radiation direction of the network device.

[0040] In the above embodiments, the network device can configure a first condition for the radiation direction corresponding to the AI ​​model for the terminal, ensuring that the terminal can determine whether there is an AI model that meets the first condition, thereby improving the accuracy of the terminal in determining the AI ​​model that meets the first condition.

[0041] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0042] Send a feedback message to the network device, the feedback message indicating at least one of the following:

[0043] Does each AI model configured in the network device satisfy the first condition?

[0044] Whether each AI model configured by the network device meets the second condition, the second condition being used to indicate the conditions required for the terminal to run the AI ​​model;

[0045] Whether the terminal meets the third condition, the third condition is used to indicate whether the terminal stores an AI model that meets the first condition and the second condition.

[0046] In the above embodiments, the terminal can send an indication to the network device whether each AI model meets the corresponding conditions, thereby improving the accuracy of the feedback messages sent by the terminal to the network device.

[0047] In conjunction with some embodiments of the first aspect, in some embodiments, satisfying the first condition includes at least one of the following:

[0048] The downlink tumble angle used between the terminal and the network device is less than or equal to the tumble angle threshold;

[0049] The azimuth angle used between the terminal and the network device is less than or equal to the azimuth angle threshold.

[0050] In the above embodiments, the types of the first condition are expanded, thereby improving the flexibility of configuring the first condition.

[0051] In conjunction with some embodiments of the first aspect, in some embodiments, satisfying the second condition includes at least one of the following:

[0052] The available storage space of the terminal is greater than the storage space threshold of the AI ​​model;

[0053] The power consumption of the terminal running the AI ​​model is less than the energy consumption threshold;

[0054] The AI ​​models supported by the terminal.

[0055] In the above embodiments, the types of second conditions are expanded, thereby improving the flexibility of configuring the second conditions.

[0056] In conjunction with some embodiments of the first aspect, in some embodiments, the feedback message includes: a model identifier that does not satisfy at least one of the first condition, the second condition, or the third condition; and the unsatisfied condition is at least one of the first condition, the second condition, or the third condition; or,

[0057] The feedback message includes multiple first indication messages, each indicating whether the corresponding AI model satisfies at least one of the first condition, the second condition, or the third condition, and each of the multiple first indication messages corresponds to an AI model.

[0058] In the above embodiments, the feedback message includes a model identifier and the corresponding unmet condition, or includes indication information to indicate whether the model meets the condition, thus expanding the ways in which the feedback message supports feedback information.

[0059] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0060] The system receives a second configuration message sent by a network device, the second configuration message being used to configure model transmission information of a first model, the first model being determined from at least one model configured by the network device for the terminal;

[0061] The model transmission information includes at least one of the model parameters or the training dataset.

[0062] In the above embodiments, the network device can transmit configuration model information to the terminal through configuration messages, which can enable the terminal to accurately obtain the first model configured by the network device and ensure the reliability of the obtained first model.

[0063] In conjunction with some embodiments of the first aspect, in some embodiments, the second configuration message is sent when the first model satisfies the first condition and the second condition but the terminal does not satisfy the third condition.

[0064] In the above embodiments, the network device sends a second configuration message when the first model meets the first and second conditions but the terminal does not meet the third condition, thereby improving the accuracy of the network device sending the second configuration message.

[0065] In conjunction with some embodiments of the first aspect, in some embodiments, the model transmission information is determined based on the capability information.

[0066] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0067] Receive a request message sent by the network device, the request message being used to request the capability information.

[0068] In the above embodiments, the network device requests whether the terminal supports model transmission capabilities and the training methods of the AI ​​model supported by the terminal through request messages, thereby improving the accuracy of the terminal's requested capabilities.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, the capability information further includes storage space supported by the terminal for storing AI models;

[0070] The storage space is associated with any of the following:

[0071] The functions of AI models;

[0072] Obtain the terminal type of the AI ​​model;

[0073] The method of sending AI models.

[0074] In the above embodiments, the content associated with the storage space is expanded, thereby improving the flexibility of the content associated with the storage space.

[0075] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0076] The network device receives a third configuration message, which is used to configure measurement resources for training or inference of AI models.

[0077] In the above embodiments, the network device configures measurement resources for the terminal to facilitate the training or inference of AI models and improve the accuracy of subsequent training or inference of AI models.

[0078] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0079] Receive a second indication message sent by the network device, the second indication message being used to activate the measurement resource;

[0080] The second indication information includes at least one of the following:

[0081] Community signage;

[0082] BWP logo;

[0083] Model identifier, which is used to indicate the first model;

[0084] Resource identifier, which is used to indicate the active measurement resource.

[0085] In the above embodiments, the corresponding measurement resources are activated by the second indication information, which improves the accuracy of the activated measurement resources, expands the types of information included in the second indication information, and improves the flexibility of the information included in the second indication information.

[0086] Secondly, embodiments of this disclosure provide a communication method, which is executed by a network device, the method comprising:

[0087] The network device receives capability information sent by the terminal, which indicates whether the terminal supports model transmission and / or supports training methods for training AI models. The capability information is used by the network device to configure model transmission information for the terminal.

[0088] In conjunction with some embodiments of the second aspect, in some embodiments, the training method includes at least one of the following:

[0089] Training based on the dataset;

[0090] Training based on model parameters;

[0091] Training is performed based on the dataset and the model parameters.

[0092] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0093] A first configuration message is sent to the terminal. The first configuration message is used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier. The first condition is used to indicate the radiation direction of the network device.

[0094] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0095] Receive a feedback message sent by the terminal, the feedback message indicating at least one of the following:

[0096] Does each AI model configured in the network device satisfy the first condition?

[0097] Whether each AI model configured by the network device meets the second condition, the second condition being used to indicate the conditions required for the terminal to run the AI ​​model;

[0098] Whether the terminal meets the third condition, the third condition is used to indicate whether the terminal stores an AI model that meets the first condition and the second condition.

[0099] In conjunction with some embodiments of the second aspect, in some embodiments, satisfying the first condition includes at least one of the following:

[0100] The downlink tumble angle used between the terminal and the network device is less than or equal to the tumble angle threshold;

[0101] The azimuth angle used between the terminal and the network device is less than or equal to the azimuth angle threshold.

[0102] In conjunction with some embodiments of the second aspect, in some embodiments, satisfying the second condition includes at least one of the following:

[0103] The available storage space of the terminal is greater than the storage space threshold of the AI ​​model;

[0104] The power consumption of the terminal running the AI ​​model is less than the energy consumption threshold;

[0105] The AI ​​models supported by the terminal.

[0106] In conjunction with some embodiments of the second aspect, in some embodiments, the feedback message includes: a model identifier that does not satisfy at least one of the first condition, the second condition, or the third condition, and the unsatisfied condition is at least one of the first condition, the second condition, or the third condition; or,

[0107] The feedback message includes multiple first indication messages, each indicating whether the corresponding AI model satisfies at least one of the first condition, the second condition, or the third condition, and each of the multiple first indication messages corresponds to an AI model.

[0108] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0109] Send a second configuration message to the terminal. The second configuration message is used to configure the model transmission information of the first model. The first model is determined from at least one model configured by the network device for the terminal.

[0110] The model transmission information includes at least one of the model parameters or the training dataset.

[0111] In conjunction with some embodiments of the second aspect, in some embodiments, the second configuration message is sent when the first model satisfies the first condition and the second condition but the terminal does not satisfy the third condition.

[0112] In conjunction with some embodiments of the second aspect, in some embodiments, the model transmission information is determined based on the capability information.

[0113] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0114] A request message is sent to the terminal, the request message being used to request the capability information.

[0115] In conjunction with some embodiments of the second aspect, in some embodiments, the capability information further includes storage space supported by the terminal for storing AI models;

[0116] The storage space is associated with any of the following:

[0117] The functions of AI models;

[0118] Obtain the terminal type of the AI ​​model;

[0119] The method of sending AI models.

[0120] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0121] A third configuration message is sent to the terminal, the third configuration message being used to configure measurement resources, the measurement resources being used to train or infer AI models.

[0122] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0123] Send a second instruction message to the terminal, the second instruction message being used to activate the measurement resource;

[0124] The second indication information includes at least one of the following:

[0125] Community signage;

[0126] BWP logo;

[0127] Model identifier, which is used to indicate the first model;

[0128] Resource identifier, which is used to indicate the active measurement resource.

[0129] Thirdly, embodiments of this disclosure provide a communication device for performing the communication method described in the first or second aspect.

[0130] Fourthly, embodiments of this disclosure provide a communication device, which includes at least one of a transceiver module and a processing module; wherein the communication device is used to execute an optional implementation of the first aspect or the second aspect.

[0131] Fifthly, embodiments of this disclosure provide a terminal, including: one or more processors; wherein the processors are configured to perform the method described in any one of the first aspects.

[0132] In a sixth aspect, embodiments of this disclosure provide a network device, including: one or more processors; wherein the processors are configured to perform the method described in any one of the second aspects.

[0133] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method as described in any one of the first or second aspects.

[0134] Eighthly, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method as described in either the first or second aspect.

[0135] In a ninth aspect, embodiments of this disclosure provide a computer program that, when run on a communication device, causes the communication device to perform the method described in either the first or second aspect.

[0136] In a tenth aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described in either the first or second aspect.

[0137] It is understood that the aforementioned communication equipment, communication system, storage medium, program product, etc., are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0138] This disclosure provides a communication method, device, system, storage medium, and program product. In some embodiments, the terms communication method, determination method, capability indication method, and model indication method may be used interchangeably.

[0139] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0140] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0141] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0142] In the embodiments disclosed herein, "multiple" refers to two or more.

[0143] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0144] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0145] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.

[0146] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "symbol," the ordinal number preceding "symbol" in "first symbol" and "second symbol" does not restrict the position or order of the "symbols." "First" and "second" do not restrict whether the "symbols" they modify are in the same message, nor do they restrict the order of "first symbol" and "second symbol." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, objects modified by different prefixes can be the same or different. For example, if the descriptive object is a "device," then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the descriptive object is "information," then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0147] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0148] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0149] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0150] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0151] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0152] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0153] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0154] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0155] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0156] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0157] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0158] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0159] Figure 1 is a schematic diagram of the architecture of a sensory system according to an embodiment of the present disclosure.

[0160] As shown in Figure 1, the communication system 100 includes a terminal 101, an access network device 102, and a core network device 103.

[0161] In some embodiments, terminal 101 includes, for example, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home, but is not limited thereto.

[0162] In some embodiments, the access network device 102 may be a node or device that connects a terminal to a wireless network. The access network device may include at least one of the following in a 5G communication system: an evolved Node B (eNB), a next-generation eNB (ng-eNB), a next-generation Node B (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open RAN, a cloud RAN, a base station in other communication systems, and an access node in a Wi-Fi system, but is not limited thereto.

[0163] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0164] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0165] In some embodiments, the core network device 103 may be a single device, including a first network element 1031, a second network element 1032, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element 1031, the second network element 1032, etc. Network elements may be virtual or physical. The core network may include, for example, at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), Next Generation Core (NGC), and 6G Core Network (6GCN).

[0166] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0167] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0168] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0169] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, the embodiments of the present disclosure relate to a communication method, which includes:

[0170] Step S2101: The network device sends a request message to the terminal.

[0171] In some embodiments, the terminal receives a request message sent by the network device.

[0172] In some embodiments, the request message is used to request capability information. This capability information indicates whether the terminal supports model transfer and / or the training methods of the AI ​​model supported by the terminal. Alternatively, the request message is used to request whether the terminal supports model transfer capabilities and the training methods of the AI ​​model supported by the terminal. Or, if the terminal supports model transfer capabilities, the request message requests the training methods of the AI ​​model supported by the terminal.

[0173] Optionally, model transmission refers to the transmission of AI models between network devices and terminals. For example, a network device sends an AI model to a terminal, and the terminal receives the AI ​​model sent by the network device. Alternatively, a terminal sends an AI model to a network device, and the network device receives the AI ​​model sent by the terminal.

[0174] Optionally, the AI ​​model can compress the measurement results on the terminal side and then decompress the compressed results on the network device side. There is a correspondence between the AI ​​model stored on the terminal and the AI ​​model stored on the network device; that is, after the terminal compresses the measurement results using the stored AI model, the AI ​​model stored on the network device needs to support decompressing the compressed measurement results obtained by the terminal to obtain the decompressed measurement results. Alternatively, the AI ​​model can predict the measurement results on the terminal side to obtain the measurement results at future times.

[0175] Optionally, the training method includes at least one of the following:

[0176] (1) Training based on dataset.

[0177] The terminal can acquire a dataset and then train an AI model based on that dataset to obtain an AI model with corresponding capabilities. For example, this AI model on the terminal can compress measurement results or predict measurement results at future moments.

[0178] For example, if the AI ​​model is used to compress measurement results, the dataset includes the measurement results and the actual compressed measurement results. When training the AI ​​model, the measurement results are input into the AI ​​model, and the AI ​​model processes them to obtain the predicted compressed measurement results. Then, the parameters of the AI ​​model are adjusted based on the difference between the actual compressed measurement results and the predicted compressed measurement results to improve the accuracy of the AI ​​model when compressing the measurement results.

[0179] (2) Training based on model parameters.

[0180] Once the terminal acquires the model parameters, it can construct an AI model based on these parameters. The successfully constructed AI model possesses corresponding capabilities. For example, on the terminal side, this AI model can compress measurement results or predict measurement results at future moments.

[0181] (3) Training based on dataset and model parameters.

[0182] In this embodiment, after the terminal obtains the dataset and model parameters, it first constructs an AI model based on the obtained model parameters, and then further trains the successfully constructed AI model based on the dataset to improve the accuracy of the AI ​​model. The method of training the AI ​​model based on the dataset in this embodiment is similar to the training method (1) in the above embodiment, and will not be described again here.

[0183] It should be noted that the names of the request messages are not limited in the embodiments disclosed herein; for example, they may be called capability request messages, capability acquisition messages, etc.

[0184] In step S2102, the terminal sends capability information to the network device.

[0185] In some embodiments, capability information is used to indicate the terminal's support for model transmission and the training methods for training AI models. This capability information is used by the network device to configure model transmission information for the terminal. Alternatively, it can be understood that the capability information is used by the network device to obtain the capabilities supported by the terminal, and subsequently configure the AI ​​model for the terminal based on these known capabilities.

[0186] Optionally, if the terminal supports model transmission, then the terminal also supports the minimum access layer storage space required for model transmission. This minimum storage space is associated with any of the following: the function of the AI ​​model; the type of terminal acquiring the AI ​​model; and the method of sending the AI ​​model.

[0187] For example, if the minimum storage space is associated with the functionality of the AI ​​model, then the minimum storage space corresponding to the functionality of different AI models may be different. Similarly, if the minimum storage space is associated with the type of terminal acquiring the AI ​​model, then the minimum storage space corresponding to different terminals acquiring the AI ​​model may be different. Furthermore, if the minimum storage space is associated with the method of transmitting the AI ​​model, then the minimum storage space corresponding to different transmission methods of different AI models may be different.

[0188] It should be noted that any of the following can be understood as the granularity of the smallest storage space: the function of the AI ​​model; the terminal type for obtaining the AI ​​model; and the method of sending the AI ​​model.

[0189] In some embodiments, the name of the minimum storage space is not limited in this disclosure, and may be, for example, minimum memory, minimum storage capacity, minimum memory capacity, etc.

[0190] In some embodiments, the capability information also includes storage space supported by the terminal for storing AI models. The terminal sends this capability information to the network device to specify the storage space for storing the AI ​​models. It should be noted that the storage space for storing the AI ​​models is larger than the minimum storage space required by the access layer.

[0191] In some embodiments, the storage space is associated with any of the following: the functionality of the AI ​​model; the type of terminal that acquires the AI ​​model; and the method of sending the AI ​​model.

[0192] For example, if storage space is associated with the functionality of an AI model, then the storage space corresponding to the functionality of different AI models may be different. As another example, if storage space is associated with the type of terminal used to acquire the AI ​​model, then the minimum storage space corresponding to different terminal types used to acquire the AI ​​model may be different. Furthermore, if storage space is associated with the method of transmitting the AI ​​model, then the storage space corresponding to different transmission methods of the AI ​​model may be different.

[0193] It should be noted that any of the following can be understood as the granularity of storage space: the function of the AI ​​model; the terminal type for obtaining the AI ​​model; and the method of sending the AI ​​model.

[0194] In some embodiments, the name of the storage space is not limited in this disclosure, and may be, for example, memory, storage capacity, memory capacity, etc.

[0195] It should be noted that the embodiments disclosed herein are illustrated using the example of a terminal supporting model transmission. In another embodiment, the capability information may also indicate that the terminal does not support model transmission, and in this case, the capability information will not indicate that the terminal supports the training method for training AI models.

[0196] In step S2103, the network device sends a first configuration message to the terminal.

[0197] In some embodiments, the terminal receives a first configuration message sent by the network device.

[0198] The first configuration message is used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier. Alternatively, it can be understood as configuring the AI ​​model identifier and the corresponding first condition. Optionally, the first condition can also be understood as the network condition of the network device, or a condition required by the network device. This first condition indicates the radiation direction of the network device.

[0199] It should be noted that the name of the first configuration message is not limited in the embodiments disclosed herein. For example, it may be a conditional configuration message, conditional configuration, etc.

[0200] Step S2104: The terminal sends a feedback message to the network device.

[0201] In some embodiments, the feedback message is used to indicate at least one of the following:

[0202] (1) Does each AI model configured on the network device meet the first condition?

[0203] In this embodiment of the disclosure, the terminal can provide feedback to the network device on whether each of the multiple AI models configured by the network device satisfies the first condition.

[0204] Each AI model configured on the network device corresponds to a required radiation direction, meaning each AI model has a required first condition. The system then determines whether each AI model meets this first condition. For example, if the first condition indicates the radiation direction of the network device, the terminal needs to determine whether the radiation direction required by each AI model is within the radiation direction indicated by the network device. If the required radiation direction is within the indicated radiation direction, the AI ​​model meets the first condition; otherwise, it does not.

[0205] Optionally, satisfying the first condition includes at least one of the following: the downlink tilt angle used between the terminal and the network device is less than or equal to a tilt angle threshold, and the azimuth angle used between the terminal and the network device is less than or equal to an azimuth angle threshold. Each AI model configured by the network device corresponds to a required downlink tilt angle between the terminal and the network device, allowing for subsequent determination of whether the downlink tilt angle between the terminal and the network device meets the requirements of each AI model. Alternatively, each AI model configured by the network device corresponds to a required azimuth angle between the terminal and the network device, allowing for subsequent determination of whether the azimuth angle between the terminal and the network device meets the requirements of each AI model.

[0206] For example, if the downlink tilt angle used between the terminal and the network device is less than or equal to the tilt angle threshold, then the AI ​​model satisfies the first condition. Similarly, if the azimuth angle used between the terminal and the network device is less than or equal to the azimuth angle threshold, then the AI ​​model satisfies the first condition. Furthermore, if both the downlink tilt angle and the azimuth angle used between the terminal and the network device are less than or equal to the azimuth angle threshold, then the AI ​​model satisfies the first condition.

[0207] (2) Whether each AI model configured by the network device meets the second condition, which is used to indicate the conditions required for the terminal to run the AI ​​model.

[0208] Optionally, satisfying the second condition includes at least one of the following: the available storage space of the terminal is greater than the storage space threshold of the AI ​​model, the power consumption of the terminal running the AI ​​model is less than the energy consumption threshold, and the terminal supports AI models.

[0209] In some embodiments, the network device can configure multiple AI models for the terminal, and the terminal will determine whether the second condition is met based on each AI model, thereby determining whether each AI model configured by the network device meets the second condition.

[0210] Optionally, the network device can configure multiple AI models for the terminal. Different AI models may correspond to different storage space thresholds, or they may correspond to the same storage space threshold. The system then determines whether each AI model configured by the network device meets its corresponding storage space threshold.

[0211] In this embodiment, the storage space threshold is not limited, but may be a memory threshold, a capacity threshold, a memory capacity threshold, etc.

[0212] For example, if the available storage space of the terminal is greater than the storage space threshold of the AI ​​model, then the AI ​​model meets the second condition. As another example, if the power consumption of the terminal running the AI ​​model is less than the power consumption threshold, then the AI ​​model meets the second condition. Furthermore, the AI ​​model supported by the terminal can be understood as the AI ​​model that needs to be judged; if the terminal supports this AI model, then the AI ​​model is determined to meet the second condition. It should be noted that the AI ​​model is determined to meet the second condition only when at least two of the above conditions are met simultaneously.

[0213] (3) Whether the terminal meets the third condition. The third condition is used to indicate whether the terminal stores an AI model that meets the first and second conditions.

[0214] In some embodiments, if the terminal determines that both the first and second conditions are met, but the terminal may not have stored an AI model that meets both conditions, then it is determined that the third condition is not met. When the terminal determines that the third condition is not met, it indicates that the AI ​​model that meets both conditions is not stored in the terminal. In this case, the terminal records the model identifier of the AI ​​model that does not meet the third condition. This feedback message indicates which AI model identifiers correspond to AI models that, while meeting the first and second conditions, were not stored in the terminal.

[0215] For example, if the terminal determines that both the first and second conditions are met, and the terminal stores an AI model that meets the first and second conditions, then the terminal is determined to meet the third condition.

[0216] In some embodiments, the feedback message includes: a model identifier that does not meet at least one of the first, second, or third conditions, and the unmet condition is at least one of the first, second, or third conditions. Alternatively, the feedback message includes a model identifier that does not meet at least one of the first, second, or third conditions, and the model identifier that does not meet the condition is at least one of the first, second, or third conditions.

[0217] In this embodiment of the disclosure, each model identifier corresponds to a condition that is not met. Alternatively, it can be understood that the sent feedback message includes the model identifier and the corresponding condition that is not met. For example, model identifier 1 and the first condition that model identifier 1 does not meet. Or, model identifier 2 and the first and third conditions that model identifier 2 does not meet.

[0218] In some embodiments, the feedback message includes multiple first indications, each corresponding to a model that satisfies at least one of a first condition, a second condition, or a third condition, and each of the multiple first indications corresponds to an AI model. Alternatively, the feedback message includes multiple first indications, each with a model identifier that indicates whether the identified model satisfies at least one of a first condition, a second condition, or a third condition.

[0219] Each first indication can correspond to an AI model. Alternatively, each first indication can indicate a model identifier, and it can also be determined whether the model indicated by the model identifier satisfies at least one of the first, second, or third conditions.

[0220] For example, first indication information 1 indicates that model identifier 1 satisfies the first and second conditions but not the third condition. First indication information 2 indicates that model identifier 2 satisfies the first, second, and third conditions.

[0221] It should be noted that in this embodiment of the disclosure, multiple conditions that are met or not met can be pre-defined. For example, the first condition is met and the second condition is met but the third condition is not met; the second condition is met, the first condition, the second condition, and the third condition are met; the third condition is met but the second condition is not met; and the fourth condition is met but the second condition is met. The terminal sends first indication information according to the above four conditions respectively, and determines the model identifier belonging to each condition by the different conditions corresponding to the sent first indication information.

[0222] In this embodiment of the disclosure, each first indication information corresponds to whether at least one of a first condition, a second condition, or a third condition is met, and each condition is associated with a corresponding model identifier. For example, if first indication information 1 corresponds to meeting the first and second conditions but not the third condition, model identifier 1 exists. As another example, if first indication information 2 corresponds to meeting the first, second, and third conditions, model identifiers 2 and 3 exist. As another example, if first indication information 3 corresponds to meeting the first condition but not the second condition, model identifier 4 exists. As another example, if first indication information 4 corresponds to not meeting the first condition but meeting the second condition, model identifiers 5 and 6 exist.

[0223] It should be noted that each of the above situations is an example, and the embodiments disclosed herein do not limit the settings for each situation.

[0224] In step S2105, the network device sends a second configuration message to the terminal.

[0225] In some embodiments, the terminal receives a second configuration message sent by the network device.

[0226] The second configuration message is used to configure the model transmission information of the first model, which is determined from at least one model configured by the network device for the terminal.

[0227] In some embodiments, the model transmission information includes at least one of model parameters or training dataset. Optionally, the model transmission information is determined based on capability information. Wherein, if the terminal supports training based on model parameters, the model transmission information includes model parameters. Alternatively, if the terminal supports training based on a dataset, the model transmission information includes the dataset. Alternatively, if the terminal supports training based on both the dataset and model parameters, the model transmission information includes both model parameters and the dataset.

[0228] In some embodiments, the second configuration message is sent when the first model satisfies the first and second conditions but the terminal does not satisfy the third condition. In this embodiment, since the terminal has determined that the first model satisfies the first and second conditions, but the terminal does not store the first model, the network device needs to send the first model to the terminal. Therefore, the second configuration message is sent to configure the first model.

[0229] In step S2106, the network device sends a third configuration message to the terminal.

[0230] In some embodiments, the terminal receives a third configuration message sent by the network device. Optionally, the third configuration message is carried in an RRC.

[0231] The third configuration message is used to configure measurement resources, which are used for training or inference of AI models. Optionally, the measurement resources include time-domain resources and frequency-domain resources.

[0232] In some embodiments, the network device configures multiple measurement resources via a third configuration message, and subsequently selects to activate one measurement resource. Optionally, the measurement resources include periodic resources, non-periodic resources, etc.

[0233] Optionally, training an AI model refers to training the AI ​​model using a dataset to give it the corresponding capabilities. For example, the AI ​​model may have the ability to compress measurement results or predict measurement results. Optionally, inferring an AI model refers to using the AI ​​model for inference, or in other words, using the AI ​​model. For example, using the AI ​​model to compress measurement results or to predict measurement results.

[0234] In step S2107, the network device sends a second instruction message to the terminal.

[0235] In some embodiments, the terminal receives second indication information sent by the network device. Optionally, the second indication information is carried in a MAC CE.

[0236] The second indication information is used to activate the measurement resource. Optionally, the second indication information includes at least one of the following:

[0237] (1) Community signage.

[0238] Here, the cell indicates a cell used for indication. In this embodiment of the disclosure, the network device activates the cell indicated by the cell identifier through the second indication information.

[0239] (2) BWP (Bandwidth Part) identifier;

[0240] The BWP identifier is used to indicate a BWP. In this embodiment of the disclosure, the network device activates the BWP indicated by the BWP identifier through the second indication information.

[0241] (3) Model identifier, which is used to indicate the first model.

[0242] In this embodiment of the disclosure, after the terminal receives the model identifier included in the second indication information, it can determine that the measurement resource activated by the network device is applied to the first model indicated by the model identifier.

[0243] (4) Resource identifier, which is used to indicate the active measurement resource.

[0244] In this embodiment of the disclosure, the resource identifier may include a TCI (Transmission Configuration Indication) status identifier, a CSI-RS (Channel State Information Reference Signal) resource set identifier, a CSI-IM (Channel State Information Interference Measurement) resource set identifier, or other identifiers used to indicate measurement resources. This embodiment of the disclosure does not limit the specific identifier.

[0245] For example, the second indication information is used to activate a periodic resource, as shown in Figure 2B. As another example, the second indication information is used to activate a non-periodic resource, as shown in Figure 2C. As yet another example, the second indication information can activate a resource associated with a resource identifier, as shown in Figure 2D.

[0246] In step S2108, the terminal trains or infers an AI model based on the activated measurement resources.

[0247] In this embodiment of the disclosure, the terminal can perform measurements based on activated measurement resources to obtain measurement results, and then train or infer AI models based on the obtained measurement results.

[0248] Optionally, if the activated measurement resource is used to train the AI ​​model, after determining the activated measurement resource, the terminal measures the received reference signal based on the measurement resource to obtain the measurement result, and obtains the actual compressed measurement result after the actual compression of the measurement result. Then, the measurement result is input into the AI ​​model to obtain the predicted compressed measurement result, and the AI ​​model is trained based on the difference between the actual compressed measurement result and the predicted compressed measurement result.

[0249] Optionally, if the activated measurement resource is used for AI model inference, after determining the activated measurement resource, the terminal measures the received reference signal based on the measurement resource to obtain the measurement result, compresses the measurement result based on the AI ​​model, and obtains the compressed measurement result. Subsequently, the compressed measurement result can be sent to the network device.

[0250] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0251] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0252] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0253] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0254] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2108. For example, at least one of steps S2101 to S2108 may be implemented as an independent embodiment.

[0255] In some embodiments, at least one of steps S2101 to S2108 is optional, and one or more of these steps may be omitted or substituted in different embodiments. In some embodiments, please refer to the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, which will not be repeated here.

[0256] Figure 3 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3, the present disclosure relates to a communication method, which includes:

[0257] Step S3101: The terminal sends capability information to the network device.

[0258] In some embodiments, the capability information is used to indicate that the terminal supports model transmission and supports training methods for training AI models, wherein the capability information is used by the network device to configure model transmission information for the terminal.

[0259] In some embodiments, the implementation of step S3101 can be referred to the implementation of step S2102 in FIG2A, and will not be repeated here.

[0260] In some embodiments, the training method includes at least one of the following:

[0261] Training based on the dataset;

[0262] Training based on model parameters;

[0263] Training based on the dataset and the model parameters.

[0264] In some embodiments, the method further includes:

[0265] The network device receives a first configuration message, which is used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier, and the first condition is used to indicate the radiation direction of the network device.

[0266] In some embodiments, the method further includes:

[0267] Send a feedback message to the network device, the feedback message indicating at least one of the following:

[0268] Does each AI model configured in the network device satisfy the first condition?

[0269] Whether each AI model configured by the network device meets the second condition, the second condition being used to indicate the conditions required for the terminal to run the AI ​​model;

[0270] Whether the terminal meets the third condition, the third condition is used to indicate whether the terminal stores an AI model that meets the first condition and the second condition.

[0271] In some embodiments, satisfying the first condition includes at least one of the following:

[0272] The downlink tumble angle used between the terminal and the network device is less than or equal to the tumble angle threshold;

[0273] The azimuth angle used between the terminal and the network device is less than or equal to the azimuth angle threshold.

[0274] In some embodiments, satisfying the second condition includes at least one of the following:

[0275] The available storage space of the terminal is greater than the storage space threshold of the AI ​​model;

[0276] The power consumption of the terminal running the AI ​​model is less than the energy consumption threshold;

[0277] The AI ​​models supported by the terminal.

[0278] In some embodiments, the feedback message includes: a model identifier that does not meet at least one of the first condition, the second condition, or the third condition; and the unmet condition is at least one of the first condition, the second condition, or the third condition; or,

[0279] The feedback message includes multiple first indication messages, each indicating whether the corresponding AI model satisfies at least one of the first condition, the second condition, or the third condition, and each of the multiple first indication messages corresponds to an AI model.

[0280] In some embodiments, the method further includes:

[0281] The system receives a second configuration message sent by a network device. The second configuration message is used to configure model transmission information of a first model, which is determined from at least one model configured by the network device for the terminal. The model transmission information includes at least one of model parameters or training dataset.

[0282] In some embodiments, the second configuration message is sent when the first model satisfies the first and second conditions but the terminal does not satisfy the third condition.

[0283] In some embodiments, the model transmission information is determined based on the capability information.

[0284] In some embodiments, the method further includes:

[0285] The terminal receives a request message sent by the network device. The request message is used to request whether the terminal supports the ability to transmit models and the training methods of the AI ​​models supported by the terminal. The capability information is sent after the terminal receives the request message.

[0286] In some embodiments, the capability information may also include storage space supported by the terminal for storing AI models;

[0287] The storage space is associated with any of the following:

[0288] The functions of AI models;

[0289] Obtain the terminal type of the AI ​​model;

[0290] The method of sending AI models.

[0291] In some embodiments, the method further includes:

[0292] The network device receives a third configuration message, which is used to configure measurement resources for training or inference of AI models.

[0293] In some embodiments, the method further includes:

[0294] Receive a second indication message sent by the network device, the second indication message being used to activate the measurement resource;

[0295] The second indication information includes at least one of the following:

[0296] Community signage;

[0297] BWP logo;

[0298] Model identifier, which is used to indicate the first model;

[0299] Resource identifier, which is used to indicate the active measurement resource.

[0300] Step S3102: The network device receives capability information sent by the terminal.

[0301] In some embodiments, the implementation of step S3102 can be found in the implementation of step S2102 in FIG2A, and will not be repeated here.

[0302] The training method includes at least one of the following:

[0303] Training based on the dataset;

[0304] Training based on model parameters;

[0305] Training based on the dataset and the model parameters.

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

[0307] A first configuration message is sent to the terminal. The first configuration message is used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier. The first condition is used to indicate the radiation direction of the network device.

[0308] In some embodiments, the method further includes:

[0309] Receive a feedback message sent by the terminal, the feedback message indicating at least one of the following:

[0310] Does each AI model configured in the network device satisfy the first condition?

[0311] Whether each AI model configured by the network device meets the second condition, the second condition being used to indicate the conditions required for the terminal to run the AI ​​model;

[0312] Whether the terminal meets the third condition, the third condition is used to indicate whether the terminal stores an AI model that meets the first condition and the second condition.

[0313] In some embodiments, satisfying the first condition includes at least one of the following:

[0314] The downlink tumble angle used between the terminal and the network device is less than or equal to the tumble angle threshold;

[0315] The azimuth angle used between the terminal and the network device is less than or equal to the azimuth angle threshold.

[0316] In some embodiments, satisfying the second condition includes at least one of the following:

[0317] The available storage space of the terminal is greater than the storage space threshold of the AI ​​model;

[0318] The power consumption of the terminal running the AI ​​model is less than the energy consumption threshold;

[0319] The AI ​​models supported by the terminal.

[0320] In some embodiments, the feedback message includes: a model identifier that does not satisfy at least one of the first condition, the second condition, or the third condition; and the unsatisfied condition is at least one of the first condition, the second condition, or the third condition; or,

[0321] The feedback message includes multiple first indication messages, each indicating whether the corresponding AI model satisfies at least one of the first condition, the second condition, or the third condition, and each of the multiple first indication messages corresponds to an AI model.

[0322] In some embodiments, the method further includes:

[0323] Send a second configuration message to the terminal. The second configuration message is used to configure the model transmission information of the first model. The first model is determined from at least one model configured by the network device for the terminal.

[0324] The model transmission information includes at least one of the model parameters or the training dataset.

[0325] In some embodiments, the second configuration message is sent when the first model satisfies the first and second conditions but the terminal does not satisfy the third condition.

[0326] In some embodiments, the model transmission information is determined based on the capability information.

[0327] In some embodiments, the method further includes:

[0328] A request message is sent to the terminal, the request message being used to request whether the terminal supports the ability to transmit models and the training methods of the AI ​​models supported by the terminal, wherein the capability information is sent after the terminal receives the request message.

[0329] In some embodiments, the capability information may also include storage space supported by the terminal for storing AI models;

[0330] The storage space is associated with any of the following:

[0331] The functions of AI models;

[0332] Obtain the terminal type of the AI ​​model;

[0333] The method of sending AI models.

[0334] In some embodiments, the method further includes:

[0335] A third configuration message is sent to the terminal, the third configuration message being used to configure measurement resources, the measurement resources being used to train or infer AI models.

[0336] In some embodiments, the method further includes:

[0337] Send a second instruction message to the terminal, the second instruction message being used to activate the measurement resource;

[0338] The second indication information includes at least one of the following:

[0339] Community signage;

[0340] BWP logo;

[0341] Model identifier, which is used to indicate the first model;

[0342] Resource identifier, which is used to indicate the active measurement resource.

[0343] Figure 4 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4, the present disclosure relates to a communication method, which includes:

[0344] Step S4101: The network device requests the UE to report its capabilities.

[0345] In particular, step S4101 is similar to step S2101 above, in which the network device sends a request message to request whether the terminal supports the ability to transmit models and the training method of the AI ​​model supported by the terminal.

[0346] In step S4102, the UE reports the model training methods it supports.

[0347] In particular, step S4102 is similar to the terminal sending capability information in step S2102 above.

[0348] In some embodiments, a UE that supports model transmission must also support the minimum access layer storage space required for model transmission. The granularity of the minimum storage space can be defined by use case, by UE, or by model transmission method. This minimum storage space can be combined with or separately counted from the minimum storage space used for data collection.

[0349] In some embodiments, UEs that support model transmission can optionally report the amount of access layer memory required for model transmission (greater than the minimum storage space). The granularity of the reported memory can be defined by use case, by UE, or by model transmission method.

[0350] Step S4103: Configure network conditions and supported configurations on the network device, and include the associated ID.

[0351] In particular, step S4103 is similar to step S2103 in the above embodiment, where the network device sends a first configuration message to configure the terminal and the first condition corresponding to the AI ​​model indicated by at least one AI model identifier.

[0352] In step S4104, the terminal sends the model association ID to the network device.

[0353] The terminal reports the model association ID in the following manner:

[0354] 1) The network-side conditions and UE-side conditions are met, and there is a usable model.

[0355] 2) Meets both network-side and UE-side conditions, but no available model.

[0356] 3) Meets network-side conditions but not UE-side conditions

[0357] 4) Meets UE-side conditions but not network-side conditions

[0358] Alternatively, the UE can indicate the reason for the lack of support in the reported message:

[0359] 1) No available model

[0360] 2) The UE-side conditions are not met.

[0361] 3) Network-side conditions are not met.

[0362] Step S4104 is similar to step S2104 in the above embodiment.

[0363] In step S4105, the network device selects a suitable model that meets the UE's requirements based on the capabilities and information reported by the UE in steps S4102 and S4104, and triggers model transmission.

[0364] Step S4105 is similar to step S2105 in the above embodiment.

[0365] Step S4106: The network device activates radio resource measurement using MAC CE.

[0366] In some embodiments, wireless resource measurement is used for training and inference data collection.

[0367] Step S4106 is similar to step S2107 in the above embodiment.

[0368] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0369] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0370] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0371] Figure 5A is a schematic diagram of the terminal structure proposed in an embodiment of this disclosure. Terminal 5100 is used to execute any of the above methods. In some embodiments, as shown in Figure 5A, terminal 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, transceiver module 5101 is used to send capability information to the network device, the capability information indicating that the terminal supports model transmission and supports training methods for training AI models, wherein the capability information is used by the network device to configure model transmission information for the terminal.

[0372] Figure 5B is a schematic diagram of the structure of a network device proposed in an embodiment of this disclosure. The network device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the network device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the transceiver module 5201 is used to receive capability information sent by a terminal, the capability information indicating that the terminal supports model transmission and supports training methods for training AI models, wherein the capability information is used by the network device to configure model transmission information for the terminal.

[0373] Optionally, the transceiver module described above is used to perform at least one of the communication steps such as sending and / or receiving performed by the terminal in any of the above methods, which will not be elaborated here. Optionally, the processing module described above is used to perform at least one of the other steps performed by the terminal in any of the above methods, which will not be elaborated here.

[0374] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a sensing function device, a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0375] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control sensing devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0376] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above-described method, and the processor 6101 performs at least one of the other steps. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0377] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In an optional embodiment, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6102 and can be used to receive data and / or instructions from the memory 6102 or other devices, and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and send the data and / or instructions to the processor 6101.

[0378] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (6) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (7) others, etc.

[0379] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0380] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0381] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.

[0382] In some embodiments, the interface circuit 6202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the interface circuit 6202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the interface circuit 6202 performs data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of the other steps.

[0383] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0384] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0385] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0386] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0387] The terminal can send capability information to the network device, indicating that the terminal has the ability to support model transmission and the training method of the AI ​​model supported by the terminal. This allows the network device to configure the AI ​​model transmission information for the terminal, ensuring that the terminal can obtain the configured AI model, improving the accuracy of AI model transmission and ensuring the reliability of subsequent processing based on the AI ​​model.

Claims

1. A communication method characterized by comprising: The method is performed by a terminal, and the method comprises: sending capability information to the network device, the capability information being used to indicate whether the terminal supports model transmission and / or a training manner in which the terminal supports training of an artificial intelligence (AI) model, wherein the capability information is used for the network device to configure model transmission information for the terminal.

2. The method of claim 1, wherein, The training manner comprises at least one of: training based on a data set; training based on model parameters; and training based on the data set and the model parameters.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: receiving a first configuration message sent by the network device, the first configuration message being used to configure a first condition corresponding to an AI model indicated by at least one AI model identifier, the first condition being used to indicate a radiation direction of the network device.

4. The method of claim 3, wherein, The method further comprises: sending a feedback message to the network device, the feedback message being used to indicate at least one of: whether each AI model configured by the network device meets the first condition; whether each AI model configured by the network device meets a second condition, the second condition being used to indicate a condition required by the terminal for running the AI model; and whether the terminal meets a third condition, the third condition being used to indicate whether the terminal stores an AI model meeting the first condition and the second condition.

5. The method of claim 4, wherein, The meeting of the first condition comprises at least one of: an adopted downlink inclination angle between the terminal and the network device being less than or equal to an inclination angle threshold value; and an adopted azimuth angle between the terminal and the network device being less than or equal to an azimuth angle threshold value.

6. The method of claim 5, wherein, The meeting of the second condition comprises at least one of: an available storage space of the terminal being greater than a storage space threshold value of the AI model; a power consumption of the terminal for running the AI model being less than an energy consumption threshold value; and an AI model supported by the terminal.

7. The method of claim 5 or 6, wherein: the feedback message comprises: model identifiers that do not meet at least one of the first condition, the second condition or the third condition, and the condition that is not met is at least one of the first condition, the second condition or the third condition; or the feedback message comprises a plurality of first indication information, each first indication information indicating whether a corresponding AI model meets at least one of the first condition, the second condition or the third condition, and each first indication information in the plurality of first indication information has a corresponding relationship with an AI model.

8. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: receiving a second configuration message sent by the network device, the second configuration message being used to configure model transmission information of a first model, the first model being determined from at least one model configured by the network device for the terminal; wherein the model transmission information comprises at least one of model parameters or a training data set.

9. The method of claim 8, wherein, The second configuration message is sent in a case where the first model meets the first condition and the second condition but the terminal does not meet the third condition.

10. The method according to any one of claims 1 to 9, characterized in that, The method further comprises: receiving a request message sent by the network device, the request message being used to request the capability information.

11. The method according to any one of claims 1 to 10, characterized in that, The capability information further comprises a storage space supported by the terminal for storing the AI model. The storage space is associated with any of the following: Function of the AI model; Terminal type for obtaining the AI model; Transmission mode of the AI model.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: receiving a third configuration message sent by the network device, the third configuration message being used for configuring a measurement resource, and the measurement resource being used for training or inference of the AI model.

13. The method of claim 12, wherein, The method further includes: receiving second indication information sent by the network device, the second indication information being used for activating the measurement resource; The second indication information includes at least one of the following: Cell identification; Bandwidth part (BWP) identification; Model identification, the model identification being used for indicating the first model; Resource identification, the resource identification being used for indicating the activated measurement resource.

14. A communication method, comprising: The method is performed by a network device, and the method includes: receiving capability information sent by a terminal, the capability information being used for indicating whether the terminal supports model transmission and / or a training mode in which the terminal trains an AI model, wherein the capability information is used for the network device to configure model transmission information for the terminal.

15. The method of claim 14, wherein, The training mode includes at least one of the following: Training based on a data set; Training based on model parameters; Training based on the data set and the model parameters.

16. The method according to claim 14 or 15, characterized in that The method further includes: sending a first configuration message to the terminal, the first configuration message being used for configuring a first condition corresponding to an AI model indicated by at least one AI model identification, and the first condition being used for indicating a radiation direction of the network device.

17. The method of claim 16, wherein, The method further includes: receiving a feedback message sent by the terminal, the feedback message being used for indicating at least one of the following: Whether each AI model configured by the network device meets the first condition; Whether each AI model configured by the network device meets a second condition, the second condition being used for indicating a condition required by the terminal for running the AI model; Whether the terminal meets a third condition, the third condition being used for indicating whether the terminal stores an AI model meeting the first condition and the second condition.

18. The method of claim 17, wherein, The first condition includes at least one of the following: An adopted downlink tilt angle between the terminal and the network device is less than or equal to a tilt angle threshold value; An adopted azimuth angle between the terminal and the network device is less than or equal to an azimuth angle threshold value.

19. The method of claim 18, wherein, The second condition includes at least one of the following: Available storage space of the terminal is greater than a storage space threshold value of the AI model; Power consumption of the terminal for running the AI model is less than an energy consumption threshold value; The terminal supports an AI model corresponding to the second condition.

20. The method of claim 18 or 19, wherein, The feedback message includes: model identification that does not meet at least one of the first condition, the second condition, or the third condition, and the condition that does not meet is at least one of the first condition, the second condition, or the third condition; or The feedback message includes a plurality of first indication information, each first indication information indicating whether a corresponding model meets at least one of the first condition, the second condition, or the third condition, and each first indication information in the plurality of first indication information has a corresponding relationship with an AI model.

21. The method of any one of claims 14 to 20, wherein, The method further includes: The second configuration message is sent to the terminal, and the second configuration message is used to configure model transmission information of a first model determined from at least one model configured by the network device for the terminal. The model transmission information includes at least one of model parameters or a training data set.

22. The method of claim 21, wherein, The second configuration message is sent when the first model meets first and second conditions but the terminal does not meet a third condition.

23. The method of any one of claims 14 to 22, wherein, The method further includes: sending a request message to the terminal, the request message being used to request the capability information.

24. The method of any one of claims 14 to 23, wherein, The capability information further includes storage space supported by the terminal for storing an AI model. The storage space is associated with any of the following: a function of the AI model; a terminal type for obtaining the AI model; a transmission mode of the AI model.

25. The method of any one of claims 14 to 24, wherein, The method further includes: sending a third configuration message to the terminal, the third configuration message being used to configure measurement resources for training or inferring an AI model.

26. The method of claim 25, wherein, The method further includes: sending second indication information to the terminal, the second indication information being used to activate the measurement resources; The second indication information includes at least one of the following: a cell identifier; a BWP identifier; a model identifier used to indicate the first model; a resource identifier used to indicate the activated measurement resources.

27. A communications device, characterized by The communication device includes: a transceiver configured to send capability information to the network device, the capability information being used to indicate whether the terminal supports model transmission and / or supports a training mode for training an AI model, wherein the capability information is used by the network device to configure model transmission information for the terminal.

28. A communications device, characterized by The communication device includes: a transceiver configured to receive capability information sent by a terminal, the capability information being used to indicate whether the terminal supports model transmission and / or supports a training mode for training an AI model, wherein the capability information is used by the network device to configure model transmission information for the terminal.

29. A communications device, comprising: The communication device is configured to perform the method of any one of claims 1 to 13 or any one of claims 14 to 26.

30. A communication system including a terminal and a network device, wherein: the terminal is configured to implement the method of any one of claims 1 to 13; the network device is configured to implement the method of any one of claims 14 to 26.

31. A storage medium storing instructions, wherein: when the instructions are run on a communication device, the communication device is caused to perform any one of claims 1 to 13 or any one of claims 14 to 26; 32. A program product comprising at least one of a program, instructions, wherein, at least one of the program and the instructions is executed by a communication device to implement the method of any one of claims 1 to 13 or any one of claims 14-26.

Images