Communication methods, communication device, communication system, storage medium and program product

Abstract

The present disclosure relates to communication methods, a communication device, a communication system, a storage medium and a program product. A method comprises: sending first information to a second device, wherein the first information is used for downloading a model and / or requesting model training; and receiving second information sent by the second device, wherein the second information is response information of the first information. That is, a first device can send the first information to the second device, so as to download the model from the second device or request the second device to train the model, thereby implementing the use of the model on the first device, and improving the processing efficiency and reliability of the first device.

Description

Communication methods, communication equipment, communication systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, communication system, storage medium, and program product. Background Technology

[0002] Non-terrestrial Network (NTN) is an important technology introduced in 5G (5th generation mobile communication technology). NTN provides wireless resources through satellites (or drones) instead of terrestrial base stations. Satellite signal processing methods are divided into transparent transmission mode and regenerative mode. In transparent transmission mode, satellites can perform frequency conversion and signal amplification without signal modulation, while in regenerative mode, satellites can perform signal modulation. Summary of the Invention

[0003] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0004] According to a first aspect of the present disclosure, a communication method is provided, performed by a first device, the method comprising:

[0005] Send first information to the second device, the first information being used to download the model and / or request training of the model;

[0006] Receive second information sent by the second device, wherein the second information is a response to the first information.

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

[0008] Receive first information sent by the first device, the first information being used to download the model and / or request training the model;

[0009] Send a second message to the first device, the second message being a response to the first message.

[0010] According to a third aspect of the embodiments of this disclosure, a communication device is provided that can be used to perform the methods described in an optional implementation of the first or second aspect.

[0011] According to a fourth aspect of the present disclosure, a communication system is provided, including a first device and a second device, wherein the first device is configured to perform a method as described in an optional implementation of the first aspect, and the second device is configured to perform a method as described in an optional implementation of the second aspect.

[0012] According to a fifth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform the method as described in an optional implementation of the first or second aspect.

[0013] According to a sixth aspect of the present disclosure, a program product is provided, including at least one of a program and instructions, wherein the program and instructions, when executed by a communication device, implement the method described in an optional implementation of the first or second aspect.

[0014] The technical solution provided in this disclosure can produce the following beneficial effects: sending first information to a second device, the first information being used to download a model and / or request training of a model; receiving second information sent by the second device, the second information being response information to the first information. In other words, the first device can send first information to the second device to download a model from the second device or request training of a model from the second device, thereby enabling the use of the model on the first device and improving the processing efficiency and reliability of the first device.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0016] 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.

[0017] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0018] Figure 1B is a schematic diagram of an NTN network according to an embodiment of the present disclosure.

[0019] Figure 1C is a schematic diagram illustrating a transparent transmission mode according to an embodiment of the present disclosure.

[0020] Figure 1D is a schematic diagram illustrating a regeneration mode according to an embodiment of the present disclosure.

[0021] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0022] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

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

[0024] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0025] Figure 4A is a schematic diagram of a model deployment of a regeneration mode according to an embodiment of the present disclosure.

[0026] Figure 4B is a schematic diagram of a model deployment of a regeneration mode according to an embodiment of the present disclosure.

[0027] Figure 4C is a schematic diagram of the lifecycle of an NTN network according to an embodiment of the present disclosure.

[0028] Figure 4D is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0029] Figure 4E is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0030] Figure 5A is a schematic diagram of the structure of a first device according to an embodiment of this disclosure.

[0031] Figure 5B is a schematic diagram of the structure of a second device proposed in an embodiment of this disclosure.

[0032] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure.

[0033] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0034] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0035] In a first aspect, embodiments of this disclosure provide a communication method executed by a first device, the method comprising:

[0036] Send first information to the second device, the first information being used to download the model and / or request training of the model;

[0037] Receive second information sent by the second device, wherein the second information is a response to the first information.

[0038] In the above embodiments, the first device can send first information to the second device to download a model from the second device or request the second device to train the model, thereby enabling the model to be used on the first device and improving the processing efficiency and reliability of the first device.

[0039] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following:

[0040] The first request is used to request the download of the first model;

[0041] The second request is used to request the second device to train the second model;

[0042] The first function includes the functions supported by the first model and / or the second model;

[0043] The first identifier includes the identifier of the first model and / or the identifier of the second model;

[0044] First auxiliary information, which is used to assist the second device in determining the first model.

[0045] In the above embodiments, the first device can download the model from the second device or request the second device to train the model in various ways, so that the accuracy of model selection is higher, thereby further improving the processing efficiency and reliability of the first device.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, the first auxiliary information includes at least one of the following:

[0047] Satellite orbital information;

[0048] Satellite ephemeris information;

[0049] Satellite computing power information;

[0050] Satellite storage space information;

[0051] The coverage area of ​​the first model.

[0052] In the above embodiments, the second device can determine the first model based on satellite-related information and / or the coverage area of ​​the first model, making the determined first model more accurate, thereby further improving the processing efficiency and reliability of the first device.

[0053] In conjunction with some embodiments of the first aspect, in some embodiments, the second information includes at least one of the following:

[0054] The first model;

[0055] The area of ​​application of the first model;

[0056] The usage time of the first model;

[0057] A first indication is used to indicate whether the second device trains the second model.

[0058] In the above embodiments, when the first device requests to download the model, the second device may send the first model and / or information related to the first model to the first device. When the first device requests the second device to train the model, the second device may inform the first device whether to train the second model.

[0059] In conjunction with some embodiments of the first aspect, in some embodiments, the area of ​​use includes at least one of the following:

[0060] Geographical location;

[0061] List of community signs;

[0062] Tracking region identifier (TAI) list;

[0063] Coverage area.

[0064] In the above embodiments, the usage area of ​​the first model can be indicated in a variety of ways, so that the first device can use the first model in a suitable area, thereby further improving the processing efficiency and reliability of the first device.

[0065] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0066] The device receives third information sent by the second device, the third information being used to indicate the second device's support capability for the model.

[0067] In the above embodiments, the second device can inform the first device of its support capabilities for the model so that the first device can make model-related decisions.

[0068] In conjunction with some embodiments of the first aspect, in some embodiments, the third information includes at least one of the following:

[0069] The second indication is used to indicate whether a third model is available;

[0070] The third indication is used to indicate whether model training is supported;

[0071] The fourth indication is used to indicate the satellite scenario supported by the third model and / or the model training;

[0072] The second function includes the third model and / or the function that supports model training.

[0073] The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

[0074] In the above embodiments, the third information may include a variety of different information, thereby improving the decision-making ability of the first device.

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

[0076] The decision to send the first information to the second device is determined based on the third information.

[0077] In the above embodiments, the first device can determine whether to send the first information to the second device based on the third information. This can avoid the first device sending invalid first information, thereby saving signaling overhead.

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

[0079] Receive the second auxiliary information sent by the second device;

[0080] Model monitoring is performed based on the second auxiliary information.

[0081] In the above embodiments, the first device can perform model monitoring based on the second auxiliary information sent by the second device, so that the first model can achieve better performance.

[0082] In conjunction with some embodiments of the first aspect, in some embodiments, the second auxiliary information includes at least one of the following:

[0083] The second identifier includes a model identifier and / or a function identifier;

[0084] A first precision threshold is used by the first device to determine whether to perform a model switch.

[0085] The fifth instruction is used to indicate the usage information and performance information of the first device storage model.

[0086] In the above embodiments, the first device can accurately monitor the model based on the second identifier, and can also determine whether to switch the model based on the first accuracy threshold to ensure the reliability of the first device. It can also store the model's usage information and performance information according to the instructions of the second device so that the second device can determine the model's performance.

[0087] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0088] A fourth message is sent to the second device, which is used by the second device to determine whether to retrain the model.

[0089] In the above embodiments, the first device may send fourth information to the second device so that the second device can determine whether to retrain the model to improve the model's accuracy.

[0090] In conjunction with some embodiments of the first aspect, in some embodiments, the fourth information includes at least one of the following:

[0091] The second identifier includes a model identifier and / or a function identifier;

[0092] The model uses time information;

[0093] Accuracy information of model inference;

[0094] Model rollback information.

[0095] In the above embodiments, the second device can determine whether to retrain the model based on a variety of different information, making the second device's performance judgment of the first model more accurate.

[0096] Secondly, embodiments of this disclosure provide a communication method executed by a second device, the method comprising:

[0097] Receive first information sent by the first device, the first information being used to download the model and / or request training the model;

[0098] Send a second message to the first device, the second message being a response to the first message.

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

[0100] The first request is used to request the download of the first model;

[0101] The second request is used to request the second device to train the second model;

[0102] The first function includes the functions supported by the first model and / or the second model;

[0103] The first identifier includes the identifier of the first model and / or the identifier of the second model;

[0104] First auxiliary information, which is used to assist the second device in determining the first model.

[0105] In conjunction with some embodiments of the second aspect, in some embodiments, the first auxiliary information includes at least one of the following:

[0106] Satellite orbital information;

[0107] Satellite ephemeris information;

[0108] Satellite computing power information;

[0109] Satellite storage space information;

[0110] The coverage area of ​​the first model.

[0111] In conjunction with some embodiments of the second aspect, in some embodiments, the second information includes at least one of the following:

[0112] The first model;

[0113] The area of ​​application of the first model;

[0114] The usage time of the first model;

[0115] A first indication is used to indicate whether the second device trains the second model.

[0116] In conjunction with some embodiments of the second aspect, in some embodiments, the area of ​​use includes at least one of the following:

[0117] Geographical location;

[0118] List of community signs;

[0119] Tracking region identifier (TAI) list;

[0120] Coverage area.

[0121] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0122] The first device sends a third message, which is used to indicate the second device's support capability for the model, and the third message is used by the first device to determine whether to send the first message to the second device.

[0123] In conjunction with some embodiments of the second aspect, in some embodiments, the third information includes at least one of the following:

[0124] The second indication is used to indicate whether a third model is available;

[0125] The third indication is used to indicate whether model training is supported;

[0126] The fourth indication is used to indicate the satellite scenario supported by the third model and / or the model training;

[0127] The second function includes the third model and / or the function that supports model training.

[0128] The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

[0129] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0130] The first model and / or the second model are determined based on the first information.

[0131] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0132] Send second auxiliary information to the first device, the second auxiliary information being used by the first device to perform model monitoring.

[0133] In conjunction with some embodiments of the second aspect, in some embodiments, the second auxiliary information includes at least one of the following:

[0134] The second identifier includes a model identifier and / or a function identifier;

[0135] A first precision threshold is used by the first device to determine whether to perform a model switch.

[0136] The fifth instruction is used to indicate the usage information and performance information of the first device storage model.

[0137] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0138] Receive the fourth message sent by the first device;

[0139] The decision to retrain the model is based on the fourth piece of information.

[0140] In conjunction with some embodiments of the second aspect, in some embodiments, the fourth information includes at least one of the following:

[0141] The second identifier includes a model identifier and / or a function identifier;

[0142] The model uses time information;

[0143] Accuracy information of model inference;

[0144] Model rollback information.

[0145] Thirdly, embodiments of this disclosure provide a first device, which may include at least one of a transceiver module and a processing module; wherein the first device may be used to execute an optional implementation of the first aspect.

[0146] Fourthly, embodiments of this disclosure provide a second device, which may include at least one of a transceiver module and a processing module; wherein the second device may be used to perform an optional implementation of the second aspect.

[0147] Fifthly, embodiments of this disclosure provide a first device that may include one or more processors; wherein the first device may be used to execute an optional implementation of the first aspect.

[0148] In a sixth aspect, embodiments of this disclosure provide a second device that may include one or more processors; wherein the second device may be used to perform an optional implementation of the second aspect.

[0149] In a seventh aspect, embodiments of this disclosure provide a communication system that may include: a first device and a second device; wherein the first device is configured to perform the method described in the optional implementation of the first aspect, and the second device is configured to perform the method described in the optional implementation of the second aspect.

[0150] Eighthly, 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 an optional implementation of the first or second aspect.

[0151] In a ninth aspect, 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 an optional implementation of the first or second aspect.

[0152] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in an optional implementation of the first or second aspect.

[0153] Eleventhly, 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 optional implementations of the first or second aspect.

[0154] It is understood that the aforementioned first device, second device, communication device, communication system, storage medium, program product, computer program, chip, or chip system can all be used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0155] This disclosure provides a communication method, communication device, communication system, storage medium, and program product. In some embodiments, the terms "information transmission method" and "information processing method," "communication method," etc., can be used interchangeably; the terms "information transmission device" and "information processing device," "communication device," "communication equipment," etc., can be used interchangeably; and the terms "information processing system," "communication system," etc., can be used interchangeably.

[0156] 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.

[0157] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0158] 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.

[0159] 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.

[0160] In some embodiments, "multiple" can refer to two or more.

[0161] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0162] 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 B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0163] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); 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, C, etc.

[0164] 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 "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "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 object being described 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.

[0165] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0166] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0167] 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”.

[0168] 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,” “node,” “function,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0169] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0170] 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.

[0171] 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.

[0172] 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 terminal can also be configured to have 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 or direct channel, and uplink link, downlink, etc., can be replaced with sidelink link or direct link.

[0173] 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.

[0174] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0175] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0176] 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.

[0177] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure. As shown in Figure 1A, the communication system 100 may include a first device 101 and a second device 102.

[0178] In some embodiments, the first device 101 may be a device on a satellite.

[0179] In some embodiments, the second device 102 may be a ground device, a high-computing-power device, or an artificial intelligence (AI) model storage device; this disclosure does not limit the specific device.

[0180] In some embodiments, the first device may be referred to as the first node, and the second device may be referred to as the second node.

[0181] In some embodiments, the first node is a base station and the second node is a core network node.

[0182] In some embodiments, the first node is a base station, and the second node is a base station.

[0183] In some embodiments, the first node is a distributed unit (DU) and the second node is a central unit (CU).

[0184] In some embodiments, the first node is a Resource Unit (RU) and the second node is a DU+CU.

[0185] In some embodiments, the first node is a base station and the second node is a base station control unit.

[0186] In some embodiments, the network device may include at least one of an access network device and a core network device.

[0187] In some embodiments, the access network device may be a node or device that connects a terminal device to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0188] 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.

[0189] 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 protocol layer functions are centrally controlled by the CU, while the remaining part or all protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0190] In some embodiments, the core network equipment may be a single device, multiple devices, or a group of devices. The core network may include at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0191] 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.

[0192] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are examples. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is an example. 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.

[0193] 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).

[0194] In some embodiments of this disclosure, Figure 1B is a schematic diagram of an NTN network according to an embodiment of this disclosure. As shown in Figure 1B, the NTN network provides wireless resources to terminals via satellite (or drone) instead of ground base stations. The UAS platform is an Unmanned Aerial System platform.

[0195] In some embodiments, the signal processing can be categorized into pass-through mode and regeneration mode, depending on the satellite's signal processing method. Figure 1C is a schematic diagram of a pass-through mode according to an embodiment of this disclosure. As shown in Figure 1C, the NTN ground station transmits the gNB signal to the satellite. The satellite converts the signal to the satellite frequency band and then transmits it to the UE via the satellite frequency band. Except for frequency conversion and signal amplification, the satellite does not demodulate the gNB signal, similar to a repeater. Figure 1D is a schematic diagram of a regeneration mode according to an embodiment of this disclosure. As shown in Figure 1D, after the NTN ground station transmits the gNB signal to the satellite, the satellite first demodulates and decodes the signal and then re-encodes and modulates it (this process is regeneration) and transmits the regenerated signal via the satellite frequency band. Here, the NG based on SRI can be NG over SRI.

[0196] In Figures 1C and 1D, 5G CN stands for 5G Core Network, Non-Geo orbit stands for Non-Geostationary orbit, SRI interface stands for Satellite Radio Interface, NG interface stands for the interface between Radio Access Network (RAN) and 5G Core Network, and N6 interface stands for the interface between User Plane Functional Unit (UPF) and External Data Network (DN).

[0197] In some embodiments, the relationship between satellite altitude, orbit, and satellite coverage of some typical NTN networks is shown in Table 1.

[0198] Table 1

[0199] In some embodiments, 5G user experience rates can reach 100 Mbit / s to 1 Gbit / s, supporting ultimate service experiences such as mobile virtual reality; 5G peak rates can reach 10 Gbit / s to 20 Gbit / s, and traffic density can reach 10 Mbit / s / m2, supporting more than a thousand times the growth of mobile service traffic in the future; 5G connection density can reach 1 million / m2, effectively supporting massive numbers of IoT devices; 5G transmission latency can reach the millisecond level, meeting the stringent requirements of vehicle networking and industrial control; 5G can support mobile speeds of 500 km / h, ensuring a good user experience in high-speed rail environments.

[0200] In some embodiments, the continued development of fields such as intelligent voice and computer vision not only brings a wide variety of applications to smart terminals, but also finds widespread use in education, transportation, home, healthcare, retail, security, and other sectors, bringing convenience to people's lives while promoting industrial upgrading in various industries. Artificial intelligence (AI) technology is also accelerating its cross-fertilization with other disciplines, integrating knowledge from different fields while providing new directions and methods for the development of various disciplines.

[0201] In some embodiments, during 3GPP Release 18, a research project on the application of artificial intelligence (AI) technology in the radio interface was established in RAN1. This project aimed to investigate how to introduce AI technology into the radio interface and explore how AI technology can assist in improving radio interface transmission technology.

[0202] In some embodiments, in research oriented towards 6G, 6G systems can provide AI services in more dimensions. This mainly includes the following three aspects:

[0203] AI-enabled connectivity: Using AI to improve communication performance, such as using AI for beam management;

[0204] Computing power services: The network side can provide computing power to the terminal side, such as helping the terminal to perform model training and model inference;

[0205] Ultimate AI Service: Enhance network transmission channels to improve the experience of AI application services.

[0206] In some embodiments, the deep integration of artificial intelligence and satellite technology can enhance satellite autonomy and mission coordination capabilities. This integration enables satellites to operate more independently in the complex and ever-changing space environment, especially in situations with long signal transmission delays. Satellites can make autonomous decisions and adjustments to ensure the successful completion of missions.

[0207] In some embodiments, the application of AI technology can transform traditional satellite data processing methods. Traditional data processing requires significant manual intervention and is inefficient. The introduction of AI technology automates and intelligently processes data, greatly improving efficiency. By learning and understanding the inherent patterns and relationships within data, AI technology can achieve precise fusion of multimodal data, providing more comprehensive and accurate information.

[0208] In some embodiments, the application of AI technology in satellite remote sensing enables satellites to automatically identify and label features in remote sensing data, improving the efficiency and accuracy of data processing. The application of AI is similar to edge computing in intelligent surveillance; by deploying AI on satellites, real-time data processing and decision-making can be achieved, reducing data transmission and processing latency.

[0209] In some embodiments, with the launch of more satellites and the formation of constellation networks, inter-satellite connectivity and cloud formation become crucial. Computational constellations composed of AI satellites will have greater practical application value; they can leverage swarm intelligence to perform complex operations, improve work efficiency, and enhance the overall stability and reliability of the system.

[0210] In some embodiments, in satellite coverage scenarios, AI can be used for satellite communication. The applications of AI technology in the field of satellite communication / Internet are shown in Table 2.

[0211] Table 2

[0212] In some embodiments, how to support AI use cases in satellite scenarios (regeneration mode) when satellite computing power is limited is an urgent problem to be solved.

[0213] Figure 2A is an interactive schematic diagram illustrating 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:

[0214] Step S2101: The second device 102 sends the third information to the first device 101.

[0215] In some embodiments, the first device 101 receives third information sent by the second device 102, but is not limited thereto. The first device 101 may also receive third information sent by other entities, in which case step S2101 may be omitted.

[0216] In some embodiments, the first device 101 obtains third information as defined by the protocol, in which case step S2101 can be omitted.

[0217] In some embodiments, the first device 101 obtains third information from the upper layer(s), in which case step S2101 can be omitted.

[0218] In some embodiments, the first device 101 processes the information to obtain the third information, in which case step S2101 can be omitted.

[0219] In some embodiments, the first device 101 predefines third information, in which case step S2101 can be omitted.

[0220] In some embodiments, the first device 101 pre-configures third information, in which case step S2101 can be omitted.

[0221] In some embodiments, the first device 101 is a movable device.

[0222] In some embodiments, the first device 101 is a device on a satellite, and the second device 102 is a ground device, a high-computing-power device, or an AI model storage device.

[0223] In some embodiments, the first device may be referred to as the first node, and the second device may be referred to as the second node.

[0224] In some embodiments, the first node is a base station and the second node is a core network node.

[0225] In some embodiments, the first node is a base station, and the second node is a base station.

[0226] In some embodiments, the first node is DU and the second node is CU.

[0227] In some embodiments, the first node is RU and the second node is DU+CU.

[0228] In some embodiments, the first node is a base station and the second node is a base station control unit.

[0229] In some embodiments, the third information is used to indicate the second device 102's ability to support the model.

[0230] In some embodiments, the third information includes at least one of the following:

[0231] The second instruction is used to indicate whether a third model is available;

[0232] The third indicator is used to indicate whether model training is supported;

[0233] The fourth instruction is used to indicate the satellite scenario supported by the third model and / or the model training.

[0234] The second function includes the third model and / or the function that supports model training.

[0235] The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

[0236] In some embodiments, the third model may be a model that has already been trained and whose performance meets the requirements.

[0237] In some embodiments, the third model may include at least one model.

[0238] In some embodiments, the satellite scene can be a satellite type, such as LEO, MEO, or GEO.

[0239] In some embodiments, the satellite scene can be the satellite's coverage area, such as mountainous areas, plains, cities, oceans, etc.

[0240] In some embodiments, the second function may include at least one of the following: interference detection, beam management, load balancing, and path optimization.

[0241] In some embodiments, the third model may also support at least one of the following functions: interference detection, beam management, load balancing, and path optimization.

[0242] In some embodiments, the model information of the third model may also be referred to as the list of available models, and this disclosure does not limit this.

[0243] Step S2102: The first device sends the first information to the second device.

[0244] In some embodiments, the second device 102 receives the first information sent by the first device 101, but is not limited thereto. The second device 102 may also receive the first information sent by other entities, in which case step S2102 may be omitted.

[0245] In some embodiments, the second device 102 obtains the first information from the upper layer(s), in which case step S2102 can be omitted.

[0246] In some embodiments, the second device 102 processes the information to obtain the third information, in which case step S2102 can be omitted.

[0247] In some embodiments, the first information is used to download the model and / or request training of the model.

[0248] For example, the first information is used to request the download of a model from the second device 102; or, for another example, the first information is used to request the second device 102 to train a model.

[0249] In some embodiments, downloading may also be referred to as transmitting or sending.

[0250] In some embodiments, after receiving the third information sent by the second device 102, the first device 101 can determine whether to send the first information to the second device 102 based on the third information.

[0251] In some embodiments, the first information includes at least one of the following:

[0252] The first request is used to request the download of the first model;

[0253] The second request is used to request the second device 102 to train the second model;

[0254] The first function includes the functions supported by the first model and / or the second model;

[0255] The first identifier includes the identifier of the first model and / or the second model;

[0256] First auxiliary information, which is used to assist the second device 102 in determining the first model.

[0257] In some embodiments, the first model may be a specified model or any model supported by the second device 102.

[0258] In some embodiments, the first model is at least one of the third models. For example, the first model is any one or more models selected from the available third models.

[0259] In some embodiments, the second model is at least one model among models that can be trained using the second device. For example, the second model is any one or more models selected from models that can be trained using the second device.

[0260] In some embodiments, the first function may include at least one of the following: interference detection, beam management, load balancing, and path optimization.

[0261] In some embodiments, if the first information includes a first request, then the first function includes functions supported by the first model.

[0262] In some embodiments, if the first information includes a second request, then the first function includes functions supported by the second model.

[0263] In some embodiments, if the first information includes a first request and a second request, then the first function includes functions supported by the first model and functions supported by the second model.

[0264] In some embodiments, if the first information includes a first request, then the first identifier includes the identifier of the first model.

[0265] In some embodiments, if the first information includes a second request, then the first function includes the identifier of the second model.

[0266] In some embodiments, if the first information includes a first request and a second request, then the first function includes the identifier of the first model and the identifier of the second model.

[0267] In some embodiments, if the first device 101 determines that a first model needs to be downloaded based on the third information, the first information may include at least one of a first request, a first function, a first identifier, and first auxiliary information, wherein the first function includes the function of the first model, and the first identifier includes the identifier of the first model. For example, the first information includes a first request and a first function; as another example, the first information includes a first request and a first identifier; yet another example, the first information includes a first request, a first identifier, and first auxiliary information.

[0268] In some embodiments, if the first device 101 determines, based on the third information, that there is no available model or that a model needs to be trained, the first information may include at least one of a second request, a first function, a first identifier, and first auxiliary information, wherein the first function includes the function of the second model, and the first identifier includes the identifier of the second model. For example, the first information may include a second request and a first function; or, for another example, the first information may include a second request and a first identifier; or, for yet another example, the first information may include a second request, a first identifier, and first auxiliary information.

[0269] In some embodiments, the first auxiliary information may include at least one of the following:

[0270] Satellite orbital information;

[0271] Satellite ephemeris information;

[0272] Satellite computing power information;

[0273] Satellite storage space information;

[0274] The coverage area of ​​the first model.

[0275] In some embodiments, the satellite's computing power information may be the available computing power of the first device 101.

[0276] In some embodiments, the satellite's storage space information may be the remaining storage space or available storage space of the first device 101.

[0277] In some embodiments, the coverage area may include at least one of the following: mountainous areas, urban areas, and ocean areas, without limitation in the embodiments disclosed herein.

[0278] In some embodiments, after the first device 101 determines the first information, it can send the first information to the second device 102.

[0279] Step S2103: The second device sends the second information to the first device.

[0280] In some embodiments, the first device 101 receives second information sent by the second device 102, but is not limited thereto. The first device 101 may also receive second information sent by other entities, in which case step S2103 may be omitted.

[0281] In some embodiments, the first device 101 obtains the second information specified by the protocol, in which case step S2103 can be omitted.

[0282] In some embodiments, the first device 101 obtains the second information from the upper layer(s), in which case step S2103 can be omitted.

[0283] In some embodiments, the first device 101 processes the information to obtain the second information, in which case step S2103 can be omitted.

[0284] In some embodiments, the first device 101 predefines second information, in which case step S2103 can be omitted.

[0285] In some embodiments, the first device 101 pre-configures the second information, in which case step S2103 can be omitted.

[0286] In some embodiments, the second information is a response to the first information.

[0287] In some embodiments, the second information includes at least one of the following:

[0288] First model;

[0289] The application area of ​​the first model;

[0290] The usage time of the first model;

[0291] A first instruction is used to indicate whether the second device 102 has trained the second model.

[0292] In some embodiments, the area of ​​use of the first model can be understood as the area to which the first model is adapted.

[0293] In some embodiments, the area of ​​use may include at least one of the following:

[0294] Geographical location;

[0295] List of community signs;

[0296] List of Tracking Area Identity (TAI);

[0297] Coverage area.

[0298] In some embodiments, the geographic location may be latitude and longitude information.

[0299] In some embodiments, the coverage area may include mountainous areas, cities, oceans, etc., but this disclosure does not limit this.

[0300] In some embodiments, the usage time of the first model is the time during which the first model can be used, such as the time period during which the first model is used, the duration of use of the first model, etc., which are not limited in this disclosure.

[0301] In some embodiments, the second device 102 may determine the first model and / or the second model based on the first information.

[0302] In some embodiments, if the first information includes a first request, the second device 102 determines the first model based on the first information.

[0303] In some embodiments, if the first information includes a second request, the second device 102 determines the second model based on the first information.

[0304] In some embodiments, the second device 102 can determine the first model and / or the second model based on the first identifier. For example, if the first identifier is an identifier of the first model, the second device 102 can determine the first model based on the first identifier; as another example, if the first identifier is an identifier of the second model, the second device 102 can determine the second model based on the first identifier; and as yet another example, if the first identifier includes both the identifier of the first model and the identifier of the second model, the second device 102 can determine both the first model and the second model based on the first identifier.

[0305] In some embodiments, the second device 102 may determine the first model and / or the second model based on the first function. For example, if the first function is interference detection, the second device 102 may determine a model for interference detection as the first model and / or the second model.

[0306] In some embodiments, the second device 102 may determine the first model and / or the second model based on the first auxiliary information. For example, the second device 102 may determine a model that meets the satellite's computing power information as the first model. It should be understood that if there are multiple models that meet the satellite's computing power information, the model with the least computing power required for the inference process may be selected as the first model, or any one of them may be selected as the first model. Furthermore, the first model may be determined based on other information in the first auxiliary information. This disclosure does not limit the scope of the embodiments.

[0307] In some embodiments, the second device 102 may determine the first model by combining the first function and the first auxiliary information. For example, the second device 102 may select multiple models that satisfy the first function, and then determine the first model from the multiple models based on the first auxiliary information.

[0308] In some embodiments, the second device 102 may determine the second model by combining the first function and the first auxiliary information. For example, the second device 102 may determine the function of the model to be trained and the computing power required by the model, thereby determining the second model to be trained.

[0309] It should be noted that the above method for determining the first model and / or the second model is for illustrative purposes only. The embodiments of this disclosure can determine the first model and / or the second model based on any one or any combination of the first information, which will not be elaborated here.

[0310] In some embodiments, if the first information instructs the second device 102 to train a model, the second information includes a first instruction, through which the second device 102 informs the first device 101 whether to start model training.

[0311] Using the above method, the first device can send first information to the second device, download the model from the second device or request the second device to train the model, thereby enabling the model to be used on the first device and improving the processing efficiency and reliability of the first device.

[0312] The methods involved in the embodiments of this disclosure may include at least one of the steps S2101 to S2103 described above. For example, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, step S2103 may be implemented as an independent embodiment, step S2101 + step S2102 may be implemented as an independent embodiment, and step S2102 + step S2103 may be implemented as an independent embodiment, but are not limited thereto.

[0313] In some embodiments, the order of any two steps in steps S2101 to S2103 can be interchanged or they can be performed simultaneously.

[0314] In some embodiments, steps S2101 to S2103 are optional, and one or more of these steps may be omitted or substituted in different embodiments. For example, step S2101 may be omitted.

[0315] In some embodiments, other alternative implementations may be described before or after the specification corresponding to FIG2A.

[0316] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2B, the present disclosure relates to a communication method, which includes:

[0317] Step S2201: The second device 102 sends the second auxiliary information to the first device 101.

[0318] In some embodiments, the first device 101 receives second auxiliary information sent by the second device 102, but is not limited thereto. The first device 101 may also receive second auxiliary information sent by other entities, in which case step S2201 may be omitted.

[0319] In some embodiments, the first device 101 obtains the second auxiliary information specified by the protocol, in which case step S2201 can be omitted.

[0320] In some embodiments, the first device 101 obtains the second auxiliary information from the upper layer(s), in which case step S2201 can be omitted.

[0321] In some embodiments, the first device 101 processes the information to obtain the second auxiliary information, in which case step S2201 can be omitted.

[0322] In some embodiments, the first device 101 predefines second auxiliary information, in which case step S2201 can be omitted.

[0323] In some embodiments, the first device 101 pre-configures the second auxiliary information, in which case step S2201 can be omitted.

[0324] In some embodiments, the second auxiliary information can be used by the first device 101 for model monitoring.

[0325] For example, the first device 101 manages and records AI model inference based on the second auxiliary information. The management of AI model inference includes model switching, and the recording includes storing model usage information and performance information.

[0326] In some embodiments, the second auxiliary information includes at least one of the following:

[0327] The second identifier includes a model identifier and / or a function identifier;

[0328] A first precision threshold is used by the first device 101 to determine whether to perform a model switch.

[0329] The fifth instruction is used to indicate the usage and performance information of the storage model of the first device 101.

[0330] In some embodiments, the second identifier may include a model identifier and / or a function identifier that require model monitoring. The function identifier may be an identifier for an AI function, which may include multiple AI models.

[0331] In some embodiments, the first precision threshold corresponding to different models may be the same, or the first precision threshold corresponding to different models may be different. This disclosure does not limit this.

[0332] In some embodiments, model switching may include using a different model or not using an AI model.

[0333] In some embodiments, the model usage information includes time information of AI model usage, which may be the usage time of AI model or the time ratio, where the time ratio may be the proportion of the time spent using AI model to the total time, and the total time is the time it takes for a satellite to orbit the Earth once.

[0334] In some embodiments, the performance information may include model inference accuracy information and model fallback information. The accuracy information may be the proportion of high-precision inference results, where high-precision inference results are those with an accuracy greater than or equal to a specified accuracy threshold. The fallback information may reflect the model's stability, including the number of fallbacks, fallback time, and / or fallback region. The number of fallbacks can be understood as the number of times the AI ​​model was exited or reselected; the fallback time can be understood as the time during which the AI ​​model was exited or reselected; and the fallback region can be understood as the region during which the AI ​​model was exited or reselected.

[0335] Step S2202: The first device 101 performs model monitoring based on the second auxiliary information.

[0336] In some embodiments, the first device 101 determines the AI ​​model and / or AI function that needs to be monitored for performance based on the second identifier.

[0337] In some embodiments, the first device 101 determines whether to perform model switching based on the first precision threshold. For example, if the precision of the AI ​​model inference is less than or equal to the first precision threshold, then model switching is performed; if the precision of the AI ​​model inference is greater than the first precision threshold, then model switching is not performed, and the AI ​​model continues to be used for inference.

[0338] In some embodiments, if the second auxiliary information includes the fifth instruction, the first device 101 stores usage information and performance information of the AI ​​model.

[0339] Step S2203: The first device 101 sends the fourth information to the second device 102.

[0340] In some embodiments, the second device 102 receives the fourth information sent by the first device 101, but is not limited thereto. The second device 102 may also receive the fourth information sent by other entities, in which case step S2203 may be omitted.

[0341] In some embodiments, the second device 102 obtains the fourth information from the upper layer(s), in which case step S2203 can be omitted.

[0342] In some embodiments, the second device 102 processes the information to obtain the fourth information, in which case step S2203 can be omitted.

[0343] In some embodiments, the fourth information is used by the second device 102 to determine whether to retrain the model.

[0344] In some embodiments, the fourth information includes at least one of the following:

[0345] The second identifier includes a model identifier and / or a function identifier;

[0346] The model uses time information;

[0347] Accuracy information of model inference;

[0348] Model rollback information.

[0349] It should be noted that the specific definition of this fourth piece of information can be found in the relevant explanation in step S2201, and will not be repeated here.

[0350] In some embodiments, when the first device 101 is connected to the second device 102, the fourth information is sent to the second device 102.

[0351] Step S2204: The second device 102 determines whether to retrain the model based on the fourth information.

[0352] In some embodiments, if the duration used by the model is less than or equal to a first duration threshold, it indicates that the model's performance is poor and the model needs to be retrained; if the duration used by the model is greater than the first duration threshold, it indicates that the model's performance is good and the model does not need to be retrained.

[0353] In some embodiments, if the accuracy of model inference is less than or equal to the second accuracy threshold, it indicates that the accuracy of model inference is relatively low, and the model needs to be retrained; if the accuracy of model inference is greater than the second accuracy threshold, it indicates that the accuracy of model inference is relatively high, and the model does not need to be retrained.

[0354] In some embodiments, if the number of backoffs of the model is greater than or equal to the threshold of the first number, it indicates that the model's performance is poor and the model needs to be retrained; if the number of backoffs of the model is less than the threshold of the first number, it indicates that the model's performance is good and the model does not need to be retrained.

[0355] In some embodiments, if the number of backoffs of the model is greater than or equal to the threshold of the first number, it indicates that the model's performance is poor and the model needs to be retrained; if the number of backoffs of the model is less than the threshold of the first number, it indicates that the model's performance is good and the model does not need to be retrained.

[0356] It should be noted that the above method for determining whether to retrain the model is an example. The embodiments of this disclosure can determine whether to retrain the model based on any one or any combination of the fourth information, which will not be elaborated here.

[0357] Using the above method, the first device can perform model monitoring based on the second auxiliary information sent by the second device and send the model monitoring results to the second device. In this way, the second device can determine whether the model needs to be retrained based on the model monitoring results, thereby further improving the accuracy of the model.

[0358] The methods involved in the embodiments of this disclosure may include at least one of the steps S2201 to S2204 described above. For example, step S2201 may be implemented as an independent embodiment, step S2202 may be implemented as an independent embodiment, step S2203 may be implemented as an independent embodiment, step S2201 + step S2202 may be implemented as an independent embodiment, step S2202 + step S2203 may be implemented as an independent embodiment, and step S2203 + step S2204 may be implemented as an independent embodiment, but are not limited thereto.

[0359] In some embodiments, steps S2201 to S2204 are all optional steps. For example, step S2201 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0360] 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.

[0361] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”

[0362] In some embodiments, the terms "component carrier (CC)," "cell," "frequency carrier," and "carrier frequency" can be used interchangeably.

[0363] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0364] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0365] 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.

[0366] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0367] In some embodiments, if an arrow in the interaction diagram representing the sending of information, signaling, etc. from one subject to another passes through other subjects, it can be interpreted as the information being forwarded from one subject to another via other subjects, or it can be interpreted as the information being sent from one subject to another without passing through other subjects.

[0368] Figure 3A is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure relates to a communication method that can be executed by a first device 101. The method may include:

[0369] Step S3101: Receive third information.

[0370] The optional implementation of step S3101 can be found in the optional implementation of step S2101 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0371] Step S3102: Send the first message.

[0372] The optional implementation of step S3102 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0373] Step S3103: Receive the second information.

[0374] The optional implementation of step S3103 can be found in the optional implementation of step S2103 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0375] Step S3104: Receive the second auxiliary information.

[0376] The optional implementation of step S3104 can be found in the optional implementation of step S2201 in Figure 2B, and other related parts in the embodiments involved in Figure 2B, which will not be repeated here.

[0377] Step S3105: Perform model monitoring based on the second auxiliary information.

[0378] The optional implementation of step S3105 can be found in the optional implementation of step S2202 in Figure 2B, and other related parts in the embodiments involved in Figure 2B, which will not be repeated here.

[0379] Step S3106: Send the fourth message.

[0380] The optional implementation of step S3106 can be found in the optional implementation of step S2203 in Figure 2B, and other related parts in the embodiments involved in Figure 2B, which will not be repeated here.

[0381] The methods involved in the embodiments of this disclosure may include at least one of the steps S3101 to S3106 described above. For example, step S3101 may be implemented as an independent embodiment, step S3102 may be implemented as an independent embodiment, step S3103 may be implemented as an independent embodiment, step S3104 may be implemented as an independent embodiment, step S3106 may be implemented as an independent embodiment, step S3101 + step S3102 may be implemented as an independent embodiment, step S3102 + step S3103 may be implemented as an independent embodiment, and step S3104 + step S3105 may be implemented as an independent embodiment, but are not limited thereto.

[0382] In some embodiments, the order of any two steps in steps S3101 to S3106 can be interchanged or they can be performed simultaneously.

[0383] In some embodiments, steps S3101 to S3106 are optional, and one or more of these steps may be omitted or substituted in different embodiments. For example, steps S3101 and S3106 may be omitted.

[0384] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, the present disclosure relates to a communication method that can be executed by a first device 101. The method may include:

[0385] Step S3201: Send the first message.

[0386] The optional implementation of step S3201 can be found in the optional implementation of step S2102 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0387] Step S3202: Receive the second information.

[0388] The optional implementation of step S3202 can be found in the optional implementation of step S2103 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0389] In some embodiments, the first information includes at least one of the following:

[0390] The first request is used to request the download of the first model;

[0391] The second request is used to request the second device to train the second model;

[0392] The first function includes the functions supported by the first model and / or the second model;

[0393] The first identifier includes the identifier of the first model and / or the identifier of the second model;

[0394] First auxiliary information, which is used to assist the second device in determining the first model.

[0395] In some embodiments, the first auxiliary information includes at least one of the following:

[0396] Satellite orbital information;

[0397] Satellite ephemeris information;

[0398] Satellite computing power information;

[0399] Satellite storage space information;

[0400] The coverage area of ​​the first model.

[0401] In some embodiments, the second information includes at least one of the following:

[0402] The first model;

[0403] The area of ​​application of the first model;

[0404] The usage time of the first model;

[0405] A first indication is used to indicate whether the second device trains the second model.

[0406] In some embodiments, the area of ​​use includes at least one of the following:

[0407] Geographical location;

[0408] List of community signs;

[0409] Tracking region identifier (TAI) list;

[0410] Coverage area.

[0411] In some embodiments, the method further includes:

[0412] The device receives third information sent by the second device, the third information being used to indicate the second device's support capability for the model.

[0413] In some embodiments, the third information includes at least one of the following:

[0414] The second indication is used to indicate whether a third model is available;

[0415] The third indication is used to indicate whether model training is supported;

[0416] The fourth indication is used to indicate the satellite scenario supported by the third model and / or the model training;

[0417] The second function includes the third model and / or the function that supports model training.

[0418] The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

[0419] In some embodiments, the method further includes:

[0420] The decision to send the first information to the second device is determined based on the third information.

[0421] In some embodiments, the method further includes:

[0422] Receive the second auxiliary information sent by the second device;

[0423] Model monitoring is performed based on the second auxiliary information.

[0424] In some embodiments, the second auxiliary information includes at least one of the following:

[0425] The second identifier includes a model identifier and / or a function identifier;

[0426] A first precision threshold is used by the first device to determine whether to perform a model switch.

[0427] The fifth instruction is used to indicate the usage information and performance information of the first device storage model.

[0428] In some embodiments, the method further includes:

[0429] A fourth message is sent to the second device, which is used by the second device to determine whether to retrain the model.

[0430] In some embodiments, the fourth information includes at least one of the following:

[0431] The second identifier includes a model identifier and / or a function identifier;

[0432] The model uses time information;

[0433] Accuracy information of model inference;

[0434] Model rollback information.

[0435] In some embodiments, AI deployment in regenerative mode can be as follows: AI model training and storage are performed on the ground, while AI model inference is performed on a satellite. Figure 4A is a schematic diagram of model deployment in regenerative mode according to an embodiment of the present disclosure. As shown in Figure 4A, the RAN is on the satellite, and LCM stands for Latent Consistency Models. Figure 4B is a schematic diagram of model deployment in regenerative mode according to an embodiment of the present disclosure. As shown in Figure 4B, the DU is on the satellite, where F1 based on SRI can be F1 over SRI. Figure 4C is a schematic diagram of the lifecycle of an NTN network according to an embodiment of the present disclosure. As shown in Figure 4C, the RAN is on the satellite and is responsible for data collection, while ground equipment is responsible for model training, model management, model storage, and model inference, where NWDAF stands for Network Data Analytics Function.

[0436] In some embodiments, ground nodes provide satellite nodes with AI / machine learning (ML) support capability information, including satellite-related capabilities, such as:

[0437] Indicates the type of satellite or the coverage area of ​​the satellite that supports AI / ML models or model training;

[0438] Indicates satellite-related functions that support AI / ML models or model training, such as satellite interference detection;

[0439] Indicates the computing power and / or storage space required to support inference for AI / ML models (considering the limited computing power and storage of satellites).

[0440] In some embodiments, when a satellite node requests an AI / ML model or model training from a ground node, it provides satellite-specific requirement information so that the ground node can select a suitable model to provide to the satellite node, including:

[0441] Satellite orbital information;

[0442] The satellite's available computing power;

[0443] Available storage space on the satellite;

[0444] The applicable coverage area of ​​the request model, such as mountainous areas, cities, oceans, etc.

[0445] In some embodiments, ground nodes transmit models to satellite nodes, the models corresponding to applicable coverage areas or times.

[0446] In some embodiments, the management of AI / ML models takes into account that satellites and ground nodes cannot maintain a connection for extended periods, thus preventing the satellite from providing real-time performance monitoring feedback. Therefore, it is advisable for the satellite to monitor performance based on suggestions from ground nodes and record model usage. When a connection is established, this information is sent to the ground nodes for model training management. This includes:

[0447] Ground nodes provide auxiliary information for performance monitoring to satellite nodes;

[0448] When a connection is established, satellite nodes provide feedback to ground nodes regarding the model's usage on the satellite:

[0449] The time or proportion of time the model was used;

[0450] The percentage of high-precision model inference results;

[0451] The number of model backoffs indicates the number of times the model has been backed up (the stability of the model).

[0452] The time and / or region information of model rollback or reselection, used to indicate the time and / or region where model rollback or reselection occurs.

[0453] Figure 4D is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4D, the present disclosure relates to a communication method that can be executed by a communication system. The method may include:

[0454] Step S4401: The first node (the node on the satellite) receives first information from the second node (the ground node, the high-computing-power node, or the AI ​​model storage node). The first information is used to indicate the models supported by the second node and / or the training functions (AI / ML capabilities) supported by the second node.

[0455] In some embodiments, the first information includes at least one of the following:

[0456] The first indication is used to indicate whether a model is available;

[0457] The second indicator is used to indicate whether model training is supported;

[0458] The third indication is used to indicate the model or the scenario supported by the model training, such as a model that supports satellite scenarios;

[0459] The first function is used to indicate the available models or functions that support model training, such as interference detection, beam management, load balancing, path optimization, etc.

[0460] A list of available models, including supported model identifiers, model functions, computing power required for inference, and storage space required for inference.

[0461] In some embodiments, the model of the satellite scene can be a specific satellite type, such as LEO, MEO, or GEO.

[0462] In some embodiments, the first node may determine, based on the first information, whether to request model download or model training from the second node, or whether to select a model from the list of available models, in order to optimize satellite communication.

[0463] Step S4402: The first node sends a first request (AI / ML model request) to the second node to request a model or model training.

[0464] The first request includes at least one of the following:

[0465] The first request indication is used to indicate the request model transmission;

[0466] The second request instruction is used to instruct the request for model training;

[0467] The first function is used to indicate the function that requests model training or model download, such as interference detection, beam management, load balancing, path optimization scheduling, etc.

[0468] The first model identifier is used to indicate that a specific model is requested;

[0469] The first auxiliary information is used to help the second node select a suitable model or train a suitable model for the first node.

[0470] The first auxiliary information may include at least one of the following:

[0471] The second node uses the satellite's orbit or ephemeris information to select an appropriate model for transmission or training.

[0472] The second node uses the satellite's computing power information to select an appropriate model for transmission or training.

[0473] The second node uses the satellite's storage space information to select an appropriate model for transmission or training.

[0474] In some embodiments, the second node selects a suitable model based on the first request information and transmits it to the first node, or the second node trains a suitable model based on the first request information and transmits it to the first node.

[0475] Step S4403: The second node sends the first feedback (AI / ML model response / transmission) to the first node. The first feedback includes at least one of the following:

[0476] The trained model;

[0477] The available area of ​​the model is used to indicate the area to which the model is adapted;

[0478] The available time of the model is used to indicate the time when the model is available.

[0479] In some embodiments, the region may be at least one of a geographic location, a cell ID list, or a TAI list.

[0480] In some embodiments, the area can be a corresponding coverage area type, such as mountainous areas, urban areas, oceans, etc.

[0481] Figure 4E is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4E, the present disclosure relates to a communication method that can be executed by a communication system. The method may include:

[0482] Step S4501: The second node sends the second information (model management auxiliary information) to the first node.

[0483] In some embodiments, the second information is used to assist the first node in managing and recording AI model inference.

[0484] The second information includes at least one of the following:

[0485] Model or function identifier, used to indicate a specific model or function identifier;

[0486] The precision threshold for inference is used to assist the first node in determining whether to switch models or continue using the model.

[0487] The performance management feedback configuration instructs the first node to record the model's usage and performance in order to assist the second node in retraining the model.

[0488] In some embodiments, the first node performs model detection based on the second information, and performs operations such as model switching or fallback based on the detection results.

[0489] Step S4502: The first node sends the third information (AI / ML model performance feedback) to the second node.

[0490] In some embodiments, the third information is used to indicate the usage of the model at the first node, including at least one of the following:

[0491] Model or function identifier, used to indicate a specific model or function identifier;

[0492] The time or proportion of time the model is used is used to indicate the time or percentage of time the model is used.

[0493] The percentage of high-precision model inference results, used to indicate the percentage of precision used in the model;

[0494] The number of model backoffs indicates the number of times the model has been backed up (the stability of the model).

[0495] The time and / or region information of model rollback, used to indicate the time and / or region information when model rollback or reselection occurs.

[0496] In some embodiments, the second node can manage model training based on third information, such as determining whether to retrain the model.

[0497] In some embodiments, the first node and the second node may be in the following situations:

[0498] The first node is the base station, and the second node is the core network node;

[0499] The first node is a base station, and the second node is a base station;

[0500] The first node is DU, and the second node is CU;

[0501] The first node is RU, and the second node is DU+CU;

[0502] The first node is the base station, and the second node is the base station control unit.

[0503] In some embodiments, "eNB" and "gNB", "base station", "NG-RAN node", and "6G RAN" can be interchanged; "MME" can be interchanged with "CN", "Access and Mobility Management Function (AMF)", "Session Management Function (SMF)", and "6G CN"; "Serving Gateway (SGW)" can be interchanged with "User Plane Function (UPF)"; "Bearer" can be interchanged with "Protocol Data Unit (PDU) session", "Evolved Radio Access Bearer (E-RAB)", "Evolved Packet System (EPS) bearer", and "Quality of Service flow (QoSflow)"; "Next Generation Application Protocol (NGAP)" can be interchanged with "S1 Application Protocol (S1AP)".

[0504] In some embodiments of this disclosure, a communication system is provided, which may include a first device and a second device, wherein the first device may execute the communication method executed by the first device in the foregoing embodiments of this disclosure; and the second device may execute the communication method executed by the second device in the foregoing embodiments of this disclosure.

[0505] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the first device in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by the second device (e.g., access network device, core network functional node, core network device, etc.) in any of the above methods.

[0506] 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), and 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), such as a Field Programmable Gate Array (FPGA), which 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.

[0507] 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. In addition, it can also be hardware circuits designed for artificial intelligence, which can be understood as ASICs, such as Neural Network Processing Units (NPUs), Tensor Processing Units (TPUs), and Deep Learning Processing Units (DPUs).

[0508] Figure 5A is a schematic diagram of the structure of a first device according to an embodiment of this disclosure. As shown in Figure 5A, the first device 101 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, the transceiver module 5101 is configured to send first information to a second device, the first information being used to download a model and / or request training a model; and to receive second information sent by the second device, the second information being response information to the first information. Optionally, the transceiver module 5101 may be used to perform at least one of the communication steps (e.g., steps S2101, S2102, S2103, S2201, S2203, but not limited thereto) performed by the first device 101 in any of the above methods, which will not be elaborated here. Optionally, the processing module 5102 may be used to perform at least one of the other steps (e.g., step S2202, but not limited thereto) performed by the first device 101 in any of the above methods, which will not be elaborated here.

[0509] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0510] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0511] Figure 5B is a schematic diagram of the structure of a second device according to an embodiment of this disclosure. As shown in Figure 5B, the second device 102 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the transceiver module 5201 is configured to receive first information sent by a first device, the first information being used to download a model and / or request training a model; and to send second information to the first device, the second information being response information to the first information. Optionally, the transceiver module 5201 may be used to perform at least one of the communication steps (e.g., steps S2101, S2102, S2103, S2201, S2203, but not limited thereto) performed by the second device 102 in any of the above methods, which will not be elaborated here. Optionally, the processing module 5202 may be used to perform at least one of the other steps (e.g., step S2204, but not limited thereto) performed by the second device 102 in any of the above methods, which will not be elaborated here.

[0512] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0513] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0514] 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 chip, chip system, or processor that supports the first 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.

[0515] As shown in Figure 6A, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, IoT devices, IoT device chips, DUs or CUs, etc.), execute programs, and process program data. The communication device 6100 is used to execute any of the above methods.

[0516] In some embodiments, the communication device 6100 further includes one or more memories 6102 for storing instructions. Optionally, all or part of the memories 6102 may also be located outside the communication device 6100.

[0517] In some embodiments, the communication device 6100 further includes one or more transceivers 6103. When the communication device 6100 includes one or more transceivers 6103, the transceivers 6103 perform at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2102, S2103, S2201, S2203, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps S2202, S2204, but not limited thereto).

[0518] In some embodiments, a transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0519] In some embodiments, the communication device 6100 may include one or more interface circuits. Optionally, the interface circuit is connected to the memory 6102, and the interface circuit can be used to receive signals from the memory 6102 or other devices, and can be used to send signals to the memory 6102 or other devices. For example, the interface circuit can read instructions stored in the memory 6102 and send the instructions to the processor 6101.

[0520] The communication device 6100 described in the above embodiments may be a first device or an Internet of Things (IoT) device, 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 and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, IoT device, smart IoT device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, first device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0521] 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.

[0522] Chip 6200 includes one or more processors 6201, which are used to perform any of the above methods.

[0523] In some embodiments, chip 6200 further includes one or more interface circuits 6203. Optionally, interface circuit 6203 is connected to memory 6202, and interface circuit 6203 can be used to receive signals from memory 6202 or other devices, and interface circuit 6203 can be used to send signals to memory 6202 or other devices. For example, interface circuit 6203 can read instructions stored in memory 6202 and send the instructions to processor 6201.

[0524] In some embodiments, the interface circuit 6203 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2102, S2103, S2201, S2203, but not limited thereto), and the processor 6201 performs at least one of other steps (e.g., steps S2202, S2204, but not limited thereto).

[0525] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0526] In some embodiments, chip 6200 further includes one or more memories 6202 for storing instructions. Optionally, all or part of the memories 6202 may be located outside of chip 6200.

[0527] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device 6100, cause the communication device 6100 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.

[0528] This disclosure also provides a program product that, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product may be a computer program product.

[0529] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method, characterized in that, Performed by a first device, the method includes: Send first information to the second device, the first information being used to download the model and / or request training of the model; Receive second information sent by the second device, wherein the second information is a response to the first information.

2. The method according to claim 1, characterized in that, The first information includes at least one of the following: The first request is used to request the download of the first model; The second request is used to request the second device to train the second model; The first function includes the functions supported by the first model and / or the second model; The first identifier includes the identifier of the first model and / or the identifier of the second model; First auxiliary information, which is used to assist the second device in determining the first model.

3. The method according to claim 2, characterized in that, The first auxiliary information includes at least one of the following: Satellite orbital information; Satellite ephemeris information; Satellite computing power information; Satellite storage space information; The coverage area of ​​the first model.

4. The method according to claim 2 or 3, characterized in that, The second information includes at least one of the following: The first model; The area of ​​application of the first model; The usage time of the first model; A first indication is used to indicate whether the second device trains the second model.

5. The method according to claim 4, characterized in that, The area of ​​use includes at least one of the following: Geographical location; List of community signs; Tracking region identifier (TAI) list; Coverage area.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: The device receives third information sent by the second device, the third information being used to indicate the second device's support capability for the model.

7. The method according to claim 6, characterized in that, The third information includes at least one of the following: The second indication is used to indicate whether a third model is available; The third indication is used to indicate whether model training is supported; The fourth indication is used to indicate the satellite scenario supported by the third model and / or the model training; The second function includes the third model and / or the function that supports model training. The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

8. The method according to claim 6 or 7, characterized in that, The method further includes: The decision to send the first information to the second device is determined based on the third information.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: Receive the second auxiliary information sent by the second device; Model monitoring is performed based on the second auxiliary information.

10. The method according to claim 9, characterized in that, The second auxiliary information includes at least one of the following: The second identifier includes a model identifier and / or a function identifier; A first precision threshold is used by the first device to determine whether to perform a model switch. The fifth instruction is used to indicate the usage information and performance information of the first device storage model.

11. The method according to claim 9 or 10, characterized in that, The method further includes: A fourth message is sent to the second device, which is used by the second device to determine whether to retrain the model.

12. The method according to claim 11, characterized in that, The fourth piece of information includes at least one of the following: The second identifier includes a model identifier and / or a function identifier; The model uses time information; Accuracy information of model inference; Model rollback information.

13. A communication method, characterized in that, Performed by a second device, the method includes: Receive first information sent by the first device, the first information being used to download the model and / or request training the model; Send a second message to the first device, the second message being a response to the first message.

14. The method according to claim 13, characterized in that, The first information includes at least one of the following: The first request is used to request the download of the first model; The second request is used to request the second device to train the second model; The first function includes the functions supported by the first model and / or the second model; The first identifier includes the identifier of the first model and / or the identifier of the second model; First auxiliary information, which is used to assist the second device in determining the first model.

15. The method according to claim 14, characterized in that, The first auxiliary information includes at least one of the following: Satellite orbital information; Satellite ephemeris information; Satellite computing power information; Satellite storage space information; The coverage area of ​​the first model.

16. The method according to claim 14 or 15, characterized in that, The second information includes at least one of the following: The first model; The area of ​​application of the first model; The usage time of the first model; A first indication is used to indicate whether the second device trains the second model.

17. The method according to claim 16, characterized in that, The area of ​​use includes at least one of the following: Geographical location; List of community signs; Tracking region identifier (TAI) list; Coverage area.

18. The method according to any one of claims 13-17, characterized in that, The method further includes: The first device sends a third message, which is used to indicate the second device's support capability for the model, and the third message is used by the first device to determine whether to send the first message to the second device.

19. The method according to claim 18, characterized in that, The third information includes at least one of the following: The second indication is used to indicate whether a third model is available; The third indication is used to indicate whether model training is supported; The fourth indication is used to indicate the satellite scenario supported by the third model and / or the model training; The second function includes the third model and / or the function that supports model training. The model information of the third model includes at least one of the following: model identifier, supported functions, computing power required for model inference through the third model, and storage space required for model inference through the third model.

20. The method according to any one of claims 14-19, characterized in that, The method further includes: The first model and / or the second model are determined based on the first information.

21. The method according to any one of claims 13-20, characterized in that, The method further includes: Send second auxiliary information to the first device, the second auxiliary information being used by the first device to perform model monitoring.

22. The method according to claim 21, characterized in that, The second auxiliary information includes at least one of the following: The second identifier includes a model identifier and / or a function identifier; A first precision threshold is used by the first device to determine whether to perform a model switch. The fifth instruction is used to indicate the usage information and performance information of the first device storage model.

23. The method according to claim 21 or 22, characterized in that, The method further includes: Receive the fourth message sent by the first device; The decision to retrain the model is based on the fourth piece of information.

24. The method according to claim 23, characterized in that, The fourth piece of information includes at least one of the following: The second identifier includes a model identifier and / or a function identifier; The model uses time information; Accuracy information of model inference; Model rollback information.

25. A communication device, characterized in that, The communication device is used to perform the communication method according to any one of claims 1-12 and 13-24.

26. A communication system, characterized in that, The device includes a first device and a second device, wherein the first device is configured to implement the communication method of any one of claims 1-12, and the second device is configured to implement the communication method of any one of claims 13-24.

27. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the communication method as described in any one of claims 1-12, 13-24.

28. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by the communication device, it implements the steps of the method according to any one of claims 1-12, 13-24.

Images