Communication method, communication apparatus, communication device, medium, and program product

Abstract

The embodiments of the present disclosure relate to a communication method, a communication apparatus, a communication device, a medium, and a program product. The communication method can be applied to a first network element. The method comprises: obtaining training data from a second network element; and on the basis of the training data, training a first model. Therefore, in the embodiments of the present disclosure, training data is obtained from a second network element, and on the basis of the training data, a first model is trained, such that support can be provided for the training of the model.

Description

Communication method, communication device, communication equipment, medium and program product Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a communication method, a communication apparatus, a communication device, a medium, and a program product. Background Art

[0002] Models such as artificial intelligence (AI) models can be deployed in network elements, which need to provide support for the management, training, and application of the models.

[0003] Summary of the Invention

[0004] In the communication system, some network elements are defined to train machine learning (ML) models, while others are defined to perform inference. This makes it impossible to support the AI / ML functional framework of the NR air interface.

[0005] The embodiments of the present disclosure provide a communication method, a communication apparatus, a communication device, a medium, and a program product, which can be used to obtain training data to train a model.

[0006] According to a first aspect of an embodiment of the present disclosure, a model-based communication method is proposed, which is applied to a first network element. The method includes: obtaining training data from a second network element; and training a first model based on the training data.

[0007] According to a second aspect of an embodiment of the present disclosure, a model-based communication method is proposed, which is applied to a third network element. The method includes: receiving a first model from a first network element, where the first model is trained by the first network element; and storing the first model.

[0008] According to a third aspect of an embodiment of the present disclosure, a model-based communication method is proposed, which is applied to a fourth network element. The method includes: sending a first message to a first network element, wherein the first message is used to request the first network element to train a first model.

[0009] According to a fourth aspect of an embodiment of the present disclosure, a communication device is proposed, including: a first transceiver module, configured to obtain training data from a second network element; and a first processing module, configured to train a first model based on the training data.

[0010] According to the fifth aspect of an embodiment of the present disclosure, a communication device is proposed, including: a second transceiver module, configured to receive a first model from a first network element, where the first model is trained by the first network element; and a second processing module, used to store the first model.

[0011] According to a sixth aspect of an embodiment of the present disclosure, a communication device is proposed, including: a third transceiver module, configured to send a first message to a first network element, wherein the first message is used to request the first network element to train a first model.

[0012] According to a seventh aspect of the embodiments of the present disclosure, a communication device is provided, comprising: at least one processor and a memory storing instructions. When the instructions are executed by the communication device, the communication device implements the model-based communication method described in the first, second, and third aspects.

[0013] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is proposed, which stores instructions. When the instructions are executed on a communication device, the communication device executes the model-based communication method described in the first, second, and third aspects.

[0014] According to a ninth aspect of the embodiments of the present disclosure, a computer program product is provided, which, when executed by a communication device, causes the communication device to perform the model-based communication method described in the first, second, and third aspects.

[0015] According to a tenth aspect of the embodiments of the present disclosure, a computer program is provided, which, when executed on a computer, causes the computer to execute the model-based communication method according to the first, second, and third aspects.

[0016] According to an eleventh aspect of the embodiments of the present disclosure, a chip or chip system is provided. The chip or chip system includes a processing circuit. The processing circuit is configured to execute the model-based communication method described in the first, second, and third aspects.

[0017] Through the embodiments of the present disclosure, training data is obtained from the second network element, and the first model is trained based on the obtained training data, which can provide support for model training.

[0018] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and do not constitute limitations on the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0020] FIG1A is a schematic diagram showing an architecture of a communication system according to an embodiment of the present disclosure.

[0021] FIG1B is a schematic diagram of an architecture of an implementation of a communication system provided according to an embodiment of the present disclosure.

[0022] FIG2A is a schematic diagram of an AI functional framework based on a communication system.

[0023] FIG2B is a schematic diagram of an ML model providing architecture based on a communication system.

[0024] FIG3 is an exemplary interaction diagram of the model-based communication method provided by an embodiment of the present disclosure.

[0025] FIG4A is a flow chart of a model-based communication method performed by a first network element side according to an embodiment of the present disclosure.

[0026] FIG4B is a flow chart of a model-based communication method executed by a third network element side according to an embodiment of the present disclosure.

[0027] FIG4C is a schematic diagram of a flow chart of a model-based communication method executed on a fourth network element side according to an embodiment of the present disclosure.

[0028] FIG4D is a flow chart of a model-based communication method performed by a second network element, a terminal, and / or an access network device according to an embodiment of the present disclosure.

[0029] Figure 4E is a flowchart of a fifth network element, terminal and / or access network device side executing a model-based communication method according to an embodiment of the present disclosure.

[0030] FIG5A is another flowchart illustrating a model-based communication method executed by a first network element side according to an embodiment of the present disclosure.

[0031] FIG5B is another flowchart illustrating a model-based communication method executed by a third network element side according to an embodiment of the present disclosure.

[0032] FIG5C is another flowchart illustrating a model-based communication method executed by a fourth network element side according to an embodiment of the present disclosure.

[0033] FIG6 is a flowchart illustrating an exemplary implementation of a model-based communication method according to an embodiment of the present disclosure.

[0034] FIG7A is a schematic structural diagram of a communication device according to an embodiment of the present disclosure.

[0035] FIG7B is a schematic structural diagram of a communication device according to an embodiment of the present disclosure.

[0036] FIG7C is a schematic structural diagram of a communication device according to an embodiment of the present disclosure.

[0037] FIG8A is a schematic structural diagram of a communication device proposed in an embodiment of the present disclosure.

[0038] FIG8B is a schematic structural diagram of a chip proposed in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The embodiments of the present disclosure provide a communication method, a communication apparatus, a communication device, a medium, and a program product.

[0040] In a first aspect, an embodiment of the present disclosure proposes a model-based communication method applied to a first network element, the method comprising: obtaining training data from a second network element; and training a first model based on the training data.

[0041] In the embodiment of the present disclosure, training data is obtained from the second network element, and the first model is trained based on the obtained training data, which can provide support for model training.

[0042] In combination with some embodiments of the first aspect, in some embodiments, the method further includes: sending the trained first model to a third network element.

[0043] In combination with some embodiments of the first aspect, in some embodiments, the first model is an artificial intelligence model, a machine learning model, or a trainable model.

[0044] In combination with some embodiments of the first aspect, in some embodiments, before obtaining training data from the second network element, the method also includes: receiving a first message from a fourth network element, wherein the first message is used to request training of the first model.

[0045] In combination with some embodiments of the first aspect, in some embodiments, before sending the trained first model to the third network element, the method also includes: sending a second message to the fourth network element, wherein the second message is used to indicate that the training of the first model is accepted.

[0046] In combination with some embodiments of the first aspect, in some embodiments, the first message carries at least one of the following: first information, the first information is used to indicate the first model; second information, the second information is used to indicate the second network element, terminal and / or access network device that collects training data; third information, the third information is used to indicate the terminal, fifth network element and / or access network device that requests model training.

[0047] In combination with some embodiments of the first aspect, in some embodiments, the first information includes identification information of the first model and / or identification information of the first model function, and the first model function is associated with the first model.

[0048] In combination with some embodiments of the first aspect, in some embodiments, the fourth network element is a first core network element, and the first core network element is used to provide a model management function.

[0049] In combination with some embodiments of the first aspect, in some embodiments, the trained first model is carried in a third message, and the third message is used to instruct the third network element to update the model.

[0050] In combination with some embodiments of the first aspect, in some embodiments, the first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

[0051] In combination with some embodiments of the first aspect, in some embodiments, the second network element is used to collect training data.

[0052] In combination with some embodiments of the first aspect, in some embodiments, the second network element includes at least one of the following: a third core network network element, the third core network network element is used to provide user plane functions; a fourth core network network element, the fourth core network element is used to provide policy control functions; a fifth core network network element, the fifth core network element is used to provide data storage functions.

[0053] In combination with some embodiments of the first aspect, in some embodiments, the third network element is used to store the trained first model.

[0054] In combination with some embodiments of the first aspect, in some embodiments, the third network element includes at least one of the following: a fifth core network network element, which is used to provide data storage function; and a sixth core network network element, which is used to provide analysis data repository function.

[0055] In a second aspect, an embodiment of the present disclosure proposes a model-based communication method, which is applied to a third network element. The method includes: receiving a first model from a first network element, where the first model is trained by the first network element; and storing the first model.

[0056] In the embodiment of the present disclosure, a first model is received from a first network element, and the first model is stored, so as to provide support for the management of the model.

[0057] In combination with some embodiments of the second aspect, in some embodiments, the first model is an artificial intelligence model, a machine learning model, or a trainable model.

[0058] In combination with some embodiments of the second aspect, in some embodiments, the first model is carried in a third message, and the third message is used to indicate an updated model.

[0059] In combination with some embodiments of the second aspect, in some embodiments, the method further includes: sending a fourth message to the access network device and / or the terminal, where the fourth message is used to indicate the first model.

[0060] In the embodiment of the present disclosure, by sending a fourth message indicating the first model to the access network device and / or the terminal, the access network device and / or the terminal can obtain the message of the first model update in a timely manner.

[0061] In combination with some embodiments of the second aspect, in some embodiments, the access network device and / or the terminal is used to perform model-based reasoning operations.

[0062] In combination with some embodiments of the second aspect, in some embodiments, the first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

[0063] In combination with some embodiments of the second aspect, in some embodiments, the third network element is used to store the trained first model.

[0064] In combination with some embodiments of the second aspect, in some embodiments, the third network element includes at least one of the following: a fifth core network network element, which is used to provide data storage function; and a sixth core network network element, which is used to provide analysis data repository function.

[0065] In a third aspect, an embodiment of the present disclosure proposes a model-based communication method, which is applied to a fourth network element. The method includes: sending a first message to a first network element, wherein the first message is used to request the first network element to train a first model.

[0066] In an embodiment of the present disclosure, a first message for requesting the first network element to train a first model is sent to the first network element, so that the first network element can train the first model.

[0067] In combination with some embodiments of the third aspect, in some embodiments, the method further includes: receiving a second message from the first network element, wherein the second message is used to indicate that the training of the first model is accepted.

[0068] In combination with some embodiments of the third aspect, in some embodiments, the first message carries at least one of the following: first information, the first information is used to indicate the first model; second information, the second information is used to indicate the second network element, terminal and / or access network device that collects training data; third information, the third information is used to indicate the terminal, fifth network element and / or access network device that requests model training.

[0069] In combination with some embodiments of the third aspect, in some embodiments, the first information includes identification information of the first model and / or identification information of the first model function, and the first model function is associated with the first model.

[0070] In combination with some embodiments of the third aspect, in some embodiments, the fourth network element is a first core network element, and the first core network element is used to provide a model management function.

[0071] In a fourth aspect, embodiments of the present disclosure provide a communication device, applied to a first network element, comprising: a first transceiver module configured to obtain training data from a second network element; and a first processing module configured to train a first model based on the training data.

[0072] In combination with some embodiments of the fourth aspect, in some embodiments, the first transceiver module is further configured to: send the trained first model to the third network element.

[0073] In combination with some embodiments of the fourth aspect, in some embodiments, the first model is an artificial intelligence model, a machine learning model, or a trainable model.

[0074] In combination with some embodiments of the fourth aspect, in some embodiments, the first transceiver module is further configured to: receive a first message from a fourth network element before obtaining training data from the second network element, wherein the first message is used to request training of the first model.

[0075] In combination with some embodiments of the fourth aspect, in some embodiments, the first transceiver module is also configured to: send a second message to the fourth network element before sending the trained first model to the third network element, wherein the second message is used to indicate that the training of the first model is accepted.

[0076] In combination with some embodiments of the fourth aspect, in some embodiments, the first message carries at least one of the following: first information, the first information is used to indicate the first model; second information, the second information is used to indicate the second network element, terminal and / or access network device that collects training data; third information, the third information is used to indicate the terminal, fifth network element and / or access network device that requests model training.

[0077] In combination with some embodiments of the fourth aspect, in some embodiments, the first information includes identification information of the first model and / or identification information of the first model function, and the first model function is associated with the first model.

[0078] In combination with some embodiments of the fourth aspect, in some embodiments, the fourth network element is a first core network element, and the first core network element is used to provide a model management function.

[0079] In combination with some embodiments of the fourth aspect, in some embodiments, the trained first model is carried in a third message, and the third message is used to instruct the third network element to update the model.

[0080] In combination with some embodiments of the fourth aspect, in some embodiments, the first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

[0081] In combination with some embodiments of the fourth aspect, in some embodiments, the second network element is used to collect training data.

[0082] In combination with some embodiments of the fourth aspect, in some embodiments, the second network element includes at least one of the following: a third core network network element, the third core network network element is used to provide user plane functions; a fourth core network network element, the fourth core network element is used to provide policy control functions; a fifth core network network element, the fifth core network element is used to provide data storage functions.

[0083] In combination with some embodiments of the fourth aspect, in some embodiments, the third network element is used to store the trained first model.

[0084] In combination with some embodiments of the fourth aspect, in some embodiments, the third network element includes at least one of the following: a fifth core network network element, which is used to provide data storage function; and a sixth core network network element, which is used to provide analysis data repository function.

[0085] In a fifth aspect, embodiments of the present disclosure provide a communication device, applied to a third network element. The communication device includes: a second transceiver module configured to receive a first model from a first network element, where the first model is trained by the first network element; and a second processing module configured to store the first model.

[0086] In combination with some embodiments of the fifth aspect, in some embodiments, the first model is an artificial intelligence model, a machine learning model, or a trainable model.

[0087] In combination with some embodiments of the fifth aspect, in some embodiments, the first model is carried in a third message, and the third message is used to indicate an updated model.

[0088] In combination with some embodiments of the fifth aspect, in some embodiments, the second transceiver module is further configured to: send a fourth message to the access network device and / or terminal, where the fourth message is used to indicate the first model.

[0089] In combination with some embodiments of the fifth aspect, in some embodiments, the access network device and / or the terminal is used to perform model-based reasoning operations.

[0090] In combination with some embodiments of the fifth aspect, in some embodiments, the first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

[0091] In combination with some embodiments of the fifth aspect, in some embodiments, the third network element is used to store the trained first model.

[0092] In combination with some embodiments of the fifth aspect, in some embodiments, the third network element includes at least one of the following: a fifth core network network element, which is used to provide data storage function; and a sixth core network network element, which is used to provide analysis data repository function.

[0093] In a sixth aspect, an embodiment of the present disclosure provides a communication device, applied to a fourth network element. The communication device includes: a third transceiver module configured to send a first message to a first network element, wherein the first message is used to request the first network element to train a first model.

[0094] In combination with some embodiments of the sixth aspect, in some embodiments, the third transceiver module is further configured to: receive a second message from the first network element, wherein the second message is used to indicate that the training of the first model is accepted.

[0095] In combination with some embodiments of the sixth aspect, in some embodiments, the first message carries at least one of the following: first information, the first information is used to indicate the first model; second information, the second information is used to indicate the second network element, terminal and / or access network device that collects training data; third information, the third information is used to indicate the terminal, fifth network element and / or access network device that requests model training.

[0096] In combination with some embodiments of the sixth aspect, in some embodiments, the first information includes identification information of the first model and / or identification information of the first model function, and the first model function is associated with the first model.

[0097] In combination with some embodiments of the sixth aspect, in some embodiments, the fourth network element is a first core network element, and the first core network element is used to provide a model management function.

[0098] In a seventh aspect, embodiments of the present disclosure provide a communication device. The communication device includes at least one processor and a memory storing instructions. When executed by the communication device, the instructions enable the communication device to implement the model-based communication method described in the first, second, and third aspects and possible implementations thereof.

[0099] In an eighth aspect, an embodiment of the present disclosure proposes a storage medium storing instructions, which, when executed on a communication device, enables the communication device to execute the model-based communication method as described in the first aspect, the second aspect, the third aspect and possible implementations thereof.

[0100] In a ninth aspect, embodiments of the present disclosure provide a computer program product. When executed by a communication device, the computer program product causes the communication device to perform the model-based communication method described in the first aspect, the second aspect, the third aspect, and possible implementations thereof.

[0101] In a tenth aspect, an embodiment of the present disclosure provides a computer program. When the computer program is executed on a computer, the computer executes the model-based communication method as described in the first aspect, the second aspect, the third aspect, and possible implementations thereof.

[0102] In an eleventh aspect, embodiments of the present disclosure provide a chip or chip system. The chip or chip system includes a processing circuit. The processing circuit is configured to execute the model-based communication method described in the first aspect, the second aspect, the third aspect, and possible implementations thereof.

[0103] It is understandable that the above-mentioned communication devices, communication equipment, storage media, computer program products, computer programs, chips, or chip systems are all used to perform the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding methods and will not be repeated here.

[0104] The embodiments of the present disclosure provide a communication method, a communication apparatus, a communication device, a medium, and a program product. In some embodiments, the terms model-based communication method, model-based information processing method, model training method, communication method, etc. can be used interchangeably.

[0105] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0106] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0107] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0108] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0109] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0110] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," and the like can be used interchangeably.

[0111] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0112] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0113] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0114] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0115] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0116] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0117] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0118] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0119] In some embodiments, the terms "network devices", "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access network node", "access point", "transmission point (TP)", "reception point (RP)", "transmission and / or reception point (TRP)" "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femtocell", "picocell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0120] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0121] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0122] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0123] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0124] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0125] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0126] FIG1A is a schematic diagram illustrating an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG1A , a communication system 100 includes an access network device 101 and a core network device 102 .

[0127] In some embodiments, the access network device 101 can be, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a satellite base station, a base station in other communication systems, and at least one of an access node in a Wi-Fi system, but is not limited thereto.

[0128] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces within the access network equipment involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0129] In some embodiments, the access network device 101 can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0130] In some embodiments, the core network device 102 may be a single device, which may integrate the first network element, the second network element, the third network element, the fourth network element, the fifth network element, etc., or may be multiple devices or device groups, each including all or part of the first network element, the second network element, the third network element, the fourth network element, the fifth network element, etc. The core network device may be virtual or physical. The core network includes, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0131] In some embodiments, the first network element may be, for example, a network data analytics function (NWDAF).

[0132] In some embodiments, the first network element can be used to support data collection and implement AI model updates, and the name is not limited to this.

[0133] In some embodiments, the second network element may be, for example, a user plane function (UPF).

[0134] In some embodiments, the second network element may be used to support routing and forwarding of user plane data packets, but the name is not limited thereto.

[0135] In some embodiments, the second network element may be, for example, a policy control function (PCF).

[0136] In some embodiments, the second network element can be used to support a unified policy framework to manage network behavior, provide policy rules to control plane functions to execute these rules, access subscription information related to policy decisions in a unified data repository (UDR), and the name is not limited to this.

[0137] In some embodiments, the second network element may be, for example, a UDR function.

[0138] In some embodiments, the second network element can be used to support unified data management (UDM) storage and retrieval of subscription data, PCF storage and retrieval of policy data, storage and retrieval of structured data for exposure, and the name is not limited to this.

[0139] In some embodiments, the second network element may be used to collect training data.

[0140] In some embodiments, the third network element may be used to store the trained first model.

[0141] In some embodiments, the third network element may be, for example, a UDR function.

[0142] In some embodiments, the third network element may be used to support the storage and retrieval of subscription data by the UDM, the storage and retrieval of policy data by the PCF, and the storage and retrieval of structured data for exposure, without limitation.

[0143] In some embodiments, the third network element may be, for example, an Analytics Data Repository Function (ADRF).

[0144] In some embodiments, a third network element may be used to support storage of trained models.

[0145] In some embodiments, the fourth network element may be, for example, an AI management function (AIMF).

[0146] In some embodiments, the fourth network element can be used to implement management and monitoring of the AI ​​model, and the name is not limited thereto.

[0147] In some embodiments, the fifth network element can be used to request the first network element to perform model training.

[0148] In some embodiments, the fifth network element may perform model-based reasoning operations.

[0149] In some embodiments, the communication system 100 may be a 5G communication system. It should be noted that the communication system 100 may also be other communication systems, such as a 4G communication system or a 6G communication system, which is not specifically limited in the present disclosure.

[0150] Figure 1B is a schematic diagram of the architecture of an implementation of a communication system according to an embodiment of the present disclosure. As shown in Figure 1B, the architecture of the 5G communication system is presented in a service-based interface manner.

[0151] Namf is a service-based interface provided by the access and mobility management function (AMF). Nadrf is a service-based interface provided by the Active Directory Response Function (ADRF). Nnwdaf is a service-based interface provided by the National Mobile Internet Provider (NWDAF). Naimf is a service-based interface provided by the American Mobile Provider (AIMF). Nudm is a service-based interface provided by the UDM. N2 is the anchor point between the AMF and the RAN. N1 is the anchor point between the AMF and the UE. Uu is the interface between the RAN and the UE.

[0152] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.

[0153] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1A , or a portion thereof, but are not limited thereto. The entities shown in FIG1A are illustrative only. The communication system may include all or part of the entities shown in FIG1A , or may include other entities other than those shown in FIG1A . The number and form of the entities may be arbitrary. The connection relationship between the entities is illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0154] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile Communications (GSM (registered trademark)), CDMA2000, ultra mobile broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), public land mobile network (PLMN) networks, device-to-device (D2D) systems, machine-to-machine (M2M) systems, Internet of Things (IoT) systems, vehicle-to-everything (V2X), systems utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0155] Based on AI network architectures, the integration of communication networks and AI technologies is progressing. In this process, data analysis through the NWDAF mechanism and AI / machine learning (ML) enable intelligent 5GC and air interfaces in data collection, machine learning model training, and analytical reasoning. By introducing 5GC support capabilities, the AIML system (system support for AI / ML-based services, AIMLsys) can support AI / ML operations at the application layer.

[0156] In some embodiments, the scope of AL services in the communication network can be expanded, thereby using AI / ML technology to realize the intelligence of 5GC and air interface, provide automation of the communication network and improve the efficiency of the 5G network architecture.

[0157] Figure 2A is a schematic diagram of an AI functional framework for a communication system. As shown in Figure 2A , an AI / ML functional framework for the NR air interface can be introduced for the RAN. This functional framework 2100 can include the following five functions: data collection function 2101, model training function 2102, management function 2103, inference function 2104, and model storage function 2105.

[0158] In some embodiments, data collection functionality 2101 is used to provide input data to model training, management, inference, and other functions. The data collected through data collection may include at least one of the following: training data, monitoring data, and inference data. Training data may be data provided to the model training functionality. Monitoring data may be data provided to the management functionality. Inference data may be data provided to the inference functionality.

[0159] In some embodiments, the model training function 2102 is used to implement AI / ML model training, verification, and testing. Here, as part of the model verification process, the model training function can generate model performance indicators. In some cases, the model training function can also be responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and conversion) based on the training data from the data collection function. The model training function can provide the trained, verified, and tested model to the model storage function, or provide an updated version of the model to the model storage function.

[0160] In some embodiments, the management function 2103 is used to perform operational supervision (e.g., selection, activation, deactivation, switching, fallback) and monitoring (e.g., performance) of the model and its functions. In some embodiments, the management function may also be responsible for decision-making to ensure that appropriate reasoning operations are implemented based on data from the data collection function and the reasoning function. The management instructions of the management function can be information used to manage the reasoning function. This information may include the selection, activation, deactivation, switching, fallback to non-AI / ML operations, etc. of the model. The model transfer request of the management function can be used to request a model from the model storage function. The management function can provide performance feedback / retention requests to the model training function, for example, for training or updating the model.

[0161] In some embodiments, the reasoning function 2104 is used to provide the output of the process of applying the model or model function. This process can use the data provided by the data collection function (i.e., reasoning data) as input. In some embodiments, the reasoning function can also be responsible for data preparation (e.g., pre-processing and cleaning, formatting, and conversion of data) based on the training data from the data collection function. The output of the reasoning function can be used by the management function to monitor the performance of the model or model function.

[0162] In some embodiments, the model storage function 2105 can be used to store trained / updated models that can be used to perform inference. The model storage function can pass the model to the inference function.

[0163] Figure 2B is a schematic diagram of an ML model provisioning architecture for a communication system. As shown in Figure 2B , in a 5G system architecture, NWDAF 2201 may include an analytics logical function (AnLF). The AnLF may provide services using a trained ML model from another NWDAF 2202. The other NWDAF may include a model training logical function (MTLF).

[0164] In some embodiments, AnLF can perform inference, obtain analytical information, and expose analytical services.

[0165] In some embodiments, the MTLF can train ML models and expose new training services (e.g., provide trained ML models).

[0166] The ML model provisioning architecture shown in Figure 2B needs to be able to support the functional framework 2100 shown in Figure 2A. In some scenarios, model-based reasoning can be implemented by access network equipment (e.g., base stations). This requires sending the model to the base station.

[0167] FIG3 is an exemplary interaction diagram of a model-based communication method provided by an embodiment of the present disclosure. As shown in FIG3 , an embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S3001 to S3009.

[0168] In the embodiment of the present disclosure, an example is given in which the core network device includes a first network element, a second network element, a third network element, a third network element, and a fifth network element, and the access network device is a gNB.

[0169] In some embodiments, the first network element may be a second core network element, configured to provide a network data analysis function (such as NWDAF).

[0170] In some embodiments, the second network element can be at least one of the following: a third core network network element, used to provide user plane functions (such as UPF); a fourth core network network element, used to provide policy control functions (such as PCF); a fifth core network network element, used to provide data storage functions (such as UDR).

[0171] In some embodiments, the third network element may be at least one of the following: a fifth core network element, used to provide data storage function (such as UDR); a sixth core network element, used to provide analysis data repository function (such as ADRF).

[0172] In some embodiments, the fourth network element may be: a first core network element, configured to provide a model management function (such as AIMF).

[0173] In some embodiments, the fifth network element may be: a second core network element (such as NWDAF).

[0174] The following example illustrates the model-based communication process, using a second core network element (e.g., NWDAF) as the first network element, a third core network element (e.g., UPF) as the second network element, a sixth core network element (e.g., ADRF) as the third network element, a first core network element (e.g., AIMF) as the fourth network element, and a gNB as the access network device. The steps below that can be performed by the ADRF can also be performed by the UDR.

[0175] Step S3001: AIMF sends a first message to NWDAF.

[0176] In some embodiments, the NWDAF may receive the first message.

[0177] In some embodiments, AIMF can be used to manage and monitor AI models, but the name is not limited thereto.

[0178] In some embodiments, the first message may be used to request training of the first model. In some embodiments, the first message may be used to request NWDAF to train the first model.

[0179] In some embodiments, the name of the first message is not limited, for example, it can be a request message, a model training request message, etc.

[0180] In some embodiments, the first message may include identification information of the AIMF. In this case, the first message may be used to request training of one or more models associated with the AIMF. The first model may be at least one of the one or more models.

[0181] In some embodiments, the first message may carry at least one of the following: first information; second information; third information.

[0182] In some embodiments, the first information may be used to indicate a first model. In some embodiments, the first information may be used to indicate a model that requires NWDAF training.

[0183] In some embodiments, the first information may include identification information of the first model and / or identification information of the first model function.

[0184] In some embodiments, a first model function may be associated with the first model.

[0185] In some embodiments, the identification information of the first model may be an identifier of the first model.

[0186] In some embodiments, the identification information of the first model may be used to identify the first model. In this case, the first message may be used to request training of the first model identified by the identification information.

[0187] In some embodiments, the identification information of the first model function may be an identifier of the model function of the first model.

[0188] In some embodiments, the identification information of the first model function may be used to identify the first model. In this case, the first message may be used to request training of the first model identified by the identification information.

[0189] In some embodiments, the identification information of the first model function can be used to identify the function of the first model. In this case, the first message can be used to request training of the function of the first model identified by the identification information of the first model function.

[0190] In some embodiments, the second information may be used to indicate the UPF, terminal, gNB, PCF and / or UDR that collects the training data.

[0191] In some embodiments, the second information may include identification information of the UPF, identification information of the terminal collecting training data, identification information of the gNB collecting training data, identification information of the PCF and / or identification information of the UDR.

[0192] In some embodiments, the identification information of the UPF may be an identifier of the UPF. In this case, the second information may be used to indicate a network element that collects training data corresponding to the identifier of the UPF.

[0193] In some embodiments, the identification information of the PCF may be an identifier of the PCF. In this case, the second information may be used to indicate a network element that collects training data corresponding to the identifier of the PCF.

[0194] In some embodiments, the identification information of the UDR may be an identifier of the UDR. In this case, the second information may be used to indicate a network element that collects training data corresponding to the identifier of the UDR.

[0195] In some embodiments, the identification information of the terminal for collecting the training data may be an identifier of the terminal. In this case, the second information may be used to indicate the terminal for collecting the training data corresponding to the identifier of the terminal.

[0196] In some embodiments, the identification information of the gNB collecting the training data may be an identifier of the gNB. In this case, the second information may be used to indicate the gNB collecting the training data corresponding to the identifier of the gNB.

[0197] In some embodiments, the third information can be used to indicate the terminal, gNB and / or fifth network element requesting model training.

[0198] In some embodiments, the third information may include identification information of the terminal requesting model training, identification information of the gNB and / or identification information of the fifth network element.

[0199] In some embodiments, the identification information of the terminal requesting model training may be an identifier of the terminal. In this case, the third information may be used to indicate the terminal corresponding to the identifier of the terminal requesting model training. The first message may be used to indicate that the terminal corresponding to the identifier of the terminal requests training of the first model.

[0200] In some embodiments, the identification information of the gNB requesting model training may be an identifier of the gNB requesting model training.

[0201] In some embodiments, the gNB that requested model training can be used to perform model-based inference operations.

[0202] In some embodiments, the identification information of the fifth network element requesting model training may be an identifier of the fifth network element.

[0203] In some embodiments, the fifth network element requesting model training may be used to perform model-based reasoning operations. Here, the fifth network element may be, for example, an NWDAF.

[0204] In some embodiments, the first model may be at least one of the following: an AI model, an ML model, a trainable model.

[0205] Step S3002: NWDAF collects training data.

[0206] In some embodiments, the NWDAF may obtain training data from at least one of the gNB, UE, UPF, PCF, and UDR.

[0207] In some embodiments, the NWDAF may send a seventh message to the UPF.

[0208] In some embodiments, the seventh message may be used to obtain training data.

[0209] In some embodiments, the name of the seventh message is not limited. For example, it can be a training data request message, a training data acquisition message, etc.

[0210] In some embodiments, the UPF may receive a seventh message.

[0211] In some embodiments, the UPF may send training data to the NWDAF according to the seventh message.

[0212] In some embodiments, the NWDAF may send a seventh message to the gNB.

[0213] In some embodiments, the gNB may receive a seventh message.

[0214] In some embodiments, the gNB may send training data to the NWDAF based on the seventh message.

[0215] In some embodiments, the NWDAF may send a seventh message to the UE.

[0216] In some embodiments, the UE may receive a seventh message.

[0217] In some embodiments, the UE may send training data to the NWDAF according to the seventh message.

[0218] In some embodiments, the NWDAF may send a seventh message to the PCF.

[0219] In some embodiments, the PCF may receive a seventh message.

[0220] In some embodiments, the PCF may send training data to the NWDAF according to the seventh message.

[0221] In some embodiments, the NWDAF may send a seventh message to the UDR.

[0222] In some embodiments, the UDR may receive a seventh message.

[0223] In some embodiments, the UDR may send training data to the NWDAF according to the seventh message.

[0224] In some embodiments, the NWDAF may receive training data sent by at least one of the gNB, UE, UPF, PCF, and UDR.

[0225] In some embodiments, NWDAF may collect training data.

[0226] In some embodiments, the training data may serve as input data to a first model training function.

[0227] In some embodiments, the training data may serve as input data for the first model.

[0228] In some embodiments, the UPF may be used to support routing and forwarding of user plane data packets, without limitation.

[0229] In some embodiments, the steps performed by the UPF may also be performed by at least one of the access network device, PCF, UDR, and terminal.

[0230] In some embodiments, PCF can be used to support a unified policy framework to manage network behavior, provide policy rules to control plane functions to enforce these rules, and subscribe to information related to policy decisions in UDRs, without limitation.

[0231] In some embodiments, the UDR may be used for storage and retrieval of subscription data by the UDM, storage and retrieval of policy data by the PCF, storage and retrieval of structured data for exposure, and the like.

[0232] In some embodiments, at least one of the access network device, UE, UPF, PCF, and UDR may be used to collect training data.

[0233] In some embodiments, the NWDAF may obtain training data in response to the first message. That is, steps S3001 and S3002 may be performed sequentially.

[0234] In some embodiments, NWDAF may obtain training data autonomously, that is, step S3001 may not need to be performed before step S3002.

[0235] Step S3003: NWDAF trains a first model based on the training data.

[0236] In some embodiments, after obtaining the training data, NWDAF may train the first model according to the training data.

[0237] In some embodiments, the first model may be sent by the ADRF to the NWDAF.

[0238] In some embodiments, the NWDAF may receive the first model.

[0239] Step S3004: NWDAF sends a second message to AIMF.

[0240] In some embodiments, the AIMF may receive the second message.

[0241] In some embodiments, the second message may be used to indicate that the training of the first model is accepted. In some embodiments, the second message may be used to indicate that the training request of the first model is accepted.

[0242] In some embodiments, the name of the second message is not limited. For example, it can be a model training response message, a response message requesting training of the first model, etc.

[0243] In some embodiments, the NWDAF may send the second message to the AIMF after training the first model based on the training data. That is, steps S3003 and S3004 may be performed sequentially.

[0244] Step S3005: NWDAF sends the trained first model to ADRF.

[0245] In some embodiments, the ADRF may receive the trained first model.

[0246] In some embodiments, after NWDAF trains the first model, a trained first model can be obtained.

[0247] In some embodiments, the trained first model may carry a third message.

[0248] In some embodiments, the ADRF may receive a third message carried by the trained first model.

[0249] In some embodiments, the third message may be used to indicate an update model.

[0250] In some embodiments, the name of the third message is not limited, for example, it can be an update model message, a local model update message, etc.

[0251] In some embodiments, ADRF can be used to store the trained first model.

[0252] In some embodiments, the steps performed by ADRF may also be performed by UDR.

[0253] In some embodiments, the UDR may be used to support the storage and retrieval of subscription data by the UDM, the storage and retrieval of policy data by the PCF, and the storage and retrieval of structured data for exposure, without limitation.

[0254] In some embodiments, ADRF can be used to support storage of trained models.

[0255] In some embodiments, the UDR may be used to support storage of trained models.

[0256] In some embodiments, after training the first model based on the training data, the NWDAF may directly send the trained first model to the ADRF. In other words, step S3004 may not need to be performed before step S3005.

[0257] Step S3006: ADRF stores the first model.

[0258] In some embodiments, the ADRF may store the first model after receiving the third message carried by the trained first model.

[0259] In some embodiments, ADRF may directly store the first model trained by NWDAF. For example, different version numbers may be used to distinguish the first model after training from the first model before training.

[0260] In some embodiments, ADRF may delete the previous first model and store the first model trained by NWDAF.

[0261] In some embodiments, the steps performed by ADRF may also be performed by UDR.

[0262] In some embodiments, after storing the first model, the ADRF may send a message about updating the first model and / or other models to the AIMF. In this case, the AIMF may receive the message about updating the first model and / or other models.

[0263] In this embodiment, by sending a message for updating the first model and / or other models to the AIMF, the AIMF can send a message for updating the first model and / or other models to the gNB, UE, and / or network function (NF).

[0264] In some embodiments, the other model may be a different model than the first model.

[0265] In some embodiments, the first model update may be a change in the version of the first model. In some embodiments, the first model update may be a change in the function of the first model.

[0266] Step S3007: ADRF sends a sixth message to NWDAF.

[0267] In some embodiments, the NWDAF may receive the sixth message.

[0268] In some embodiments, the sixth message may be used to indicate that the first model has been updated (eg, the first model has been trained). In some embodiments, the sixth message may be used to indicate that the ADRF has stored the trained first model.

[0269] In some embodiments, the sixth message may include at least one of the following: identification information of the first model, identification information of the first model function, and an acknowledgement character (ACK).

[0270] In some embodiments, the name of the sixth message is not limited. For example, it can be a model update completion message, a model updated message, etc.

[0271] In some embodiments, the steps performed by ADRF may also be performed by UDR.

[0272] In some embodiments, after sending the sixth message to the NWDAF, the ADRF may send a message about the first model and / or other model updates to the AIMF. In this case, the AIMF may receive the message about the first model and / or other model updates.

[0273] Step S3008: The gNB and / or UE sends a fifth message.

[0274] In some embodiments, the ADRF may receive the fifth message.

[0275] In some embodiments, the steps performed by the gNB and / or UE may also be performed by the NF. Here, the NF may perform model-based reasoning operations.

[0276] In some embodiments, the NF may be a NWDAF, where the NWDAF may perform model-based reasoning operations.

[0277] In some embodiments, the fifth message may be used to subscribe to updates of the first model. In some embodiments, the fifth message may be used to subscribe to updates of the first model from the ADRF.

[0278] In some embodiments, the fifth message may be used to subscribe to an update notification service from ADRF. In some embodiments, the fifth message may be used to request ADRF to send a notification for an update of the first model.

[0279] In some embodiments, the name of the fifth message is not limited, for example, it can be a subscription message, a model update request message, etc.

[0280] In some embodiments, the fifth message may include identification information of the gNB and / or UE. In this case, the fifth message may be used to subscribe to updates of one or more models associated with the gNB and / or UE. The first model may be at least one of the one or more models.

[0281] In some embodiments, the fifth message may include identification information of the NF. In this case, the fifth message may be used to subscribe to updates of one or more models associated with the NF. The first model may be at least one of the one or more models.

[0282] In some embodiments, the fifth message may include at least one of the following: identification information of the first model, identification information of the first model function.

[0283] In some embodiments, the gNB may be configured to perform model-based reasoning operations.

[0284] In some embodiments, the terminal may be configured to perform model-based reasoning operations.

[0285] In some embodiments, the ADRF may receive a fifth message sent by the gNB, UE, and / or NF after storing the first model. In other words, step S3007 may not need to be performed before step S3008.

[0286] In some embodiments, the AIMF may receive a message indicating that the first model and / or other models are updated. In this case, the gNB, UE, and / or NF may send a fifth message to the AIMF.

[0287] In some embodiments, the AIMF may receive the fifth message.

[0288] Step S3009: The ADRF sends a fourth message to the gNB and / or UE.

[0289] In some embodiments, the gNB may receive a fourth message.

[0290] In some embodiments, the UE may receive a fourth message.

[0291] In some embodiments, the NF may receive the fourth message, where the NF may perform a model-based reasoning operation.

[0292] In some embodiments, the fourth message may be used to indicate the first model. In some embodiments, the fourth message may be used to indicate that the first model has been updated.

[0293] In some embodiments, the name of the fourth message is not limited, for example, it can be an update notification message, an update indication message, etc.

[0294] In some embodiments, the fourth message may include at least one of the following: identification information of the first model, identification information of the first model function.

[0295] In some embodiments, the gNB, UE, and / or NF may determine that the first model has been updated based on the fourth message. In some embodiments, the gNB, UE, and / or NF may determine that the first model has been updated based on the identification information of the first model and / or the identification information of the first model function carried in the fourth message.

[0296] In some embodiments, the ADRF may directly trigger the sending of the fourth message to the gNB, UE, and / or NF after sending the sixth message. In other words, step S3008 may not need to be performed before step S3009.

[0297] In some embodiments, after storing the first model, the ADRF may directly trigger the sending of the fourth message to the gNB, UE, and / or NF. In other words, steps S3007 and S3008 may not need to be performed before step S3009.

[0298] In some embodiments, the AIMF receives the fifth message. In this case, the AIMF may send a fourth message to the gNB, UE, and / or NF.

[0299] In this embodiment, after receiving the message indicating that the first model is updated and the fifth message for subscribing to updates of the first model and / or other models, the AIMF can promptly send a message indicating that the first model and / or other models have been updated to the gNB, UE, and / or NF, so that the gNB, UE, and / or NF can obtain the updated first model and / or other models to perform model inference operations.

[0300] In some embodiments, the AIMF may directly trigger the sending of a fourth message to the gNB, UE, and / or NF after receiving a message about the first model and / or other model updates.

[0301] In this embodiment, after receiving the message indicating that the first model and / or other models have been updated, the AIMF directly sends a message indicating that the first model and / or other models have been updated to the gNB, UE, and / or NF, so that the gNB, UE, and / or NF can obtain the updated first model and / or other models to perform model inference operations.

[0302] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0303] In some embodiments, the terms "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based" and the like may be used interchangeably.

[0304] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0305] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0306] In some embodiments, the determination or judgment can be performed by a value represented by 1 bit (0 or 1), or by a true or false value (Boolean value) represented by true or false, or by comparison of numerical values ​​(for example, comparison with a predetermined value), but is not limited thereto.

[0307] The model-based communication method according to the embodiments of the present disclosure may include at least one of steps S3001 to S3009. For example, step S3001 may be implemented as an independent embodiment, step S3008 may be implemented as an independent embodiment, the combination of steps S3002, S3003, and S3005 may be implemented as an independent embodiment, the combination of steps S3005 and S3006 may be implemented as an independent embodiment, and the combination of steps S3008, S3006, and S3007 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0308] In some embodiments, steps S3002, S3003, S304, S3005, S3006, S3007, S3008, and S3009 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0309] In some embodiments, steps S3001, S3002, S3003, S304, S3005, S3006, S3007, and S3009 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0310] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3 .

[0311] Figure 4A is a flow chart illustrating a model-based communication method performed by a first network element according to an embodiment of the present disclosure. As shown in Figure 4A , the present embodiment relates to a model-based communication method. The model-based communication method includes steps S4101 to S4106.

[0312] Step S4101, obtain the first message.

[0313] The optional implementation of step S4101 can refer to the optional implementation of step S3001 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0314] Step S4102: Obtain training data.

[0315] The optional implementation of step S4102 can refer to the optional implementation of step S3002 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0316] Step S4103: train the first model based on the training data.

[0317] The optional implementation of step S4103 can refer to the optional implementation of step S3003 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0318] Step S4104, sending the second message.

[0319] The optional implementation of step S4104 can refer to the optional implementation of step S3004 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0320] Step S4105: Send the trained first model.

[0321] The optional implementation of step S4105 can refer to the optional implementation of step S3005 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0322] Step S4106, obtain the sixth message.

[0323] The optional implementation of step S4106 can refer to the optional implementation of step S3007 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0324] FIG4B is a flow chart illustrating a model-based communication method implemented by a third network element according to an embodiment of the present disclosure. As shown in FIG4B , the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S4201 to S4205.

[0325] Step S4201, obtain the first trained model.

[0326] The optional implementation of step S4201 can refer to the optional implementation of step S3005 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0327] Step S4202: store the first model.

[0328] The optional implementation of step S4202 can refer to the optional implementation of step S3006 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0329] Step S4203, sending the sixth message.

[0330] The optional implementation of step S4203 can refer to the optional implementation of step S3007 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0331] Step S4204, obtain the fifth message.

[0332] The optional implementation of step S4204 can refer to the optional implementation of step S3008 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0333] Step S4205: Send the fourth message.

[0334] The optional implementation of step S4205 can refer to the optional implementation of step S3009 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0335] Figure 4C is a flow chart illustrating a model-based communication method implemented on a fourth network element side according to an embodiment of the present disclosure. As shown in Figure 4C, the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S4301 to S4302.

[0336] Step S4301, sending the first message.

[0337] The optional implementation of step S4301 can refer to the optional implementation of step S3001 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0338] Step S4302, obtain the second message.

[0339] The optional implementation of step S4302 can refer to the optional implementation of step S3004 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0340] Figure 4D is a flow chart illustrating a model-based communication method implemented by a second network element, terminal, and / or access network device according to an embodiment of the present disclosure. As shown in Figure 4D , the present disclosure embodiment relates to a model-based communication method. The model-based communication method includes step S4401.

[0341] Step S4401: Send training data.

[0342] The optional implementation of step S4401 can refer to the optional implementation of step S3002 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0343] Figure 4E is a flowchart illustrating a fifth network element, terminal, and / or access network device performing a model-based communication method according to an embodiment of the present disclosure. As shown in Figure 4E , the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S4501 to S4502.

[0344] Step S4501, sending the fifth message.

[0345] The optional implementation of step S4501 can refer to the optional implementation of step S3008 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0346] Step S4502, obtain the fourth message.

[0347] The optional implementation of step S4502 can refer to the optional implementation of step S3009 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0348] Figure 5A is another schematic diagram of a flow chart of a model-based communication method performed by a first network element according to an embodiment of the present disclosure. As shown in Figure 5A, the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S5101 to S5102.

[0349] Step S5101, obtaining training data.

[0350] The optional implementation of step S5101 can refer to the optional implementation of step S3002 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0351] Step S5102: train the first model based on the training data.

[0352] The optional implementation of step S5102 can refer to the optional implementation of step S3003 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0353] FIG5B is another flow diagram of a model-based communication method performed by a third network element side according to an embodiment of the present disclosure. As shown in FIG5B , the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes steps S5201 to S5202.

[0354] Step S5201, obtain the first trained model.

[0355] The optional implementation of step S5201 can refer to the optional implementation of step S3005 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0356] Step S5202: store the first model.

[0357] The optional implementation of step S5202 can refer to the optional implementation of step S3006 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0358] FIG5C is another flow diagram of a fourth network element side executing a model-based communication method according to an embodiment of the present disclosure. As shown in FIG5C , the embodiment of the present disclosure relates to a model-based communication method. The model-based communication method includes step S5301.

[0359] Step S5301, sending the first message.

[0360] The optional implementation of step S5301 can refer to the optional implementation of step S3001 in Figure 3 and other related parts in the embodiment involved in Figure 3, which will not be repeated here.

[0361] Hereinafter, the embodiments of the present disclosure are exemplarily described through specific implementation methods.

[0362] Referring again to the architecture shown in FIG. 1B , the functions of the AIMF (ie, the first network element), the ADRF (ie, the second network element), the NWDAF (ie, the third network element), and the UDM are described.

[0363] In some embodiments, the AIMF may be a new network element that is responsible for the lifecycle management (LCM) of the AI ​​model (e.g., registration, selection, activation, deactivation, switching) and supports gNB (i.e., access network equipment) to subscribe to the AI ​​model update notification service.

[0364] In some embodiments, ADRF may be an enhanced function that is used to store trained AI models.

[0365] In some embodiments, NWDAF can be an enhanced function that is used to implement data collection and AI model training. In addition, NWDAF can also send AI model update notifications to AIMF.

[0366] In some embodiments, the UDM may be an enhanced function for storing subscription data related to the AI ​​model for the UE.

[0367] Figure 6 is a flowchart of an exemplary implementation of a model-based communication method according to an embodiment of the present disclosure. As shown in Figure 6, the model-based communication method may exemplarily include steps S601 to S606.

[0368] Step S601: AIMF / other NF (ie, the fourth network element) sends a model training request to NWDAF.

[0369] In some embodiments, the NWDAF receives model training requests from the AIMF or other NFs.

[0370] In some embodiments, the model training request may include a UE ID (i.e., identification information of a terminal requesting model training), an AI model ID (i.e., identification information of a first model) or an AI model function ID (i.e., identification information of a first model function), and a network element ID for training data (i.e., identification information of a second network element for collecting training data).

[0371] In step S602 , the NWDAF performs training data collection to collect training data from network elements used for training data and trains an AI model (ie, a first model).

[0372] In step S603, the NWDAF sends a response message to the AIMF and / or other NFs. Here, the response message may be used to indicate that the training of the AI ​​model is accepted.

[0373] Step S604: NWDAF sends the trained / updated AI model to AIMF and / or other NFs.

[0374] In some embodiments, after completing the AI ​​model training and obtaining the trained / updated AI model, the NWDAF can upload the trained / updated AI model to the ADRF (i.e., the third network element) or the NF storing the AI ​​model (i.e., the third network element).

[0375] In step S605 , the ADRF updates the local AI model using the received trained / updated AI model.

[0376] In some embodiments, after updating the local AI model, the ADRF may send a message about the local AI model and / or other model updates to the AIMF. In this case, the AIMF may receive the message about the local AI model and / or other model updates.

[0377] In some embodiments, the AIMF may receive a subscription message from the UE, gNB, and / or NF. Here, the subscription message may be used to subscribe to updates of the first model and / or other models.

[0378] In some embodiments, after receiving a message about updates to the local AI model and / or other models, the AIMF may send the AI ​​model to the UE, gNB, and / or NF that have subscribed to these updates.

[0379] In step S606, the ADRF sends the AI ​​model to the UE, gNB, and / or NF that have subscribed to these updates.

[0380] Step S607: ADRF feeds back an ACK indicating that the local AI model update is complete to NWDAF.

[0381] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device) in any of the above methods.

[0382] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions, and in actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), and the functions of some or all of the above units or modules are realized by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD), taking a field programmable gate array (FPGA) as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by software called by the processor, and the rest by hardware circuits.

[0383] In the embodiment of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and execution capability, such as a CPU, a microprocessor, a graphics processing unit (GPU) (also understood as a microprocessor), or a digital signal processor (DSP); in another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit, and the logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration 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 a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0384] As shown in Figure 7A, Figure 7A is a structural diagram of a communication device shown according to an embodiment of the present disclosure. The structure of the above-mentioned communication device 7100 can be as shown in Figure 7A. The communication device 7100 can be applied to a first network element. The communication device 7100 includes: a first transceiver module 7101 and a first processing module 7102. In some embodiments, the first transceiver module 7101 is used to obtain training data from the second network element; the first processing module 7102 is used to train the first model based on the training data. In some embodiments, the above-mentioned first transceiver module 7101 is configured to perform at least one of the communication steps such as sending and / or receiving performed by the network device in any of the above methods (for example, step S4101, step S4102, step S4104, step S4105, step S4106), which will not be repeated here.

[0385] In some embodiments, the first transceiver module 7101 may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the first transceiver module 7101 may be interchangeable with a transceiver.

[0386] As shown in Figure 7B, Figure 7B is a structural diagram of a communication device shown according to an embodiment of the present disclosure. The structure of the above-mentioned communication device 7200 can be as shown in Figure 7B. The communication device 7200 can be applied to a third network element. The communication device 7200 includes: a second transceiver module 7201 and a second processing module 7202. In some embodiments, the second transceiver module 7201 is used to receive a first model from a first network element, and the first model is trained by the first network element; the second processing module 7202 is used to store the first model. In some embodiments, the above-mentioned second transceiver module 7201 is configured to perform at least one of the communication steps such as sending and / or receiving performed by the terminal in any of the above methods (for example, step S4201, step S4203, step S4204, step S4205), which will not be repeated here.

[0387] In some embodiments, the second transceiver module 7201 may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the second transceiver module 7201 may be interchangeable with a transceiver.

[0388] As shown in Figure 7C, Figure 7C is a structural diagram of a communication device shown according to an embodiment of the present disclosure. The structure of the above-mentioned communication device 7300 can be as shown in Figure 7C. The communication device 7300 can be applied to the fourth network element. The communication device 7300 includes: a third transceiver module 7301. In some embodiments, the third transceiver module 7301 is used to send a first message to the first network element, wherein the first message is used to request the first network element to train a first model. In some embodiments, the above-mentioned third transceiver module 7301 is configured to perform at least one of the communication steps such as sending and / or receiving (for example, step S4301, step S4302) performed by the fourth network element in any of the above methods, which will not be repeated here.

[0389] In some embodiments, the third transceiver module 7301 may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the third transceiver module 7301 may be interchangeable with a transceiver.

[0390] Figure 8A is a schematic diagram of the structure of a communication device proposed in an embodiment of the present disclosure. Communication device 8100 can be a first network element, a third network element, a fourth network element, an access network device, a terminal (e.g., user equipment, etc.), a chip, a chip system, or a processor that supports communication device 8100 to implement any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above methods. Communication device 8100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0391] As shown in Figure 8A, the communication device 8100 includes one or more processors 8101. The processor 8101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the network node (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. Optionally, the communication device 8100 is used to perform the steps of any of the above methods. Optionally, one or more processors 8101 are used to call instructions to cause the communication device 8100 to perform the steps of any of the above methods.

[0392] In some embodiments, the communication device 8100 further includes one or more transceivers 8102. When the communication device 8100 includes one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., step S3001, step S3002, step S3004, step S3005, step S3007, step S3008, step S3009, but not limited thereto), and the processor 8101 performs at least one of the other steps (e.g., step S3003, step S3006, but not limited thereto). In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface may be interchangeable, the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be interchangeable, and the terms receiver, receiving unit, receiver, and receiving circuit may be interchangeable.

[0393] In some embodiments, the communication device 8100 further includes one or more memories 8103 for storing data. Alternatively, all or part of the memories 8103 may be located outside the communication device 8100. In alternative embodiments, the communication device 8100 may include one or more interface circuits 8104. Optionally, the interface circuits 8104 are connected to the memories 8103 and may be configured to receive data from the memories 8103 or other devices, or to send data to the memories 8103 or other devices. For example, the interface circuits 8104 may read data stored in the memories 8103 and send the data to the processor 8101.

[0394] The communication device 8100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 8100 described in the present disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 8A. The access network device may be an independent device or may be part of a larger device. For example, the terminal may be: (1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0395] FIG8B is a schematic diagram of a chip structure according to an embodiment of the present disclosure. In the case where the communication device 8100 can be a chip or a chip system, reference can be made to the schematic diagram of the chip structure 8200 shown in FIG8B , but the present disclosure is not limited thereto.

[0396] The chip 8200 includes one or more processors 8201. The chip 8200 is configured to execute the steps of any of the above methods.

[0397] In some embodiments, chip 8200 further includes one or more interface circuits 8202. Terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 8200 further includes one or more memories 8203 for storing data. Alternatively, all or part of memory 8203 may be located external to chip 8200. Optionally, interface circuit 8202 is connected to memory 8203 and may be used to receive data from memory 8203 or other devices, or may be used to send data to memory 8203 or other devices. For example, interface circuit 8202 may read data stored in memory 8203 and send the data to processor 8201.

[0398] In some embodiments, the interface circuit 8202 performs at least one of the communication steps of sending and / or receiving in the above method. For example, the interface circuit 8202 performing the communication steps of sending and / or receiving in the above method means that the interface circuit 8202 performs data exchange between the processor 8201, the chip 8200, the memory 8203, or the transceiver device.

[0399] The modules and / or devices described in various embodiments, such as virtual devices, physical devices, and chips, can be arbitrarily combined or separated according to circumstances. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0400] The present disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 8100, causes the communication device 8100 to perform the steps of any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto, and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto, and may also be a temporary storage medium.

[0401] The embodiments of the present disclosure further provide a computer program product. When the computer program product is executed by the communication device 8100, the communication device 8100 executes the steps of any of the above methods.

[0402] The embodiments of the present disclosure also provide a computer program, which, when executed on a computer, enables the computer to execute the steps of any of the above methods.

[0403] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the embodiments disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0404] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A model-based communication method, applied to a first network element, comprising: Obtaining training data from a second network element; Based on the training data, a first model is trained.

2. The method according to claim 1, further comprising: The trained first model is sent to the third network element.

3. The method according to claim 1 or 2, wherein: The first model is an artificial intelligence model, a machine learning model or a trainable model.

4. The method according to any one of claims 1 to 3, wherein: Before obtaining the training data from the second network element, the method further includes: A first message is received from a fourth network element, wherein the first message is used to request training of a first model.

5. The method according to claim 4, wherein Before sending the trained first model to the third network element, the method further includes: Send a second message to the fourth network element, where the second message is used to indicate that the training of the first model is accepted.

6. The method according to claim 4 or 5, wherein: The first message carries at least one of the following: first information, where the first information is used to indicate the first model; second information, where the second information is used to indicate a second network element, terminal and / or access network device that collects training data; The third information is used to indicate the terminal, fifth network element and / or access network device requesting model training.

7. The method according to claim 6, wherein: The first information includes identification information of the first model and / or identification information of a first model function, and the first model function is associated with the first model.

8. The method according to any one of claims 4 to 7, wherein: The fourth network element is the first core network element, and the first core network element is used to provide model management functions.

9. The method according to any one of claims 1 to 8, wherein: The trained first model is carried in a third message, and the third message is used to instruct the third network element to update the model.

10. The method according to any one of claims 1 to 9, wherein: The first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

11. The method according to any one of claims 1 to 10, wherein: The second network element is used to collect the training data.

12. The method according to claim 11, wherein The second network element includes at least one of the following: a third core network network element, configured to provide a user plane function; a fourth core network element, configured to provide a policy control function; The fifth core network network element is used to provide a data storage function.

13. The method according to any one of claims 1 to 12, wherein: The third network element is used to store the trained first model.

14. The method according to claim 13, wherein The third network element includes at least one of the following: A fifth core network network element, configured to provide a data storage function; The sixth core network element is used to provide an analysis data storage repository function.

15. A model-based communication method, applied to a third network element, the method comprising: receiving a first model from a first network element, where the first model is trained by the first network element; The first model is stored.

16. The method according to claim 15, wherein The first model is an artificial intelligence model, a machine learning model or a trainable model.

17. The method according to claim 15 or 16, wherein The first model is carried in a third message, and the third message is used to indicate an updated model.

18. The method according to any one of claims 15 to 17, wherein: The method further comprises: A fourth message is sent to the access network device and / or the terminal, where the fourth message is used to indicate the first model.

19. The method according to claim 18, wherein The access network device and / or terminal is used to perform model-based reasoning operations.

20. The method according to any one of claims 15 to 19, wherein The first network element is a second core network element, and the second core network element is used to provide a network data analysis function.

21. The method according to any one of claims 15 to 20, wherein: The third network element is used to store the trained first model.

22. The method according to claim 21, wherein The third network element includes at least one of the following: A fifth core network network element, configured to provide a data storage function; The sixth core network element is used to provide an analysis data storage repository function.

23. A model-based communication method, applied to a fourth network element, the method comprising: A first message is sent to a first network element, wherein the first message is used to request the first network element to train a first model.

24. The method according to claim 23, wherein The method further comprises: A second message is received from the first network element, wherein the second message is used to indicate that the training of the first model is accepted.

25. The method according to claim 23 or 24, wherein The first message carries at least one of the following: first information, where the first information is used to indicate the first model; second information, where the second information is used to indicate a second network element, terminal and / or access network device that collects training data; The third information is used to indicate the terminal, fifth network element and / or access network device requesting model training.

26. The method according to claim 25, wherein The first information includes identification information of the first model and / or identification information of a first model function, and the first model function is associated with the first model.

27. The method according to any one of claims 23 to 26, wherein: The fourth network element is the first core network element, and the first core network element is used to provide model management functions.

28. A communication device comprising: a first transceiver module configured to obtain training data from a second network element; The first processing module is configured to train a first model based on the training data.

29. A communication device comprising: a second transceiver module configured to receive a first model from a first network element, where the first model is trained by the first network element; The second processing module is configured to store the first model.

30. A communication device comprising: The third transceiver module is configured to send a first message to the first network element, wherein the first message is used to request the first network element to train a first model.

31. A communication device comprising: at least one processor; at least one processor; a memory storing instructions; When the instruction is executed by the communication device, the communication device implements the model-based communication method according to any one of claims 1 to 27.

32. A storage medium storing instructions, which, when executed on a communication device, causes the communication device to execute the model-based communication method according to any one of claims 1 to 27.

33. A computer program product comprising a computer program, which, when run on a communication device, causes the communication device to perform the model-based communication method according to any one of claims 1 to 27.

Images