Communication method and device

Abstract

The invention provides a communication method and equipment. The method comprises the following steps: acquiring one or more AI cases; and interacting with a network element of a first plane to obtain a trained first AI model related to the AI use case, the first plane at least comprising an intelligent plane, a data plane and a computing plane. By adding an intelligent plane, a data plane and a calculation plane in a network structure, generation and training of AI models of different use cases are realized, advanced AI and a mobile network can be integrated, and then diversity of AI functions can be increased in the mobile network, so that the capability of intelligently controlling network parameters by using the AI functions can be utilized, and the network performance of the mobile network can be improved. And the performance of the existing communication system and the service experience quality of the user are improved.

Description

Communication methods and devices

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods and devices.

[0002] The application scenarios of artificial intelligence (AI) technologies, represented by deep learning (DL) and reinforcement learning (RL), largely overlap with future mobile communication technologies (such as 5G and 6G). Therefore, in the face of the evolution of future mobile networks, how to add AI functions to future mobile networks has become a research hotspot.

[0003]

[0004] This disclosure presents a communication method and device.

[0005] According to a first aspect of the embodiments of this disclosure, a communication method is provided, performed by a network device, the method comprising:

[0006] Obtain one or more use cases;

[0007] Interact with network elements of the first plane to obtain a trained first AI model relevant to the use case, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0008] According to a second aspect of the embodiments of this disclosure, another communication method is proposed, executed by a network element of a first plane, the method comprising:

[0009] Interact with network devices to determine a trained first AI model relevant to one or more use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0010] According to a third aspect of the embodiments of this disclosure, another communication method is proposed, executed by a terminal device, the method comprising:

[0011] The network device receives deployment information of a third AI model sent by the network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0012] According to a fourth aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0013] The processing module is used to obtain one or more use cases;

[0014] The transceiver module is used to interact with network elements of the first plane to obtain a trained first AI model related to the use case, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0015] According to a fifth aspect of the embodiments of this disclosure, a network element of a first plane is proposed, comprising:

[0016] The transceiver module is used to interact with network devices to determine a trained first AI model for one or more use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0017] According to a sixth aspect of the embodiments of this disclosure, a terminal device is provided, comprising:

[0018] The transceiver module receives deployment information of a third AI model sent by a network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0019] According to a seventh aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0020] One or more processors;

[0021] The processor is used to invoke instructions to cause the communication device to execute the communication method described in the first aspect.

[0022] According to an eighth aspect of the embodiments of this disclosure, a network element of a first plane is proposed, comprising:

[0023] One or more processors;

[0024] The processor is used to invoke instructions to cause the communication device to execute the communication method described in the second aspect.

[0025] According to a ninth aspect of the embodiments of this disclosure, a device is proposed, comprising:

[0026] One or more processors;

[0027] The processor is used to invoke instructions to cause the communication device to execute the communication method described in the third aspect.

[0028] According to a tenth aspect of the present disclosure, a communication system is provided, comprising: a network device, network elements of a first plane, and a terminal device, wherein the network device is configured to implement the communication method described in the first aspect, the network elements of the first plane are configured to implement the communication method described in the second aspect, and the terminal device is configured to implement the communication method described in the third aspect.

[0029] According to an eleventh aspect of the present disclosure, a storage medium is provided that stores instructions, characterized in that, when the instructions are executed on a communication device, the communication device performs a communication method as described in any one of the first, second, and third aspects.

[0030] According to a twelfth aspect of the present disclosure, a program product is provided that, when the computer program product is run on a communication device, causes the communication device to perform the communication method as described in any one of the first, second, and third aspects.

[0031] According to a thirteenth aspect of the present disclosure, a chip or chip system is provided. The chip or chip system includes processing circuitry configured to perform the communication method described in any one of the first, second, and third aspects described above.

[0032] In the above embodiments, the network device acquires one or more use cases and, through interaction with network elements of the first plane, obtains a pre-trained first AI model related to the use cases. The first plane includes at least an intelligent plane, a data plane, and a computing plane. In this disclosure, by adding an intelligent plane, data plane, and computing plane to the network structure, the generation and training of AI models for different use cases are achieved. This enables the integration of advanced AI with the mobile network, thereby increasing the diversity of AI functions within the mobile network. This allows the AI ​​functions to intelligently control network parameters, improving the performance of existing communication systems and the quality of user service experience.

[0033] Understandably, the aforementioned network devices, network elements and terminal devices of the first plane, communication systems, storage media, program products, chips or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0034] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0035] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0036] Figure 1B is another exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0037] Figures 2A-2E are exemplary interactive schematic diagrams of a communication method provided according to embodiments of the present disclosure.

[0038] Figures 3A-3F are schematic flowcharts of the communication method provided according to embodiments of the present disclosure.

[0039] Figures 4A-4B are schematic flowcharts of a communication method provided according to embodiments of the present disclosure.

[0040] Figures 5A-5B are schematic flowcharts of the communication method provided according to embodiments of the present disclosure.

[0041] Figure 6A is a schematic diagram of a communication method provided according to an embodiment of the present disclosure.

[0042] Figure 6B is a schematic diagram of a communication method provided according to an embodiment of the present disclosure.

[0043] Figure 7 is a schematic diagram of the structure of a communication device provided according to an embodiment of the present disclosure.

[0044] Figure 8A is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure;

[0045] Figure 8B is a schematic diagram of the structure of a chip provided in an embodiment of this disclosure.

[0046] This disclosure presents a communication method and device.

[0047] In a first aspect, embodiments of this disclosure provide a communication method applicable to network devices, the method comprising:

[0048] Obtain one or more AI use cases;

[0049] Interact with network elements of the first plane to obtain a trained first AI model related to the AI ​​use case, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0050] In the above embodiments, the network device acquires one or more AI use cases and obtains a pre-trained first AI model related to the use cases by interacting with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane. In this disclosure, by adding an intelligent plane, data plane, and computing plane to the network structure, the generation and training of AI models for different use cases are achieved. This enables the integration of advanced AI with the mobile network, thereby increasing the diversity of AI functions in the mobile network. This allows the ability to intelligently control network parameters using AI functions, improving the performance of existing communication systems and the quality of user service experience.

[0051] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0052] The AI ​​use cases are interpreted and evaluated to generate modeling information for the model;

[0053] Interact with network elements of the intelligent plane to obtain a second AI model related to the AI ​​use case generated based on the modeling information;

[0054] The second AI model is trained by interacting with network elements in the data plane and computing plane to obtain the first AI model.

[0055] In the above embodiments, the network device can interpret and evaluate AI use cases to obtain modeling information of the model, thereby generating an initial second AI model based on the modeling information, so that the network device can realize the self-construction of capabilities and services.

[0056] In conjunction with some embodiments of the first aspect, in some embodiments, interaction with network elements of the intelligent plane includes:

[0057] Send the modeling information to the network elements of the intelligent plane;

[0058] The system receives the second AI model constructed based on the modeling information sent by the network element of the intelligent plane.

[0059] In the above embodiments, the network device can interact with the network elements of the intelligent plane to build a second AI model, providing the ability to add an intelligent plane to the network structure to achieve self-construction of the AI ​​model.

[0060] In conjunction with some embodiments of the first aspect, in some embodiments, interaction with network elements of the data plane includes:

[0061] The first information sent to the network element of the data plane;

[0062] The network elements of the data plane collect sample data related to the second AI model.

[0063] In the above embodiments, the newly added data plane in the network structure can provide separate data capabilities for the network AI function, such as data acquisition, data processing, data modeling, data analysis and data application, which is conducive to quickly identifying data that matches the AI ​​model and thus improving the accuracy of model training.

[0064] In conjunction with some embodiments of the first aspect, in some embodiments, interaction with network elements in the computing plane includes:

[0065] Send the second information to the network element of the computing plane;

[0066] The network element receiving the computing plane provides the first computing capability for the second AI model.

[0067] In the above embodiments, the newly added computing plane in the network structure can provide separate computing power for the network AI function. In turn, the computing plane determines the first computing power required for training the second AI model, making the matching of the AI ​​model's computing power more accurate and conducive to the rational use of computing power.

[0068] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0069] The first resource corresponding to the second AI model is determined based on the first computing power;

[0070] The second AI model is trained based on the first resource and the sample data to obtain the first AI model.

[0071] In the above embodiments, physical resources related to network AI functions are added to the resource layer of the network structure. When AI model generation and training are required, corresponding resources can be allocated to network devices, which is beneficial to resource management and allocation.

[0072] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0073] Receive third information sent by the terminal device;

[0074] In response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0075] In the above embodiments, the terminal device can obtain the deployment information of the AI ​​model trained by the network device, thereby enabling the AI ​​model to be deployed locally on the terminal device and enabling inference of relevant information of the terminal device based on the local AI model.

[0076] In conjunction with some embodiments of the first aspect, in some embodiments, after receiving the third information sent by the receiving terminal device, the method further includes:

[0077] The terminal device makes AI decisions based on the third information, and sends AI decision information to the terminal device.

[0078] In the above embodiments, AI decision information can be fed back to the terminal device, so that the terminal device can determine whether a matching AI model can be obtained for reasoning.

[0079] In conjunction with some embodiments of the first aspect, in some embodiments, after sending the deployment information of the third AI model to the terminal device, the method further includes:

[0080] Send first data to the terminal device, wherein the first data is one of the following:

[0081] Sample data used for fine-tuning the third AI model;

[0082] The model parameter update data of the third AI model.

[0083] In the above embodiments, first data can be sent to the terminal device to update the AI ​​model deployed locally on the terminal device, thereby improving the inference ability of the AI ​​model.

[0084] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0085] A fourth message is sent to the terminal device, the fourth message being used to instruct the terminal device to unload the computing power related to the third AI model.

[0086] In the above embodiments, computing power offloading information can be sent to the terminal device, thereby freeing up the terminal device's resources.

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

[0088] The first intelligent flow corresponding to the control plane entity interacts with the core network through the control plane intelligent entity and the intelligent entity of the intelligent plane.

[0089] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0090] The second intelligent flow corresponding to the user plane entity interacts with the core network through the user plane intelligent entity and the intelligent entity of the intelligent plane.

[0091] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0092] The service flow corresponding to the user plane entity interacts with the core network through the intelligent entity of the intelligent plane.

[0093] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0094] The signal flow corresponding to the control plane entity interacts with the core network through the intelligent entity of the intelligent plane.

[0095] In the above embodiments, intelligent entities on the newly added intelligent plane can process intelligent flows, service flows, and signal flows, and different workflows can be processed through AI models, thereby improving the AI ​​capabilities of the network.

[0096] Secondly, embodiments of this disclosure propose a communication method applicable to network elements in a first plane, the method comprising:

[0097] Interact with network devices to determine a trained first AI model relevant to one or more use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0098] In the above embodiments, by adding an intelligent plane, a data plane, and a computing plane to the network structure, AI models for different use cases can be generated and trained. This enables the integration of advanced AI with the mobile network, thereby increasing the diversity of AI functions in the mobile network. As a result, the ability of AI functions to intelligently control network parameters can be utilized to improve the performance of existing communication systems and the quality of user service experience.

[0099] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0100] Receive the modeling information for the use case sent by the network device;

[0101] An initial second AI model related to the use case was constructed based on the modeling information;

[0102] The system receives the second AI model constructed based on the modeling information sent by the network element of the intelligent plane.

[0103] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0104] Receive the first information sent by the network device;

[0105] Based on the first information, sample data related to the second AI model is collected and sent to the network device. The sample data is used to train the second AI model to obtain the first AI model.

[0106] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0107] Receive the second information sent by the network device;

[0108] The first computing power is determined based on the second information and provided to the second AI model.

[0109] The first computing power is fed back to the network device, and the first computing power is used to generate and train the second AI model to obtain the first AI model.

[0110] Thirdly, embodiments of this disclosure provide a communication method applicable to terminal devices, the method comprising:

[0111] The network device receives deployment information of a third AI model sent by the network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0112] In the above embodiments,

[0113] In conjunction with some embodiments of the third aspect, in some embodiments, the deployment information of the first AI model sent by the receiving network device includes:

[0114] The third message sent to the network device;

[0115] In response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0116] In conjunction with some embodiments of the third aspect, in some embodiments, after the third information is sent to the network device, the method further includes:

[0117] Receive AI decision information from the terminal device sent by the network device.

[0118] In conjunction with some embodiments of the third aspect, in some embodiments, after receiving the deployment information of the third AI model sent by the network device, the method further includes:

[0119] Receive first data sent by the network device, wherein the first data is one of the following:

[0120] Sample data used for fine-tuning the third AI model;

[0121] The model parameter update data of the third AI model.

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

[0123] Receive the fourth information sent by the network device;

[0124] The second computing power related to the third AI model is unloaded based on the fourth information.

[0125] Fourthly, embodiments of this disclosure provide a network device, which includes:

[0126] The processing module is used to obtain one or more use cases;

[0127] The transceiver module is used to interact with network elements of the first plane to obtain a trained first AI model related to the use case, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0128] Fifthly, embodiments of this disclosure provide a network element for a first plane, the network element for the first plane comprising:

[0129] The transceiver module is used to interact with network devices to determine a trained first AI model for one or more use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0130] Sixthly, embodiments of this disclosure provide a terminal device, which includes:

[0131] The transceiver module receives deployment information of a third AI model sent by a network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0132] In a seventh aspect, embodiments of this disclosure provide a communication device, comprising:

[0133] One or more processors;

[0134] The processor is configured to invoke instructions to cause the communication device to execute the communication method described in any one of the first, second, and third aspects.

[0135] Eighthly, embodiments of this disclosure provide a communication system, characterized in that it includes a network device, network elements of a first plane, and a terminal device, wherein the network device is configured to implement the communication method described in the first aspect, the network elements of the first plane are configured to implement the communication method described in the second aspect, and the terminal device is configured to implement the communication method described in the third aspect.

[0136] In a ninth aspect, embodiments of this disclosure provide a storage medium storing instructions, characterized in that, when the instructions are executed on a communication device, the communication device performs a communication method as described in any one of the first, second, and third aspects.

[0137] In a tenth aspect, embodiments of this disclosure provide a computer program product that, when run on a communication device, causes the communication device to perform the communication method as described in any one of the first, second, and third aspects.

[0138] Eleventhly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to optional implementations of the first, second, and third aspects above.

[0139] Understandably, the aforementioned network devices, network elements of the first plane, terminal devices, communication systems, storage media, computer program products, chips, or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0140] This disclosure provides a communication method. In some embodiments, terms such as determining method, information processing method, information sending method, and information receiving method can be used interchangeably. Terms such as communication device, information processing device, determining device, information sending device, and information receiving device can be used interchangeably. Terms such as information processing system, communication system, information sending system, and information receiving system can be used interchangeably.

[0141] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0142] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0143] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0144] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0145] In the embodiments of this disclosure, "multiple" refers to two or more.

[0146] In some embodiments, the terms “at least one of”, “at least one of”, “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0147] The descriptions in this disclosure, such as "at least one of A, B, C..." or "A and / or B and / or C...", include the case where any one of A, B, C... exists alone, as well as the case where any combination of any of A, B, C... exists alone. Each case can exist alone. For example, "at least one of A, B, C" includes the cases of A alone, B alone, C alone, A and B combination, A and C combination, B and C combination, and A and B and C combination. For example, A and / or B includes the cases of A alone, B alone, and A and B combination.

[0148] In some embodiments, the notation "in one case A, in another case B" or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: A is executed regardless of B, i.e., A is executed in some embodiments; B is executed regardless of A, i.e., B is executed in some embodiments; A and B are selectively executed, i.e., A and B are selected for execution in some embodiments; A and B are both executed, i.e., A and B are executed in some embodiments. The same applies when there are more branches such as A, B, and C.

[0149] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0150] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0151] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0152] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0153] 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”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0154] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0155] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0156] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0157] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures that replace communication between access network devices, core network devices, or network devices and terminals with communication between multiple terminals (e.g., also referred to as device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, uplink link, downlink link, etc., can be replaced with sidelink link.

[0158] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0159] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0160] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0161] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0162] The correspondences shown in the tables of this disclosure can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values; this disclosure is not limiting. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows of the tables in this disclosure may not be configured. Furthermore, appropriate modifications and adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the headers of the above tables can also use other names that the communication device can understand, and the values ​​or representations of the parameters can also be other values ​​or representations that the communication device can understand. In the implementation of the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or hash tables, etc.

[0163] The predefined terms in this disclosure can be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0164] As shown in Figure 1A, the communication system 100 includes a terminal 101, an access network device 102, and a core network device 103.

[0165] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0166] In some embodiments, the access network device 102 may be a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0167] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0168] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0169] In some embodiments, the core network device 103 may be a single device, including a first network element 1031, a second network element 1032, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element 1031, the second network element 1032, etc. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0170] Optionally, the core network equipment may include one or more of the following: Location Management Function (LMF) network element, User Plane Function (UPF) network element, Policy Control Function (PCF) network element, Application Function (AF) network element, Network Data Analytics Function (NWDAF) network element, Access and Mobility Management Function (AMF) network element, Authentication Server Function (AUSF) network element, Session Management Function (SMF) network element, and Unified Data Management (UDM) network element.

[0171] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0172] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0173] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other deterministic methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0174] Figure 1B illustrates a three-layer, five-plane three-dimensional logical network architecture for a 6G network proposed in this disclosure, and also provides a physical network architecture for deploying native AI within the access network. As shown in Figure 1B, from a horizontal logical perspective, the 6G network can be divided into a resource layer, a network function layer, and an application service layer.

[0175] In some embodiments, the resource layer provides underlying resources such as wireless, computing, and storage, and provides corresponding support and services for the generation of functions in the network function layer.

[0176] In some embodiments, the network function layer combines one or more network functions to form a specific network function, providing the most basic network service capabilities to meet the needs of the application layer and the service layer.

[0177] In some embodiments, the application and service layer provides support for the client's services and applications, enabling service customization.

[0178] In terms of vertical logic, in addition to the traditional communication plane and management plane, 6G networks also have a data plane, a calculation plane, and an intelligence plane.

[0179] In some embodiments, the communication plane may include functions such as channel state awareness, network capabilities providing, and service requirements acquiring.

[0180] In some embodiments, the data plane generally refers to the logical functions related to various data information processing, including data functions closely related to AI operations (such as AI sample data collection, cleaning, feature extraction, etc.) and data functions not strongly related to AI operations (such as big data collection and modeling, analysis and reasoning, etc.).

[0181] In some embodiments, the logical functions of the data plane mainly include data acquisition, data processing, data modeling, data analysis, and data application.

[0182] In some embodiments, the data plane can provide logical functions and sample data for data processing related to resource state perception, network state perception, and service requirements perception.

[0183] In some embodiments, the intelligent plane provides global AI capabilities through the collaborative efforts of distributed intelligent nodes, enabling the autonomous generation of AI models. A key capability of the intelligent plane is the orchestration of AI services, used to arrange, manage, and schedule end-to-end services and resources related to AI. AI service orchestration focuses on the analysis and arrangement of AI services. AI services are mapped to logical AI workflows. Depending on the type of AI service, the logical AI workflow can contain different modular AI models, such as recurrent neural network modules, LSTM modules, and convolutional neural network (CNN) modules. The logical AI workflow requires sequentially acquiring and processing data. Furthermore, the QoS requirements of AI services will be considered in the logical AI workflow. During business deployment, the logical AI workflow is mapped to physical resources. The physical resources mapped to the logical AI workflow include heterogeneous resources such as computing resources (CPU / GPU / NPU), network connectivity and communication resources, and storage resources.

[0184] In some embodiments, the computing plane may include functions such as computing power modeling and state awareness, computing power awareness routing, and requirements awareness and computing power call.

[0185] In some embodiments, the management plane can manage and control the communication plane, the intelligence plane, the data plane and the computing plane, as well as the resource pool, the network function layer and the application and service layer.

[0186] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, the embodiments of the present disclosure relate to a communication method, which includes:

[0187] Step S2101: Obtain one or more AI use cases.

[0188] In some embodiments, a set of use cases can be configured. Optionally, the set of use cases includes one or more AI use cases, where each AI use case may correspond to a different AI business.

[0189] In some embodiments, the use cases in the use case set can be generated based on some business information.

[0190] In some embodiments, the use case set can be generated online or offline for subsequent configuration.

[0191] In some embodiments, the set of use cases can be polled or traversed to obtain subsequent use cases for generating AI models.

[0192] In some embodiments, one or more use cases for generating AI models may be determined from a set of use cases based on indications.

[0193] Step S2102: Interpret and evaluate the AI ​​use cases to generate modeling information for the model.

[0194] In some embodiments, an interpreter can perform algorithmic interpretation of AI use cases to determine their inherent logical relationships. Furthermore, syntactic analysis and semantic correctness checks can be performed on the AI ​​use cases, and a syntax tree corresponding to the use cases can be constructed.

[0195] In some embodiments, evaluating the Quality of Service (QoS) parameters of an AI model for AI use cases can yield QoS parameters related to the AI ​​model, which can be used to evaluate and optimize the model's performance and reliability during runtime.

[0196] In some embodiments, the QoS parameters related to the AI ​​model may include, but are not limited to, the following parameters:

[0197] AI model response time, AI model throughput, AI model prediction accuracy and reliability, AI model resource utilization, AI model stability and latency jitter, etc.

[0198] In some embodiments, after the interpreter outputs interpretation information and QoS parameters, the modeling information of the AI ​​model can be determined based on the interpretation information and QoS parameters of the interpreter. The modeling information can be used to construct an initial second AI model corresponding to the use case.

[0199] In some embodiments, the modeling information may include, but is not limited to, the following:

[0200] The type of model, for example, can include classification, regression, clustering, generative, or other types of models.

[0201] The model's architecture, for example, can employ a convolutional neural network (CNN), a recurrent neural network (RNN), a Transformer, or other types of network structures.

[0202] The number of parameters and layers in the model, such as the number of hidden layers, the number of neurons in each layer, and the activation function.

[0203] Information related to the sample data, such as its source, size, and preprocessing methods.

[0204] Information related to the training process, such as the optimization algorithm used by the model (e.g., gradient descent, Adam, etc.), learning rate adjustment strategy, batch size, strategies to prevent model overfitting and regularization, and performance evaluation metrics for the model (e.g., accuracy, recall, F1 score, etc.).

[0205] Step S2103: Send modeling information to the network elements of the intelligent plane.

[0206] In some embodiments, after obtaining the modeling information, the modeling information can be sent to the network elements of the intelligent plane. Optionally, the network elements of the intelligent plane can generate an initial second AI model of the constructed use case based on the modeling information.

[0207] In some embodiments, the intelligent plane can orchestrate and manage AI services, such as generating AI models for AI services and optimizing AI models, and can schedule end-to-end services and resources related to AI services.

[0208] In some embodiments, the AI ​​model may include, but is not limited to: channel state information prediction model, location information prediction model, network optimization and monitoring module, user behavior analysis model, etc.

[0209] In step S2104, the network element of the intelligent plane sends an initial second AI model of the use cases constructed based on the modeling information.

[0210] In some embodiments, the network element of the intelligent plane can send the initial second AI model of the use case to the network device when generating the use case. Optionally, the network device receives the initial second AI model of the use case sent by the network element of the intelligent plane.

[0211] Step S2105: Send the first information to the network element in the data plane.

[0212] In some embodiments, the network device sends first information to a network element in the data plane; optionally, the network element in the data plane receives the first information. Further, sample data is collected for the second AI model based on the first information.

[0213] In some embodiments, the first information may be used to instruct the training of a second AI model.

[0214] In some embodiments, the first information may be used to indicate the sample data required to acquire the second AI model.

[0215] In some embodiments, the name of the first information is not limited, and it may be, for example, "training request information", "data acquisition information", "data collection request", "sample data request information", etc.

[0216] In some embodiments, the first information may carry a model identifier of the second AI model. The network elements of the data plane may collect corresponding sample data based on the model identifier. Optionally, after collecting the sample data, the network elements of the data plane may preprocess the sample data to obtain the final sample data. For example, data cleaning, data integration, data transformation, and data encoding may be performed on the training samples.

[0217] In step S2106, the network element in the data plane sends sample data related to the second AI model.

[0218] In some embodiments, the webpage of the data plane can send sample data related to the second AI model to the network device, and optionally, the network device can receive sample data related to the second AI model.

[0219] In some embodiments, after the data plane network element collects sample data, it can preprocess the sample data to obtain the final sample data, and send the final sample data related to the second AI model to the network device.

[0220] In some embodiments, the data plane can implement logical functions related to various data information processing, such as data functions closely related to AI functions. Optionally, these include AI sample data collection, cleaning, feature extraction, big data collection and modeling, analysis and reasoning, etc.

[0221] In some embodiments, the logical functions of the data plane may include, but are not limited to, data acquisition, data processing, data modeling, data analysis, and data application.

[0222] Step S2107: Send the second information to the network elements of the computing plane.

[0223] In some embodiments, the network device may send second information to network elements of the computing plane, and optionally, the network elements of the computing plane receive the second information. Further, the second information is used to provide first computing power for the second AI model.

[0224] In some embodiments, the second information may be used to instruct the training of a second AI model.

[0225] In some embodiments, the second information may be used to indicate the first computing power required to provide the second AI model.

[0226] In some embodiments, the name of the second information is not limited, and it may be, for example, “training request information”, “capability acquisition information”, “capability allocation request”, “model training request”, etc.

[0227] In some embodiments, the second information may carry a model identifier of the second AI model, and the network elements of the computing plane may determine a first computing capability for the second AI model based on the model identifier.

[0228] In step S2108, the network element of the computing plane sends the first computing power provided to the second AI model.

[0229] In some embodiments, after determining the first computing capability for the second AI model, the network element of the computing plane can send the first computing capability to the network device. Optionally, the network device can receive the first computing capability corresponding to the second AI model.

[0230] In some embodiments, the first computing capability includes, but is not limited to, computing power, communication capability, and storage capability. For example, computing power may include the required performance and quantity of CPUs, GPUs, and NPUs; another example is the size of the storage resources for the sample data required by the AI ​​model. Yet another example is determining the communication capability based on the latency of the AI ​​model, such as the required amount of communication resources.

[0231] Step S2109: Obtain the first resource allocated to the second AI model based on the first computing power.

[0232] In some embodiments, the network device may obtain first resources related to the second AI model from the resource layer based on first computing power. Optionally, the first resources may include, but are not limited to, heterogeneous resources such as computing resources, network connection communication resources, and storage resources. Optionally, computing resources may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), and neural processing units (NPUs).

[0233] As shown in Figure 1B, the resource layer can provide underlying resources such as wireless, computing, and storage, and provide corresponding support and services for the generation of functions in the network function layer. After acquiring the first computing capability, the resource layer can allocate first resources matching the first computing capability to the second AI model.

[0234] Step S2110: Use the first resource and sample data to train the second AI model to obtain the first AI model.

[0235] In some embodiments, after obtaining the first resource, an AI model can be generated based on the first resource. A second AI model can be trained based on the first resource and sample data to obtain the first AI model. Optionally, a training termination condition can be set. When the training termination condition is met, training can be terminated to obtain the trained first AI model.

[0236] Step S2111: The terminal device sends third information to the network device.

[0237] In some embodiments, the terminal device may send third information to the network device. Optionally, the terminal device may send the third information via uplink signaling. Optionally, the network device may receive the third information, and further, the network device may determine the AI ​​model based on the third information.

[0238] In some embodiments, the third information carries AI service-related information requested by the terminal device. Optionally, the AI ​​service-related information may include the model identifier of the requested AI model. Optionally, the AI ​​service-related information may include descriptive information of the requested AI model.

[0239] In some embodiments, the third information is used to instruct the network device to determine an AI model for the terminal device.

[0240] In some embodiments, the third information is used to instruct the network device to match an AI model for the terminal device.

[0241] In some embodiments, the third information is used to instruct the network device to query the AI ​​model for the terminal device.

[0242] In some embodiments, the name of the third information is not limited, and it may be, for example, "model request information", "model deployment request", "prediction request information", etc.

[0243] In step S2112, the network device sends AI decision information to the terminal device.

[0244] In some embodiments, the network device may make AI decisions for the terminal device based on third-party information, determine whether AI services can be provided to the terminal device, further generate AI decision information based on the judgment result, and feed it back to the terminal device.

[0245] In some embodiments, AI decision information can indicate whether a terminal device uses AI functions.

[0246] In some embodiments, the third information may include the capability information of the terminal device, and the terminal device may be used to determine whether it has the capability to support AI functions.

[0247] In some embodiments, the third information may include the status information of the terminal device, which can be used to determine whether the terminal device currently has the capability to support AI functions.

[0248] In some embodiments, the network device can determine whether there is a third AI model matching the third information in the trained first AI model based on the AI-related information carried by the third information. Optionally, if there is no third AI model matching the third information in the trained first AI model, AI decision information indicating that the terminal device does not support the use of AI functions can be generated. Optionally, if there is a third AI model matching the third information in the trained first AI model, AI decision information indicating that the terminal device supports the use of AI functions can be generated.

[0249] Step S2113: In response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0250] In some embodiments, the network device can use multiple first AI models trained based on multiple use cases. After obtaining third information, it can determine whether there is a third AI model among the multiple first AI models that matches the third information. Optionally, the model identifier d carried in the third information is compared with the model identifier D of each first AI model. If there is a D that matches d, the comparison is made. i It can be determined that a third AI model exists that matches the third information, and this D... i The identified first AI model is used as the third AI model. Optionally, the model description information t carried by the third information is compared with the description information T of each first AI model. If there is a T that matches t, then... i It can be determined that a third AI model exists that matches the third information, and this T i The first AI model described is used as the third AI model.

[0251] In some embodiments, the network device may send deployment information of a third AI model to the terminal device. Optionally, upon receiving the deployment information of the third AI model, the terminal device may deploy the third AI model locally on the terminal device based on the deployment information.

[0252] In some embodiments, the deployment information of the third AI model may include, but is not limited to, one of the following:

[0253] The model structure of the third AI model;

[0254] Model parameters of the third AI model;

[0255] The amount of resources required for the third AI model;

[0256] The performance parameters of the third AI model.

[0257] Step S2114: The network device sends the first data to the terminal device.

[0258] Step S2115: Update the third AI model based on the first data.

[0259] In some embodiments, the first data may include, but is not limited to, one of the following:

[0260] Sample data used for fine-tuning the third AI model;

[0261] The third AI model's parameter update data.

[0262] In some embodiments, if the first data is sample data for fine-tuning the third AI model, the terminal device can fine-tune and train the third AI model based on this sample data to further improve the performance of the third AI model and make it more in line with the application requirements of the terminal device.

[0263] In some embodiments, if the first data is the model parameter update data of the third AI model, the terminal device can update the third AI model based on this model parameter update data to better meet the application requirements of the terminal device.

[0264] In some embodiments, the terminal device may proactively request first data from the network device if the prediction information from the third AI model does not meet expectations.

[0265] In some embodiments, the network device may proactively send first data to the terminal device. For example, the first data may be sent to the terminal device periodically or based on higher-layer signaling.

[0266] Step S2116: The network device sends the fourth information to the terminal device.

[0267] In some embodiments, the network device may send fourth information to the terminal device, and optionally, the terminal device may receive the fourth information.

[0268] In some embodiments, the fourth information is used to instruct the terminal device to unload the second computing power associated with the third AI model.

[0269] In some embodiments, the name of the fourth information is not limited, and it may be, for example, "unloading information", "model indication information", "capability unloading information", etc.

[0270] In some embodiments, the network device may send a fourth message to the terminal device when the third AI model needs to be deleted.

[0271] In some embodiments, when a network device determines that a conflict has occurred in the second computing power allocated to a third AI model, it may send a fourth message to the terminal device.

[0272] Step S2117: The terminal device unloads the second computing power related to the third AI model.

[0273] In some embodiments, the fourth information carries the model identifier and / or capability information of the third AI model.

[0274] In some embodiments, the terminal device may determine the third AI model whose offloading capability is required based on the model identifier carried in the fourth information.

[0275] In some embodiments, the terminal device may offload all the second computing capabilities related to the third AI model based on the fourth information.

[0276] In some embodiments, the fourth information may carry the computing power that needs to be unloaded. The terminal device can determine the second computing power that the third AI model needs to unload based on the capability information carried by the fourth information and unload part of the computing power.

[0277] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0278] In some embodiments, the terms "uplink", "uplink", and "physical uplink" can be used interchangeably, as can the terms "downlink", "downlink", and "physical downlink", as well as the terms "sidelink", "sidelink", "sidelink communication", "sidelink communication", "direct connection", "direct link", "direct communication", and "direct link communication".

[0279] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0280] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".

[0281] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.

[0282] In some embodiments, terms such as wireless access scheme and waveform can be used interchangeably.

[0283] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0284] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0285] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0286] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0287] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data after receiving it; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the receiver to respond to the sent content.

[0288] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2117.

[0289] For example, steps S2101+S2102+S2103+S2104 can be implemented as an independent embodiment, and steps S2104+S2105+S2106+S2107+S2108+S2109+S2110 can be implemented as an independent embodiment. Steps 109+S2110, S2111+S2113, S2110+S2113, S2111+S2112+S2113, and S2111+S2113+S2114+S2115 can be implemented as independent embodiments, but are not limited thereto.

[0290] In some embodiments, steps S2105 and S2107 can be swapped in order, and steps S2114 and S2116 can be swapped in order.

[0291] In some embodiments, steps S2112, S2114 to S2117 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0292] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2B, the embodiments of the present disclosure relate to a communication method, which includes:

[0293] Step S2101: Obtain one or more use cases.

[0294] The optional implementation of step S2201 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0295] Step S2202: Interpret and evaluate the use cases to generate modeling information for the model.

[0296] The optional implementation of step S2202 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0297] Step S2203: Send modeling information to the network elements of the intelligent plane.

[0298] The optional implementation of step S2203 can be found in the optional implementation of step S2103 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0299] In step S2204, the network element of the intelligent plane sends an initial second AI model of the use case constructed based on the modeling information.

[0300] The optional implementation of step S2204 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0301] Step S2205: Send the first information to the network element in the data plane.

[0302] The optional implementation of step S2205 can be found in the optional implementation of step S2105 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0303] In step S2206, the network element in the data plane sends sample data related to the second AI model.

[0304] The optional implementation of step S2206 can be found in the optional implementation of step S2106 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0305] In step S2207, the network device sends the second information to the network element of the computing plane.

[0306] The optional implementation of step S2207 can be found in the optional implementation of step S2107 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0307] In step S2208, the network element of the computing plane sends the first computing power provided to the second AI model.

[0308] The optional implementation of step S2208 can be found in the optional implementation of step S2108 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0309] Step S2209: Obtain the first resource allocated to the second AI model based on the first computing power.

[0310] The optional implementation of step S2209 can be found in the optional implementation of step S2109 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0311] Step S2210: Use the first resource and sample data to train the second AI model to obtain the first AI model.

[0312] The optional implementation of step S2210 can be found in the optional implementation of step S2110 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0313] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2210.

[0314] For example, steps S2101+S2102+S2103+S2104 can be implemented as an independent embodiment, as can steps S2104+S2105+S2106+S2107+S2108+S2109+S2110, as can steps S2101+S2102+S2103+S2104+S2105+S2106+S2107+S2108+S2109+S2110, but are not limited thereto.

[0315] In some embodiments, steps S2105 and S2107 can be swapped in order.

[0316] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0317] Figure 2C is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2C, the embodiments of the present disclosure relate to a communication method, which includes:

[0318] Step S2301: Obtain one or more AI use cases.

[0319] The optional implementation of step S2301 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0320] Step S2302: Interact with the network elements of the first plane to obtain a trained first AI model related to the AI ​​use case.

[0321] In some embodiments, the first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0322] The optional implementations of step S2302 can be found in the optional implementations of steps S2102 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0323] In step S2303, the terminal device sends third information to the network device.

[0324] The optional implementation of step S2303 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0325] In step S2304, the network device sends AI decision information to the terminal device.

[0326] The optional implementation of step S2304 can be found in the optional implementation of step S2112 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0327] In step S2305, in response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0328] The optional implementation of step S2305 can be found in the optional implementation of step S2113 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0329] Step S2306: The network device sends the first data to the terminal device.

[0330] In step S2307, the terminal device updates the third AI model based on the first data.

[0331] The optional implementations of steps S2306 to S2307 can be found in the optional implementations of steps S2114 to S2115 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0332] In step S2308, the network device sends the fourth information to the terminal device.

[0333] The optional implementation of step S2308 can be found in the optional implementation of step S2116 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0334] Step S2309: The terminal device unloads the second computing power related to the third AI model.

[0335] The optional implementation of step S2309 can be found in the optional implementation of step S2117 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0336] The communication method involved in the embodiments of this disclosure may include at least one of steps S2301 to S2309.

[0337] For example, steps S2301+S2302 can be implemented as an independent embodiment, steps S2301+S2302+S2303+S2305 can be implemented as an independent embodiment, steps S2301+S2302+S2303+S2304+S2305 can be implemented as an independent embodiment, and steps S2301+S2302+S2303+S2305+S2306+S2307 can be implemented as an independent embodiment, but are not limited thereto.

[0338] In some embodiments, steps S2306 and S2308 can be swapped in order.

[0339] In some embodiments, steps S2304, S2306 to S2309 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0340] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0341] Figure 2D is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2D, the embodiments of the present disclosure relate to a communication method, which includes:

[0342] Step S2401: The terminal device sends third information to the network device.

[0343] The optional implementation of step S2401 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0344] In step S2402, the network device sends AI decision information to the terminal device.

[0345] The optional implementation of step S2401 can be found in the optional implementation of step S2112 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0346] In step S2403, in response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0347] The optional implementation of step S2403 can be found in the optional implementation of step S2113 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0348] In step S2404, the network device sends the first data to the terminal device.

[0349] In step S2405, the terminal device updates the third AI model based on the first data.

[0350] The optional implementations of steps S2404 to S2405 can be found in the optional implementations of steps S2114 to S2115 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0351] Step S2406: The network device sends the fourth information to the terminal device.

[0352] The optional implementation of step S2406 can be found in the optional implementation of step S2116 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0353] Step S2407: The terminal device unloads the second computing power related to the third AI model.

[0354] The optional implementation of step S2407 can be found in the optional implementation of step S2117 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0355] The communication method involved in the embodiments of this disclosure may include at least one of steps S2401 to S2407.

[0356] For example, steps S2401+S2403 can be implemented as an independent embodiment, steps S2401+S2402+S2403 can be implemented as an independent embodiment, steps S2401+S2403+S2404+S2405 can be implemented as an independent embodiment, and steps S2401+S2403+S2406+S2407 can be implemented as an independent embodiment, but are not limited thereto.

[0357] In some embodiments, steps S2404 and S2406 can be swapped in order.

[0358] In some embodiments, steps S2402, S2404 to S2407 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0359] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0360] Figure 2E is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2E, the embodiments of the present disclosure relate to a communication method, which includes:

[0361] The intelligent flow between the UE and network devices can include a first intelligent flow oriented towards the control plane and a second intelligent flow oriented towards the user plane. It can be understood that the intelligent flow refers to the processing procedures related to adding AI functions to the network architecture, which may include, but are not limited to, the collection of sample data for the AI ​​model, data parameters, training of the AI ​​model, deployment of the AI ​​model, optimization or fine-tuning, configuration or modification of the AI ​​model's parameters, AI model inference, and result feedback.

[0362] In some embodiments, the first intelligent flow corresponding to the control plane entity can interact with the core network through the control plane intelligence entity and the online intelligence entity of the intelligent plane. It is understood that the control plane entity can send the first intelligent flow to itself, and then to the intelligent entity of the intelligent plane. The intelligent entity of the intelligent plane processes the first intelligent flow to obtain the UE's first relevant information. Further, the intelligent entity of the intelligent plane sends the UE's first relevant information to the core network. The core network can make decisions based on the UE's first relevant information, obtain the UE's first relevant information decision, and send it to the UE.

[0363] In some embodiments, the second intelligent flow corresponding to the user plane entity interacts with the core network through the user plane intelligence entity and the intelligent entity online in the intelligent plane. It is understood that the user plane entity can send the second intelligent flow to itself, and then to the intelligent entity in the intelligent plane. The intelligent entity in the intelligent plane processes the second intelligent flow to obtain the second relevant information of the UE. Further, the intelligent entity in the intelligent plane sends the second relevant information of the UE to the core network. The core network can make decisions based on the second relevant information of the UE, obtain the second relevant decision of the UE, and send it to the UE.

[0364] In some embodiments, the UE can send a signal stream to a control plane entity. The control plane entity then sends the signal stream to an intelligent entity in the intelligent plane. The intelligent entity in the intelligent plane processes the signal stream and sends the processing result to the core network. The core network then makes a network decision based on the processing result and sends the network decision back to the UE. It is understood that the signal stream is used for transmitting various control signaling on the control plane, which may include, but is not limited to, UE registration, reading system information, location updates, and configuration parameters. In some embodiments, the UE can send a service stream to a user plane entity. The user plane entity then sends the service stream to an intelligent entity in the intelligent plane. The intelligent entity in the intelligent plane processes the service stream and sends the processing result to the core network. The core network then makes a service decision based on the processing result and sends the decision back to the UE. It is understood that the service stream is the logical processing flow related to various applications provided by the network to the user, which may include, but is not limited to, information push, filtering, querying, updating, and storing service-related data sources, reporting user behavior data, and user application feedback.

[0365] In some embodiments, the smart plane includes online smart entities and offline smart entities.

[0366] Figure 3A is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, the embodiments of the present disclosure relate to a communication method applicable to network devices, and the method includes:

[0367] Step S3101: Obtain one or more AI use cases.

[0368] The optional implementation of step S3101 can be found in the optional implementation of step S2101 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0369] Step S3102: Interpret and evaluate the AI ​​use cases to generate modeling information for the model.

[0370] The optional implementation of step S3102 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0371] Step S3103: Send modeling information to the network elements of the intelligent plane.

[0372] The optional implementation of step S3103 can be found in the optional implementation of step S2103 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0373] Step S3104: Receive the second AI model constructed based on modeling information sent by the network element of the intelligent plane.

[0374] The optional implementation of step S3104 can be found in the optional implementation of step S2104 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0375] Step S3105: Send the first information to the network element in the data plane.

[0376] The optional implementation of step S3105 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0377] Step S3106: Receive sample data related to the second AI model collected by the network elements of the data plane.

[0378] The optional implementation of step S3106 can be found in the optional implementation of step S2106 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0379] Step S3107: Send the second information to the network elements of the computing plane.

[0380] The optional implementation of step S3107 can be found in the optional implementation of step S2107 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0381] Step S3108: Receive the first computing power provided by the network elements of the computing plane for the second AI model.

[0382] The optional implementation of step S3108 can be found in the optional implementation of step S2108 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0383] Step S3109: Obtain the first resource of the second AI model based on the first computing power.

[0384] The optional implementation of step S3109 can be found in the optional implementation of step S2109 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0385] Step S3110: Train the second AI model based on the first resource and sample data to obtain the first AI model.

[0386] The optional implementation of step S3110 can be found in the optional implementation of step S2110 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0387] Step S3111: Receive third information sent by the terminal device.

[0388] The optional implementation of step S3111 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0389] Step S3112: Send AI decision information to the terminal device.

[0390] The optional implementation of step S3112 can be found in the optional implementation of step S2112 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0391] Step S3113: In response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0392] The optional implementation of step S3113 can be found in the optional implementation of step S2113 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0393] Step S3114: Send the first data to the terminal device.

[0394] The optional implementations of step S3114 can be found in the optional implementations of steps S2114 to S2115 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0395] Step S3115: Send the fourth information to the terminal device.

[0396] The optional implementations of step S3115 can be found in the optional implementations of steps S2116 to S2117 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0397] The communication method involved in the embodiments of this disclosure may include at least one of steps S3101 to S3117.

[0398] For example, steps S3101+S3102+S3103+S3104 can be implemented as an independent embodiment, and steps S3104+S3105+S3106+S3107+S3108+S3109+S3110 can be implemented as an independent embodiment. Steps 109+S3110, S3111+S3113, S3110+S3113, S3111+S3112+S3113, and S3111+S3113+S3114+S3115 can be implemented as independent embodiments, but are not limited thereto.

[0399] In some embodiments, steps S3105 and S3107 can be swapped in order, and steps S3114 and S3115 can be swapped in order.

[0400] In some embodiments, steps S3112, S3114 to S3115 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0401] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, the embodiments of the present disclosure relate to a communication method applicable to network devices, and the method includes:

[0402] Step S3201: Obtain one or more AI use cases.

[0403] The optional implementation of step S3201 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0404] Step S3202: Interpret and evaluate the AI ​​use cases to generate modeling information for the model.

[0405] The optional implementation of step S3202 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0406] Step S3203: Send modeling information to the network elements of the intelligent plane.

[0407] The optional implementation of step S3203 can be found in the optional implementation of step S2103 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0408] Step S3204: Receive the second AI model constructed based on modeling information sent by the network element of the intelligent plane.

[0409] The optional implementation of step S3204 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0410] Step S3205: Send the first information to the network element in the data plane.

[0411] The optional implementation of step S3205 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0412] Step S3206: Receive sample data related to the second AI model collected by network elements in the data plane.

[0413] The optional implementation of step S3206 can be found in the optional implementation of step S2106 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0414] Step S3207: Send the second information to the network elements of the computing plane.

[0415] The optional implementation of step S3207 can be found in the optional implementation of step S2107 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0416] Step S3208: Receive the first computing power provided by the network elements of the computing plane for the second AI model.

[0417] The optional implementation of step S3208 can be found in the optional implementation of step S2108 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0418] Step S3209: Obtain the first resource of the second AI model based on the first computing power.

[0419] The optional implementation of step S3209 can be found in the optional implementation of step S2109 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0420] Step S3210: Train the second AI model based on the first resource and sample data to obtain the first AI model.

[0421] The optional implementation of step S3210 can be found in the optional implementation of step S2110 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0422] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2320.

[0423] For example, steps S3201+S3202+S3203+S3204 can be implemented as an independent embodiment, steps S3204+S3205+S3206+S3207+S3208+S3209+S3210 can be implemented as an independent embodiment, and steps S3201+S3202+S3203+S3204+S3205+S3206+S3207+S3208+S3209+S3210 can be implemented as an independent embodiment, but are not limited thereto.

[0424] In some embodiments, steps S3205 and S3207 can be swapped in order.

[0425] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0426] Figure 3C is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3C, the embodiments of the present disclosure relate to a communication method applicable to network devices, and the method includes:

[0427] Step S3301: Obtain one or more AI use cases.

[0428] The optional implementation of step S3301 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0429] Step S3302: Interact with the network elements of the first plane to obtain a trained first AI model related to the AI ​​use case.

[0430] The optional implementation of step S3302 can be found in the optional implementation of steps S2102 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0431] Step S3303: Receive third information sent by the terminal device.

[0432] The optional implementation of step S3303 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0433] Step S3304: Send AI decision information to the terminal device.

[0434] The optional implementation of step S3304 can be found in the optional implementation of step S2112 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0435] In step S3305, in response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0436] The optional implementation of step S3305 can be found in the optional implementation of step S2113 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0437] Step S3306: Send the first data to the terminal device.

[0438] The optional implementations of step S3306 can be found in the optional implementations of steps S2114 to S2115 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0439] Step S3307: Send the fourth information to the terminal device.

[0440] The optional implementations of step S3307 can be found in the optional implementations of steps S2116 to S2117 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0441] The communication method involved in the embodiments of this disclosure may include at least one of steps S3301 to S3307.

[0442] For example, steps S3302+S3303 can be implemented as an independent embodiment, steps S3301+S3302+S3303+S3305 can be implemented as an independent embodiment, steps S3301+S3303+S3304+S3305 can be implemented as an independent embodiment, steps S3301+S3303+S3304+S3305+S3306 can be implemented as an independent embodiment, and steps S3301+S3302+S3303+S3305 can be implemented as an independent embodiment, but are not limited thereto.

[0443] In some embodiments, steps S3306 and S3307 can be swapped in order.

[0444] In some embodiments, steps S3304, S3306 to S3307 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0445] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0446] Figure 3D is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3D, the embodiments of the present disclosure relate to a communication method applicable to network devices, and the method includes:

[0447] Step S3401: Obtain one or more AI use cases.

[0448] The optional implementation of step S3401 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0449] Step S3402: Interpret and evaluate the AI ​​use cases to generate modeling information for the model;

[0450] The optional implementation of step S3402 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0451] Step S3403: Interact with network elements of the intelligent plane to obtain an initial second AI model related to AI use cases generated based on modeling information.

[0452] The optional implementation of step S3403 can be found in the optional implementation of step S2103 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0453] Step S3404: Interact with network elements in the data plane and computing plane to train the second AI model and obtain the first AI model.

[0454] The optional implementations of step S3404 can be found in the optional implementations of steps S2104 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0455] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0456] Figure 3E is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3E, the embodiments of the present disclosure relate to a communication method applicable to network devices, and the method includes:

[0457] Step S3501: Obtain one or more AI use cases.

[0458] The optional implementation of step S3501 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0459] Step S3502: Interact with the network elements of the first plane to obtain a trained first AI model related to the AI ​​use case.

[0460] The optional implementations of step S3502 can be found in the optional implementations of steps S2102 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0461] Step S3503: Receive third information sent by the terminal device.

[0462] The optional implementation of step S3503 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0463] Step S3504: In response to the existence of a third AI model in the first AI model that matches the third information, the deployment information of the third AI model is sent to the terminal device.

[0464] The optional implementation of step S3504 can be found in the optional implementation of step S2113 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0465] In this embodiment or example, unless contradictory, the steps can be independent, arbitrarily combined, or interchanged in order. Optional methods or examples can be arbitrarily combined and can be arbitrarily combined with any steps in other embodiments or examples. Figure 3F is a schematic flowchart of a communication method according to an embodiment of this disclosure.

[0466] As shown in Figure 3F, this disclosure relates to a communication method applicable to network devices, and the method includes:

[0467] Step S3601: Obtain one or more AI use cases.

[0468] The optional implementation of step S3601 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0469] Step S3602: Interact with the network elements of the first plane to obtain a trained first AI model related to the AI ​​use case.

[0470] The optional implementation of step S3602 can be found in the optional implementation of steps S2102 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0471] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0472] Figure 4A is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4A, the present disclosure relates to a communication method applicable to network elements in a first plane, the method comprising:

[0473] Step S4101: Receive modeling information for use cases sent by the network device.

[0474] The optional implementation of step S4101 can be found in the optional implementation of step S2102 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0475] Step S4102: Construct an initial second AI model related to the use cases based on the modeling information.

[0476] The optional implementation of step S4102 can be found in the optional implementation of step S2103 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0477] Step S4103: Send the second AI model, constructed based on the modeling information, to the network device.

[0478] The optional implementation of step S4103 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0479] Step S4104: Receive the first information sent by the network device.

[0480] The optional implementation of step S4104 can be found in the optional implementation of step S2105 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0481] Step S4105: Based on the first information, collect sample data related to the second AI model and send it to the network device.

[0482] The optional implementation of step S4105 can be found in the optional implementation of step S2106 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0483] Step S4106: Receive the second information sent by the network device.

[0484] The optional implementation of step S4106 can be found in the optional implementation of step S2107 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0485] Step S4107: Determine the first computing power provided to the second AI model based on the second information, and feed back the first computing power to the network device.

[0486] In some embodiments, the first computing power is used to determine the first resources required for the second AI model.

[0487] The optional implementations of step S4107 can be found in the optional implementations of steps S2108 to S2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0488] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0489] Figure 4B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4B, the present disclosure relates to a communication method applicable to network elements in a first plane, the method comprising:

[0490] Step S4201: Interact with network devices to determine one or more pre-trained first AI models related to use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane.

[0491] The optional implementations of step S4201 can be found in the optional implementations of steps S2101 to 2110 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0492] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0493] Figure 5A is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 5A, the present disclosure relates to a communication method applicable to terminal devices, and the method includes:

[0494] Step 5101: Send the third information to the network device.

[0495] The optional implementation of step S5101 can be found in the optional implementation of step S2111 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0496] Step 5102: Receive AI decision information from the terminal device sent by the network device.

[0497] The optional implementation of step S5102 can be found in the optional implementation of step S2112 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0498] Step 5103: Receive deployment information of the third AI model sent by the network device.

[0499] In some embodiments, the third AI model is a trained AI model obtained by the network device interacting with network elements of the first plane, wherein the first plane includes at least an intelligent plane, a data plane, and a computing plane.

[0500] In some embodiments, the third AI model is the AI ​​model that matches the third information among a plurality of trained first AI models.

[0501] The optional implementation of step S5103 can be found in the optional implementation of step S2113 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0502] Step 5104: Receive the first data sent by the network device and update the third AI model based on the first data.

[0503] In some embodiments, the first data is one of the following: sample data for fine-tuning the third AI model, or model parameter update data for the third AI model.

[0504] The optional implementations of step S5104 can be found in the optional implementations of steps S2114 to S2115 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0505] Step 5105: Receive the fourth message sent by the network device.

[0506] Step 5106: Unload the second computing power related to the third AI model based on the fourth information.

[0507] The optional implementations of steps S5105 to S5106 can be found in the optional implementations of steps S2116 to S2117 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0508] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0509] Figure 5B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 5B, the present disclosure relates to a communication method applicable to terminal devices, and the method includes:

[0510] Step 5201: Receive deployment information of the third AI model sent by the network device. The third AI model is a trained AI model obtained by the network device through interaction with the network elements of the first plane. The first plane includes at least the intelligent plane, the data plane, and the computing plane.

[0511] The optional implementations of step S5201 can be found in the optional implementations of steps S2111 to S2117 in Figure 2A, as well as other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0512] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0513] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0514] The following is an exemplary description of the above method.

[0515] Intelligent agents perform AI-related tasks, such as data collection, AI model training and inference, and the generation and optimization of artificial intelligence algorithms to meet the needs of native networks, as shown in Figure 6A, deploying an AI-native 6G network. The RAN includes an AI use case generator module and an AI use case interpreter / evaluation module. The AI ​​use case generator module can generate multiple use cases, such as use case 1, use case 2, ..., use case m. The AI ​​use case interpreter / evaluation module interprets and evaluates the AI ​​use cases, inputting them into the model optimization module for algorithm strategy optimization to obtain the trained AI model. The model optimization module can include an AI model algorithm knowledge base, a computing network, and a data network. The computing network and data network learn from the AI ​​model's knowledge base to train the first AI model. It is understandable that the computing power network can interact with the network elements of the computing plane to obtain computing power, and the data network can interact with the network elements of the data plane to obtain sample data for training AI models.

[0516] In some embodiments, the RAN may also include a cloud-native platform through which AI models or functions can be built to improve the AI ​​capabilities of network devices.

[0517] In some embodiments, the RAN may further include a calculation unit, a storage unit, and a network unit to implement other communication functions related to the RAN.

[0518] In some embodiments, the RAN may send AI decision information to the UE to indicate to the UE whether an AI model can be used.

[0519] In some embodiments, the RAN can send deployment information of the AI ​​model to the UE to enable the AI ​​model to be deployed locally on the UE.

[0520] In some embodiments, the RAN can send computing power offload information to the UE to release the resources occupied by the AI ​​model.

[0521] In some embodiments, the RAN can send data to the UE, which may be sample data for fine-tuning the training of the AI ​​model or updated data of the model parameters of the AI ​​model.

[0522] In some embodiments, the UE may be equipped with a corresponding module to enable interaction with the RAN. Optionally, the UE may include a UE decision module, which can receive AI decision information sent by the RAN.

[0523] In some embodiments, the UE may further include an AI inference module that can receive deployment information of an AI model and perform inference based on the deployed AI model.

[0524] In some embodiments, the UE may also include a computing module that can provide physical resources for the use of the AI ​​model.

[0525] In some embodiments, the UE may also include a data module that can provide the AI ​​model with relevant data from the terminal device during inference.

[0526] In some embodiments, the network architecture can evolve from a 5G network deployment, as shown in Figure 6B. The NG-RAN includes multiple gNBs, data acquisition functions, and AI functions. The gNBs communicate with the data acquisition functions via a first interface (e.g., labeled GD), with the AI ​​functions via a second interface (e.g., labeled GA), and with the data acquisition functions via a third interface (e.g., labeled DA). The first interface can be an existing communication interface or a newly added one. Optionally, gNBs can communicate with each other via the Xn-C interface. Each gNB includes gNB-CU and gNB-DU. gNB-CUs communicate with each other via the F1 interface, and gNB-CUs and gNB-DUs can also communicate via the F1 interface. Furthermore, the NG-RAN communicates with the core network (5GC or 6GC) via the NG interface.

[0527] As shown in Figure 6B, advanced AI capabilities can be integrated with the upcoming 6G mobile network. From this perspective, the 6G wireless network can be considered a mobile AI network, mainly considering the following aspects:

[0528] As shown in Figure 6B

[0529] Endogenous networks with AI capabilities have the following architectural characteristics:

[0530] (1) Endogenous self-construction: Through a closed-loop process of "perception, training, verification, reasoning, and execution", the endogenous self-construction of capabilities and services is achieved.

[0531] (2) Intelligent capabilities, including related data capabilities and computing capabilities. Individual data capabilities and computing capabilities may not be strongly correlated with intelligent capabilities.

[0532] (3) Embedded intelligence can provide intelligent services to the system itself, and the system can obtain services without opening the capabilities;

[0533] (4) Cooperative control and scheduling management, emphasizing real-time cooperative control and non-real-time / semi-real-time scheduling management respectively. Cooperative control can be...

[0534] Quality-oriented, task-centered, and quick to respond to internal and external needs;

[0535] (5) Endogenous security: The endogenous security foundation that runs through the entire network provides endogenous security perception, defense and prevention functions for various functions and resources of the system.

[0536] This paper points out the drawbacks of existing 5G+AI network architectures that employ external and patched network solutions, and the necessity of an endogenous intelligent 6G network architecture. It presents the functional structure and logical architecture diagram of an endogenous intelligent 6G network, along with some proposed physical network architectures.

[0537] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0538] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0539] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0540] Figure 7 is a schematic diagram of the structure of a communication device proposed in an embodiment of this disclosure. As shown in Figure 7, the communication device 7100 may include at least one of a transceiver module 7101, a processing module 7102, etc.

[0541] In some embodiments, the communication device 7100 is a network device. The processing module is used to acquire one or more AI use cases, and the transceiver module is used to interact with network elements of a first plane to acquire a trained first AI model related to the AI ​​use case. The first plane includes at least an intelligence plane, a data plane, and a computing plane. Optionally, the transceiver module and the processing module are used 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, which will not be elaborated here.

[0542] In some embodiments, the communication device 7100 is a network element of a first plane, and the transceiver module is used to interact with the network device to determine a trained first AI model related to one or more AI use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane. Optionally, the transceiver module is used to perform at least one of the communication steps such as sending and / or receiving performed by the second communication device in any of the above methods, which will not be elaborated here.

[0543] In some embodiments, the communication device 7100 is a terminal device, and the transceiver module is used to receive deployment information of a third AI model sent by the network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane, wherein the first plane includes at least an intelligent plane, a data plane, and a computing plane. Optionally, the transceiver module is used to perform at least one of the communication steps such as sending and / or receiving performed by the second communication device in any of the above methods, which will not be elaborated here.

[0544] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0545] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0546] Figure 8A is a schematic diagram of the structure of the communication device 8100 proposed in an embodiment of this disclosure. The communication device 8100 can be a network device, a network element of the first plane, or a terminal device. It can also be a chip, chip system, or processor that supports the network device in implementing any of the above methods; a chip, chip system, or processor that supports the network element of the first plane in implementing any of the above methods; or a chip, chip system, or processor that supports the terminal device in implementing any of the above methods. The communication device 8100 can be used to implement the methods described in the above method embodiments, and specific details can be found in the descriptions in the above method embodiments.

[0547] 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, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 8100 can be used to execute any of the above methods. Optionally, one or more processors 8101 can be used to invoke instructions to cause the communication device 8100 to execute any of the above methods.

[0548] In some embodiments, the communication device 8100 further includes one or more transceivers 8103. When the communication device 8100 includes one or more transceivers 8103, the transceiver 8103 performs at least one of the communication steps such as sending and / or receiving in the above-described method, which will not be repeated here, while the processor 8101 performs other steps. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated together. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, sending unit, transmitter, sending circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0549] In some embodiments, the communication device 8100 further includes one or more memories 8102 for storing data. Optionally, all or part of the memories 8102 may be located outside the communication device 8100. In optional embodiments, the communication device 8100 may include one or more interface circuits 8104. Optionally, the interface circuits 8104 are connected to the memories 8102 and can be used to receive data from the memories 8102 or other devices, and to send data to the memories 8102 or other devices. For example, the interface circuits 8104 can read data stored in the memories 8102 and send the data to the processor 8101.

[0550] The communication device 8100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 8100 described in this disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG8A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0551] Figure 8B is a schematic diagram of the structure of chip 8200 according to an embodiment of this disclosure. For cases where the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of chip 8200 shown in Figure 8B, but it is not limited thereto.

[0552] Chip 8200 includes one or more processors 8201. Chip 8200 is used to perform any of the methods described above.

[0553] In some embodiments, chip 8200 further includes one or more interface circuits 8202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 8200 further includes one or more memories 8203 for storing data. Optionally, all or part of the memories 8203 may be located outside of chip 8200. Optionally, interface circuit 8202 is connected to memory 8203, and interface circuit 8202 can be used to receive data from memory 8203 or other devices, and interface circuit 8202 can be used to send data to memory 8203 or other devices. For example, interface circuit 8202 can read data stored in memory 8203 and send the data to processor 8201.

[0554] In some embodiments, the interface circuit 8202 performs at least one of the communication steps such as sending and / or receiving in the above-described method, which will not be elaborated further here. For example, the interface circuit 8202 performing the communication steps such as sending and / or receiving in the above-described method refers to the interface circuit 8202 performing data interaction between the processor 8201, the chip 8200, the memory 8203, or the transceiver device. In some embodiments, the processor 8201 performs other steps.

[0555] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0556] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device 8100, cause the communication device 8100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0557] This disclosure also provides a program product that, when executed by the communication device 8100, causes the communication device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0558] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0559] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0560] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0561] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0562] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

A communication method, characterized in that, Applicable to network devices, the method includes: acquiring one or more AI use cases; interacting with network elements of a first plane to acquire a trained first AI model related to the AI ​​use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane. The method according to claim 1, characterized in that, The method further includes: interpreting and evaluating the AI ​​use case to generate modeling information; interacting with network elements of the intelligent plane to obtain a second AI model related to the AI ​​use case generated based on the modeling information; and interacting with network elements of the data plane and computing plane to train the second AI model to obtain the first AI model. The method according to claim 2, characterized in that, The step of interacting with the network elements of the intelligent plane to obtain a second AI model related to the AI ​​use case generated based on the modeling information further includes: sending the modeling information to the network elements of the intelligent plane; and receiving the second AI model constructed based on the modeling information sent by the network elements of the intelligent plane. The method according to claim 2, characterized in that, Interacting with network elements of the data plane includes: sending first information to network elements of the data plane; and receiving sample data related to the second AI model collected by network elements of the data plane. The method according to claim 2, characterized in that, Interacting with network elements of the computing plane includes: sending second information to network elements of the computing plane; and receiving first computing capabilities provided by network elements of the computing plane for the second AI model. The method according to claim 5, characterized in that, The method further includes: determining a first resource for the second AI model based on the first computing power; and training the second AI model based on the first resource and the sample data to obtain the first AI model. The method according to any one of claims 1-6, characterized in that, The method further includes: receiving third information sent by a terminal device; and in response to the existence of a third AI model in the first AI model that matches the third information, sending deployment information of the third AI model to the terminal device. The method according to claim 7, characterized in that, After receiving the third information sent by the terminal device, the method further includes: making AI decisions on the terminal device based on the third information, and sending AI decision information to the terminal device. The method according to claim 7, characterized in that, After sending the deployment information of the third AI model to the terminal device, the method further includes: sending first data to the terminal device, wherein the first data is one of the following: sample data for fine-tuning the third AI model; or model parameter update data of the third AI model. The method according to claim 2, characterized in that, The method further includes sending a fourth message to the terminal device, the fourth message being used to instruct the terminal device to unload the computing power related to the third AI model. The method according to claim 1, characterized in that, The method further includes: the first intelligent flow corresponding to the control plane entity interacts with the core network through the control plane intelligent entity and the intelligent entity of the intelligent plane. The method according to claim 1, characterized in that, The method further includes: the second intelligent flow corresponding to the user plane entity interacts with the core network through the user plane intelligent entity and the intelligent entity of the intelligent plane. The method according to claim 1, characterized in that, The method further includes: the service flow corresponding to the user plane entity interacts with the core network through the intelligent entity of the intelligent plane. The method according to claim 1, characterized in that, The method further includes: the signal flow corresponding to the control plane entity interacts with the core network through the intelligent entity of the intelligent plane. A communication method, characterized in that, For network elements in a first plane, the method includes: interacting with network devices to determine a trained first AI model relevant to one or more AI use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane. The method according to claim 15, characterized in that, The method further includes: receiving modeling information of the AI ​​use case sent by the network device; constructing an initial second AI model related to the AI ​​use case based on the modeling information; and receiving the second AI model constructed based on the modeling information sent by a network element of the intelligent plane. The method according to claim 15, characterized in that, The method further includes: receiving first information sent by the network device; collecting sample data related to the second AI model based on the first information, and sending it to the network device, wherein the sample data is used to train the second AI model to obtain the first AI model. The method according to claim 15, characterized in that, The method further includes: receiving second information sent by the network device; determining a first computing power to be provided for the second AI model based on the second information; and feeding back the first computing power to the network device, wherein the first computing power is used to determine a first resource for the second AI model. A communication method, characterized in that, Applicable to terminal devices, the method includes: receiving deployment information of a third AI model sent by a network device, wherein the third AI model is a trained AI model obtained by the network device through interaction with network elements of a first plane, wherein the first plane includes at least an intelligent plane, a data plane, and a computing plane. The method according to claim 19, characterized in that, The step of receiving deployment information of the first AI model sent by the network device includes: sending third information to the network device; and receiving deployment information of the third AI model in the first AI model that matches the third information sent by the network device. The method according to claim 20, characterized in that, After sending the third information to the network device, the method further includes receiving AI decision information from the terminal device sent by the network device. The method according to claim 19, characterized in that, After receiving the deployment information of the third AI model sent by the network device, the method further includes: receiving first data sent by the network device, and updating the third AI model based on the first data; wherein the first data is one of the following: sample data for fine-tuning the third AI model; or model parameter update data of the third AI model. The method according to claim 19, characterized in that, The method further includes: receiving fourth information sent by the network device; and unloading the second computing power related to the third AI model according to the fourth information. A network device, characterized in that, include: The processing module is used to acquire one or more AI use cases; The transceiver module is used to interact with network elements of the first plane to obtain a trained first AI model related to the AI ​​use case, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane. A network element in a first plane, characterized in that, include: The transceiver module is used to interact with network devices to determine a trained first AI model related to one or more AI use cases, wherein the first plane includes at least an intelligence plane, a data plane, and a computing plane. A terminal device, characterized in that, include: The transceiver module is used to receive deployment information of a third AI model sent by a network device. The third AI model is a trained AI model obtained by the network device through interaction with network elements of the first plane. The first plane includes at least an intelligent plane, a data plane, and a computing plane. A network device, characterized in that, include: One or more processors; wherein the terminal is configured to perform the communication method according to any one of claims 1-14. A network element in a first plane, characterized in that, include: One or more processors; wherein the access network device is configured to perform the communication method according to any one of claims 15-18. A terminal device, characterized in that, include: One or more processors; wherein the first network element is configured to perform the communication method according to any one of claims 19-23. A communication system, characterized in that, The device includes a network device, network elements of a first plane, and a terminal device, wherein the network device is configured to implement the communication method of any one of claims 1-14, the network elements of the first plane are configured to implement the communication method of any one of claims 15-18, and the terminal device is configured to implement the communication method of any one of claims 19-23. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the communication method as described in any one of claims 1-14, 15-18, and 19-23. A program product, when run on a communication device, causes the communication device to perform the communication method as described in any one of claims 1-14, 15-18, and 19-23.

Images