Communication method and apparatus, storage medium and electronic device

Abstract

A communication method and apparatus, a storage medium, and an electronic device, relating to the technical field of communications. The method is applied to terminal UE, and comprises: sending a message or signaling to a target device, the message or signaling comprising a first message, the first message being used for the target device to perform model management, and the first message comprising UE capability information and / or user assistance information. When the UE has an AI function, the UE reports, in a message or signaling manner, the UE capability information to the target device located on the network side, thereby implementing transfer of the UE capability information.

Description

Communication methods and devices, storage media and electronic devices

[0001] Cross-references to related applications

[0002] This disclosure claims priority to Chinese Patent Application No. 202510127789.5, filed on January 27, 2025, entitled "Communication Method and Apparatus, Storage Medium and Electronic Device", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of communication technology, and in particular to a communication method and apparatus, a storage medium and an electronic device. Background Technology

[0004] The 6G wireless air interface will be designed with AI in its core. Compared with 5G, the communication scenarios will include the integration of artificial intelligence and communication. The key capabilities will be expanded compared with 5G, including new indicators related to perception, AI, sustainability, coverage, interoperability and positioning.

[0005] For the artificial intelligence functions newly introduced in the 6G wireless air interface, the terminal needs to design corresponding functional parameters to realize the reporting process mechanism and response transmission process of various terminal capabilities.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] This disclosure provides a communication method and apparatus, a storage medium and an electronic device, which at least to some extent realizes terminal capability reporting.

[0008] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0009] According to one aspect of this disclosure, a communication method is provided, applied to a terminal UE, the method comprising: sending a message or signaling to a target device, the message or signaling including a first message, the first message being used by the target device to perform model management; the first message including: UE capability information and / or user assistance information.

[0010] In some embodiments, the target device includes at least one of the following: a base station, a location server, a location management function, a location network element, a core network element, an intelligent computing unit, an intelligent unit, a RAN AI layer, a network data analysis function, a centralized unit, a distributed unit, a wireless AI management layer, a RAN AI management unit, a network element or network device responsible for location, and an AI / ML related network element or function or entity.

[0011] In some embodiments, signaling includes at least one of the following: management plane messages / signaling, control plane messages / signaling, user plane messages / signaling, intelligent plane messages / signaling, data plane messages / signaling, compute plane messages / signaling, system messages, NAS / AS signaling, dedicated configuration messages / signaling, RRC / higher layer protocol signaling, MAC CE, access control layer signaling, open interface protocol signaling, and DCI / physical layer signaling.

[0012] In some embodiments, the first message further includes: an AI / ML data collection information element; the AI / ML data collection information element is used to indicate whether the UE supports data acquisition function and whether it supports collecting and / or transmitting data for at least one of AI / ML training / inference / performance testing.

[0013] In some embodiments, the first message further includes: an AI / ML monitoring information element; the AI / ML monitoring information element is used to indicate whether the UE supports model performance monitoring and / or reporting of AI / ML model performance metrics and / or service quality.

[0014] In some embodiments, the first message further includes: an AI / ML power saving information element; the AI / ML power saving information element is used to indicate whether the UE supports using AI / ML terminal and / or network power saving.

[0015] In some embodiments, the first message further includes: a terminal storage capacity information element; the terminal storage capacity information element is used to indicate the size of the storage space supporting AI model training or inference.

[0016] In some embodiments, the first message further includes: a computing power capability information element; the computing power capability information element is used to indicate the amount of computing power supporting AI model training or inference.

[0017] In some embodiments, the first message further includes: AI / ML function information element; the AI / ML function information element is used to indicate the AIML function or feature / feature group supported by the UE.

[0018] In some embodiments, model management includes at least one of: model identification, model delivery, model deployment, model inference, data acquisition, model training, model activation / deactivation, and model performance testing.

[0019] In some embodiments, model management includes at least one of: AI / ML model management, AI model management, ML model management, model lifecycle management, AI management, and ML management.

[0020] According to another aspect of this disclosure, a communication method is also provided, applied to a target device, the method comprising: performing model management based on a first message included in a message or signaling sent by a terminal UE; the first message including: UE capability information and / or user assistance information.

[0021] According to another aspect of this disclosure, a communication apparatus is also provided, applied to a terminal UE, the apparatus comprising: a transmitting module for transmitting a message or signaling to a target device, the message or signaling including a first message, the first message being used by the target device to perform model management; the first message including: UE capability information and / or user assistance information.

[0022] According to another aspect of this disclosure, a communication apparatus is also provided, applied to a target device, the apparatus comprising: a model management module for performing model management based on a first message included in a message or signaling sent by a terminal UE; the first message including: UE capability information and / or user assistance information.

[0023] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform a communication method of any of the above via executing the executable instructions.

[0024] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the communication method described above.

[0025] According to another aspect of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements a communication method of any of the above.

[0026] The communication method, apparatus, storage medium, and electronic device provided in the embodiments of this disclosure, when applied to a terminal UE, include: sending a message or signaling to a target device, wherein the target device performs model management according to a first message included in the message or signaling; the first message includes: UE capability information.

[0027] In this embodiment, when the UE has AI capabilities, the UE reports its capability information to the target device on the network side via messages or signaling, thus realizing the transmission of UE capability information. This enables subsequent functions such as enabling / disabling and information interaction for UEs supporting AI capabilities on the radio side. It allows the network side to understand the UE's support for AI functions and technologies, supports the lifecycle management of the radio interface model, and ensures the model's self-organization, self-operation, self-optimization, and self-evolution on the RAN side. This facilitates the lifecycle management of the radio interface model, enabling the network to manage and control the AI ​​model, and allowing AI to intrinsically improve the performance of the wireless communication system. Through the above-mentioned structured UE capability information reporting mechanism, this disclosure not only achieves comprehensive awareness of the UE's AI / ML capabilities but, more importantly, provides the network side with refined decision-making basis. This allows the network to dynamically allocate AI models, adjust training strategies, and optimize inference task deployment based on the UE's actual computing power, storage, functional support, and data collection intentions, thereby significantly improving the utilization efficiency of radio resources and the overall intelligence level of the communication system while ensuring user experience.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0030] Figure 1 shows a first schematic diagram of a communication method according to an embodiment of the present disclosure.

[0031] Figure 2 shows a second schematic diagram of a communication method according to an embodiment of the present disclosure.

[0032] Figure 3 shows a first schematic diagram of a communication device according to an embodiment of the present disclosure.

[0033] Figure 4 shows a second schematic diagram of a communication device according to an embodiment of the present disclosure.

[0034] Figure 5 shows a structural block diagram of a computer device for a communication method according to an embodiment of the present disclosure. Detailed Implementation

[0035] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0036] To facilitate understanding, before introducing the embodiments of this disclosure, the following explanations are provided for several terms involved in the embodiments of this disclosure:

[0037] In 6G (sixth generation mobile communication technology), AI / ML (Artificial Intelligence and Machine Learning) will play an even more central and indispensable role. As networks become more complex and data volumes explode, traditional rule-based network management and optimization methods may no longer be sufficient. AI / ML will provide support in several areas, including at least: intelligent resource management, automated network slicing, enhanced user experience, ultra-reliable low-latency communication (URLLC), self-organizing networks (SON), security and privacy protection, edge computing, and full-duplex communication.

[0038] The specific implementation methods of the embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0039] In some embodiments, the terminal device may also be referred to as UE (User Equipment). In specific implementations, the terminal device may be a mobile phone, a tablet personal computer, a laptop computer, a personal digital assistant (PDA), a mobile internet device (MID), a wearable device, or an in-vehicle device, etc. It should be noted that the specific type of terminal device is not limited in the embodiments of the present invention.

[0040] Figure 1 shows a first schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 1, the communication method provided in this embodiment of the present disclosure includes S101.

[0041] Step S101: Send a message or signaling to the target device. The message or signaling includes a first message, which is used by the target device to perform model management. The first message includes: UE capability information and / or user assistance information.

[0042] Target devices (such as base stations and RAN AI management units) can perform precise model management based on received, structured UE capability information and / or user-assisted information. This includes not only model identification, transmission, and deployment, but more importantly, dynamic model activation / deactivation, performance monitoring, and version iteration based on the UE's real-time capabilities and context. This closed-loop management mechanism ensures that AI models can truly achieve self-organization, self-operation, self-optimization, and self-evolution (Self-X) on the RAN side, forming the cornerstone for building an endogenous 6G AI network.

[0043] In this embodiment, when the UE has AI functionality, the UE reports its capability information to the target device on the network side via messages or signaling, thus realizing the transmission of UE capability information. This enables subsequent function activation / deactivation and information exchange processes for UEs supporting AI functionality on the radio side. It allows the network side to know the UE's support for AI functions and technologies, supports the lifecycle management of the radio interface model, and ensures the model's self-organization, self-operation, self-optimization, and self-evolution on the RAN side. This facilitates the lifecycle management of the radio interface model, enabling the network to manage and control the AI ​​model, and allowing AI to intrinsically improve the performance of the wireless communication system.

[0044] In the evolution from 5G to 6G communication, it was explicitly stated that the 6G radio interface will be an AI-inherent design; the three major scenarios of 5G have expanded to six major scenarios of 6G, with the addition of the integration of artificial intelligence and communication; the nine key capabilities of 5G have expanded to fifteen capability indicators of 6G, with the addition of indicators related to perception, AI, sustainability, coverage, interoperability, and positioning. For the AIML function newly introduced into the radio interface, the terminal needs to design corresponding new functional parameters to define the reporting mechanisms and processes for various new terminal capabilities. Therefore, it is necessary to study and define the functional parameters that the UE can report to the network side, as well as the corresponding process mechanisms and response transmission procedures, when the UE has AI and ML capabilities.

[0045] In this embodiment, a set of specific UE capability parameters for AI / ML functions is designed based on the UE capability framework. This can enable / disable the corresponding functions and perform information interaction for UEs that support AI and ML functions on the radio side. This design is a necessary design for the radio side to implement AI and ML beam management schemes.

[0046] In the embodiment, the UE capability information includes at least one of the following: AI / ML capability information element, UE supported feature / feature group information element, and beam management information element.

[0047] In this embodiment, UE capability information (User Equipment Capability Reporting) is a key piece of information in a mobile communication network. The UE uses this information to report its supported functions and technical parameters to the network side. In this embodiment, UE capability information includes at least one of the following: AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements. UE capability information has multiple configuration options and can be used in different scenarios. The descriptions of the above information elements can take other forms, all of which are within the scope of protection of this disclosure embodiment. AI / ML capability information elements can be equivalent to various other information elements such as AI / ML capability indication information elements, AI capability information elements, ML capability information elements, AI functional capability information elements, and model-related information elements.

[0048] In this embodiment, sending a message or signaling to the target device includes: the terminal UE sending a message or signaling to the target device.

[0049] When a UE sends its capability information to a target device, it includes the capability information in a first message and sends it to the target device via a message or signaling.

[0050] In the embodiments, the terminal UE sends a message or signaling to the target device, including: the terminal UE sending a message or signaling to the target device, or: the terminal UE responding to a UE capability information request (e.g., an AI / ML capability request) sent by the target device and sending a message or signaling to the target device.

[0051] Sending UE capability information to the target device involves two reporting processes: active reporting and passive reporting.

[0052] When a UE actively reports, the terminal UE sends a message or signaling to the target device, and the target device performs model management based on the first message included in the message or signaling.

[0053] When the UE reports passively or responds, the UE receives a UE capability information request (e.g., an AI / ML capability request) sent by the target device. The UE sends a message or signaling to the target device according to the UE capability information request, and the target device performs model management according to the first message included in the message or signaling.

[0054] The reporting mechanism disclosed herein balances flexibility and efficiency. For high-capacity smart terminals, proactive reporting reduces network-side query signaling and accelerates service establishment; for ordinary terminals, on-demand querying effectively controls signaling overhead, avoids unnecessary broadcasting of capability information, and optimizes system signaling load.

[0055] In this embodiment, sending a message or signaling to the target device includes: the terminal UE receiving a UE capability information request (e.g., an AI / ML capability request) sent by the target device; and the terminal UE sending a message or signaling to the target device.

[0056] As an example, the target device sends an AI / ML capability request to the terminal UE. The terminal UE receives an AI / ML capability determination message or signaling, and then sends a message or signaling back to the target device. The target device performs model management based on the first message included in the message or signaling. The AI / ML capability request sent by the target device to the terminal UE can be a UECapabilityEnqiry message. An AI / ML capability request can be equivalent to a UE capability request, a UE capability information request, a terminal capability request, a model-related capability request, etc.

[0057] In this embodiment, the first message is at least one of user assistance information message, terminal capability information message, and location provision capability message.

[0058] When the UE communicates with the target device, the first message can be a UE Assistance Information (UAI) message, a UE Capability Information message, or a Location Provide Capabilities (LPP) message. The first message can be at least one or more of the following combinations: UE Assistance Information message, UE Capability Information message, and LPP provide capabilities message.

[0059] In this embodiment, the target device includes at least one of the following: a base station, a location server, a positioning management function, a positioning network element, a core network element, an intelligent computing unit, an intelligent unit, a RAN AI layer (Radio Access Network), a network data analysis function, a centralized unit, a distributed unit, a wireless AI management layer, a RAN AI management unit, a network element or network device responsible for positioning, and an AI / ML related network element or function or entity.

[0060] The terminal UE sends messages or signaling to the target device to achieve communication between the terminal UE and the target device, so as to send the UE capability information of the terminal UE to the target device. The target device can be a physical network device on the network side, or a network element or functional unit on the network side. Specifically, the target device can be at least one of the following: base station, location server, location management function (LMF), positioning network element, core network element, intelligent computing unit, intelligent unit, RAN AI layer, network data analysis function (NWDAF), central unit (CU), distributed unit (DU), wireless AI management layer, RAN AI management unit, network element or network device responsible for positioning, and AI / ML related network element or function or entity.

[0061] In the embodiments, the aforementioned signaling includes at least one of the following: management plane messages / signaling, control plane messages / signaling, user plane messages / signaling, intelligent plane messages / signaling, data plane messages / signaling, computing plane messages / signaling, system messages, NAS / AS (Non-Access Stratum / Access Stratum) signaling, dedicated configuration messages / signaling, RRC (Radio Resource Control) / higher layer protocol signaling, MAC CE (Medium Access Control Control Element), access control layer signaling, open interface protocol signaling, and DCI (Downlink Control Information) / physical layer signaling.

[0062] In the embodiments described above, the signaling sent by the terminal UE to the target device can be carried in various forms of messages or signaling. Specifically, the signaling sent by the terminal UE to the target device may include at least one of the following: management plane messages / signaling, control plane messages / signaling, user plane messages / signaling, intelligent plane messages / signaling, data plane messages / signaling, computing plane messages / signaling, system messages, NAS / AS signaling, dedicated configuration messages / signaling, RRC / higher layer protocol signaling, MAC CE, access control layer signaling, open interface protocol signaling, and DCI / physical layer signaling.

[0063] In the embodiment, the first message further includes at least one of the following: a reported UE-side supported function, an available / applicable function, a supported function, a feature / feature group, and an additional condition.

[0064] The UE capability information in the first message also includes at least one of the following: AI / ML capabilities, positioning capabilities, beam-related capabilities, and CSI-related capabilities. The UE capability information is associated with an associated ID. The process by which the terminal sends the UE capability information to the target device is used to support the target device in performing at least one of model identification and function identification on the terminal.

[0065] In the embodiment, if AI / ML capability information elements appear, then the UE supports AI / ML functions or the UE capability information includes AI / ML capability reporting or the UE supports AI / ML capability reporting.

[0066] The presence of AI / ML capability information elements indicates that these elements are enabled or defined. The AI / ML capability information element (General Parameters) can be aiML-Support-r19. The presence of aiML-Support-r19 indicates that the AI / ML capability information element is enabled or defined, suggesting that the UE supports AI / ML functions, or that the UE's capability information includes AI / ML capability reporting, or that the UE supports AI / ML capability reporting.

[0067] In the embodiments, it is also included that the information elements included in the UE capability information are fixed or optional.

[0068] The UE capability information includes at least AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements. These AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements can be either fixed (Mandatory) or optional (Optional).

[0069] In the embodiments, at least one of the AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements is fixed, or at least one information element is optional, or all information elements are fixed, or all information elements are optional.

[0070] The definition of UE capability parameters follows these rules: When a UE supports AI / ML functions, the functional information elements of that terminal capability are fixed, and for specific / dedicated functional parameters, the subordinate AI / ML related feature parameters are optional.

[0071] Different terminals may have different information cell configurations (optional or mandatory). For example, some terminals may have fixed information cells while others may have optional information cells. The UE capability information of different terminals may be sent in two ways: active and passive, with fixed or optional AI / ML related information cells.

[0072] For smart terminal UEs with AI wireless air interface communication capabilities, a fixed cell configuration can be used to reduce the network side's requests for related capability information from the terminal, making AI-related UE capability information a mandatory option.

[0073] For ordinary terminals or low-capability terminals such as Redcap, the use of optional cell configuration can reduce the number of cells sent for UE capability information and reduce the signaling load per call. When the terminal has the corresponding function or the network side needs to enable AI capability, AI / ML capability is reported in the form of UE capability request.

[0074] This disclosure provides a design for dynamically configuring the mandatory / optional status of information cells for different terminal types (such as full-featured UE vs. RedCap), which enables adaptive pruning of signaling messages. This ensures that the key AI capability information of high-capability terminals can always be known by the network, while minimizing the signaling load and processing complexity of single capability reporting for resource-constrained terminals, thereby improving the system's compatibility and scalability.

[0075] In this embodiment, the first message further includes: an AI / ML model management information element; this element indicates whether the UE supports at least one of the following operations: downloading, updating, and deleting AI / ML models. By explicitly reporting the UE's support for model lifecycle management operations, the network side can avoid issuing update commands to UEs that do not support model updates, or forcibly pushing large models to UEs with insufficient storage space. This effectively prevents signaling interaction failures, resource waste, and potential service interruptions, ensuring the reliability and efficiency of the model management process.

[0076] The first message, in addition to the information elements mentioned above, also includes AI / ML model management information elements. Specifically, aiML-ModelManagement-r19 is defined as the AI / ML model management information element, used to indicate whether the UE supports at least one of the following operations: downloading, updating, and deleting AI / ML models. Specifically, the AI / ML model management information element uses binary bits or Boolean type identifiers to indicate whether it supports receiving model downloads, model updates, and model deletions from the network side.

[0077] In this embodiment, the first message further includes: an AI / ML inference information element; this AI / ML inference information element is used to indicate whether the UE supports executing AI / ML inference tasks locally, and / or deploying AI / ML models locally and / or supports cloud-edge / edge-device / cloud collaborative inference. This element enables the network to accurately determine the UE's inference deployment mode. For UEs that support local inference, the network can offload latency-sensitive tasks (such as beam prediction and CSI compression) to the UE side, greatly reducing air interface transmission latency and backhaul network load; for UEs that only support cloud-based collaborative inference, the network can optimize task splitting points and data transmission paths, balancing UE power consumption and network resource consumption while ensuring Quality of Service (QoS).

[0078] The first message, in addition to the above information elements, also includes AI / ML inference information elements. By defining aiML-Inference-r19 as the AI / ML inference information element, it indicates whether the UE supports executing AI / ML inference tasks locally, and / or local deployment of AI / ML models, and / or supports cloud-edge / edge-device / cloud-based collaborative inference. Specifically, the AI / ML inference information element uses binary bit strings to sequentially represent whether local model deployment and cloud-edge / edge-device / cloud-based collaborative inference are supported.

[0079] In this embodiment, the first message further includes: an AI / ML data collection information element; this element indicates whether the UE supports data collection functionality and whether it supports collecting and / or transmitting data for at least one of AI / ML training / inference / performance testing. By distinguishing the UE's willingness to collect and report different types (training, inference, performance testing) and different sensitivities (latency-sensitive / non-sensitive) of data, this solution achieves a fine trade-off between user privacy and model performance. Based on this information, the network can request key training samples only from UEs that are willing and able to provide high-quality, low-latency data, significantly improving the data quality and convergence speed of distributed AI training frameworks such as federated learning, while respecting user privacy preferences.

[0080] First Message, in addition to the above information elements, also includes AI / ML data collection information elements. By defining aiML-DataCollection-r19 as the AI / ML data collection information element, it indicates whether the UE supports data acquisition functionality and whether it supports collecting and / or transmitting data for at least one of AI / ML training / inference / performance testing. Specifically, the AI / ML data collection information element uses binary bits or an enumeration type to identify whether data acquisition functionality is supported. It uses a binary bit string or an enumeration array to indicate whether data acquisition for training, inference, and performance testing is supported; 1 indicates support, and 0 indicates no support. The string indication can distinguish that some terminals (IoT terminals, redcap terminals) support latency-insensitive data acquisition, while some latency-sensitive data acquisition, such as inference or performance testing, is not supported.

[0081] In this embodiment, the first message further includes: an AI / ML monitoring information element; the AI / ML monitoring information element is used to indicate whether the UE supports model performance monitoring and / or reporting of AI / ML model performance metrics and / or service quality.

[0082] The first message, in addition to the above information elements, also includes AI / ML monitoring information elements. By defining aiML-Monitoring-r19 as the AI / ML monitoring information element, it is used to indicate whether the UE supports model performance monitoring and / or reporting of AI / ML model performance metrics and / or Quality of Service (QoS). Specifically, the AI / ML monitoring information element uses binary bits or an enumeration type, where 0 indicates that model performance detection and reporting is not supported, and 1 indicates that model performance detection and reporting is supported.

[0083] In this embodiment, the first message further includes: an AI / ML energy-saving information element; the AI / ML energy-saving information element is used to indicate whether the UE supports using AI / ML terminal and / or network energy saving.

[0084] The first message, in addition to the above information elements, also includes an AI / ML energy-saving information element; by defining aiML-EnergySaving-r19 as the AI / ML energy-saving information element, it is used to indicate whether the UE supports using AI / ML terminal and / or network energy saving. Specifically, the AI / ML energy-saving information element uses binary bits or an enumeration type, with 1 indicating support and 0 indicating no support.

[0085] In this embodiment, the first message further includes: a terminal storage capacity information element; the terminal storage capacity information element is used to indicate the size of the storage space supporting AI model training or inference.

[0086] In addition to the information elements mentioned above, the first message also includes a terminal storage capacity information element; this element indicates the size of the storage space supporting AI model training or inference. Specifically, the terminal storage capacity information element is divided into M storage space levels using a standard predefined format, with each level representing a different storage space size.

[0087] In this embodiment, the first message further includes: a computing power capability information element; the computing power capability information element is used to indicate the amount of computing power supporting AI model training or inference.

[0088] The first message, in addition to the above information elements, also includes computing power capability information elements; these information elements indicate the amount of computing power supporting AI model training or inference. Specifically, they are divided into M computing power capability levels in a standard predefined format, with each level representing a different computing power capability; alternatively, they can be an array of multiple indices, where different elements represent heterogeneous computing power capabilities such as CPU computing power, GPU computing power, and NPU computing power.

[0089] Reporting specific storage space levels and computing power capabilities (such as CPU / GPU / NPU) enables the network side to accurately match and distribute AI models on demand. For example, the network can allocate complex deep neural network models to high-computing-power UEs to achieve optimal performance, while allocating lightweight models to low-power RedCap terminals. This maximizes the overall energy efficiency of the system while meeting the differentiated needs of different terminals.

[0090] In the embodiment, the first message further includes: AI / ML function information element; the AI / ML function information element is used to indicate the AIML function or feature / feature group supported by the UE.

[0091] The first message, in addition to the above information elements, also includes AI / ML function information elements; by defining aiML-Functionality-r19 as the AI / ML function information element, it is used to indicate the AIML functions or features / feature groups supported by the UE.

[0092] In the embodiments, when an AI / ML capability information element appears, the AI / ML capability information element or the first message includes at least one of the following: AI / ML model management information element, AI / ML inference information element, AI / ML data collection information element, AI / ML monitoring information element, AI / ML energy saving information element, terminal storage capability information element, computing power capability information element, and AI / ML function information element.

[0093] When AI / ML capability information elements appear, these elements may include at least one of the following: AI / ML model management information elements, AI / ML inference information elements, AI / ML data collection information elements, AI / ML monitoring information elements, AI / ML energy-saving information elements, terminal storage capability information elements, computing power capability information elements, and AI / ML function information elements. The functions and definitions of these elements have been described above and will not be elaborated upon further here.

[0094] Furthermore, when an AI / ML capability information element appears, the first message can be at least one of the following: AI / ML model management information element, AI / ML inference information element, AI / ML data collection information element, AI / ML monitoring information element, AI / ML energy saving information element, terminal storage capacity information element, computing power capacity information element, and AI / ML function information element. The functions and definitions of the above information elements have been described above and will not be elaborated further here.

[0095] When AI / ML capability information elements appear, the aforementioned AI / ML model management information elements, AI / ML inference information elements, AI / ML data collection information elements, AI / ML monitoring information elements, AI / ML energy saving information elements, terminal storage capability information elements, computing power capability information elements, and AI / ML function information elements can be either information elements belonging to the first message or information elements belonging to the AI / ML capability information elements.

[0096] In the embodiment, if a feature / feature group information element supported by the UE appears, then the UE supports the feature / feature group; the feature / feature group information element or the first message includes at least one of the following: AI / ML direct positioning information element, AI / ML assisted positioning information element, AI / ML beam management information element, AI / ML predicted CSI management information element, AI / ML compressed CSI feedback information element, AI / ML assisted interference prediction information element, AI / ML assisted handover optimization information element, AI / ML network status prediction information element, and AI / ML network security enhancement information element.

[0097] The appearance of a UE-supported feature / feature group information element indicates that the UE-supported feature / feature group information element is enabled or defined, and that the UE supports that feature / feature group. At this time, the feature / feature group information element or the first message includes at least one of the following: AI / ML direct positioning information element, AI / ML assisted positioning information element, AI / ML beam management information element, AI / ML predicted CSI management information element, AI / ML compressed CSI feedback information element, AI / ML assisted interference prediction information element, AI / ML assisted handover optimization information element, AI / ML network status prediction information element, and AI / ML network security enhancement information element.

[0098] In the embodiment, the feature / feature group information element supported by the UE is defined as optional or mandatory. When the information element appears present, it indicates that the UE supports the feature / feature group, which includes the relevant information element definition.

[0099] In the embodiments, at least one of the following is included: AI / ML direct positioning information element to indicate whether the UE supports direct AI / ML positioning technology; AI / ML assisted positioning information element to indicate whether the UE supports AI / ML assisted positioning technology; AI / ML beam management information element to indicate whether the UE supports AI / ML beam management technology; AI / ML predicted CSI management information element to indicate whether the UE supports AI / ML predicted CSI management technology; AI / ML compressed CSI feedback information element to indicate whether the UE supports AI / ML compressed CSI feedback technology; AI / ML assisted interference prediction information element to indicate whether the UE supports AI / ML assisted interference prediction technology; AI / ML assisted handover optimization information element to indicate whether the UE supports AI / ML assisted handover optimization technology; AI / ML network state prediction information element to indicate whether the UE supports network state prediction; and AI / ML network security enhancement information element to indicate whether the UE supports using AI / ML technology to enhance network security.

[0100] In this embodiment, aiML-DirectPositioning-r19 is defined as an AI / ML direct positioning information element to indicate whether the UE supports direct AI / ML positioning technology. The estimated UE direct position information is obtained through model training and inference deployed on the UE side or LMF side.

[0101] In this embodiment, aiML-AssistedPositioning-r19 is defined as an AI / ML-assisted positioning information element to indicate whether the UE supports AI / ML-assisted positioning technology, thereby improving the accuracy and reliability of positioning. This element can indicate the measurement quantity used in the form of a string or an array. For example, each bit of the string indicates the supported measurement quantity CIR / TOA / TDOA / Multi-RTT, etc.

[0102] In this embodiment, aiML-BeamPrediction-r19 is defined as an AI / ML beam management information element to indicate whether the UE supports AI / ML beam management technology. This allows for optimized beam selection through time-domain or spatial-domain beam prediction, reducing beam measurement and selection trials, improving signal coverage, and minimizing interference. One approach is to define separate spatial-domain beam prediction elements, time-domain beam prediction elements, and joint space-time-frequency beam prediction elements. Another approach uses a single element to indicate the supported beam prediction type through different bit positions (0 / 1) in a binary bit string or an enumerated array.

[0103] In this embodiment, aiML-PredictiveCSIManagement-r19 is defined as the AI / ML predictive CSI management information element to indicate whether the UE supports AI / ML predictive CSI (Channel State Information) management technology, so as to predict changes in channel state information in advance and improve CSI accuracy.

[0104] In the embodiment, aiML-CompressedCSIFeedback-r19 is defined as the AI / ML compressed CSI feedback information element to indicate whether the UE supports AI / ML compressed CSI feedback technology, so as to reduce feedback overhead and improve system capacity. It also includes whether it supports centralized / single-sided model training, dual-sided model training, etc. For example, a string or enumeration type is used to indicate the model training type of CSI compressed feedback supported by the terminal side.

[0105] In this embodiment, aiML-InterferencePrediction-r19 is defined as an AI / ML-assisted interference prediction information element to indicate whether the UE supports AI / ML-assisted interference prediction technology, so as to dynamically adjust the transmission strategy, reduce interference and improve signal quality.

[0106] In this embodiment, aiML-HandoverOptimization-r19 is defined as an AI / ML-assisted handover optimization information element to indicate whether the UE supports AI / ML-assisted handover optimization technology, so as to achieve smoother network handover and reduce the drop rate.

[0107] In this embodiment, aiML-NetworkPrediction-r19 is defined as an AI / ML network state prediction information element to indicate whether the UE supports network state prediction, such as traffic prediction and signal quality prediction.

[0108] In this embodiment, aiML-SecurityEnhancement-r19 is defined as an AI / ML network security enhancement information element to indicate whether the UE supports using AI / ML technology to enhance network security, such as anomaly detection and intrusion prevention.

[0109] In the embodiment, when one of the beam management conditions is met, the first message further includes at least one of the following: aperiodic beam information reporting element, beam assist information reporting element, uplink / downlink beam prediction element, beam information reporting framework element, and beam scan measurement reporting element; the beam management conditions include at least one of the following: the UE capability information includes a beam management element, an AI / ML beam management element is defined / occurs, and the UE supports / has AI beam prediction capability.

[0110] When the beam management conditions are met, the UE capability information includes at least one of the following: beam management information element, AI / ML beam management information element is defined / occurs, and the UE supports / possesses AI beam prediction capability. The corresponding first message also includes at least one of the following: aperiodic beam information reporting information element, beam auxiliary information reporting information element, uplink / downlink beam prediction information element, beam information reporting framework information element, and beam scan measurement reporting information element.

[0111] In the embodiment, when the UE capability information includes beam management related information elements, when the UE supports / has AI beam prediction capability, and when the aiML-BeamPrediction-r19 information element is defined / occurs, the first message also includes the definition of beam management related information elements.

[0112] The embodiment includes at least one of the following: an aperiodic beam information reporting element used to indicate whether the UE supports at least one of aperiodic beam data acquisition or beam prediction performance detection reporting; a beam auxiliary information reporting element used to indicate whether the UE supports reporting auxiliary information for model training; an uplink / downlink beam prediction element used to indicate whether the UE supports at least one of uplink / downlink beam prediction, inter-cell beam prediction, or inter-frequency beam prediction; a beam information reporting framework element used to indicate whether the UE supports beam prediction model training; and a beam scan measurement reporting element used by the UE to indicate whether it supports scanning reporting of all / partial beams, or single / dual-sided beam measurement reporting on the base station side and / or the UE side.

[0113] The aperiodic beam information reporting cell indicates whether the UE supports aperiodic beam data acquisition or beam prediction performance testing reporting. The beam auxiliary information reporting cell indicates whether the UE supports reporting auxiliary information used for model training, such as UE reception angle and UE beam direction information. The uplink / downlink beam prediction cell indicates whether the UE supports uplink / downlink beam prediction, inter-cell beam prediction, and inter-frequency beam prediction. The beam information reporting framework cell indicates whether the UE supports beam prediction model training. The beam scan measurement reporting cell is used by the UE to indicate whether it supports scanning reporting of all / partial beams and whether it supports single / dual-sided beam measurement reporting on the base station side and / or the UE side.

[0114] In the embodiment, the beam information reporting framework information element includes: the maximum number of beam measurement periodic / semi-persistent and aperiodic reporting configurations, whether auxiliary information is supported, the types and / or number of supported beam auxiliary information reports, whether data acquisition access layer and application layer caching are supported, the maximum number of (transmit / receive) beam (measurement) reports, the maximum number of (store / cachate / activate / deactivate / inactive / monitor) beam prediction models, the minimum / maximum number of beam measurements: the number of beam measurements input to the model, and at least one of the maximum / minimum number of inter-cell / inter-frequency beam reports for L1 / L3 RSRP measurements.

[0115] In this embodiment, the beam information reporting framework indicates whether the UE supports beam prediction model training. This capability signaling includes the following parameters / elements: the maximum number of beam measurement periodic / semi-persistent and aperiodic reporting configurations; whether auxiliary information is supported, the types and / or number of supported beam auxiliary information reports; whether data acquisition access layer and application layer caching are supported; the maximum number of (transmit / receive) beam (measurement) reports; the maximum number of (store / cache / activate / deactivate / inactive / monitor) beam prediction models; the minimum / maximum number of beam measurements: the number of beam measurements input to the model; and the maximum / minimum number of inter-cell / inter-frequency beam reports for L1 / L3 RSRP measurements.

[0116] This disclosure provides embodiments that report specific AI / ML application scenarios (such as beam management, positioning, CSI feedback, etc.) supported by the UE in a fine-grained manner, enabling the network side to activate and configure corresponding AI workflows. For example, when it is known that the UE supports AI beam prediction, the base station can immediately enable a prediction algorithm based on historical data and configure corresponding aperiodic measurement reporting, thereby significantly reducing the overhead of traditional beam scanning and improving link robustness and spectrum efficiency in mobile scenarios.

[0117] In this embodiment, model management includes at least one of the following: model identification, model delivery, model deployment, model inference, data acquisition, model training, model activation / deactivation, and model performance testing.

[0118] When the target device performs model management based on the first message, it performs at least one of the following: model identification, model transfer, model deployment, model inference, data acquisition, model training, model activation / deactivation, and model performance testing. The data acquired during data acquisition is used for model training.

[0119] In this embodiment, model management includes at least one of: AI / ML model management, AI model management, ML model management, model lifecycle management, AI management, and ML management.

[0120] When the target device performs model management based on the first message, the target device performs at least one of the following: AI / ML model management, AI model management, ML model management, model lifecycle management, AI management, and ML management.

[0121] Figure 2 shows a second schematic diagram of a communication method in an embodiment of the present disclosure. As shown in Figure 2, the present disclosure also provides a communication method applied to a target device, the method including S201.

[0122] Step S201: Perform model management based on the first message included in the message or signaling sent by the terminal UE; the first message includes: UE capability information and / or user assistance information.

[0123] This disclosure, through its embodiments, defines how a UE transmits terminal-side AI / ML capabilities to a second device (e.g., a base station). This enables the network side to understand the support status of terminal AI / ML related functions and technical features, supports the lifecycle management of the radio interface AI / ML model, and is a foundational patent for the radio interface AI / ML technology framework. It ensures the self-organization, self-operation, self-optimization, and self-evolution of the AI / ML model on the RAN side. By defining reporting parameters related to AI beam management capabilities in AI / ML terminal capability reporting, the second device (e.g., a base station, network management system) understands the beam management functions supported by the terminal side (e.g., temporal beam prediction, spatial beam prediction), support for intra-cell / inter-cell / inter-frequency prediction, data acquisition and reporting, and cache support. This enables the AI-inherent RAN to support AI-based beam prediction technical features / functions. The AI / ML terminal capability reporting is defined to have both active and passive modes, supporting multiple reporting configurations such as periodic / semi-persistent / aperiodic, providing high flexibility.

[0124] The embodiments disclosed herein are applicable to the reporting of AI / ML terminal capabilities on the wireless side. They can be configured on the RAN side through the network side to enable the terminal to report relevant AI / ML capabilities to management network elements / layers such as base stations and network management systems, thereby facilitating the lifecycle management of AI / ML models on the wireless air interface, enabling the network to manage and control AI models, and enabling AI to intrinsically improve the performance of wireless communication systems.

[0125] This disclosure provides a method for reporting AI / ML capabilities of 5G-Advanced and 6G wireless terminals. It is applicable to 5G-A and future 6G networks, enabling base stations, wireless network management, related network elements, and AI / ML management entities / logical functions / layers to obtain specific information about the terminal's AI / ML-related functions / technical features through terminal AI / ML capability reporting. This enables wireless intelligent air interface AI / ML model lifecycle management and improves the performance of wireless communication systems through endogenous AI technology.

[0126] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution comply with the relevant provisions of national laws and regulations. The various types of data, such as personal identity data, operational data, and behavioral data related to individuals, customers, and groups, obtained in the embodiments of this disclosure have all been authorized.

[0127] Based on the same inventive concept, this disclosure also provides a communication device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0128] Figure 3 shows a first schematic diagram of a communication device according to an embodiment of the present disclosure. As shown in Figure 3, the device is applied to a terminal UE and includes:

[0129] The sending module 301 is used to send a message or signaling to the target device. The message or signaling includes a first message, which is used by the target device to perform model management. The first message includes: UE capability information and / or user assistance information.

[0130] It should be noted that the sending module 301 mentioned above corresponds to S101 in the method embodiment. The examples and application scenarios implemented by the above module and the corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment. It should be noted that the above module, as part of the apparatus, can be executed in a computer system such as a set of computer-executable instructions.

[0131] Based on the same inventive concept, this disclosure also provides a communication device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0132] Figure 4 shows a second schematic diagram of a communication device according to an embodiment of the present disclosure. As shown in Figure 4, the device is applied to a target device and includes:

[0133] The model management module 401 is used to perform model management based on a first message included in the message or signaling sent by the terminal UE; the first message includes: UE capability information and / or user assistance information.

[0134] It should be noted that the model management module 401 mentioned above corresponds to S201 in the method embodiment. The examples and application scenarios implemented by the above module and the corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment. It should be noted that the above module, as part of the apparatus, can be executed in a computer system such as a set of computer-executable instructions.

[0135] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0136] The electronic device 500 according to this embodiment of the present disclosure will now be described with reference to FIG5. The electronic device 500 shown in FIG5 is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present disclosure.

[0137] As shown in Figure 5, the electronic device 500 is presented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including storage unit 520 and processing unit 510).

[0138] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 510 can perform the steps of the above-described communication method embodiments and achieve the corresponding technical effects, which will not be repeated here.

[0139] Storage unit 520 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 5201 and / or cache memory 5202, and may further include a read-only memory (ROM) 5203.

[0140] Storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0141] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0142] Electronic device 500 can also communicate with one or more external devices 540 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0143] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0144] In particular, according to embodiments of this disclosure, the process described above with reference to the flowchart can be implemented as a computer program product, which includes a computer program that, when executed by a processor, implements the above-described communication method.

[0145] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the communication methods described above is stored thereon. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0146] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0147] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0148] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0149] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0150] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0151] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A communication method, executed by a terminal UE, the method comprising: Send a message or signaling to the target device, wherein the message or signaling includes a first message, the first message being used by the target device to perform model management; The first message includes: UE capability information and / or user assistance information.

2. The communication method according to claim 1, wherein, The UE capability information includes at least one of the following: AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements.

3. The communication method according to claim 1, wherein, Sending messages or signaling to the target device includes: the terminal UE sending messages or signaling to the target device.

4. The communication method according to claim 3, wherein, The terminal UE sending a message or signaling to the target device includes: the terminal UE sending a message or signaling to the target device, or: the terminal UE responding to a request to receive UE capability information sent by the target device and sending a message or signaling to the target device.

5. The communication method according to claim 1, wherein, Sending messages or signaling to the target device includes: The terminal UE receives a UE capability information request sent by the target device; The terminal UE sends messages or signaling to the target device.

6. The communication method according to claim 1, wherein The first message is at least one of user assistance information message, terminal capability information message, and location provision capability message.

7. The communication method according to claim 1, wherein The target device includes at least one of the following: base station, location server, positioning management function, positioning network element, core network element, intelligent computing unit, intelligent unit, RAN AI layer, network data analysis function, centralized unit, distributed unit, wireless AI management layer, RAN AI management unit, network element or network device responsible for positioning, and AI / ML related network element or function or entity.

8. The communication method according to claim 1, wherein The signaling includes at least one of the following: management plane messages / signaling, control plane messages / signaling, user plane messages / signaling, intelligent plane messages / signaling, data plane messages / signaling, computing plane messages / signaling, system messages, NAS / AS signaling, dedicated configuration messages / signaling, RRC / higher layer protocol signaling, MAC CE, access control layer signaling, open interface protocol signaling, and DCI / physical layer signaling.

9. The communication method according to claim 1, wherein, If an AI / ML capability information element appears, then the UE supports AI / ML functions, or the UE capability information includes AI / ML capability reporting, or the UE supports AI / ML capability reporting.

10. The communication method according to claim 2, wherein Also includes: The information elements included in the UE capability information may be fixed or optional.

11. The communication method according to claim 10, wherein At least one of the AI / ML capability information elements, UE-supported feature / feature group information elements, and beam management information elements is fixed, or at least one information element is optional, or all information elements are fixed, or all information elements are optional.

12. The communication method according to claim 1, wherein, The first message further includes: an AI / ML model management information element; the AI / ML model management information element is used to indicate whether the UE supports at least one of the operations of downloading, updating and deleting AI / ML models.

13. The communication method according to claim 1, wherein, The first message also includes: AI / ML inference information element; the AI / ML inference information element is used to indicate whether the UE supports performing AI / ML inference tasks locally, and / or local deployment of AI / ML models and / or supports cloud-edge-device / edge-device / cloud-based collaborative inference.

14. The communication method according to claim 1, wherein, The first message also includes: an AI / ML data collection information element; the AI / ML data collection information element is used to indicate whether the UE supports data acquisition function and whether it supports collecting and / or transmitting data for at least one of AI / ML training / inference / performance testing.

15. The communication method according to claim 1, wherein, The first message also includes: an AI / ML monitoring information element; the AI / ML monitoring information element is used to indicate whether the UE supports model performance monitoring and / or reporting of AI / ML model performance metrics and / or service quality.

16. The communication method of claim 1, wherein, The first message also includes: AI / ML energy-saving information element; the AI / ML energy-saving information element is used to indicate whether the UE supports using AI / ML terminal and / or network energy saving.

17. The communication method according to claim 1, wherein The first message also includes: a terminal storage capacity information element; the terminal storage capacity information element is used to indicate the size of the storage space supporting AI model training or inference.

18. The communication method according to claim 1, wherein, The first message also includes: a computing power capability information element; the computing power capability information element is used to indicate the amount of computing power supporting AI model training or inference.

19. The communication method according to claim 1, wherein, The first message also includes: AI / ML function information element; the AI / ML function information element is used to indicate the AIML function or feature / feature group supported by the UE.

20. The communication method of claim 1, wherein, When an AI / ML capability information element appears, the AI / ML capability information element or the first message includes at least one of the following: AI / ML model management information element, AI / ML inference information element, AI / ML data collection information element, AI / ML monitoring information element, AI / ML energy saving information element, terminal storage capability information element, computing power capability information element, and AI / ML function information element.

21. The communication method according to claim 1, wherein, If the feature / feature group information element supported by the UE appears, then the UE supports the feature / feature group; The feature / feature group information element or the first message includes at least one of the following: AI / ML direct positioning information element, AI / ML assisted positioning information element, AI / ML beam management information element, AI / ML predicted CSI management information element, AI / ML compressed CSI feedback information element, AI / ML assisted interference prediction information element, AI / ML assisted handover optimization information element, AI / ML network status prediction information element, and AI / ML network security enhancement information element.

22. The communication method according to claim 21, wherein, Includes at least one of the following: the AI / ML direct positioning information element indicates whether the UE supports direct AI / ML positioning technology; the AI / ML assisted positioning information element indicates whether the UE supports AI / ML assisted positioning technology; the AI / ML beam management information element indicates whether the UE supports AI / ML beam management technology; the AI / ML predicted CSI management information element indicates whether the UE supports AI / ML predicted CSI management technology; the AI / ML compressed CSI feedback information element indicates whether the UE supports AI / ML compressed CSI feedback technology; the AI / ML assisted interference prediction information element indicates whether the UE supports AI / ML assisted interference prediction technology; the AI / ML assisted handover optimization information element indicates whether the UE supports AI / ML assisted handover optimization technology; the AI / ML network state prediction information element indicates whether the UE supports network state prediction; and the AI / ML network security enhancement information element indicates whether the UE supports using AI / ML technology to enhance network security.

23. The communication method according to claim 1, wherein, When one of the beam management conditions is met, the first message further includes at least one of the following: aperiodic beam information reporting element, beam assist information reporting element, uplink / downlink beam prediction element, beam information reporting framework element, and beam scan measurement reporting element; the beam management conditions include at least one of the following: the UE capability information includes a beam management element, AI / ML beam management element is defined / occurs, and the UE supports / has AI beam prediction capability.

24. The communication method according to claim 23, wherein, Including at least one of the following: the aperiodic beam information reporting element is used to indicate whether the UE supports at least one of aperiodic beam data acquisition or beam prediction performance detection reporting; the beam auxiliary information reporting element is used to indicate whether the UE supports the reporting of auxiliary information for model training. The uplink / downlink beam prediction information element is used to indicate whether the UE supports at least one of uplink / downlink beam prediction, inter-cell beam prediction, and inter-frequency beam prediction; the beam information reporting framework information element is used to indicate whether the UE supports beam prediction model training; the beam scan measurement reporting information element is used by the UE to indicate whether it supports scanning reporting of all / partial beams, and whether it supports single / dual-sided beam measurement reporting on the base station side and / or the UE side.

25. The communication method according to claim 24, wherein, The beam information reporting framework information element includes: the maximum number of beam measurement periodic / semi-persistent and aperiodic reporting configurations, whether auxiliary information is supported, the types and / or number of supported beam auxiliary information reports, whether data acquisition access layer and application layer caching are supported, the maximum number of (transmit / receive) beam (measurement) reports, the maximum number of (store / cachate / activate / deactivate / inactive / monitor) beam prediction models, the minimum / maximum number of beam measurements: the number of beam measurements input to the model, and at least one of the maximum / minimum number of inter-cell / inter-frequency beam reports for L1 / L3 RSRP measurements.

26. The communication method according to claim 1, wherein, Model management includes at least one of the following: model identification, model delivery, model deployment, model inference, data acquisition, model training, model activation / deactivation, and model performance testing.

27. The communication method according to claim 1, wherein, Model management includes at least one of the following: AI / ML model management, AI model management, ML model management, model lifecycle management, AI management, and ML management.

28. A communication method performed by a target device, the method comprising: Model management is performed based on the first message included in the message or signaling sent by the terminal UE; The first message includes: UE capability information and / or user assistance information.

29. A communication device applied to a terminal UE, the device comprising: A sending module is used to send a message or signaling to a target device, wherein the message or signaling includes a first message, and the first message is used by the target device to perform model management. The first message includes: UE capability information and / or user assistance information.

30. A communication device applied to a target device, the device comprising: The model management module is used to perform model management based on the first message included in the message or signaling sent by the terminal UE; The first message includes: UE capability information and / or user assistance information.

31. An electronic device, comprising: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the communication method according to any one of claims 1 to 27 or claim 28 by executing the executable instructions.

32. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the communication method according to any one of claims 1 to 27 or claim 28.

33. A computer program product comprising a computer program that, when executed by a processor, implements the communication method according to any one of claims 1 to 27 or claim 28.

Images