Function and model management method and device and communication equipment

Abstract

The invention relates to a function and model management method and device and communication equipment. The method comprises the following steps: receiving a first RRC configuration message issued by a network; the first RRC configuration message comprises at least one of a network side additional condition / auxiliary information, a terminal autonomous decision indication, a reporting mode, a reference signal type, an execution condition and a measurement gap; managing functions and / or models according to the first RRC configuration message and / or the measurement result; the management comprises at least one of selection, activation, deactivation, switching and rollback; sending a first message to the network; the first message comprises a decision and / or a reason of the management; receiving a second RRC configuration message sent by the network; the second RRC configuration message comprises the processing of the network on the terminal. By adopting the method, the terminal side function / model can be managed in time, and the reliability of the terminal side function / model is improved.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus and communication device for managing functions and models. Background Technology

[0002] Currently, AI / ML (Artificial Intelligence / Machine Learning) technology has been introduced into the communications field as a candidate solution for technologies such as channel prediction, beam management, and positioning accuracy enhancement. To ensure the efficient operation of AI / ML in communication systems and to promote the intelligent, automated, and personalized development of communication networks, lifecycle management of AI / ML functions / models is necessary.

[0003] In existing lifecycle management schemes, decisions are typically made by the network. The network can issue management decisions to the terminal based on information uploaded by the terminal and its own information. However, when the terminal state changes, the functions / models activated on the terminal side may not match the terminal state. In this case, the network cannot make corresponding lifecycle management decisions in a timely manner, causing the functions / models on the terminal side to become inapplicable or even unable to function properly.

[0004] Therefore, current lifecycle management technologies for functions / models suffer from the problem of unreliability of terminal-side functions / models. Summary of the Invention

[0005] This application provides a method, apparatus, terminal device, network device, storage medium, and computer program product for managing functions and models, which can improve the reliability of terminal-side functions / models.

[0006] A method for managing functions and models, applied to a terminal; the method includes:

[0007] Receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0008] Based on the first RRC configuration message and / or measurement results, the function and / or model are managed; the management includes at least one of selection, activation, deactivation, switching, and rollback.

[0009] Send a first message to the network; the first message contains the management decision and / or reason;

[0010] The system receives a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0011] A method for managing functions and models, applied to a network; the method includes:

[0012] Send a first RRC configuration message to the terminal; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0013] The terminal sends a first message; the first message contains a decision and / or reason for managing the function and / or model; the management includes at least one of selection, activation, deactivation, switching, and rollback.

[0014] A second RRC configuration message is sent to the terminal; the second RRC configuration message contains the network's processing of the terminal.

[0015] A management device for functions and models, applied to a terminal; the device includes:

[0016] The terminal receiving module is used to receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap;

[0017] The terminal management module is used to manage functions and / or models based on the first RRC configuration message and / or measurement results; the management includes at least one of selection, activation, deactivation, switching, and rollback;

[0018] A terminal sending module is used to send a first message to the network; the first message contains the management decision and / or reason;

[0019] The receiving module is configured to receive a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0020] A management device for functions and models, applied to a network; the device includes:

[0021] The network sending module is used to send a first RRC configuration message to the terminal; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap;

[0022] A network receiving module is configured to receive a first message sent by the terminal; the first message contains a decision and / or reason for managing the function and / or model; the management includes at least one of selection, activation, deactivation, switching, and rollback;

[0023] The processing and sending module is used to send a second RRC configuration message to the terminal; the second RRC configuration message contains the network's processing of the terminal.

[0024] A terminal device includes: a receiver, a processor, and a transmitter;

[0025] The receiver is configured to receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap;

[0026] The processor is configured to manage functions and / or models based on the first RRC configuration message and / or measurement results; the management includes at least one of selection, activation, deactivation, switching, and rollback.

[0027] The transmitter is configured to send a first message to the network; the first message contains the management decision and / or reason;

[0028] The receiver is further configured to receive a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0029] A network device includes: a transmitter and a receiver;

[0030] The transmitter is used to send a first RRC configuration message to the terminal; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0031] The receiver is configured to receive a first message sent by the terminal; the first message contains a decision and / or reason for managing a function and / or model; the management includes at least one of selection, activation, deactivation, switching, and rollback;

[0032] The transmitter is further configured to send a second RRC configuration message to the terminal; the second RRC configuration message contains the network's processing of the terminal.

[0033] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0034] Receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0035] Based on the first RRC configuration message and / or measurement results, the function and / or model are managed; the management includes at least one of selection, activation, deactivation, switching, and rollback.

[0036] Send a first message to the network; the first message contains the management decision and / or reason;

[0037] The system receives a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0038] A computer program product includes a computer program, characterized in that, when executed by a processor, the computer program implements the functions and model management method provided in the embodiments of this application, the method being:

[0039] Receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0040] Based on the first RRC configuration message and / or measurement results, the function and / or model are managed; the management includes at least one of selection, activation, deactivation, switching, and rollback.

[0041] Send a first message to the network; the first message contains the management decision and / or reason;

[0042] The system receives a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0043] The aforementioned management methods, devices, terminal equipment, network equipment, storage media, and computer program products manage artificial intelligence and / or machine learning functions and / or models by receiving a first RRC configuration message from the network and, based on the first RRC configuration message and / or measurement results, sending a first message to the network and receiving a second RRC configuration message from the network. This enables the terminal to autonomously decide on the lifecycle management scheme for AI / ML functions / models based on the RRC configuration message from the network and the measurement results of the received beam, and to send the decision and / or reasons to the network. Since the lifecycle management scheme is autonomously decided by the terminal, lifecycle management can be performed in a timely manner when the terminal state changes, thereby improving the reliability of the terminal-side functions / models. Attached Figure Description

[0044] Figure 1 This is a schematic diagram illustrating the application environment of a management method for functions and models in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a method for managing functions and models in one embodiment;

[0046] Figure 3 This is a flowchart illustrating the management method for functions and models in another embodiment;

[0047] Figure 4 This is an interactive flowchart of a function / model lifecycle management method based on terminal autonomous decision-making in one embodiment;

[0048] Figure 5 This is a schematic diagram of the structure of a terminal device in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] Figure 1 This is a schematic diagram of an application environment for managing functions and models provided in an embodiment of this application. For example... Figure 1 As shown, this scenario includes a terminal 102 and a network device 104. The terminal 102 and the network device 104 communicate wirelessly.

[0051] Among them, network equipment 104 can be a base station (BTS) in Global System for Mobile communication (GSM) or Code Division Multiple Access (CDMA), a base station (NodeB, NB) in Wideband Code Division Multiple Access (WCDMA), an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a base station in a 5G network, etc., and is not limited here.

[0052] Terminal 102 may be a wireless terminal, which can be a device providing voice and / or other service data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a Radio Access Network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) or a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, exchanging voice and / or data with the RAN. The wireless terminal may also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, access terminal, user terminal, user agent, user device, or user equipment, without limitation herein.

[0053] Before introducing the specific embodiments of this application, the technical terms involved in this application will be explained:

[0054] AI / ML: Artificial Intelligence / Machine Learning;

[0055] Functions / Models: AI / ML functions and / or models;

[0056] RRC: Radio Resource Control;

[0057] MAC: Medium Access Control;

[0058] SS / PBCH: Synchronization Signal / Physical Broadcast Channel;

[0059] CSI-RS: Channel Statement Information-Reference Signal;

[0060] Set B: Measurement beam, input to the AI / ML model;

[0061] Set A: Inference beam, the output of the AI / ML model;

[0062] L1-RSRP: L1-Reference Signal Received Power, physical layer reference signal received power;

[0063] Top-1 beam: Optimal beam;

[0064] Top-K beams: the top K best beams.

[0065] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0066] In one embodiment, such as Figure 2 As shown, a method for managing functions and models is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0067] Step S202: Receive the first RRC configuration message sent by the network; the first RRC configuration message contains at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision instruction, reporting method, reference signal type, execution conditions, and measurement gap.

[0068] Here, "network" refers to network devices. The first RRC configuration message can be an RRC configuration message sent by the network device to the terminal. Network-side additional conditions / auxiliary information can be additional conditions or auxiliary information provided by the network side to the terminal for lifecycle management of functions / models. Terminal autonomous decision indication can be a message instructing the terminal whether to autonomously perform lifecycle management. Reporting method can be the method by which the terminal sends the first message to the network device, including but not limited to periodic reporting or event-triggered reporting. The first message can be a message sent by the terminal to the network device containing lifecycle management decisions and / or reasons. Reference signal type can be the type of reference signal sent by the network device to the terminal, including but not limited to reference signals based on SS / PBCH blocks or reference signals based on CSI-RS. Execution conditions can be the conditions under which the terminal performs lifecycle management decisions such as selection, activation, deactivation, switching, and rollback. Measurement interval can be the time period during which the terminal measures the received signal.

[0069] In a specific implementation, the network can send a first RRC configuration message to the terminal. The first RRC configuration message contains at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap. The terminal receives the first RRC configuration message sent by the network.

[0070] Step S204: Based on the first RRC configuration message and / or measurement results, manage the function and / or model; management includes at least one of selection, activation, deactivation, switching, and rollback.

[0071] The measurement results can be measurements of the received beams, including but not limited to the L1-RSRP of Set A / Set A subset, the beam identifier of the Top-1 beam, and the beam identifier of the Top-K beam. Management refers to lifecycle management. Selection can be the process of activating an AI / ML function / model among multiple models for the same AI / ML enabled function. Activation can be enabling an AI / ML function / model for a specific AI / ML supported function. Deactivation can be disabling an AI / ML function / model for a specific AI / ML enabled function. Switching can be deactivating the currently activated AI / ML function / model and activating a different AI / ML function / model for a specific AI / ML supported function. Rollback can be deactivating the currently activated AI / ML function / model and reverting to a non-AI / ML operation.

[0072] In practice, the terminal can measure the received beam, obtain the measurement results, and perform lifecycle management of its own AI / ML functions / models based on the first RRC configuration message and / or the measurement results, including at least one of the following: selecting, activating, deactivating, switching, and rolling back functions / models.

[0073] In practical applications, the terminal can measure the L1-RSRP, beam identifier of the Top-1 beam, and beam identifier of the Top-K beam of Set A / Set A subset during specified measurement intervals. Based on the measurement results, it can calculate the L1-RSRP differential and beam prediction accuracy. Based on the calculated L1-RSRP differential and beam prediction accuracy, it can select, activate, deactivate, switch, and roll back its own functions / models.

[0074] Step S206: Send a first message to the network; the first message contains the management decision and / or reason.

[0075] The decision can be the result of selecting, activating, deactivating, switching, or rolling back a function / model. The reasons can be, but are not limited to, the inference results of the function / model, the monitoring results on the terminal side, etc. The inference results can be the beam information obtained by the function / model inference, and the monitoring results on the terminal side include, but are not limited to, L1-RSRP differential, beam prediction accuracy, etc.

[0076] In practice, the terminal can generate a first message based on its decision and / or reasons for lifecycle management of its own functions / models, and send the first message to the network. The network receives the first message and determines whether to accept the terminal's lifecycle management decision based on the decision and / or reasons in the first message.

[0077] Step S208: Receive the second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0078] The second RRC configuration message can be another RRC configuration message sent by the network device to the terminal. It can include inference data collection configuration for the terminal, confirmation instruction for the terminal, or rollback instruction for the terminal. The inference data collection configuration can be configuration information provided by the network side for the terminal to collect inference data. The confirmation instruction can be an instruction to confirm receipt of the first message. The rollback instruction can be a message instructing the terminal to roll back the function / model.

[0079] In specific implementation, if the network accepts the terminal's lifecycle management decision, it sends a second RRC configuration message carrying the inference data collection configuration. When the terminal receives the second RRC configuration message, it extracts the inference data collection configuration provided by the network from the second RRC configuration message. If the network does not accept the terminal's lifecycle management decision, it sends a second RRC configuration message carrying a rollback instruction. When the terminal receives the second RRC configuration message, it can roll back its own AI / ML functions / models. The network can also simply confirm receipt of the first message after receiving the first message without performing any other processing.

[0080] The aforementioned management method for functions and models involves receiving a first RRC configuration message from the network, and based on the first RRC configuration message and / or measurement results, performing lifecycle management on the AI ​​and / or machine learning functions and / or models. This includes sending a first message to the network and receiving a second RRC configuration message from the network. This allows the terminal to autonomously decide on the lifecycle management scheme for AI / ML functions / models based on the RRC configuration message from the network and the measurement results of the received beam, and then send the decision and / or reasons to the network. Because the lifecycle management scheme is autonomously decided by the terminal, lifecycle management can be performed promptly when the terminal's state changes, improving the reliability of the terminal-side functions / models.

[0081] In one embodiment, the aforementioned network-side additional conditions / auxiliary information includes at least one of the following: the configuration of Set B, the configuration of Set A, the mapping relationship between Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, and antenna height.

[0082] The configuration of Set B can be its configuration information, including but not limited to the number of beams, beam identifiers, beam order, beam pattern (fixed / random / pre-configured continuous / discontinuous beams), the number of historical measurement time instances, and the number of predicted future time instances. The configuration of Set A can be its configuration information, including but not limited to the number of beams, beam identifiers, beam order, beam pattern (e.g., fixed / random / pre-configured continuous / discontinuous beams), the number of historical measurement time instances, and the number of predicted future time instances. Beam tilt angle, beam azimuth angle, beam elevation angle, and beam codebook can be the tilt angle, azimuth angle, elevation angle, and codebook of the network-side transmit / receive beams, respectively. Deployment scenario can be the scenario in which the terminals are deployed. Terminal distribution can be the distribution of the terminals. Transmission power can be the power of the signal transmitted by the network side. Antenna configuration can be the configuration of the network-side transmit / receive antennas, such as the number of antennas. Antenna height can be the height of the network-side transmit / receive antennas.

[0083] In a specific implementation, the network can send a first RRC configuration message to the terminal containing additional conditions / auxiliary information on the network side. The additional conditions / auxiliary information on the network side includes at least one of the following: the configuration of Set B, the configuration of Set A, the mapping relationship between Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, and antenna height.

[0084] In this embodiment, by configuring additional network-side conditions / auxiliary information, network-side information can be transmitted to the terminal, enabling the terminal to make more reliable lifecycle management decisions based on the network-side information.

[0085] In one embodiment, in the spatial domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A. In the temporal domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A; or Set B is the same as Set A.

[0086] In specific implementations, in the spatial domain, the mapping relationship between Set B and Set A can be that Set B and Set A are different and Set B is not a subset of Set A, or Set B is a subset of Set A; in the temporal domain, the mapping relationship between Set B and Set A can be that Set B and Set A are different and Set B is not a subset of Set A, or Set B is a subset of Set A, or Set B and Set A are the same.

[0087] In this embodiment, by configuring the mapping relationship between Set B and Set A in the time domain and spatial domain, the functions / models can be restricted according to the actual application situation, thereby increasing the reliability of the functions / models.

[0088] In one embodiment, the terminal autonomous decision instruction is used to instruct the terminal to autonomously manage and / or report functions and / or models.

[0089] In practice, the terminal can determine whether to autonomously manage the lifecycle of a function / model based on the terminal autonomous decision-making instruction in the first RRC configuration message. For example, if the terminal autonomous decision-making instruction allows autonomous decision-making, the terminal can autonomously select, activate, deactivate, switch, or roll back functions / models. Otherwise, if the terminal autonomous decision-making instruction does not allow autonomous decision-making, the terminal cannot autonomously select, activate, deactivate, switch, or roll back functions / models, and the network side needs to perform lifecycle management on the terminal.

[0090] In this embodiment, by configuring terminal autonomous decision permission, the terminal can be instructed to perform lifecycle management autonomously or non-autonomously, increasing the flexibility of lifecycle management on the terminal side.

[0091] In one embodiment, the method further includes: measuring the received beam of the reference signal to obtain a measurement result; the reference signal includes a reference signal based on the SS / PBCH block or a reference signal based on CSI-RS.

[0092] The receiving beam can be the beam sent by the network device and received by the terminal.

[0093] In practice, the terminal can measure the received beam to obtain the measurement result. The received beam can be a received beam based on the reference signal of the SS / PBCH block, or it can be a received beam based on the reference signal of CSI-RS.

[0094] In this embodiment, by measuring the received beam of the reference signal, the measurement results can be obtained. Based on the reference signal, the L1-RSRP of Set A / Set A subset, the beam identifier of Top-1 beam, the beam identifier of Top-K beam, and other measurement results can be obtained, and the accuracy of the measurement results is high.

[0095] In one embodiment, the measurement results include at least one of the L1-RSRP of Set A / Set A subset, Top-1 beam identifier, and Top-K beam identifier.

[0096] Here, Set A / Set A subset refers to Set A or a subset of Set A. The Top-1 beam identifier can be the beam identifier of the optimal beam. The Top-K beam identifier can be the beam identifier of the K optimal beams.

[0097] In this embodiment, by setting the measurement results to include at least one of L1-RSRP, Top-1 beam identifier, and Top-K beam identifier of Set A / Set A subset, lifecycle management can be automatically performed based on the terminal's measurement results, thereby improving the efficiency of lifecycle management.

[0098] In one embodiment, step S204 may specifically include: managing the function and / or model based on at least one of the following: measurement results, inference results, execution conditions, terminal capabilities, feasibility of the function / model on the terminal, additional conditions on the terminal side, and additional conditions / auxiliary information on the network side.

[0099] The inference result can be the result of inference performed by the model already activated on the terminal. Terminal capabilities include, but are not limited to, the terminal's memory, power, computing resources, and supported functions / models. The feasibility of each function / model on the terminal can be information on whether each function / model is feasible on the terminal. Additional conditions on the terminal side can be information that allows the terminal to autonomously manage its lifecycle.

[0100] In practice, the terminal can autonomously manage its own function / model lifecycle based on the measurement results obtained from measuring the received beam, according to at least one of the following: inference results, execution conditions (L1-RSRP differential greater than the first threshold, beam prediction accuracy less than the second threshold, etc.), terminal capabilities (memory, power, computing resources, supported functions / models, etc.), feasibility of the function / model on the terminal, additional conditions on the terminal side (speed, deployment scenario, beam azimuth angle, beam elevation angle, antenna configuration, antenna height, etc.) and additional conditions / auxiliary information on the network side (configuration of Set B and Set A, mapping of Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, antenna height, etc.).

[0101] In this embodiment, by managing the function and / or model based on at least one of the following: measurement results, inference results, execution conditions, terminal capabilities, feasibility of the function / model on the terminal, additional conditions on the terminal side, and additional conditions / auxiliary information on the network side, the reliability of the terminal's autonomous lifecycle management can be improved.

[0102] In one embodiment, the execution conditions include at least one of L1-RSRP differential being greater than a first threshold and beam prediction accuracy being less than a second threshold. At least one of the execution conditions, the first threshold, and the second threshold is configured by the network. Step S204 may specifically include: if any of the execution conditions are met, managing functions and / or models based on terminal capabilities. Terminal capabilities include at least one of the terminal's memory, power consumption, computing resources, and supported functions / models.

[0103] Here, L1-RSRP differential can be the difference between the measured value and the true value of L1-RSRP. Beam prediction accuracy can be the accuracy of inference performed by the function / model. The first threshold and the second threshold can be the pre-set L1-RSRP differential threshold and beam prediction accuracy threshold, respectively. Memory, power, and computing resources can be the current memory, power, and computing resource status of the terminal, respectively. Supported functions / models can be all functions and / or models supported by the terminal.

[0104] In specific implementation, the terminal can measure at least one of the following: L1-RSRP of Set A / Set A subset, beam identifier of Top-1 beam, and beam identifier of Top-K beam, and calculate the L1-RSRP difference and / or beam prediction accuracy. If the L1-RSRP difference is greater than a preset first threshold, and / or the beam prediction accuracy is less than a preset second threshold, the terminal can autonomously select, activate, deactivate, switch, or rollback at least one of the following based on its own memory, power, computing resources, and supported functions / models: at least one of these. The execution conditions, the first threshold, and the second threshold can be configured by the network side and notified to the terminal.

[0105] In this embodiment, if any of the execution conditions are met, the functions and / or models can be managed based on the terminal's capabilities. This allows the terminal to autonomously manage its lifecycle according to pre-set trigger conditions, thereby improving the flexibility of lifecycle management.

[0106] In one embodiment, the terminal-side additional conditions include at least one of speed, deployment scenario, beam azimuth angle, beam elevation angle, antenna configuration, and antenna height.

[0107] Among these, speed can be the terminal's movement speed. Deployment scenario can be the scenario in which the terminal is deployed. Beam azimuth and beam elevation can be the azimuth and elevation angles of the terminal's transmit / receive beams, respectively. Antenna configuration can be the configuration of the terminal's transmit / receive antennas, such as the number of antennas. Antenna height can be the height of the terminal's transmit / receive antennas.

[0108] In this embodiment, by setting additional conditions on the terminal side, including at least one of speed, deployment scenario, beam azimuth angle, beam elevation angle, antenna configuration, and antenna height, the terminal can autonomously perform lifecycle management based on the additional conditions on the terminal side, thereby improving the efficiency of lifecycle management.

[0109] In one embodiment, the cause includes at least one of the inference result of the function / model and the first monitoring result.

[0110] The inference results of the function / model can be the results obtained by inferring from the function / model on the terminal side. The first monitoring result can be the monitoring result on the terminal side, including but not limited to the L1-RSRP differential and beam prediction accuracy calculated by the terminal side.

[0111] In specific implementation, the terminal can determine the decision and / or reason for selecting, activating, deactivating, switching, or rolling back its own functions / models based on the first RRC configuration message and / or measurement results. The reason may include the inference results of the terminal-side functions / models, as well as the monitoring results of the terminal-side (L1-RSRP differential, beam prediction accuracy, etc.).

[0112] In this embodiment, by setting the reasons for lifecycle management, the network can be provided with decisions and / or reasons for terminal-side lifecycle management, thereby improving the reliability of the network's decision on whether to accept the terminal's lifecycle management.

[0113] In one embodiment, the first message is reported to the network via UEAssistanceInformation signaling.

[0114] Among them, UEAssistanceInformation signaling can be terminal-side assistance information signaling, that is, signaling sent by the terminal to the network carrying terminal-side assistance information.

[0115] In practice, the terminal can carry the first message in the UEAssistanceInformation signaling and send it to the network.

[0116] In this embodiment, reliable transmission of the first message can be ensured by configuring the transmission signaling of the first message.

[0117] In one embodiment, the network's processing of the terminal includes at least one of inference data collection configuration, confirmation instruction, and rollback instruction.

[0118] In specific implementation, if the network accepts the terminal's lifecycle management decision, it sends a second RRC configuration message carrying the inference data collection configuration. When the terminal receives the second RRC configuration message, it extracts the inference data collection configuration provided by the network from the second RRC configuration message. If the network does not accept the terminal's lifecycle management decision, it sends a second RRC configuration message carrying a rollback instruction. When the terminal receives the second RRC configuration message, it can roll back its own AI / ML functions / models. The network can also simply confirm receipt of the first message after receiving the first message without performing any other processing.

[0119] In this embodiment, by setting the network's processing of the terminal to include at least one of inference data collection configuration and rollback indication, the terminal can use the inference data collection configuration to perform function / model inference when the network side accepts lifecycle management decisions, and roll back the function / model when the network side does not accept lifecycle management decisions, thus ensuring the reliable operation of the terminal-side function / model.

[0120] In one embodiment, such as Figure 3 As shown, a method for managing functions and models is provided, which can be applied to... Figure 1 Taking network device 104 as an example, the following steps are included:

[0121] Step S302: Send a first RRC configuration message to the terminal; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision instruction, reporting method, reference signal type, execution conditions, and measurement gap;

[0122] Step S304: Receive a first message sent by the terminal; the first message contains a decision and / or reason for managing the function and / or model; management includes at least one of selection, activation, deactivation, switching, and rollback;

[0123] Step S306: Send a second RRC configuration message to the terminal; the second RRC configuration message contains the network's processing of the terminal.

[0124] In a specific implementation, the network device can send a first RRC configuration message to the terminal. Based on the received first RRC configuration message and the measurement results obtained by measuring the received beam, the terminal can autonomously select, activate, deactivate, switch, or roll back at least one of its own AI / ML functions / models, and generate a first message containing lifecycle management decisions and / or reasons. The first message is then sent to the network device. After receiving the first message, the network device can obtain the decisions and / or reasons in the first message, and generate a second RRC configuration message based on whether to accept the lifecycle management decision on the terminal side, and return the second RRC configuration message to the terminal.

[0125] The management method for the above functions and models, by sending a first RRC configuration message to the terminal, receiving a first message sent by the terminal, and sending a second RRC configuration message to the terminal, enables the terminal to autonomously decide on the lifecycle management scheme for AI / ML functions / models based on the RRC configuration messages sent by the network and the measurement results of the received beam, and send the decision and / or reasons to the network. Since the lifecycle management scheme is autonomously decided by the terminal, lifecycle management can be performed in a timely manner when the terminal state changes, thereby improving the reliability of the terminal-side functions / models.

[0126] In one embodiment, the aforementioned first RRC configuration message is carried by an OtherConfig message.

[0127] Among them, OtherConfig messages can be other configuration messages, that is, messages sent from the network to the terminal that carry other configuration information.

[0128] In practice, the network device can carry the first RRC configuration message in the OtherConfig message and send it to the terminal.

[0129] In this embodiment, by carrying the first RRC configuration message in the OtherConfig message, the reliable transmission of the first RRC configuration message can be guaranteed.

[0130] In one embodiment, the method further includes: determining whether to accept the decision based on at least one of a first message, a second monitoring result, and additional network-side conditions / auxiliary information; wherein the second monitoring result includes at least one of throughput, block error rate, signaling overhead, and packet delay.

[0131] The second monitoring result can be the monitoring result from the network side, including but not limited to throughput, block error rate, signaling overhead, packet delay, etc. calculated by the network side.

[0132] In specific implementation, the network device can determine whether to accept the terminal's lifecycle management decision based on the received first message, its own second monitoring result, and at least one of the network-side additional conditions / auxiliary information. If it accepts the terminal's lifecycle management decision, it sends a second RRC configuration message carrying the inference data collection configuration to the terminal. Otherwise, if it does not accept the terminal's lifecycle management decision, it sends a second RRC configuration message carrying a rollback instruction to the terminal, instructing the terminal to roll back the function / model.

[0133] In this embodiment, by determining whether to accept the decision based on at least one of the first message, the second monitoring result, and additional conditions / auxiliary information from the network side, the terminal can obtain information on whether the network accepts or does not accept its lifecycle management decision. This allows the lifecycle management decision on the terminal side to fully consider network side conditions and improve the reliability of lifecycle management.

[0134] To facilitate a deeper understanding of the embodiments of this application by those skilled in the art, a specific example will be used for illustration below.

[0135] This application introduces a function / model lifecycle management method for scenarios where terminal states change rapidly. In this method, after receiving configuration messages from the network, the terminal performs measurements in the configured measurement time slots (measurement intervals) to determine whether the measurement indicators (measurement results) meet the execution conditions issued by the network. If the measurement indicators meet the execution conditions, the terminal combines the measurement results, terminal capabilities, and additional conditions on the terminal side to select / activate / deactivate / rollback / switch functions / models, and sends the lifecycle management decision and model monitoring results to the network to ensure the normal operation of terminal services.

[0136] In one embodiment, a method for managing the lifecycle of a function / model based on terminal autonomous decision-making is provided, applied to a terminal, including:

[0137] Receive a first RRC configuration message sent by the network. The first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, allowing terminal autonomous decision-making (terminal autonomous decision-making instruction), reporting method, reference signal type, execution conditions, and measurement gap.

[0138] Based on the measurement results, perform at least one of the following: function / model selection, activation, deactivation, switching, and rollback;

[0139] Send a first message to the network, the first message containing at least one of the following: terminal function / model selection, activation, deactivation, switching, rollback result and / or reason.

[0140] In one embodiment, the aforementioned network-side additional conditions / auxiliary information includes at least one of the following: configuration of Set B and Set A, mapping of Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, and antenna height.

[0141] In one embodiment, Set B is defined as the measurement beam, which is the input to the model inference, and Set A is defined as the prediction beam (inference beam), which is the output of the model inference.

[0142] In one embodiment, the configuration of Set B and Set A includes at least one of the following: number of beams in Set B, number of beams in Set A, beam ID in Set B, beam ID in Set A, beam order in Set B, beam order in Set A, Set B mode (fixed / random / pre-configured continuous / discontinuous beams), number of historical measurement time instances, and number of predicted future time instances.

[0143] In one embodiment, when the mapping relationship between Set B and Set A is in the spatial domain, the relationship between Set B and Set A is any one of the following: Set B and Set A are different (Set B is not a subset of Set A), or Set B is a subset of Set A.

[0144] In one embodiment, when the mapping relationship between Set B and Set A is in the time domain, the relationship between Set B and Set A is any one of the following: Set B and Set A are different (Set B is not a subset of Set A), Set B is a subset of Set A, or Set B and Set A are the same.

[0145] In one embodiment, the above-mentioned allow terminal autonomous decision-making instruction indicates that the terminal can autonomously perform at least one of the following: function / model selection, activation, deactivation, switching, and rollback.

[0146] In one embodiment, the above reporting method is periodic reporting or event triggering.

[0147] In one embodiment, the reference signal type is based on SS / PBCH blocks or CSI-RS.

[0148] In one embodiment, the aforementioned reference signal based on the SS / PBCH block or CSI-RS is used by the terminal to obtain beam measurement results.

[0149] In one embodiment, the above execution conditions include one or more triggering conditions.

[0150] In one embodiment, the measurement gap indicates the time period during which the terminal is used for measurement.

[0151] In one embodiment, the measurement results include at least one of the L1-RSRP of Set A / Set A subset, the beam ID of Top-1 beam, and the beam ID of Top-K beam.

[0152] In one embodiment, based on the measurement results, the terminal can also perform function / model lifecycle management based on at least one of the following: prediction results (inference results), execution conditions, terminal capabilities, feasibility of the function / model on the terminal, additional conditions on the terminal side, and additional conditions / auxiliary information on the network side.

[0153] In one embodiment, the above prediction result is the inference result of the terminal's activated model.

[0154] In one embodiment, the above execution conditions include at least one of L1-RSRP differential being greater than a first threshold and beam prediction accuracy being less than a second threshold.

[0155] In one embodiment, the aforementioned terminal capabilities include at least one of the terminal's memory, power consumption, computing resources, and supported functions / models.

[0156] In one embodiment, the aforementioned terminal-side additional conditions include at least one of speed, scene, beam azimuth angle, beam elevation angle, antenna settings, and antenna height.

[0157] In one embodiment, the above definition of function / model selection is the process of selecting one AI / ML function / model from multiple models to activate the same AI / ML function.

[0158] In one embodiment, the definition of the above-mentioned function / model activation is to enable AI / ML functions / models for specific AI / ML support functions.

[0159] In one embodiment, the definition of deactivating the above-mentioned function / model is to disable the AI / ML function / model for a specific AI / ML enabled function.

[0160] In one embodiment, the above-mentioned function / model switching is defined as deactivating the currently active AI / ML function / model and activating different AI / ML functions / models for specific AI / ML supported functions.

[0161] In one embodiment, the definition of the above-mentioned function / model rollback is to deactivate the currently active AI / ML function / model and roll back to a non-AI / ML operation.

[0162] In one embodiment, the reasons for the above-mentioned terminal function / model selection, activation, deactivation, switching, and rollback include at least one of the terminal-side reasoning results and monitoring results for the function / model.

[0163] In one embodiment, the aforementioned first message may be carried by UEAssistanceInformation signaling.

[0164] In one embodiment, a function / model lifecycle management method based on terminal autonomous decision-making is provided, applied to a network, including:

[0165] Send a first RRC reconfiguration message to the terminal. The first RRC reconfiguration message includes at least one of the following: network-side additional conditions / auxiliary information, allowing the terminal to make autonomous decisions, reporting method, reference signal type, execution conditions, and measurement gap.

[0166] The receiving terminal sends a first message, which includes at least one of the following: terminal function / model selection, activation, deactivation, switching, rollback result and / or reason.

[0167] In one embodiment, the aforementioned first RRC configuration message may be carried by OtherConfig.

[0168] In one embodiment, the network receives a first message sent by the terminal and determines whether to accept the terminal's lifecycle management decision based on at least one of the following: terminal function / model selection, activation, deactivation, switching, rollback results, reasons for terminal function / model selection, activation, deactivation, switching, rollback, network-side monitoring results, and network-side additional conditions.

[0169] In one embodiment, the network-side monitoring results mentioned above include at least one of throughput, block error rate, signaling overhead, and packet latency.

[0170] In one embodiment, if the network accepts the terminal's lifecycle management decision, the network issues a second RRC reconfiguration message to provide inference data collection configuration.

[0171] In one embodiment, if the network does not accept the terminal's lifecycle management decision, the network issues a third RRC reconfiguration message to instruct the terminal to perform a function / model rollback.

[0172] Figure 4 An interactive flowchart is provided for a terminal-based autonomous decision-making method for function / model lifecycle management. Based on... Figure 4 A method for managing the lifecycle of a function / model based on terminal autonomous decision-making may include the following steps:

[0173] Step S401: The network sends UECapabilityEnquiry information, requesting the terminal to report the functions it supports in AI / ML.

[0174] In step S402, the terminal reports the functions it supports to the network through UECapabilityInformation.

[0175] Step S403: Send an RRC reconfiguration message to provide network configuration and request the terminal to report the applicable functions of the UE;

[0176] Step S404: The terminal reports the applicable functions to the network;

[0177] Step S405: The network sends an RRC reconfiguration message to the terminal to provide inference configuration;

[0178] Step S406: The network activates, deactivates, infers, or monitors available functions via RRC, MAC CE (MAC Control Element), or DCI (Downlink Control Information) signaling.

[0179] Step S407: The network collects additional conditions on the network side and sends the first RRC reconfiguration information to the terminal. The first RRC reconfiguration information includes additional conditions / auxiliary information on the network side, allows the terminal to make autonomous decisions, reporting method, reference signal type, execution conditions, and measurement gap.

[0180] Step S408: The terminal collects measurement results, including L1-RSRP of Set A / Set A subset, beam ID of Top-1 beam, and beam ID of Top-K beam;

[0181] Step S409a: If the L1-RSRP difference is greater than the first threshold, the terminal performs function / model selection / activation / deactivation / switching / rollback based on the terminal's capabilities.

[0182] Step S409b: If the beam prediction accuracy is less than the first threshold, the terminal performs function / model selection / activation / deactivation / switching / rollback based on the terminal's capabilities.

[0183] In step S410, the terminal reports the first message via L1 signaling, including terminal function / model selection, activation, deactivation, switching, rollback result and / or reason;

[0184] Step S411: The network receiving terminal sends the first message and monitors network-side indicators, including throughput, block error rate, signaling overhead, and data packet delay.

[0185] Step S412: Based on the terminal function / model selection, activation, deactivation, switching, and rollback results, the reasons for terminal function / model selection, activation, deactivation, switching, and rollback, the network-side monitoring results, and the network-side additional conditions, the network determines whether to accept the terminal's lifecycle management decision.

[0186] Step S413a: If the network accepts the management decision reported by the terminal, the network provides the inference data collection configuration to the terminal through the second RRC reconfiguration signaling.

[0187] In step S413b, if the network refuses to accept the management decision reported by the terminal, the network instructs the terminal to perform a function / model rollback through the third RRC reconfiguration signaling.

[0188] The aforementioned lifecycle management method for the terminal autonomous decision-making function / model enables the terminal to make autonomous decisions and send management decision reports to the network in scenarios where the terminal state changes rapidly. This reduces signaling consumption between the network and the terminal and lowers service response latency.

[0189] Furthermore, by combining a lifecycle management mechanism that integrates triggering events, terminal capabilities, and additional terminal-side conditions, the terminal can make lifecycle management decisions based on measurement results, terminal capabilities, and additional terminal-side conditions. Threshold-based triggering conditions enable the network to indirectly monitor the terminal, ensuring the controllability of the terminal's autonomous management behavior. Management based on terminal capabilities and additional terminal-side conditions improves the flexibility of the terminal's decision-making methods and ensures the high reliability of the AI / ML terminal's functions / models.

[0190] It should be understood that, although Figure 2-4 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-4 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0191] In one embodiment, a function and model management device is provided, applied to a terminal; the device includes:

[0192] The terminal receiving module is used to receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap;

[0193] The terminal management module is used to manage functions and / or models based on the first RRC configuration message and / or measurement results; the management includes at least one of selection, activation, deactivation, switching, and rollback;

[0194] A terminal sending module is used to send a first message to the network; the first message contains the management decision and / or reason;

[0195] The receiving module is configured to receive a second RRC configuration message sent by the network; the second RRC configuration message contains the network's processing of the terminal.

[0196] In one embodiment, the network-side additional conditions / auxiliary information includes at least one of the following: the configuration of Set B, the configuration of Set A, the mapping relationship between Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, and antenna height.

[0197] In one embodiment, in the spatial domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A. In the time domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A; or Set B is the same as Set A.

[0198] In one embodiment, the terminal autonomous decision instruction is used to instruct the terminal to autonomously manage and / or report the functions and / or models.

[0199] In one embodiment, the apparatus further includes a terminal measurement module for measuring the received beam of the reference signal to obtain the measurement result; the reference signal includes a reference signal based on the SS / PBCH block or a reference signal based on CSI-RS.

[0200] In one embodiment, the measurement results include at least one of the L1-RSRP of Set A / Set A subset, Top-1 beam identifier, and Top-K beam identifier.

[0201] In one embodiment, the terminal management module is further configured to manage the function and / or model based on at least one of the measurement results, inference results, execution conditions, terminal capabilities, feasibility of the function / model on the terminal, additional conditions on the terminal side, and additional conditions / auxiliary information on the network side.

[0202] In one embodiment, the execution conditions include at least one of L1-RSRP differential being greater than a first threshold and beam prediction accuracy being less than a second threshold.

[0203] In one embodiment, at least one of the execution conditions, the first threshold, and the second threshold is configured by the network.

[0204] In one embodiment, the terminal management module is further configured to manage the functions and / or models based on the terminal capabilities if any of the execution conditions are met.

[0205] In one embodiment, the terminal capabilities include at least one of the terminal's memory, power consumption, computing resources, and supported functions / models.

[0206] In one embodiment, the terminal-side additional conditions include at least one of speed, deployment scenario, beam azimuth angle, beam elevation angle, antenna configuration, and antenna height.

[0207] In one embodiment, the cause includes at least one of the functional / model inference result and the first monitoring result.

[0208] In one embodiment, the first message is reported to the network via UEAssistanceInformation signaling.

[0209] In one embodiment, the network's processing of the terminal includes at least one of inference data collection configuration, confirmation instruction, and rollback instruction.

[0210] In one embodiment, a management device for functions and models is provided, applied to a network; the device includes:

[0211] The network sending module is used to send a first RRC configuration message to the terminal; the first RRC configuration message includes at least one of the following: network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting method, reference signal type, execution conditions, and measurement gap;

[0212] A network receiving module is configured to receive a first message sent by the terminal; the first message contains a decision and / or reason for managing the function and / or model; the management includes at least one of selection, activation, deactivation, switching, and rollback;

[0213] The processing and sending module is used to send a second RRC configuration message to the terminal; the second RRC configuration message contains the network's processing of the terminal.

[0214] In one embodiment, the first RRC configuration message is carried by an OtherConfig message.

[0215] In one embodiment, the device further includes a network determination module, configured to determine whether to accept the decision based on at least one of the first message, the second monitoring result, and the network-side additional conditions / auxiliary information.

[0216] In one embodiment, the second monitoring result includes at least one of throughput, block error rate, signaling overhead, and packet latency.

[0217] Specific limitations regarding the management device for functions and models can be found in the above description of the management methods for functions and models, and will not be repeated here. Each module in the aforementioned management device for functions and models can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0218] In one embodiment, a communication device is provided, see [link to previous document]. Figure 5 . Figure 5 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Figure 5 The terminal device 500 shown includes at least one processor 501, a memory 502, at least one network interface 504, and a user interface 503. The various components in the terminal device 500 are coupled together via a bus system 505. It is understood that the bus system 505 is used to implement communication between these components. In addition to a data bus, the bus system 505 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 5 Various buses are designated as bus system 505. Additionally, embodiments of this application also include a transceiver 506, which may consist of multiple elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium.

[0219] The user interface 503 may include a display, keyboard, or clicking device, such as a mouse, trackball, touchpad, or touchscreen.

[0220] It is understood that the memory 502 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 502 of the systems and methods described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0221] In some implementations, memory 502 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating system 5021 and application programs 5022.

[0222] The operating system 5021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 5022 includes various applications, such as a media player and a browser, used to implement various application functions. Programs implementing the methods of this application embodiment can be included in application program 5022.

[0223] In this embodiment, by calling a program or instruction stored in memory 502, specifically a program or instruction stored in application program 5022, the receiver is configured to receive a first RRC configuration message sent by the network; the first RRC configuration message includes at least one of network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting methods, reference signal types, execution conditions, and measurement gaps; the processor is configured to manage functions and / or models according to the first RRC configuration message and / or measurement results; the management includes at least one of selection, activation, deactivation, switching, and rollback; the transmitter is configured to send a first message to the network; the first message includes the management decision and / or reason; the receiver is also configured to receive a second RRC configuration message sent by the network; the second RRC configuration message includes the network's processing of the terminal.

[0224] The methods disclosed in some or all of the above embodiments of this application can also be applied to processor 501, or implemented by processor 501, or implemented by processor 501 in conjunction with other components (e.g., transceivers). Processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 501 or by instructions in the form of software. The processor 501 mentioned above may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 502, and processor 501 reads the information from memory 502 and, in conjunction with its hardware, completes the steps of the above method.

[0225] It is understood that the embodiments described in this application can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or combinations thereof.

[0226] For software implementation, the technology described in the embodiments of this application can be implemented by modules (e.g., procedures, functions, etc.) that perform the functions described in the embodiments of this application. The software code can be stored in memory and executed by processor 501. The memory can be implemented in processor 501 or external to processor 501.

[0227] In one embodiment, the network-side additional conditions / auxiliary information includes at least one of the following: the configuration of Set B, the configuration of Set A, the mapping relationship between Set B and Set A, beam tilt angle, beam azimuth angle, beam elevation angle, beam codebook, deployment scenario, terminal distribution, transmission power, antenna configuration, and antenna height.

[0228] In one embodiment, in the spatial domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A. In the time domain, the mapping relationship between Set B and Set A includes any one of the following: Set B is different from Set A, and Set B is not a subset of Set A; or Set B is a subset of Set A; or Set B is the same as Set A.

[0229] In one embodiment, the terminal autonomous decision instruction is used to instruct the terminal to autonomously manage and / or report the functions and / or models.

[0230] In one embodiment, the processor is further configured to measure the received beam of the reference signal to obtain the measurement result; the reference signal includes a reference signal based on the SS / PBCH block or a reference signal based on CSI-RS.

[0231] In one embodiment, the measurement results include at least one of the L1-RSRP of Set A / Set A subset, Top-1 beam identifier, and Top-K beam identifier.

[0232] In one embodiment, the processor is further configured to manage the function and / or model based on at least one of the measurement results, inference results, execution conditions, terminal capabilities, feasibility of the function / model on the terminal, additional conditions on the terminal side, and additional conditions / auxiliary information on the network side.

[0233] In one embodiment, the execution conditions include at least one of L1-RSRP differential being greater than a first threshold and beam prediction accuracy being less than a second threshold.

[0234] In one embodiment, at least one of the execution condition, the first threshold, and the second threshold is configured by the network.

[0235] In one embodiment, the processor is further configured to manage the functions and / or models based on the terminal capabilities if any of the execution conditions are met.

[0236] In one embodiment, the terminal capabilities include at least one of the terminal's memory, power consumption, computing resources, and supported functions / models.

[0237] In one embodiment, the terminal-side additional conditions include at least one of speed, deployment scenario, beam azimuth angle, beam elevation angle, antenna configuration, and antenna height.

[0238] In one embodiment, the cause includes at least one of the functional / model inference result and the first monitoring result.

[0239] In one embodiment, the first message is reported to the network via UEAssistanceInformation signaling.

[0240] In one embodiment, the network's processing of the terminal includes at least one of inference data collection configuration, confirmation instruction, and rollback instruction.

[0241] In one embodiment, a network device is also provided, comprising: at least one processor, a memory, at least one network interface, and a transceiver, wherein the transceiver may be multiple elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium. In this embodiment, by invoking a program or instructions stored in the memory, the transmitter is configured to send a first RRC configuration message to a terminal; the first RRC configuration message includes at least one of network-side additional conditions / auxiliary information, terminal autonomous decision-making instructions, reporting methods, reference signal types, execution conditions, and measurement gaps; the receiver is configured to receive a first message sent by the terminal; the first message includes a decision and / or reason for managing functions and / or models; the management includes at least one of selection, activation, deactivation, switching, and rollback; the transmitter is configured to send a second RRC configuration message to the terminal; the second RRC configuration message includes the network's processing of the terminal.

[0242] In one embodiment, the first RRC configuration message is carried by an OtherConfig message.

[0243] In one embodiment, the processor may be specifically configured to determine whether to accept the decision based on at least one of the first message, the second monitoring result, and the network-side additional conditions / auxiliary information.

[0244] In one embodiment, the second monitoring result includes at least one of throughput, block error rate, signaling overhead, and packet latency.

[0245] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0246] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the above-described method embodiments.

[0247] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0248] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0249] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A function and model management method characterized by comprising: The method is applied to a terminal, and comprises the following steps: receiving a first RRC configuration message issued by a network; the first RRC configuration message comprises at least one of network-side additional conditions / auxiliary information, a terminal self-determination indication, a reporting mode, a reference signal type, an execution condition, and a measurement gap; managing a function and / or a model according to the first RRC configuration message and / or a measurement result; the management comprises at least one of selection, activation, deactivation, switching, and fallback; sending a first message to the network; the first message comprises a decision and / or a reason of the management; receiving a second RRC configuration message sent by the network; the second RRC configuration message comprises a processing of the terminal by the network.

2. The method of claim 1, wherein, The network-side additional conditions / auxiliary information comprise at least one of a configuration of Set B, a configuration of Set A, a mapping relationship between the Set B and the Set A, a beam tilt angle, a beam azimuth angle, a beam elevation angle, a beam codebook, a deployment scenario, a terminal distribution, a transmission power, an antenna configuration, and an antenna height.

3. The method of claim 2, wherein, In a spatial domain, the mapping relationship between the Set B and the Set A comprises any one of the following: The Set B is different from the Set A, and the Set B is not a subset of the Set A; The Set B is a subset of the Set A. In a time domain, the mapping relationship between the Set B and the Set A comprises any one of the following: The Set B is different from the Set A, and the Set B is not a subset of the Set A; The Set B is a subset of the Set A; The Set B is the same as the Set A.

4. The method of claim 1, wherein, The terminal self-determination indication is used to instruct the terminal to manage and / or report the function and / or the model.

5. The method of claim 1, wherein, The method further comprises: measuring a receiving beam of a reference signal to obtain the measurement result; the reference signal comprises a SS / PBCH block-based reference signal or a CSI-RS-based reference signal.

6. The method of claim 1, wherein, The measurement result comprises at least one of L1-RSRP of Set A / Set A subset, Top-1 beam identification, and Top-K beam identification.

7. The method of claim 1, wherein, The management of the function and / or the model according to the first RRC configuration message and / or the measurement result comprises: managing the function and / or the model according to at least one of the measurement result, an inference result, the execution condition, a terminal capability, a feasibility of the function / model at the terminal, a terminal-side additional condition, and the network-side additional conditions / auxiliary information.

8. The method of claim 7, wherein, The execution condition comprises at least one of L1-RSRP difference greater than a first threshold value and beam prediction accuracy less than a second threshold value.

9. The method of claim 8, wherein, At least one of the execution condition, the first threshold value, and the second threshold value is configured by the network.

10. The method of claim 8, wherein, The management of the function and / or the model according to the first RRC configuration message and / or the measurement result further comprises: If any of the execution conditions is met, the function and / or model is managed based on the terminal capability.

11. The method of claim 7, wherein, The terminal capability includes at least one of memory, power, computing resource, supported function / model of the terminal.

12. The method of claim 7, wherein, The terminal-side additional condition includes at least one of speed, deployment scenario, beam azimuth, beam elevation, antenna configuration, antenna height.

13. The method of claim 1, wherein, The reason includes at least one of function / model inference result, first monitoring result.

14. The method of claim 1, wherein, The first message is reported to the network through UEAssistanceInformation signaling.

15. The method of claim 1, wherein, The processing of the terminal by the network includes at least one of inference data collection configuration, confirmation indication, fallback indication.

16. A function and model management method characterized by comprising: Applied to a network; the method includes: sending a first RRC configuration message to a terminal; the first RRC configuration message includes at least one of network-side additional condition / auxiliary information, terminal autonomous decision indication, reporting mode, reference signal type, execution condition and measurement gap; receiving a first message sent by the terminal; the first message includes a decision and / or reason for managing a function and / or model; the management includes at least one of selection, activation, deactivation, switching and fallback; sending a second RRC configuration message to the terminal; the second RRC configuration message includes processing of the terminal by the network.

17. The method of claim 16, wherein, The first RRC configuration message is carried by an OtherConfig message.

18. The method of claim 16, wherein, The method further includes: determining whether to accept the decision according to at least one of the first message, second monitoring result and network-side additional condition / auxiliary information.

19. The method of claim 18, wherein, The second monitoring result includes at least one of throughput, block error rate, signaling overhead and packet delay.

20. A function and model management apparatus characterized by comprising: Applied to a terminal; the apparatus includes: a terminal receiving module, configured to receive a first RRC configuration message issued by a network; the first RRC configuration message includes at least one of network-side additional condition / auxiliary information, terminal autonomous decision indication, reporting mode, reference signal type, execution condition and measurement gap; a terminal management module, configured to manage a function and / or model according to the first RRC configuration message and / or measurement result; the management includes at least one of selection, activation, deactivation, switching and fallback; a terminal sending module, configured to send a first message to the network; the first message includes a decision and / or reason of the management; a processing receiving module, configured to receive a second RRC configuration message sent by the network; the second RRC configuration message includes processing of the terminal by the network.

21. A function and model management apparatus characterized by comprising: Applied to a network; the apparatus includes: a network sending module, configured to send a first RRC configuration message to a terminal; the first RRC configuration message includes at least one of network-side additional condition / auxiliary information, terminal autonomous decision indication, reporting mode, reference signal type, execution condition and measurement gap; The network receiving module is configured to receive a first message sent by the terminal; the first message comprises a decision and / or a reason for managing a function and / or a model; the management comprises at least one of selection, activation, deactivation, switching, and fallback. The processing sending module is configured to send a second RRC configuration message to the terminal; the second RRC configuration message comprises a processing of the terminal by the network.

22. A terminal device, comprising: The method comprises the following steps: The receiver, the processor, and the transmitter; The receiver is configured to receive a first RRC configuration message issued by the network; The first RRC configuration message comprises at least one of network-side additional conditions / auxiliary information, a terminal autonomous decision indication, a reporting mode, a reference signal type, an execution condition, and a measurement gap; The processor is configured to manage a function and / or a model according to the first RRC configuration message and / or a measurement result; the management comprises at least one of selection, activation, deactivation, switching, and fallback; The transmitter is configured to send a first message to the network; the first message comprises a decision and / or a reason for the management; The receiver is further configured to receive a second RRC configuration message sent by the network; the second RRC configuration message comprises a processing of the terminal by the network.

23. A network device, comprising: The method comprises the following steps: The transmitter and the receiver; The transmitter is configured to send a first RRC configuration message to the terminal; The first RRC configuration message comprises at least one of network-side additional conditions / auxiliary information, a terminal autonomous decision indication, a reporting mode, a reference signal type, an execution condition, and a measurement gap; The receiver is configured to receive a first message sent by the terminal; the first message comprises a decision and / or a reason for managing a function and / or a model; the management comprises at least one of selection, activation, deactivation, switching, and fallback; The transmitter is further configured to send a second RRC configuration message to the terminal; the second RRC configuration message comprises a processing of the terminal by the network.

24. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 19.

25. A computer program product comprising a computer program, characterised in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 19.

Images