A communication method, apparatus, system, and storage medium

Abstract

The application provides a communication method, device, system and storage medium, aiming to improve the transmission reliability in beam management. The communication method of the application comprises: receiving a first message, the first message being used to determine first configuration information; sending a second message, the second message being used to indicate the expected loading time of the first model; and sending fifth information, the fifth information being sent based on the first resource in the case that a first timer expires, the first timer being determined based on the expected loading time, a second timer being determined based on the expected loading time, and the first configuration information being activated in the case that the first timer expires. The first communication device can first send the loading state of the first model and the expected loading time of the first model to the second communication device, so that the second communication device can synchronize the activation completion time of the first configuration information with the first communication device, thereby improving the transmission reliability in beam management.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method, apparatus, system and storage medium. Background Technology

[0002] In the field of communications, beam management plays an irreplaceable role in communication systems. Efficient beam management enables terminal and network devices to quickly discover and switch to the optimal beam pair, ensuring system stability and reliability. Beam management achieves efficient signal transmission through dynamic interaction between network and terminal devices, utilizing directional beams.

[0003] Currently, terminal devices can use models for beam management. This means the network side can first send the configuration information required for model inference to the terminal side, which then loads the model, activates the received configuration information, and uses the model to predict the signal quality of the beam, reporting the prediction results to the network device. However, because the activation completion time of configuration information cannot be synchronized between the terminal device and the network device, the network device may fail to successfully decode the prediction results reported by the terminal device, resulting in low transmission reliability during beam management. Summary of the Invention

[0004] This application provides a communication method, apparatus, system, and storage medium, with the aim of improving transmission reliability during beam management.

[0005] To achieve the above objectives, this application provides the following technical solution:

[0006] The first aspect of this application provides a communication method that can be applied to a first communication device. For example, the first communication device may be a communication equipment (e.g., a terminal device), or the first communication device may be a component of the communication equipment (e.g., a processor, circuit, chip, or chip system responsible for communication functions), or the first communication device may also be a logic module or software that can implement all or part of the functions of the communication equipment. The following description uses a first communication device as an example. In this method, the first communication device receives a first message, which includes first information and second information. The first information is used to determine a first model, and the second information is used to determine first configuration information. The first communication device sends a second message, which includes third information and fourth information. The third information is used to indicate the loading status of the first model, and the fourth information is used to indicate the estimated loading time of the first model, which is determined based on the loading status. The first communication device sends a fifth message, which is sent based on a first resource when the first timer expires. The first timer is determined by the first communication device based on the estimated loading time, and the first resource is configured by the second communication device after the second timer expires. The second timer is determined by the second communication device based on the estimated loading time. The fifth message includes the prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer expires.

[0007] In the above implementation scheme, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the expected loading time of the first model to the second communication device. Then, after the first timer determined based on the expected loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0008] In one possible implementation of the first aspect of this application, the first message further includes sixth information, which indicates the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time. In the above implementation, the second communication device can also notify the first communication device of the expected activation time of the first configuration information via the first message. That is, the second communication device can notify the first communication device of the activation time requirement of the first configuration information, so that the first communication device can set the first timer by comprehensively considering the expected activation time of the first configuration information and the expected loading time of the first model, and send the prediction result of the first model after the first timer expires. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and reserves first resources for the first communication device to report the prediction result of the first model after the second timer expires, thereby enabling successful decoding of the prediction result reported by the first communication device, and thus improving the transmission reliability during beam management.

[0009] In one possible implementation of the first aspect of this application, the timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is also the maximum value between the expected loading time and the desired activation time. In this implementation, after determining the expected loading time of the first model and the desired activation time of the first configuration information, the first communication device can use the maximum value between the expected loading time and the desired activation time as the timing duration of the first timer. Similarly, the second communication device can also use the maximum value between the expected loading time and the desired activation time as the timing duration of the second timer. That is, when determining the activation completion time of the first configuration information, the first and second communication devices can comprehensively consider their respective requirements regarding the activation duration of the first configuration information. This allows the second and first communication devices to accurately synchronize the activation completion time of the first configuration information, enabling the second communication device to successfully decode the prediction results reported by the first communication device, thereby improving the transmission reliability during beam management.

[0010] In one possible implementation of the first aspect of this application, the timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated delay of the air interface transmission. In the above implementation scheme, after determining the expected loading time of the first model and the expected activation time of the first configuration information, the first communication device can use the maximum value of the expected loading time and the expected activation time as the timing duration of the first timer; after determining the expected loading time of the first model and the expected activation time of the first configuration information, the second communication device can use the difference between the maximum value of the expected loading time and the expected activation time and the estimated air interface transmission delay as the timing duration of the second timer. That is, when determining the activation completion time of the first configuration information, the first and second communication devices can comprehensively consider the requirements of the first and second communication devices on the activation duration of the first configuration information. Furthermore, when determining the activation completion time of the first configuration information, the second communication device can also consider the estimated air interface transmission delay of the second message. This allows the second and first communication devices to accurately synchronize the activation completion time of the first configuration information, enabling the second communication device to successfully decode the prediction results reported by the first communication device, thereby improving the transmission reliability during beam management.

[0011] In one possible implementation of the first aspect of this application, the loading status of the first model indicated by the third information includes loading or loading completed. In the above implementation, the loading status of the first model reported by the first communication device through the second message can include loading or loading completed. That is, the first communication device can report the loading status of the first model as loading before determining that the first model has not yet been loaded, and can report the loading status of the first model as loading completed after determining that the first model has been loaded, so that the second communication device can accurately determine the loading status of the first model.

[0012] In one possible implementation of the first aspect of this application, when the loading status of the first model indicated by the third information is "loading," the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is "loading complete," the estimated loading time is equal to 0. In the above implementation, when the first communication device determines that the first model has not yet been loaded, it can determine the estimated loading time of the first model based on the loading progress, etc., and at this time, the estimated loading time of the first model can be greater than 0. When the first communication device determines that the first model has been loaded, it can determine that the estimated loading time is equal to 0, that is, the first model can be activated immediately for prediction. In other words, the first communication device can determine the corresponding expected loading time based on the loading status of the first model and send it to the second communication device, so that the second communication device and the first communication device can accurately synchronize the activation completion time of the first configuration information, enabling the second communication device to successfully decode the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0013] In one possible implementation of the first aspect of this application, when the loading status of the first model indicated by the third information is "loading," and the first communication device completes the loading of the first model before the first timer expires, the method further includes: sending a seventh message, the seventh message indicating that the loading status of the first model is "loading complete." In the above implementation, when the loading status of the first model reported by the first communication device is "loading," that is, when the first model has not yet been loaded, the first communication device can, after the first model has been loaded, send a seventh message to the second communication device to inform it that the first model has been loaded, so that the second communication device can accurately determine the loading status of the first model.

[0014] In one possible implementation of the first aspect of this application, the first configuration information includes a periodic inference channel state information report configuration (CSI-ReportConfig). In the above implementation, the first configuration information carried in the first message sent by the second communication device may include the periodic inference CSI-ReportConfig. After the first model is loaded, the first communication device can activate the periodic inference CSI-ReportConfig and send it to the physical layer. This allows the first model to make predictions based on the periodic inference CSI-ReportConfig and obtain prediction results. The first communication device can then send the prediction results of the first model after a first timer expires, based on the expected loading time of the first model. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device and reserve first resources for the first communication device to report the prediction results of the first model after the second timer expires. This enables successful decoding of the prediction results reported by the first communication device, thereby improving transmission reliability during beam management.

[0015] In one possible implementation of the first aspect of this application, the first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

[0016] The second aspect of this application provides a communication method that can be applied to a second communication device. For example, the second communication device can be a communication equipment (such as a network device), or it can be a component of the communication equipment (such as a processor, circuit, chip, or chip system responsible for communication functions), or it can be a logic module or software that can implement all or part of the functions of the communication equipment. The following description uses a second communication device as an example. In this method, the second communication device sends a first message, which includes first information and second information. The first information is used to determine a first model, and the second information is used to indicate first configuration information. The second communication device receives a second message, which includes third information and fourth information. The third information is used to indicate the loading status of the first model, and the fourth information is used to indicate the estimated loading time of the first model, which is determined based on the loading status. The second communication device receives a fifth message, which is sent by the first communication device based on a first resource when the first timer expires. The first timer is determined by the first communication device based on the estimated loading time, and the first resource is configured after the second timer expires. The second timer is determined by the second communication device based on the estimated loading time. The fifth message includes a prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer expires.

[0017] In the above implementation scheme, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the expected loading time of the first model to the second communication device. Then, after the first timer determined based on the expected loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0018] In one possible implementation of the second aspect of this application, the first message further includes sixth information, the sixth information being used to indicate the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

[0019] In one possible implementation of the second aspect of this application, the timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

[0020] In one possible implementation of the second aspect of this application, the timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

[0021] In one possible implementation of the second aspect of this application, the loading status of the first model indicated by the third information includes loading or loading completed.

[0022] In one possible implementation of the second aspect of this application, when the loading status of the first model indicated by the third information is loading, the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is loading complete, the estimated loading time is equal to 0.

[0023] In one possible implementation of the second aspect of this application, when the loading status of the first model indicated by the third information is "loading," and the first communication device completes loading of the first model before the first timer expires, the method further includes:

[0024] Receive a seventh message, which indicates that the loading status of the first model is complete.

[0025] In one possible implementation of the second aspect of this application, the first message further includes a Channel State Information Reporting Configuration (CSI-ReportConfig), and the prediction result is obtained by the first model based on the CSI-ReportConfig.

[0026] In one possible implementation of the second aspect of this application, the first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

[0027] A third aspect provides a communication device including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the methods in any possible implementation of any of the above aspects. Optionally, the communication device further includes a memory. Optionally, the communication device further includes a communication interface, and the processor is coupled to the communication interface.

[0028] In one implementation, the communication interface may be a transceiver, or an input / output interface.

[0029] In another implementation, the communication device is a chip configured in a terminal device. When the communication device is a chip configured in a terminal device, the communication interface can be an input / output interface.

[0030] Fourthly, a communication device is provided, including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the methods in any possible implementation of any of the above aspects. Optionally, the communication device further includes a memory. Optionally, the communication device further includes a communication interface, and the processor is coupled to the communication interface.

[0031] In one implementation, the communication interface may be a transceiver, or an input / output interface.

[0032] In another implementation, the communication device is a chip configured in a satellite. When the communication device is a chip configured in a satellite, the communication interface can be an input / output interface.

[0033] Fifthly, a processor is provided, comprising: an input circuit, an output circuit, and a processing circuit. The processing circuit is configured to receive signals through the input circuit and transmit signals through the output circuit, causing the processor to execute a method in any possible implementation of any aspect.

[0034] In specific implementation, the processor can be one or more chips, the input circuit can be input pins, the output circuit can be output pins, and the processing circuit can be transistors, gate circuits, flip-flops, and various logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver, and the signal output by the output circuit can be, for example, but not limited to, output to and transmitted by a transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as both the input circuit and the output circuit at different times. This application does not limit the specific implementation of the processor and various circuits.

[0035] In a sixth aspect, a communication device is provided, including a processor and a memory. The processor is used to read instructions stored in the memory and to receive signals via a receiver and transmit signals via a transmitter to execute the method in any possible implementation of any of the above aspects.

[0036] Optionally, the processor may be one or more, and the memory may be one or more.

[0037] In a seventh aspect, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code or instructions) that, when the computer program is run, causes a computer to perform a method in any possible implementation of any of the above aspects.

[0038] Eighthly, a computer-readable storage medium is provided that stores a computer program (also referred to as code or instructions) that, when run on a computer, causes the computer to perform the methods in any possible implementation of any of the preceding aspects.

[0039] Ninthly, embodiments of this application provide a chip system including one or more processors for calling and executing instructions stored in memory, causing the methods in the above aspects or the first possible implementation of the aspects to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0040] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0041] In a tenth aspect, a communication system is provided, including the aforementioned terminal equipment and network equipment (including access network equipment and core network equipment). Optionally, the communication system may further include other equipment that communicates with the terminal equipment and / or network equipment.

[0042] Eleventhly, a communication device is provided, comprising a transceiver module and a processing module, the communication device being used to perform the method in any possible implementation of any of the preceding aspects. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the system architecture of the communication system provided in the embodiments of this application;

[0044] Figure 2 A flowchart illustrating a communication method provided in an embodiment of this application;

[0045] Figure 3 A flowchart illustrating another communication method provided in an embodiment of this application;

[0046] Figure 4 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0047] Figure 5 This is a structural example diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The terminology used in the following embodiments is for the purpose of describing specific embodiments only and is not intended to be a limitation of this application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "the," "the," "the," and "this" are intended to also include expressions such as "one or more," unless the context clearly indicates otherwise. It should also be understood that in the embodiments of this application, "one or more" refers to one, two, or more; "and / or" describes the relationship between related objects, indicating that three relationships may exist; for example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0049] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0050] The "multiple" mentioned in the embodiments of this application refers to two or more. It should be noted that in the description of the embodiments of this application, terms such as "first" and "second" are used only for the purpose of distinguishing descriptions and should not be construed as indicating or implying relative importance, nor should they be construed as indicating or implying order.

[0051] To better understand the solutions of the embodiments of this application, the relevant terms and concepts that may be involved in the embodiments of this application will be introduced below.

[0052] 1. Beam Management

[0053] Beam management refers to the process by which network devices and terminal devices dynamically select, maintain, and optimize directional beam pairs used for uplink and downlink transmission through a series of physical layer and access network higher-layer processes. The core objective of beam management is to ensure that, in complex wireless environments, the transmitting and receiving ends can always select the optimal beam direction for communication, thereby compensating for high-frequency signal propagation loss, improving coverage, and meeting the high data rate, low latency, and reliable connection requirements of 5G and future communication systems. The core processes of beam management include:

[0054] (1) Beam sweeping: Sending and receiving beams in a predefined direction within a specific period or time period to cover a specific spatial area.

[0055] (2) Beam measurement: to evaluate the quality of the received signal. Common indicators include the received power of the reference signal and the signal-to-interference-to-noise ratio.

[0056] (3) Beam selection: Based on the measurement results, select one or more optimal beams on the network side or the terminal side.

[0057] (4) Beam reporting: The terminal device reports the beam quality measurement results and decision information to the network device so that the network device can adjust the transmission strategy.

[0058] (5) Beam indication: The network device notifies the terminal device to use the specified beam for data transmission.

[0059] (6) Beam switching: When the quality of the current beam deteriorates, switch to another beam with better quality.

[0060] (7) Beam recovery: The process of quickly restoring communication when a beam failure causes a link interruption.

[0061] 2. Radio Resource Control (RRC) Signaling

[0062] RRC signaling is a core protocol in communication systems used to control and manage radio resources. By defining the signaling interaction rules between terminal devices and network devices, RRC signaling enables functions such as establishing, maintaining, releasing, and allocating radio connections. The core functions of RRC signaling include connection establishment and release, radio resource configuration and reconfiguration, measurement and mobility management, neighbor cell management, and connectionless state control.

[0063] RRC signaling can include RRC reconfiguration messages and RRC reconfiguration complete messages. The RRC reconfiguration message is an instruction sent by the network device to the terminal device to modify the configuration parameters of the RRC connection. The RRC reconfiguration message allows the network to dynamically adjust radio resource allocation based on current needs (such as network congestion, changes in channel quality, user mobility, etc.), supporting diverse services and applications. The RRC reconfiguration complete message is a response message sent by the terminal device to the network device after successfully executing the RRC reconfiguration. The RRC reconfiguration complete message indicates that the terminal device has completed the parameter update according to the reconfiguration instruction and is ready to continue communication.

[0064] 3. Channel State Information Report Configuration (CSI-ReportConfig)

[0065] CSI-ReportConfig is a key parameter set in the RRC layer signaling, used to define the specific rules for terminal devices to report channel state information (CSI) to network devices. It covers core elements such as reporting content, method, timing, and resource association, and is fundamental to optimizing radio resource management and improving communication quality in communication systems. CSI-ReportConfig can define the reporting content, that is, specify the CSI parameters that the terminal device needs to report, such as channel quality indicators, precoding matrix indicators, and rank indicators. CSI-ReportConfig can also define and configure the reporting method, such as periodic, semi-persistent, and aperiodic. CSI-ReportConfig can also be associated with measurement resources. It can be understood that periodic inference CSI-ReportConfig can be channel state information reporting configuration information that network devices periodically send to terminal devices for inference and prediction based on AI models.

[0066] 4. Uplink control information (UCI)

[0067] UCI (User Control Information) is critical control information sent by terminal devices to network devices, primarily used for feedback on channel status, confirmation of data reception, and sending scheduling requests. The content carried by UCI can include the following three categories:

[0068] Hybrid Automatic Repeat Request Acknowledgment (HARQ ACK) / Negative Acknowledgment (NACK): Used to indicate whether downlink data transmission was successfully received. If data reception is successful, the terminal device sends an acknowledgment signal; if data reception fails, the terminal device sends a non-acknowledgment signal, requesting the base station to retransmit the data.

[0069] Scheduling request (SR): When a UE has uplink data to send, it will request uplink resource allocation from the base station through the SR.

[0070] CSI includes Channel Quality Indicator, Precoding Matrix Indicator, and Rank Indicator, which are used to describe the current state of the wireless channel and help the base station optimize downlink transmission parameters, such as modulation scheme, coding strategy, and precoding matrix.

[0071] 5. Physical uplink shared channel (PUSCH)

[0072] PUSCH is the primary uplink channel for terminal devices to send data and control information to network devices. Its core functions include:

[0073] Transmitting uplink user data: The PUSCH carries uplink service data from terminal devices, including user data (such as voice, video, and file uploads) and upper-layer signaling. For example, in live video streaming, the terminal device sends a real-time video stream to the base station via the PUSCH.

[0074] Transmitting UCI: The PUSCH can transmit control information such as HARQ-ACK, channel quality indication, precoding matrix indication, and rank indication. When physical uplink control channel resources are insufficient, UCI can be transmitted on the PUSCH to optimize resource utilization.

[0075] Support for channel estimation: PUSCH can carry a probe reference signal for network devices to perform uplink channel estimation, optimize beamforming and resource allocation.

[0076] The system architecture of the embodiments of this application is described below.

[0077] The embodiments of this application are applied to communication systems, which can be second-generation (2G) communication systems, third-generation (3G) communication systems, LTE systems, fifth-generation (5G) communication systems, LTE and 5G hybrid architectures, 5G new radio (5G NR) systems, and new communication systems that will emerge in the future development of communication.

[0078] A communication system includes a first device and a second device. The first device can be a network-side device used to provide network communication functions; in some cases, it is also called a network device or network element. Network devices are typically base stations (including functional units of base stations, or combinations of functional units of base stations) or core network units. Core network units can be functional units within the core network, including but not limited to Access and Mobility Management Function (AMF) units or Session Management Function (SMF) units. The second device can be a device accessing the network, typically a terminal device. An example of a communication system is as follows: Figure 1 As shown, Figure 1 It includes base station 11 and terminal 12.

[0079] In the embodiments provided in this application, the base station can be any device with wireless transceiver capabilities, including but not limited to: evolved Node B (nodeB, eNB, or e-nodeB) in Long Term Evolution (LTE), base station (gNodeB or gNB) or transmission receiving point / transmission reception point (TRP) in New Radio (NR), base stations in subsequent 3GPP evolutions, access nodes in Wi-Fi systems, wireless relay nodes, wireless backhaul nodes, etc. The base station can be: macro base station, micro base station, pico base station, small cell, relay station, or balloon station, etc. The base station can include one or more co-located or non-co-located transmission reception points (TRPs). The base station can also be a radio controller, centralized unit (CU), and / or distributed unit (DU) in a cloud radioaccess network (CRAN) scenario. The base station can communicate with terminal devices or communicate with terminal devices through relay stations. Terminal devices can communicate with multiple base stations using different technologies. For example, a terminal device can communicate with a base station that supports LTE networks, or with a base station that supports 5G networks, or even have dual connections with both LTE and 5G base stations.

[0080] In the embodiments provided in this application, the terminal device can take various forms, such as a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, vehicle-mounted terminal device, wireless terminal device in self-driving, wireless terminal device in remote medical care, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, wireless terminal device in smart home, wearable terminal device, etc. The terminal device may also be referred to as a terminal device, user equipment (UE), access terminal device, vehicle-mounted terminal device, industrial control terminal device, UE unit, UE station, mobile station, mobile station, remote station, remote terminal device, mobile device, UE terminal device, terminal device, wireless communication device, UE agent, or UE device, etc. The terminal device can also be a fixed terminal device or a mobile terminal device.

[0081] In the field of communications, beam management plays an irreplaceable role in communication systems. Efficient beam management enables terminal and network devices to quickly discover and switch to the optimal beam pair, ensuring system stability and reliability. Beam management achieves efficient signal transmission through dynamic interaction between network and terminal devices, utilizing directional beams.

[0082] Beam management algorithms based on artificial intelligence (AI) and machine learning (ML) technologies have brought new opportunities to next-generation wireless communication technologies. Among them, beam prediction based on AI / ML technologies can be placed on the network side or the terminal side.

[0083] When an AI model is deployed on the terminal side, the network device can first send an RRC reconfiguration message to the terminal device. This RRC reconfiguration message may carry configuration information for channel quality prediction or beam prediction based on the AI ​​model. Regarding the periodic inference CSI-ReportConfig configuration information carried in the RRC reconfiguration message, after the terminal device informs the network device via an RRC reconfiguration completion message that it is adapted to this configuration information, it can automatically activate this configuration information to enable channel quality prediction or beam prediction based on the AI ​​model and this configuration information, without waiting for further activation instructions from the network. However, before receiving and parsing the RRC reconfiguration completion message from the terminal device, the network device cannot determine whether the terminal device has already activated the configuration information carried in the RRC reconfiguration message, i.e., it cannot determine whether the configuration information has been fully activated, and therefore cannot synchronize the activation completion time with the terminal device. Consequently, it cannot determine whether the terminal device will send the inference results of the AI ​​model at the physical layer. Understandably, when periodic CSI transmissions and scheduled PUSCH transmissions overlap in the time domain, the terminal device needs to multiplex the UCI into a designated resource unit of the PUSCH, and the PUSCH transport block needs to perform rate matching around the UCI resources. However, if the network device cannot determine whether the terminal device will send the AI ​​model inference results at the physical layer, it will lead to a PUSCH resource matching dilemma. That is, if the network device believes that the terminal device has multiplexed the UCI carrying the AI ​​model inference results on the PUSCH and reserved the corresponding resources, but the terminal device has not actually multiplexed the UCI on the PUSCH, the network device will fail to decode the PUSCH. Similarly, if the network device believes that the terminal device has not multiplexed the UCI carrying the AI ​​model inference results on the PUSCH and has not reserved the corresponding resources, but the terminal device has actually multiplexed the UCI on the PUSCH, it will also lead to the network device failing to decode the PUSCH. Therefore, because the activation completion time of configuration information cannot currently be synchronized between the terminal device and the network device, it is easy for the network device to fail to successfully decode the prediction results reported by the terminal device, resulting in low transmission reliability during beam management.

[0084] To make the technical solution of this application clearer and easier to understand, a communication method according to an embodiment of this application is described below with reference to the accompanying drawings. The communication method provided in this application embodiment can be applied to a first communication device and a second communication device. For example, the first communication device can be a communication device (such as a terminal device), or it can be a component of a communication device (such as a processor, circuit, chip, or chip system responsible for communication functions), or it can be a logic module or software capable of implementing all or part of the functions of the communication device. The second communication device can be a communication device (such as a network device), or it can be a component of a communication device (such as a processor, circuit, chip, or chip system responsible for communication functions), or it can be a logic module or software capable of implementing all or part of the functions of the communication device.

[0085] The following explanation uses the first communication device and the second communication device as examples.

[0086] Please see Figure 2 , Figure 2 The diagram shown is a flowchart of a communication method provided in an embodiment of this application. The communication method provided in this application mainly includes the following steps:

[0087] S201. The second communication device sends a first message, and correspondingly, the first communication device receives the first message.

[0088] The first message includes first information and second information. The first information is used to determine the first model, and the second information is used to determine the first configuration information.

[0089] In this embodiment, after determining that the first communication device will load a model for beam management, the second communication device can determine the first model used by the first communication device for beam management, and the first configuration information required for beam management of the first model. The second communication device then sends the first information for determining the first model and the second information for determining the first configuration information to the first communication device via a first message. This allows the first communication device to determine and load the first model based on the first information, thereby completing the subsequent beam management process based on the first model and the first configuration information. Specifically, the first information may include the identification information of the first model; that is, after receiving the first message, the first communication device can determine and load the first model based on the identification information. The second information may be an index of the first configuration information or specific parameter values ​​of the first configuration information; this embodiment does not limit this. For example, the first message may include an RRC reconfiguration message, and the first model may include an AI model. Furthermore, it should be noted that the activation completion time of the first configuration information should be later than the loading completion time of the first model. After loading the first model, the first communication device can immediately activate the first configuration information for inference prediction, or it can activate the first configuration information for inference prediction after a certain period of time.

[0090] It is understood that the first message may include one or more configuration information, which can be used for the measurement or prediction of signal quality parameters. After receiving the first message, the first communication device can perform the parsing of the configuration information and the checking of the loading status of the first model in parallel, thereby further shortening the processing time and reducing the processing latency.

[0091] In one possible implementation of this application embodiment, the first configuration information includes the periodic inference channel state information report configuration CSI-ReportConfig.

[0092] In this embodiment, the first configuration information carried in the first message sent by the second communication device may include periodic inference CSI-ReportConfig. After the first model is loaded, the first communication device can activate periodic inference CSI-ReportConfig and send it to the physical layer so that the first model can perform predictions based on periodic inference CSI-ReportConfig to obtain prediction results. It is understood that the first message may also include periodic inference CSI-ReportConfig, which can be used in the prediction process of the first model. That is, after receiving the first message and loading the first model, the first communication device can perform beam prediction or channel state information prediction based on the first model and periodic inference CSI-ReportConfig to obtain prediction results.

[0093] S202. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0094] The second message includes a third message and a fourth message. The third message indicates the loading status of the first model, and the fourth message indicates the estimated loading time of the first model. The estimated loading time is determined based on the loading status.

[0095] In this embodiment, after receiving the first message, the first communication device can load and determine the first model based on the first information in the first message. It is understood that when the data volume of the first model is large, the loading time of the first communication device for the first model is usually greater than the processing delay of the first message. Therefore, when the processing delay of the first message is reached, the first communication device may not have finished loading the first model, or it may have already pre-loaded the first model, meaning the first model has been loaded. Alternatively, the loading of the first model may fail due to the first model not being deployed on the first communication device or other reasons. Therefore, the loading status of the first model can include loading complete, loading in progress, or loading failed.

[0096] Specifically, during the processing delay of the first message, the first communication device can report the loading status of the first model as "loading in progress" to the second communication device before determining that the first model has not yet been loaded; after determining that the first model has been loaded, it can report the loading status of the first model as "loading completed" to the second communication device, so that the second communication device can accurately determine the loading status of the first model. When the first communication device cannot load the first model, it can report the loading status of the first model as "loading failed" to the second communication device.

[0097] In this embodiment of the application, after determining the loading status of the first model, the first communication device can inform the second communication device of the loading status of the first model through third information. For example, when the loading status of the first model is "loading complete", the third information can be "applicabilityStatus = applicable"; when the loading status of the first model is "loading in progress", the third information can be "applicabilityStatus = loadingInProgress"; when the loading status of the first model is "loading failed", the third information can be "applicabilityStatus = inapplicable".

[0098] In this embodiment, after determining the loading status of the first model, the first communication device can further determine the estimated loading time of the first model. Specifically, when the first communication device determines that the first model has not yet been fully loaded, it can determine the estimated loading time of the first model based on the loading progress, etc., that is, determine how much more time the first model is expected to take to complete loading. At this time, the estimated loading time of the first model can be greater than 0. When the first communication device determines that the first model has been fully loaded, it can determine that the estimated loading time is equal to 0, that is, the first model can be activated immediately for prediction.

[0099] In this embodiment, after determining the estimated loading time of the first model, the first communication device can inform the second communication device of the estimated loading time of the first model through a fourth piece of information. For example, the fourth piece of information can be `modelActivationDelay = t`, where `t` is greater than or equal to 0, and the unit can be milliseconds (ms). It should be noted that when the loading status of the first model is "loading complete," the first communication device may not send the fourth piece of information to the second communication device; that is, both the first and second communication devices can default to the estimated loading time of the first model being 0.

[0100] It should be noted that if the first communication device fails to load the first model, that is, when the third information reported to the second communication device is applicableabilityStatus = inapplicable, the expected loading time reported to the second communication device can be t = infinite.

[0101] In this embodiment, after determining the loading status and the expected loading time of the first model, the first communication device can inform the second communication device of the loading status of the first model through third information and inform the second communication device of the expected loading time of the first model through fourth information. This enables the second communication device and the first communication device to accurately synchronize the activation completion time of the first configuration information, allowing the second communication device to successfully decode the prediction results reported by the first communication device, thereby improving the transmission reliability during beam management.

[0102] S203. The first communication device sends the fifth information, and correspondingly, the second communication device receives the fifth information.

[0103] The fifth information is sent based on the first resource when the first timer times out. The first timer is determined by the first communication device based on the expected loading time. The first resource is configured by the second communication device after the second timer times out. The second timer is determined by the second communication device based on the expected loading time. The fifth information includes the prediction result of the first model, which is predicted based on the first configuration information. The first configuration information is activated when the first timer times out.

[0104] In this embodiment, after determining the expected loading time of the first model, the first communication device can first determine a first timer based on the expected loading time of the first model and start the first timer. After the first timer expires, the first model is started and the first configuration information is immediately activated to perform prediction and obtain the prediction result of the first model. The prediction result of the first model is then sent to the second communication device via a fifth message. Simultaneously, after receiving the second message, the second communication device can determine a second timer based on the expected loading time of the first model and start the second timer. After the second timer expires, it reserves a first resource for the first communication device to send the fifth message and can receive the fifth message sent by the first communication device based on the first resource. That is, the first communication device can immediately activate the first configuration information after the first timer determined based on the expected loading time of the first model expires. Similarly, the second communication device can determine that the first configuration information has been activated after the second timer determined based on the expected loading time of the first model expires. In other words, the second communication device can synchronize the activation completion time of the first configuration information with the first communication device and reserve a first resource for the first communication device to report the prediction result of the first model after the second timer expires, thereby successfully decoding the prediction result reported by the first communication device and improving the transmission reliability during beam management. It is understandable that the timing duration of the first timer can be the same as that of the second timer. For example, T1_wait = T2_wait = t, that is, the timing duration of the first timer T1_wait and the timing duration of the second timer T2_wait can be the same as the expected loading time t.

[0105] For example, the first message may also include a periodic inference channel state information report configuration (CSI-ReportConfig), and the fifth message may include uplink control information (UCI). After sending the second message, the first communication device may start a first timer with a timing duration of T1_wait=t, and after the first timer expires, submit the periodic inference CSI-ReportConfig to the underlying layer. The physical layer of the first communication device begins to reuse the UCI, which includes the inference results of the first model, in the PUSCH, and sends the prediction results of the first model to the second communication device based on the UCI. Meanwhile, after receiving the second message, the second communication device can start a second timer with a duration of T2_wait=t. After the second timer expires, it can send an "AI inference UCI decoding enable" command to the physical layer of the second communication device. This means that the physical layer can activate the function of decoding the UCI containing the inference result of the first model and reserve UCI resources for subsequent PUSCH scheduling. Finally, after receiving the UCI sent by the first communication device based on the UCI resources, the second communication device can decode the UCI to obtain the prediction result of the first model. In other words, the first and second communication devices can synchronize the activation completion time of the first configuration information based on the first and second timers, thereby enabling the second communication device to successfully decode the prediction result reported by the first communication device, thus improving the transmission reliability during beam management.

[0106] In one possible implementation of this application embodiment, the first message further includes a sixth message, which is used to indicate the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

[0107] In this embodiment, the second communication device can also notify the first communication device of the expected activation time of the first configuration information via a first message. That is, the second communication device can notify the first communication device of the activation time requirement of the first configuration information, so that the first communication device can set a first timer by combining the expected activation time of the first configuration information and the estimated loading time of the first model. The second communication device can then send the prediction result of the first model after the first timer expires. This allows the second communication device to synchronize with the first communication device at the activation completion time of the first configuration information, and reserves first resources for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management. For example, the sixth information can be activationOffsetTime = k, where the expected activation time k of the first configuration information can be greater than or equal to 0, and the unit is ms.

[0108] It is understandable that the second communication device can determine the expected activation time of the first configuration information based on the first communication device's requirements regarding latency, etc. When the second communication device determines that the expected activation time k of the first configuration information is 0, it can be assumed that the second communication device expects the first communication device to immediately activate the first model for beam prediction. When the second communication device determines that the expected activation time k of the first configuration information is 0, the second communication device may also choose not to send the sixth information to the first communication device. That is, if the second communication device does not send the sixth information indicating the expected activation time of the first configuration information to the first communication device, both the first and second communication devices can default to the expected activation time k of the first configuration information being 0. Furthermore, when the first communication device determines the expected activation time k of the first configuration information and the expected loading time t of the first model, it can further determine the timing duration of the first timer based on these two times. Similarly, when the second communication device determines the expected activation time k of the first configuration information and the expected loading time t of the first model, it can further determine the timing duration of the second timer based on these two times.

[0109] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

[0110] In this embodiment, after determining the expected loading time of the first model and the expected activation time of the first configuration information, the first communication device can use the maximum value between the expected loading time and the expected activation time as the timing duration of the first timer, i.e., the timing duration of the first timer is T1_wait=max(k,t). Similarly, the second communication device can also use the maximum value between the expected loading time and the expected activation time as the timing duration of the second timer, i.e., the timing duration of the second timer is T2_wait=max(k,t). In other words, when determining the activation completion time of the first configuration information, the first and second communication devices can comprehensively consider their requirements for the activation duration of the first model, thereby enabling the second and first communication devices to accurately synchronize the activation completion time of the first configuration information. This allows the second communication device to successfully decode the prediction results reported by the first communication device, thereby improving the transmission reliability during beam management.

[0111] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

[0112] In this embodiment, after determining the expected loading time of the first model and the expected activation time of the first configuration information, the first communication device can use the maximum value between the expected loading time and the expected activation time as the timing duration of the first timer, i.e., the timing duration of the first timer is T1_wait=max(k,t). After determining the expected loading time of the first model and the expected activation time of the first configuration information, the second communication device can use the difference between the maximum value between the expected loading time and the expected activation time and the estimated air interface transmission delay as the timing duration of the second timer, i.e., the timing duration of the second timer is T2_wait=max(k,t)-T_delay_est, where T_delay_est is the estimated air interface transmission delay between the first and second communication devices. That is, when determining the activation completion time of the first configuration information, the first communication device and the second communication device can comprehensively consider the requirements of the first communication device and the second communication device in terms of the activation duration of the first configuration information. Furthermore, when determining the activation completion time of the first configuration information, the second communication device can also consider the estimated delay of the air interface transmission of the second message. This allows the second communication device and the first communication device to accurately synchronize the activation completion time of the first configuration information, enabling the second communication device to successfully decode the prediction results reported by the first communication device, thereby improving the transmission reliability during beam management.

[0113] Understandably, since the first communication device starts the first timer immediately after sending the second message, while the second communication device starts the second timer only after receiving the second message, there may be an air interface transmission delay between the time the first communication device starts sending the second message and the time the second communication device receives the second message. Therefore, in order to further improve the synchronization accuracy of the activation completion time, the timing duration of the second timer started by the second communication device can be one air interface transmission estimated delay less than the timing duration of the first timer started by the first communication device. This allows the first timer and the second timer to time out at the same time as much as possible, thereby maximizing the synchronization accuracy of the activation completion time of the first configuration information.

[0114] As illustrated by the examples in the foregoing embodiments, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the estimated loading time of the first model to the second communication device. Then, after the first timer determined based on the estimated loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0115] Please see Figure 3 , Figure 3 The diagram shown is a flowchart of a communication method provided in an embodiment of this application. The communication method provided in this application mainly includes the following steps:

[0116] S301. The second communication device sends a first message, and correspondingly, the first communication device receives the first message.

[0117] The first message includes first information and second information. The first information is used to determine the first model, and the second information is used to determine the first configuration information.

[0118] S302. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0119] The second message includes a third message and a fourth message. The third message indicates the loading status of the first model, and the fourth message indicates the estimated loading time of the first model. The estimated loading time is determined based on the loading status.

[0120] The contents of steps S301-S302 above are similar to those of steps S201-S202 in the previous embodiment, and will not be repeated here in the embodiments of this application.

[0121] S303. The first communication device starts the first timer.

[0122] The first timer is determined based on the expected loading time of the first model.

[0123] In this embodiment, after determining the expected loading time of the first model, the first communication device can first determine a first timer based on the expected loading time of the first model and start the first timer so that the first model can be activated to perform prediction after the first timer expires, and the prediction result of the first model can be obtained. The prediction result of the first model is then sent to the second communication device through the fifth information. It can be understood that the timing duration of the first timer can be represented by T1_wait.

[0124] In one possible implementation of this application embodiment, the second communication device may also notify the first communication device of the expected activation time of the first configuration information via a first message. That is, the second communication device can notify the first communication device of the activation time requirement of the first configuration information, so that the first communication device can set the first timer by comprehensively considering the expected activation time of the first configuration information and the estimated loading time of the first model. It is understood that the second communication device can determine the expected activation time of the first configuration information based on the first communication device's requirements regarding latency, etc. When the second communication device determines that the expected activation time k=0, it can be assumed that the second communication device expects the first communication device to immediately activate the first model for beam prediction. When the second communication device determines that the expected activation time k=0, the second communication device may also choose not to send the sixth message to the first communication device. That is, if the second communication device does not send the sixth message indicating the expected activation time of the first configuration information to the first communication device, both the first and second communication devices can default to the expected activation time k=0. Furthermore, when the first communication device determines the expected activation time k of the first configuration information and the expected loading time t of the first model, it can further determine the timing duration of the first timer based on the expected activation time k of the first configuration information and the expected loading time t of the first model.

[0125] For example, after determining the expected loading time of the first model and the expected activation time of the first configuration information, the first communication device can use the maximum value between the expected loading time and the expected activation time as the timing duration of the first timer, that is, the timing duration of the first timer T1_wait=max(k,t).

[0126] S304. The second communication device starts the second timer.

[0127] The second timer is determined based on the expected loading time of the first model.

[0128] In this embodiment, after receiving the second message, the second communication device can determine the second timer based on the expected loading time of the first model and start the second timer so as to reserve the first resource for sending the fifth message to the first communication device after the second timer expires. It is understood that the timing duration of the second timer can be represented by T2_wait.

[0129] In one possible implementation of this application embodiment, the second communication device can determine the expected activation time of the first configuration information based on the requirements of the first communication device in terms of latency, etc. When the second communication device determines that the expected activation time k of the first configuration information is 0, it can be assumed that the second communication device expects the first communication device to immediately activate the first model for beam prediction. When the second communication device determines that the expected activation time k of the first configuration information is 0, the second communication device may also choose not to send the sixth information to the first communication device. That is, if the second communication device does not send the sixth information indicating the expected activation time of the first configuration information to the first communication device, both the first and second communication devices can default to the expected activation time k of the first configuration information being 0. Furthermore, when determining the expected activation time k of the first configuration information and the estimated loading time t of the first model, the second communication device can further determine the timing duration of the second timer based on the expected activation time k of the first configuration information and the estimated loading time t of the first model.

[0130] For example, the second communication device may also use the maximum value between the expected loading time and the expected activation time as the timing duration of the second timer, that is, the timing duration of the second timer T2_wait=max(k,t).

[0131] For example, after determining the expected loading time of the first model and the expected activation time of the first configuration information, the second communication device can use the difference between the maximum value of the expected loading time and the expected activation time and the estimated air interface transmission delay as the timing duration of the second timer, i.e., the timing duration of the second timer T2_wait = max(k,t) - T_delay_est, where T_delay_est is the estimated air interface transmission delay between the first and second communication devices. When determining the activation completion time of the first configuration information, the second communication device can also consider the estimated air interface transmission delay of the second message, thereby enabling the second and first communication devices to accurately synchronize the activation completion time of the first configuration information. This allows the second communication device to successfully decode the prediction results reported by the first communication device, thus improving the transmission reliability during beam management.

[0132] Understandably, since the first communication device starts the first timer immediately after sending the second message, while the second communication device starts the second timer only after receiving the second message, there may be an air interface transmission delay between the time the first communication device starts sending the second message and the time the second communication device receives the second message. Therefore, in order to further improve the synchronization accuracy of the activation completion time, the timing duration of the second timer started by the second communication device can be one air interface transmission estimated delay less than the timing duration of the first timer started by the first communication device. This allows the first timer and the second timer to time out at the same time as much as possible, thereby maximizing the synchronization accuracy of the activation completion time of the first configuration information.

[0133] S305. The first communication device sends the seventh information, and correspondingly, the second communication device receives the seventh information.

[0134] The seventh piece of information indicates that the loading status of the first model is complete.

[0135] In this embodiment, when the loading status of the first model reported by the first communication device is "loading," meaning the first model has not yet been fully loaded, the first communication device can send a seventh message to the second communication device after the first model has been fully loaded to indicate that the first model has been loaded. This allows the second communication device to accurately determine the loading status of the first model and avoids the first communication device frequently updating the loading status of the first model to the second communication device, thus reducing signaling overhead. For example, the seventh message can be User Equipment Assistance Information (UAI).

[0136] Understandably, if the first communication device has not yet finished loading the first model when sending the second message (i.e., the first model is in the loading state), and the first communication device completes loading the first model before the first timer expires, the first communication device can inform the second communication device that the first model has been loaded via the seventh message. However, since the first timer has not yet expired, even though the first communication device has finished loading the first model, it will not immediately activate the first configuration information, that is, it will not immediately send the first configuration information to the physical layer, and it will not immediately use the first model to make predictions based on the first configuration information. Instead, it will wait until the first timer expires before activating the first model for prediction. Similarly, after the second communication device determines that the first model has been loaded by receiving the seventh message, since the second timer has not yet expired, the second communication device will not immediately send the fifth message to reserve the first resource for the first communication device. Instead, it will wait until the second timer expires before reserving the first resource.

[0137] S306. The first communication device sends the fifth information, and correspondingly, the second communication device receives the fifth information.

[0138] The fifth information is sent based on the first resource when the first timer times out. The first timer is determined based on the expected loading time. The first resource is configured by the second communication device after the second timer times out. The second timer is determined based on the expected loading time. The fifth information includes the prediction result of the first model. The prediction result is obtained based on the prediction of the first configuration information. The first configuration information is activated when the first timer times out.

[0139] The content of step S306 above is similar to that of step S203 in the previous embodiment, and will not be repeated here.

[0140] As illustrated by the examples in the foregoing embodiments, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the estimated loading time of the first model to the second communication device. Then, after the first timer determined based on the estimated loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0141] Furthermore, it should be noted that the communication method provided in this application embodiment can also be applied in the following scenarios:

[0142] (1) Other AI inference use cases

[0143] Applicable to UE-side AI model scenarios such as CSI prediction, mobility optimization, and energy-saving control:

[0144] For example, in CSI prediction use cases, the UE needs to load a prediction model (larger size). The expected loading time t can be reported through the "loadingInProgress" status. The base station can synchronously schedule the decoding resources of the CSI prediction report through the timer T_wait to avoid the loss of prediction report due to slow model loading.

[0145] (2) Dual connectivity and carrier aggregation scenarios

[0146] In dual-connectivity and carrier aggregation scenarios, the master node and slave node may be configured with AI inference settings respectively:

[0147] Application method: The primary node and the secondary node respectively issue activationOffsetTime(k1 / k2), and the UE calculates timers T_wait1 and T_wait2. After the timeout, the configuration of the corresponding node is activated to ensure that the inference report UCI reuse of the primary and secondary nodes does not conflict and avoid cross-node interference.

[0148] (3) RRC recovery and reconstruction scenario

[0149] During the RRCReestablishment / RRCReestablishment process, the UE needs to restore its previous AI inference configuration:

[0150] Application method: The base station carries activationOffsetTime(k) in the RRCResume message. The UE reports "applicable" (already retained) or "loadingInProgress" (requires reloading) according to the local model loading status (whether it is retained in RAM). The base station synchronously resumes the decoding behavior through timer T_wait to avoid data transmission failure after recovery.

[0151] (4) Low-power IoT devices

[0152] Low-power IoT devices have limited memory / computing power, resulting in longer model loading times (hundreds of milliseconds).

[0153] Application method: The UE reports "loadingInProgress" and the expected loading time t (e.g., 500ms). The base station sets the expected loading time k=600ms (for redundancy). Then the timer T_wait=600ms. The base station schedules PUSCH after the timeout to avoid resource waste caused by slow loading of low-power devices.

[0154] (5) Sixth Generation (6G) AI Native Air Interface Scenarios

[0155] In 6G, UE-side AI models (such as intelligent beam prediction and semantic communication) will become a fundamental capability, with larger model sizes (hundreds of MB) and more complex loading processes.

[0156] Application method: Expand the range of T_wait values ​​(support 0~10s), and the UE can report multiple loading progress segments (such as t1=2s (model segment 1 loading), t2=5s (model segment 2 loading)). The base station dynamically adjusts the k value to achieve gradual activation, which meets the flexible scheduling requirements of 6G for AI functions.

[0157] Figure 4 This is a schematic diagram of a communication device provided in an embodiment of this application. The communication device is used to implement the function of the first communication device in the above method embodiment, and the communication device specifically includes:

[0158] Receiving module 401 is used to receive a first message, the first message including first information and second information, the first information being used to determine a first model, and the second information being used to determine first configuration information;

[0159] The sending module 402 is used to send a second message, the second message including third information and fourth information, the third information being used to indicate the loading status of the first model, and the fourth information being used to indicate the estimated loading time of the first model, the estimated loading time being determined based on the loading status;

[0160] The sending module 402 is further configured to send fifth information, which is sent based on a first resource when the first timer times out. The first timer is determined by the first communication device based on the estimated loading time. The first resource is configured by the second communication device after the second timer times out. The second timer is determined by the second communication device based on the estimated loading time. The fifth information includes the prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer times out.

[0161] In one possible implementation of this application embodiment, the first message further includes sixth information, which is used to indicate the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

[0162] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

[0163] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

[0164] In one possible implementation of this application embodiment, the loading status of the first model indicated by the third information includes loading or loading completed.

[0165] In one possible implementation of this application embodiment, when the loading status of the first model indicated by the third information is loading, the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is loading complete, the estimated loading time is equal to 0.

[0166] In one possible implementation of this application embodiment, when the loading status of the first model indicated by the third information is "loading," and the first communication device completes loading of the first model before the first timer expires, the device further includes:

[0167] The sending module 402 is also used to send a seventh message, which is used to indicate that the loading status of the first model is complete.

[0168] In one possible implementation of this application embodiment, the first configuration information includes a periodic inference channel state information report configuration (CSI-ReportConfig).

[0169] In one possible implementation of this application embodiment, the first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

[0170] As illustrated by the examples in the foregoing embodiments, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the estimated loading time of the first model to the second communication device. Then, after the first timer determined based on the estimated loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0171] It should be noted that the physical device corresponding to the transmitting module 402 can be a transmitter, and the physical device corresponding to the receiving module 401 can be a receiver.

[0172] The above Figure 4 The communication device described above can also be used to implement the function of the second communication device in the above method embodiments, and the communication device specifically includes:

[0173] Sending module 402 is used to send a first message and second information, the first message including first information, the first information being used to determine a first model, and the second information being used to indicate first configuration information;

[0174] The receiving module 401 is used to receive a second message, the second message including third information and fourth information, the third information being used to indicate the loading status of the first model, the fourth information being used to indicate the estimated loading time of the first model, the estimated loading time being determined based on the loading status;

[0175] The receiving module 401 is used to receive fifth information, which is sent by the first communication device based on a first resource when the first timer times out. The first timer is determined by the first communication device based on the estimated loading time. The first resource is configured after the second timer times out. The second timer is determined based on the estimated loading time of the second communication device. The fifth information includes the prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer times out.

[0176] In one possible implementation of this application embodiment, the first message further includes sixth information, which is used to indicate the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

[0177] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

[0178] In one possible implementation of this application embodiment, the timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

[0179] In one possible implementation of this application embodiment, the loading status of the first model indicated by the third information includes loading or loading completed.

[0180] In one possible implementation of this application embodiment, when the loading status of the first model indicated by the third information is loading, the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is loading complete, the estimated loading time is equal to 0.

[0181] In one possible implementation of this application embodiment, when the loading status of the first model indicated by the third information is "loading," and the first communication device completes loading of the first model before the first timer expires, the device further includes:

[0182] The receiving module 401 is used to receive seventh information, which indicates that the loading status of the first model is complete.

[0183] In one possible implementation of this application embodiment, the first configuration information includes periodic inference CSI-ReportConfig.

[0184] In one possible implementation of this application embodiment, the first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

[0185] As illustrated by the examples in the foregoing embodiments, after receiving the first configuration information, the first communication device can first send the loading status of the first model and the estimated loading time of the first model to the second communication device. Then, after the first timer determined based on the estimated loading time of the first model expires, the first configuration information is activated again, and the prediction result of the first model is predicted based on the first configuration information and sent to the second communication device. This allows the second communication device to synchronize the activation completion time of the first configuration information with the first communication device, and to reserve the first resource for the first communication device to report the prediction result of the first model after the second timer expires. This enables successful decoding of the prediction result reported by the first communication device, thereby improving the transmission reliability during beam management.

[0186] Figure 5 This application provides an example of the composition of an electronic device. The electronic device may be a first device, including but not limited to a base station and a core network unit. Figure 5A simplified schematic diagram of a base station structure is shown. The base station includes sections 510, 520, and 530. Section 510 is mainly used for baseband processing and base station control; section 510 is typically the control center of the base station, often referred to as a processor, used to control the base station to perform the processing operations on the first device side in the above method embodiments. Section 520 is mainly used to store computer program code and data; section 520 is often referred to as a memory. Section 530 is mainly used for the transmission and reception of radio frequency signals and the conversion between radio frequency signals and baseband signals; section 530 is often referred to as a transceiver module, transceiver, transceiver circuit, or transceiver unit. The transceiver module of section 530, also referred to as a transceiver or transceiver unit, includes an antenna 533 and radio frequency circuitry, where the radio frequency circuitry is mainly used for radio frequency processing. Optionally, the device in section 530 used to implement the receiving function can be regarded as a receiver, and the device used to implement the transmitting function can be regarded as a transmitter; that is, section 530 includes a receiver 532 and a transmitter 531. A receiver can also be called a receiving module, receiver, or receiving circuit, while a transmitter can be called a transmitting module, transmitter, or transmitting circuit.

[0187] Sections 510 and 520 may include one or more circuit boards, each of which may include one or more processors and one or more memories. The processors are used to read and execute programs from the memories to implement baseband processing functions and control the base station. If multiple circuit boards exist, they can be interconnected to enhance processing capabilities. As an alternative implementation, multiple circuit boards may share one or more processors, multiple circuit boards may share one or more memories, or multiple circuit boards may simultaneously share one or more processors.

[0188] For example, in one implementation, the transceiver module in section 530 is used to execute the transceiver-related processes performed by the base station (first device) in the aforementioned method embodiments. The processor in section 510 is used to execute the processing-related processes performed by the base station in the aforementioned method embodiments.

[0189] It should be understood that Figure 5 This is for illustrative purposes only and not as a limitation. The network devices mentioned above, including processors, memory, and transceivers, may be independent of... Figure 5 The structure shown.

[0190] This application also provides a communication system, which may include a first device (e.g., a network device such as a base station) and a second device (e.g., a terminal device such as a mobile phone).

[0191] In this application, the terminal device or network device may include a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on top of the operating system layer. The hardware layer may include hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory (also known as main memory). The operating system layer may be any one or more computer operating systems that implement business processing through processes, such as Linux, Unix, Android, iOS, or Windows. The application layer may include applications such as browsers, address books, word processing software, and instant messaging software.

[0192] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0193] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or modules, and may be electrical, mechanical, or other forms.

[0194] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0195] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0196] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the essential contribution of the technical solution of this application, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the processes of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0197] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A communication method characterized by comprising: Applied to a first communication device, the method includes: Receive a first message, the first message including first information and second information, the first information being used to determine a first model, and the second information being used to determine first configuration information; Send a second message, which includes third and fourth information. The third information indicates the loading status of the first model, and the fourth information indicates the estimated loading time of the first model, which is determined based on the loading status. A fifth message is sent, which is sent based on a first resource when the first timer times out. The first timer is determined by the first communication device based on the estimated loading time. The first resource is configured by the second communication device after the second timer times out. The second timer is determined by the second communication device based on the estimated loading time. The fifth message includes the prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer times out.

2. The method of claim 1, wherein, The first message also includes a sixth message, which indicates the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

3. The method of claim 2, wherein, The timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

4. The method of claim 2, wherein, The timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

5. The method according to any one of claims 1 to 4, characterized in that, The third information indicates the loading status of the first model, including loading or loading completed.

6. The method of claim 5, wherein, When the loading status of the first model indicated by the third information is "loading", the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is "loading completed", the estimated loading time is equal to 0.

7. The method of claim 5, wherein, If the loading status of the first model indicated by the third information is "loading," and the first communication device completes loading of the first model before the first timer expires, the method further includes: Send a seventh message, which indicates that the loading status of the first model is complete.

8. The method according to any one of claims 1 to 4, characterized in that, The first configuration information includes the periodic inference channel state information reporting configuration CSI-ReportConfig.

9. The method according to any one of claims 1 to 4, characterized in that, The first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

10. A communication method characterized by comprising: Applied to a second communication device, the method includes: Send a first message, the first message including first information and second information, the first information being used to determine a first model, and the second information being used to indicate first configuration information; Receive a second message, the second message including third information and fourth information, the third information being used to indicate the loading status of the first model, the fourth information being used to indicate the estimated loading time of the first model, the estimated loading time being determined based on the loading status; The fifth information is received when the first communication device sends it based on a first resource after the first timer times out. The first timer is determined by the first communication device based on the expected loading time. The first resource is configured after the second timer times out. The second timer is determined by the second communication device based on the expected loading time. The fifth information includes the prediction result of the first model, which is predicted based on the first configuration information, which is activated when the first timer times out.

11. The method of claim 10, wherein, The first message also includes a sixth message, which indicates the expected activation time of the first configuration information; the first timer is determined by the first communication device based on the expected loading time and the expected activation time, and the second timer is determined by the second communication device based on the expected loading time and the expected activation time.

12. The method of claim 11, wherein, The timing duration of the first timer is the maximum value between the expected loading time and the desired activation time, and the timing duration of the second timer is the maximum value between the expected loading time and the desired activation time.

13. The method of claim 11, wherein, The timing duration of the first timer is the maximum value between the estimated loading time and the expected activation time, and the timing duration of the second timer is the difference between the maximum value between the estimated loading time and the expected activation time and the estimated air interface transmission delay.

14. The method according to any one of claims 10 to 13, characterized in that, The third information indicates the loading status of the first model, including loading or loading completed.

15. The method of claim 14, wherein, When the loading status of the first model indicated by the third information is "loading", the estimated loading time is greater than 0; when the loading status of the first model indicated by the third information is "loading completed", the estimated loading time is equal to 0.

16. The method of claim 14, wherein, If the loading status of the first model indicated by the third information is "loading," and the first communication device completes loading of the first model before the first timer expires, the method further includes: Receive a seventh message, which indicates that the loading status of the first model is complete.

17. The method according to any one of claims 10 to 13, characterized in that, The first configuration information includes periodic inference CSI-ReportConfig.

18. The method according to any one of claims 10 to 13, characterized in that, The first message includes a Radio Resource Control (RRC) reconfiguration message, the second message includes an RRC reconfiguration completion message, the first model includes an artificial intelligence model, and the fifth information includes uplink control information (UCI).

19. A communications device, characterized by The device includes a processor coupled to a memory storing a program or instructions, the processor executing the program or instructions to cause the device to perform the method as described in any one of claims 1 to 18.

20. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, When the computer program or instructions are executed, they cause the computer to perform the method as described in any one of claims 1 to 18.

21. A communication system, characterized by Includes the communication device as described in claim 19.

22. A chip system, characterized by The chip system includes one or more processors, which are configured to retrieve and execute instructions stored in memory, such that the method as described in any one of claims 1 to 18 is performed.

Images