Communication method and apparatus

By performing AI operations in stages on the terminal device and utilizing the time period configuration indicated by the network device, the power consumption problem when AI operations and communication coexist is solved, achieving power reduction and performance guarantee.

WO2026130098A1PCT designated stage Publication Date: 2026-06-25HUAWEI TECH CO LTD

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
HUAWEI TECH CO LTD
Filing Date
2025-12-01
Publication Date
2026-06-25

AI Technical Summary

Technical Problem

In terminal devices, when AI operation and communication coexist, how can we reduce power consumption to improve power utilization efficiency?

Method used

By performing AI operations in non-continuous time periods, the AI ​​operation time can be flexibly configured using time periods indicated by network devices or determined by terminal devices, ensuring that AI operations and communication services do not interfere with each other, and power consumption is managed by using timers or sub-AI operations.

Benefits of technology

It effectively reduces the power consumption of terminal devices and improves the performance and resource utilization of AI operation and communication services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025139030_25062026_PF_FP_ABST
    Figure CN2025139030_25062026_PF_FP_ABST
Patent Text Reader

Abstract

The present application discloses a communication method and apparatus. The method comprises: a terminal apparatus determining a first time period, wherein the first time period is used for executing a first AI operation, and the first time period comprises at least two non-consecutive time periods; and executing the first AI operation in the at least two non-consecutive time periods. In embodiments of the present application, the terminal apparatus can execute an AI operation within a time period for executing the AI operation, and does not execute the AI operation outside the time period for executing the AI operation. In other words, the terminal apparatus can periodically perform an AI operation, thereby reducing power consumption of the terminal apparatus.
Need to check novelty before this filing date? Find Prior Art

Description

A communication method and apparatus

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411914407.5, filed on December 20, 2024, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0004] With the development of the network, artificial intelligence (AI) technology can be introduced into the network to achieve network intelligence.

[0005] Currently, AI-related operations can include data collection (e.g., collecting AI model training data and / or AI model inference data), AI model training, AI model inference, and AI model performance monitoring. In future mobile communications, there may be scenarios where AI operations and communication coexist. This means that terminal devices need to perform both communication services and AI operations. Since terminal devices have limited power, reducing power consumption in scenarios where AI operations and communication coexist is a pressing technical problem that needs to be solved. Summary of the Invention

[0006] This application provides a communication method and apparatus for reducing the power consumption of terminal devices.

[0007] In a first aspect, embodiments of this application provide a communication method applicable to a terminal device, which is a terminal-side device, such as a terminal equipment, or other device including terminal equipment functions, or a chip system (or chip) or other functional module capable of implementing the functions of the terminal equipment, and the chip system or functional module being, for example, disposed in the terminal equipment. The method includes: determining a first time period, the first time period being used to perform a first AI operation, the first time period including at least two non-contiguous time periods; and performing the first AI operation within the at least two non-contiguous time periods.

[0008] In this embodiment, the terminal device can perform AI operations during the designated time period and not perform AI operations outside of that period. In other words, the terminal device can perform AI operations in stages, thereby reducing its power consumption.

[0009] In one possible implementation, determining the first time period includes: receiving first information from the network device, the first information being used to determine the first time period.

[0010] In this embodiment, a method is provided for a terminal device to determine a first time period. For example, the network device indicates the first time period to the terminal device. That is, the network device can configure the first time period for the terminal device as needed, which is more flexible.

[0011] In one possible implementation, the first information includes one or more of the following: first indication information, which is used to determine one or more of the start time, end time, or duration of the first time period; and second indication information, which is used to indicate that the first time period corresponds to a first reference signal.

[0012] In this embodiment, multiple methods are provided for the network device to indicate a first time period to the terminal device. For example, the network device can indicate to the terminal device, through first indication information, one or more of the start time, end time, or duration of one or more non-contiguous time periods within the first time period, without relying on other indications from the network device, thus saving signaling overhead. This indication method can also be understood as a direct indication method. As another example, the network device can indicate to the terminal device, through second indication information, that the first time period corresponds to a first reference signal. The terminal device can then determine the first time period based on the first reference signal. This indication method can also be understood as an indirect indication method. Therefore, the methods by which the network device indicates the first time period to the terminal device are quite flexible.

[0013] In one possible implementation, the first indication information further indicates the number of cycles corresponding to the first time period.

[0014] In this embodiment, the first time period includes at least two non-contiguous time periods for performing AI operations, which may belong to one cycle, multiple cycles, or not belong to any cycle. The network device may indicate to the terminal device the number of cycles to which the at least two non-contiguous time periods for performing AI operations belong in the first time period, so that the terminal device can determine the at least two non-contiguous time periods for performing AI operations included in the first time period.

[0015] In one possible implementation, the first information includes the second indication information, and the method further includes: receiving the first reference signal from the network device; and determining the start time of the first time period based on the time when the terminal device receives the first reference signal.

[0016] In this embodiment, if the first reference signal corresponds to a first time period, the terminal device can determine the start time of the first time period based on the time when the terminal device receives the first reference signal.

[0017] In one possible implementation, the time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or, the time difference between the time when the terminal device sends the first report and the start time of the first time period is a second offset, the first report corresponds to the first reference signal, and the time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

[0018] In this embodiment, the terminal device can determine the start time of the first time period based on the time when the terminal device receives the first reference signal and the first offset; or, if the terminal device sends a first report corresponding to the first reference signal to the network device after receiving the first reference signal from the network device, the terminal device can determine the time when the terminal device sends the first report and the second offset to determine the start time of the first time period. Therefore, the method by which the terminal device determines the start time of the first time period is quite flexible.

[0019] In one possible implementation, the method further includes: receiving second information from the network device, the second information indicating that the first time period corresponds to the first reference signal in the second time period; and determining the end time of the first time period based on the end time of the second time period.

[0020] In this embodiment, the terminal device can initiate the correspondence between the first time period and the first reference signal at the start time of the second time period. After initiating the correspondence, if the terminal device receives the first reference signal from the network device, it will determine the start time of the first time period based on the time at which the terminal device receives the first reference signal. The terminal device can de-correspond to the first time period and the first reference signal at the end time of the second time period. After de-corresponding, if the terminal device receives the first reference signal from the network device, it will not determine the start time of the first time period based on the time at which it receives the first reference signal. Therefore, the terminal device can determine the end time of the first time period based on the end time of the second time period, for example, the end time of the second time period is equal to or later than the end time of the first time period.

[0021] In one possible implementation, determining the first time period includes: determining the first time period based on a third time period, wherein the third time period is used to perform communication services.

[0022] In this embodiment, a method is provided for a terminal device to determine a first time period. For example, when a third time period for performing communication services is related to a first time period for performing a first AI operation, the terminal device can determine the first time period for performing the first AI operation based on the third time period for performing communication services, so that the terminal device's performance of AI operations and its performance of communication services do not interfere with each other, thereby ensuring the performance of AI operations and communication services as much as possible in scenarios where AI operations and communication coexist.

[0023] In one possible implementation, the method further includes: receiving third information from a network device, wherein the first time period and the third time period do not overlap or partially overlap.

[0024] In this embodiment, the network device can indicate to the terminal device various possibilities regarding the relationship between the first time period and the third time period, such as non-overlapping or partial overlap, so that the terminal device's execution of AI operations and communication services do not interfere with each other. This ensures the performance of both AI operations and communication services as much as possible in scenarios where AI operations and communication coexist. Alternatively, the terminal device can determine the relationship between the first time period and the third time period through other means, without limitation.

[0025] In one possible implementation, the start time of the first time period is equal to the end time of the third time period; or, the end time of the first time period is equal to the start time of the third time period; or, the start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, the end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, the start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, the end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

[0026] In this embodiment, several possibilities are provided for the first time period and the third time period to not overlap or partially overlap. For example, when the first time period and the third time period do not overlap, the start time of the first time period is equal to the end time of the third time period, or the end time of the first time period is equal to the start time of the third time period, or the start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset, or the end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset. As another example, when the first time period and the third time period partially overlap, the start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period, or the end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period. This ensures that AI operations and communication services performed by the terminal device do not interfere with each other, thereby maximizing the performance of both AI operations and communication services in scenarios where they coexist.

[0027] In one possible implementation, the method further includes: sending fourth information to the network device, the fourth information being used to request updates to the first time period and / or the third time period, the third time period being used to perform communication services, the first time period and the third time period not overlapping or partially overlapping; and / or receiving fifth information from the network device, the fifth information being used to instruct updates to the first time period and / or the third time period, the third time period being used to perform communication services, the first time period and the third time period not overlapping or partially overlapping.

[0028] In this embodiment, the terminal device or network device can update the first time period according to the needs of the terminal device when performing the first AI operation, thereby ensuring the performance of the AI ​​operation. For example, the fourth or fifth information can directly indicate the update of the first time period, or the fourth or fifth information can indirectly indicate the update of the first time period, that is, indicate the update of the third time period, which is more flexible.

[0029] In one possible implementation, the fourth information is sent by the terminal device when a first condition is met, and the fifth information is sent by the network device when a first condition is met. The first condition includes one or more of the following: a first time difference is less than or equal to a second time difference; or, the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to a first priority threshold; or, the target performance of the first AI operation is greater than or equal to a first target performance; or, the end time of the first time period is later than the time when the terminal device ends the execution of the first AI operation; wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends the execution of the first AI operation.

[0030] In this implementation, multiple triggering conditions are provided for updating the first time period. For example, if the first time difference is less than or equal to the second time difference, it indicates that the terminal device cannot complete the first AI operation within the first time period. Therefore, to meet the requirements of the first AI operation, the terminal device determines that the first time period needs to be updated, i.e., the first time period is increased. As another example, if the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to the first priority threshold, it indicates that the terminal device cannot complete the first AI operation with a higher priority within the first time period. Since the first AI operation has a higher priority, the terminal device needs to meet the requirements of the first AI operation, and thus determines that the first time period needs to be updated, i.e., the first time period is increased. As yet another example, if the target performance of the first AI operation is greater than or equal to the first target performance, it indicates that the time required for the terminal device to execute the first AI operation is large, and the terminal device cannot complete the first AI operation within the first time period. Therefore, to meet the requirements of the first AI operation, the terminal device determines that the first time period needs to be updated, i.e., the first time period is increased. For example, if the end time of the first time period is later than the time when the terminal device finishes executing the first AI operation, it means that the terminal device does not execute the first AI operation for part of the first time period. Therefore, in order to improve resource utilization, the terminal device performs communication services during the time when it does not execute the first AI operation in the first time period. The terminal device determines that the first time period needs to be updated, that is, the first time period is reduced.

[0031] In one possible implementation, the start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

[0032] In this implementation, a relationship between multiple time periods for performing AI operations is provided, such as different start times, durations, end times, or corresponding AI operations.

[0033] In one possible implementation, before performing the first AI operation in the at least two non-contiguous time periods, the method further includes: determining that the first time period has been activated.

[0034] In this embodiment, after the terminal device determines the first time period, and before executing the first AI operation within the first time period, it can determine whether the first time period is active. If the terminal device determines that the first time period is active, the terminal device can execute the first AI operation within the first time period. If the terminal device determines that the first time period is not active, the terminal device cannot execute the first AI operation within the first time period.

[0035] In one possible implementation, the method further includes: receiving sixth information from the network device, the sixth information being used to indicate activation of the first time period.

[0036] In this implementation, if the first AI operation is triggered by the terminal device, the terminal device requests the network device to activate the first time period; or, if the first AI operation is triggered by the network device, the network device may proactively activate the first time period for the terminal device.

[0037] In one possible implementation, the method further includes: when the first time difference is less than or equal to the second time difference, starting a first timer corresponding to the first time period, and performing the first AI operation during the running time of the first timer; wherein the first time difference is the time difference between the time when the terminal device starts performing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts performing the first AI operation and the time when the terminal device ends performing the first AI operation.

[0038] In this embodiment, if the first time difference is less than or equal to the second time difference, it means that the terminal device cannot complete the first AI operation within the first time period. Therefore, in order to meet the requirements of the first AI operation, the terminal device can extend the first time period by starting the first timer corresponding to the first time period, thereby ensuring that the terminal device can complete the first AI operation.

[0039] In one possible implementation, the first AI operation includes a first sub-AI operation and a second sub-AI operation. The method further includes: when the terminal device finishes executing the first sub-AI operation, starting a second timer corresponding to the first sub-AI operation; entering a sleep state or performing communication services during the running time of the second timer; and starting to execute the second sub-AI operation at the end time of the second timer.

[0040] In this embodiment, the terminal device can divide an AI operation into multiple sub-AI operations and start a second timer in the middle of any two sub-AI operations, so that the terminal device can enter a sleep state during the running time of the second timer, thereby reducing the power consumption of the terminal device, or perform communication services during the running time of the second timer, thereby improving resource utilization.

[0041] Secondly, embodiments of this application also provide a communication method. This method can be applied to a network device, which is a network-side communication device, such as a network equipment, or other devices including network equipment functions, or a chip system (or chip) or other functional module. The chip system or functional module can implement the functions of the network equipment, and the chip system or functional module is, for example, disposed in the network equipment. The method includes: sending first information or third information to a terminal device, wherein the first information is used to determine a first time period, the first time period including at least two non-contiguous time periods, the third information is used to indicate that the first time period and the third time period do not overlap or partially overlap, the first time period is used to perform a first AI operation, and the third time period is used to perform communication services.

[0042] In one possible implementation, the first information includes one or more of the following: first indication information, which is used to determine one or more of the start time, end time, or duration of the first time period; and second indication information, which is used to indicate that the first time period corresponds to a first reference signal.

[0043] In one possible implementation, the first indication information further indicates the number of cycles corresponding to the first time period.

[0044] In one possible implementation, the first information includes the second indication information, and the method further includes: sending the first reference signal to the terminal device, wherein the time at which the terminal device receives the first reference signal is related to the start time of the first time period.

[0045] In one possible implementation, the time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or, the time difference between the time when the terminal device sends the first report and the start time of the first time period is a second offset, the first report corresponds to the first reference signal, and the time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

[0046] In one possible implementation, the method further includes: sending second information to the terminal device, the second information indicating that the first time period corresponds to the first reference signal in a second time period, and the end time of the second time period is related to the end time of the first time period.

[0047] In one possible implementation, the start time of the first time period is equal to the end time of the third time period; or, the end time of the first time period is equal to the start time of the third time period; or, the start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, the end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, the start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, the end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

[0048] In one possible implementation, the method further includes: receiving fourth information from the terminal device, the fourth information being used to request an update to the first time period and / or the third time period; and / or sending fifth information to the terminal device, the fifth information being used to instruct an update to the first time period and / or the third time period.

[0049] In one possible implementation, the fourth information is sent by the terminal device when a first condition is met, and the fifth information is sent by the network device when the first condition is met. The first condition includes one or more of the following: a first time difference is less than or equal to a second time difference; or, the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to a first priority threshold; or, the target performance of the first AI operation is greater than or equal to a first target performance; or, the end time of the first time period is later than the time when the terminal device ends the execution of the first AI operation; wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends the execution of the first AI operation.

[0050] In one possible implementation, the start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

[0051] In one possible implementation, the method further includes sending a sixth message to the terminal device, the sixth message being used to indicate activation of the first time period.

[0052] Thirdly, embodiments of this application also provide a communication device. The communication device can be the terminal device described in the first aspect above. The communication device possesses the functions of the aforementioned terminal device. The communication device is, for example, a terminal equipment, or other equipment including terminal equipment functions, or a chip system (or chip) or other functional module. The chip system or functional module can implement the functions of the terminal equipment, and the chip system or functional module is, for example, disposed in the terminal equipment. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both sending and receiving functions. When the transceiver unit implements the sending function, it can be called a sending unit (sometimes also called a sending module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The sending unit and the receiving unit can be the same functional module, which is called the transceiver unit and can implement both sending and receiving functions; or, the sending unit and the receiving unit can be different functional modules, and the transceiver unit is a general term for these functional modules.

[0053] In one embodiment, the processing unit is configured to determine a first time period, the first time period being used to perform a first AI operation; and to perform the first AI operation during the first time period.

[0054] Fourthly, embodiments of this application also provide a communication device. The communication device can be the network device described in the second aspect above. The communication device possesses the functions of the aforementioned network device. The communication device is, for example, a network device, or other device including network device functions, or a chip system (or chip) or other functional module. The chip system or functional module can implement the functions of a network device, and the chip system or functional module is, for example, disposed within a network device. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both transmitting and receiving functions. When the transceiver unit implements the transmitting function, it can be called a transmitting unit (sometimes also called a transmitting module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The transmitting unit and the receiving unit can be the same functional module, which is called the transceiver unit and can implement both transmitting and receiving functions; or, the transmitting unit and the receiving unit can be different functional modules, and the transceiver unit is a collective term for these functional modules.

[0055] In one embodiment, the transceiver unit is configured to send first information or third information to a terminal device, wherein the first information is used to determine a first time period, and the third information is used to indicate that the first time period and the third time period do not overlap or partially overlap, the first time period is used to perform a first AI operation, and the third time period is used to perform a communication service.

[0056] Fifthly, a communication device is provided, which can be the terminal device described in the first aspect above. The communication device possesses the functions of the terminal device described above. The communication device is, for example, a terminal equipment, or other equipment including the functions of a terminal equipment, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of a terminal equipment, and the chip system or functional module is, for example, disposed in a terminal equipment. The communication device includes a processor for executing the functions of the terminal device described in the first or third aspect above. Optionally, the communication device further includes a memory. The memory is used to store a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods executed by the terminal device in the above aspects. Optionally, the memory and the processor are integrated together.

[0057] Sixthly, a communication device is provided, which can be a network device as described in the second aspect above. The communication device possesses the functions of the aforementioned network device. The communication device is, for example, a network equipment, or other equipment including network equipment functions, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of a network equipment, and the system-on-a-chip or functional module is, for example, disposed within a network equipment. The communication device includes a processor for executing the functions of the network device as described in the second or fourth aspect above. Optionally, the communication device further includes a memory. The memory stores a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods performed by the network device in the aforementioned aspects. Optionally, the memory and the processor are integrated together.

[0058] A seventh aspect provides a communication system including a terminal device and a network device. The terminal device is used to perform the method described in the first aspect. For example, the terminal device can be implemented using the communication device described in the third or fifth aspect. The network device is used to perform the method described in the second aspect. For example, the network device can be implemented using the communication device described in the fourth or sixth aspect.

[0059] Eighthly, a computer-readable storage medium is provided for storing a computer program or instructions that, when executed, cause the methods performed by the terminal device or network device in the above aspects to be implemented.

[0060] Ninthly, a computer program product containing instructions is provided, which, when the computer program or instructions are run on a computer, causes the methods described in the above aspects to be implemented.

[0061] In a tenth aspect, a chip system is provided, including a processor and an interface, the processor being configured to call and execute instructions from the interface to enable the chip system to implement the methods described above.

[0062] The beneficial effects of the second to tenth aspects and their embodiments described above can be referred to the beneficial effects of the first aspect and any of its embodiments, and will not be repeated here. Attached Figure Description

[0063] Figure 1 is a schematic diagram of a communication system provided in an embodiment of this application;

[0064] Figure 2 is a schematic diagram of a wireless access network intelligent controller provided in an embodiment of this application;

[0065] Figure 3 is a schematic diagram of an artificial intelligence module provided in an embodiment of this application;

[0066] Figure 4a is a schematic diagram of a DRX mechanism provided in an embodiment of this application;

[0067] Figure 4b is a schematic diagram of a DRX cycle provided in an embodiment of this application;

[0068] Figure 4c is a schematic diagram of another DRX cycle provided in an embodiment of this application;

[0069] Figure 5 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0070] Figure 6 is a schematic diagram of a first time period provided in an embodiment of this application;

[0071] Figure 7a is a flowchart illustrating another communication method provided in an embodiment of this application;

[0072] Figure 7b is a schematic diagram of another first time period provided in an embodiment of this application;

[0073] Figure 7c is a schematic diagram of another first time period provided in an embodiment of this application;

[0074] Figure 8a is a flowchart illustrating another communication method provided in an embodiment of this application;

[0075] Figure 8b is a schematic diagram of a first time period and a third time period provided in an embodiment of this application;

[0076] Figure 8c is a schematic diagram of another first time period and a third time period provided in an embodiment of this application;

[0077] Figure 9a is a schematic diagram of the first time period and the first timer provided in an embodiment of this application;

[0078] Figure 9b is a schematic diagram of the first time period and the second timer provided in an embodiment of this application;

[0079] Figure 10 is a schematic diagram of a communication device provided in an embodiment of this application;

[0080] Figure 11 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0081] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0082] The technical solutions provided in the embodiments of this application can be applied to communication systems related to the 3rd Generation Partnership Project (3GPP), such as Long Term Evolution (LTE) communication systems, 5th Generation (5G) mobile communication systems (specifically, New Radio (NR) communication systems, or NR communication systems that introduce Multi-Input Multi-Output (MIMO) technology), or they can also be applied to other next-generation mobile communication systems, other similar communication systems, or communication systems in the future evolution process. Other similar communication systems may include Wireless Fidelity (WiFi), Vehicle-to-Everything (V2X), Internet of Things (IoT) systems, Narrow Band Internet of Things (NB-IoT) systems, or the Industrial Internet, etc.

[0083] Referring to Figure 1, it is a schematic diagram of the structure of a communication system provided in an embodiment of this application. As shown in Figure 1, the communication system may include a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system may also include the Internet 300.

[0084] The wireless access network 100 may include at least one access network device (such as access network devices 110a and 110b in Figure 1, collectively referred to as access network device 110) and at least one terminal device (such as terminal devices 120a-120j in Figure 1, collectively referred to as terminal device 120). The wireless access network 100 may also include other devices, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). Terminal device 120 is wirelessly connected to access network device 110. Access network device 110 is wirelessly or wired connected to core network 200. Core network device 210 in core network 200 and access network device 110 in wireless access network 100 may be different physical devices, or they may be the same physical device integrating core network logical functions and wireless access network logical functions. Access network device 110 and core network device 210 may be referred to as network devices.

[0085] The radio access network 100 can be a 3GPP-related communication system (such as a 5G mobile communication system) or a future mobile communication system. The radio access network 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), or a WiFi system. The radio access network 100 can also be a communication system that integrates two or more of the above systems.

[0086] Access network equipment 110, also known as RAN node, RAN entity, or access node, is used to help terminal equipment 120 achieve wireless access.

[0087] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, in V2X technology, a RAN node can be a roadside unit (RSU).

[0088] In another possible scenario, multiple RAN nodes can collaborate to assist terminal device 120 in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). The CU can perform the functions of the radio resource control (RRC) protocol and packet data convergence protocol (PDCP) of the base station, and can also perform the functions of the service data adaptation protocol (SDAP). The DU can perform the functions of the radio link control (RLC) layer and medium access control (MAC) layer of the base station, and can also perform some or all of the physical (PHY) layer functions. For specific descriptions of the above protocol layers, please refer to the relevant technical specifications of 3GPP.

[0089] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0090] In different systems, RAN nodes can communicate with different devices. For example, as shown in Figure 2, in an ORAN system, RAN nodes (such as CU, DU, or RU) can communicate with the RAN intelligent controller (RIC). RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs).

[0091] Near real-time RICs are used for model training and / or inference. For example, they are used to train artificial intelligence (AI) models and then use those AI models for inference. Near real-time RICs can obtain information from RAN nodes and / or terminal devices. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminal devices. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0092] Non-real-time RICs are used for model training and / or inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain information from RAN nodes and / or terminal devices. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminal devices. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0093] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Optionally, near real-time and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (such as CUs or DUs), while non-real-time RICs can be set in operation administration and maintenance (OAM) systems, cloud servers, or other RAN nodes.

[0094] For example, as shown in Figure 3, in an ORAN system, network elements are connected via interfaces (e.g., NG, Xn, or F1) or air interfaces. These network element nodes, such as RAN nodes, terminal devices, or one or more devices in the OAM system, are equipped with one or more AI modules (for simplicity, only one is shown in Figure 3). A RAN node can be a single RAN node or multiple RAN nodes, for example, including CUs and DUs. CUs and / or DUs can also be equipped with one or more AI modules. Optionally, a CU can be further divided into CU-CPs and CU-UPs. One or more AI models are configured in CU-CPs and / or CU-UPs.

[0095] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0096] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0097] In this embodiment, the access network device 110 and its components (such as chips, processing units, or processors) can be collectively referred to as network devices. For example, it can be the access network device 110 shown in FIG1, or it can be the chip (system) in the access network device 110 in FIG1.

[0098] The embodiments of this application do not limit the device form of the access network device 110. The apparatus for implementing the functions of the access network device 110 can be the access network device 110 itself; it can also be an apparatus capable of supporting the access network device 110 in implementing the functions, such as a chip system. This apparatus can be installed in the access network device 110 or used in conjunction with the access network device 110. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the access network device 110 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0099] Terminal equipment 120, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., refers to a device that provides voice and / or data connectivity to a user.

[0100] Terminal device 120 can be a handheld device, vehicle-mounted device, or other device with wireless connectivity. For example, terminal device 120 can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device (e.g., smartwatch, smart bracelet, pedometer, smart glasses, etc.), vehicle-mounted device (e.g., car, bicycle, electric vehicle, airplane, ship, train, high-speed rail, etc.), satellite terminal, virtual reality (VR) device, augmented reality (AR) device, smart point of sale (POS) machine, customer-premises equipment (CPE), light user equipment (light UE), reduced capability user equipment (REDCAP UE), wireless terminal in industrial control, smart home device (e.g., refrigerator, television, air conditioner, electricity meter, etc.), smart robot, robotic arm, workshop equipment, wireless terminal in autonomous driving, wireless terminal in telemedicine, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, or wireless terminal in smart home, flying equipment (e.g., smart robot, hot air balloon, drone, airplane), etc. Terminal device 120 can also be a vehicle device, such as a complete vehicle device, vehicle module, vehicle chip, on-board unit (OBU), or telematics box (T-BOX). Terminal device 120 can also be other devices with terminal functions; for example, terminal device 120 can also be a device that plays a terminal function in device-to-device (D2D) communication.

[0101] In the embodiments of this application, the terminal device 120 and its components (such as chips, processing units, or processors) can be collectively referred to as a terminal device. For example, it can be the terminal device 120 shown in FIG1, or it can be the chip (system) in the terminal device 120 in FIG1.

[0102] The embodiments of this application do not limit the device form of the terminal device 120. The device used to implement the functions of the terminal device 120 can be the terminal device 120 itself; it can also be a device capable of supporting the terminal device 120 in implementing the functions, such as a chip system. This device can be installed in the terminal device 120 or used in conjunction with the terminal device 120. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the terminal device 120 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0103] Core network equipment 210 may include different network elements in different communication systems. For example, in a 4G mobile communication system, core network equipment 210 includes user plane network elements and control plane network elements. User plane network elements include serving gateways (SGW) and packet data network gateways (PGW), etc. Control plane network elements include mobility management entities (MME). In a 5G mobile communication system, core network equipment 210 includes user plane network elements and control plane network elements. User plane network elements include user plane functions (UPF). The control plane network elements include authentication server function (AUSF) network elements, access and mobility management function (AMF), session management function (SMF), network slicing selection function (NSSF), network exposure function (NEF), network repository function (NRF), policy control function (PCF), unified data management (UDM), application function (AF), network slice-specific authentication and authorization function (NSSAAF), service communication proxy (SCP), network slice admission control function (NSACF), and edge application server discovery function (EASDF), etc. Of course, the core network equipment 210 may also include other network elements, which are not listed here.

[0104] In this embodiment, the core network device 210 and its components (such as chips, processing units, or processors) can be collectively referred to as network devices. For example, it can be the core network device 210 shown in FIG1, or it can be the chip (system) in the core network device 210 in FIG1.

[0105] The embodiments of this application do not limit the device form of the core network device 210. The apparatus used to implement the functions of the core network device 210 can be the core network device 210 itself; it can also be an apparatus capable of supporting the core network device 210 in implementing the functions, such as a chip system. This apparatus can be installed in the core network device 210 or used in conjunction with the core network device 210. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the core network device 210 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0106] The communication system applicable to the embodiments of this application has been briefly introduced above. The relevant technical solutions involved in the embodiments of this application are described below.

[0107] I. RRC Idle State and RRC Connected State

[0108] RRC idle state (or RRC disconnected state) refers to a situation where the terminal device, after camping on a cell, has not established an RRC connection with the network device. In this state, the terminal device can receive paging messages from the network device, but cannot transmit data. RRC connected state refers to a situation where the terminal device, after camping on a cell, has established an RRC connection with the network device through a random access procedure. In this state, data transmission between the terminal device and the network device is possible.

[0109] II. Connected-discontinuous reception (C-DRX or DRX) mechanism

[0110] In communication between terminal devices and network devices, the DRX mechanism is introduced to save power for the terminal device. For example, Figure 4a is a schematic diagram of a DRX mechanism provided in an embodiment of this application. In the DRX-off scenario shown in Figure 4a, the terminal device will continuously detect the Physical Downlink Control Channel (PDCCH) regardless of whether it is in the RRC idle state or the RRC connected state. However, data transmission between the terminal device and the network device is not always required. Most of the time, there is no data interaction between the terminal device and the network device. If the terminal device continues to detect the PDCCH at this time, it will obviously consume a lot of power. Therefore, under the premise of ensuring effective data transmission, it is necessary to design a mechanism to save the power of the terminal device. This mechanism is called the DRX mechanism. In the DRX-on scenario shown in Figure 4a, when data transmission is required between the terminal device and the network device, the terminal device can detect and receive the PDCCH; otherwise, the terminal device turns off the receiver and does not detect and receive the PDCCH, thereby reducing the power consumption of the terminal device and extending the standby time of the terminal device. It can be understood that in this application, receiving the PDCCH refers to receiving the information carried on the PDCCH.

[0111] It can be understood that the DRX mechanism essentially configures the DRX cycle for the terminal device. For example, Figure 4b is a schematic diagram of a DRX cycle provided by an embodiment of this application. As shown in Figure 4b, the time is divided into consecutive DRX cycles. The DRX cycle consists of "On Duration" (wake-up period or wake-up time or activation period or activation time) and "Opportunity for DRX" (sleep period or sleep time). During the "On Duration" period, the terminal device detects and receives the Physical Downlink Control Channel (PDCCH). During the "Opportunity for DRX" period, the terminal device does not detect and receive the PDCCH to reduce power consumption.

[0112] When a terminal device is configured with a DRX cycle, its state can be divided into DRX active state and DRX sleep state. During the DRX active period, the terminal device is in the DRX active state; during the DRX sleep period, it is in the DRX sleep state. When the terminal device is in the DRX active period, it will detect and receive the PDCCH. If the terminal device is in the DRX sleep period, it will not detect and receive the PDCCH to reduce power consumption.

[0113] Key parameters of the DRX cycle include one or more of the following: DRX onDurationTimer; DRX inactivityTimer; DRX hybrid automatic repeat request (HARQ) round trip time (RTT) timer; and DRX retransmission timer.

[0114] For example, Figure 4c is a schematic diagram of another DRX cycle provided in an embodiment of this application. As shown in (1) of Figure 4c, at the start time of the DRX cycle, the terminal device starts the DRX activation period timer, and the DRX activation period begins when the DRX activation period timer starts running. If the terminal device receives a PDCCH for scheduling data during the running of the DRX activation period timer, the terminal device will start the DRX deactivation timer, so that the terminal device is always in the DRX activation period. It can be understood that the time when the terminal device is originally in the active state is the time when the DRX activation period timer is running. Running the DRX deactivation timer can extend the time when the terminal device is in the active state until the DRX deactivation timer expires, or the terminal device receives a related medium access control (MAC) control element (CE) to stop the DRX activation period timer and the DRX deactivation timer, and then the terminal device ends the DRX activation period and enters the DRX sleep period.

[0115] As shown in Figure 4c(2), after the terminal device receives the PDCCH used for scheduling data, it sends a HARQ feedback to the network device to indicate whether the data was successfully received. If successfully received, it sends an ACK; if unsuccessfully received, it sends a NACK. If the network device receives a NACK, it will retransmit the data after a certain period of time, called the round-trip time. When the terminal device sends a NACK to the network device, it starts the DRX Hybrid Automatic Repeat Request Round-Trip Timer. During the operation of the DRX Hybrid Automatic Repeat Request Round-Trip Timer, the terminal device does not need to detect the PDCCH used for scheduling data. At the end of the DRX Hybrid Automatic Repeat Request Round-Trip Timer, the terminal device starts the DRX Retransmission Timer. During the operation of the DRX Retransmission Timer, the terminal device needs to detect the PDCCH used for scheduling data.

[0116] DRX cycles can be divided into long cycles and short cycles based on the duration of the DRX dormancy period. Long cycles have a longer DRX dormancy period, while short cycles have a shorter DRX dormancy period.

[0117] The conditions under which a terminal device enters a DRX short cycle include: the terminal device receiving a DRX command MAC CE and configuring a DRX short cycle; and the DRX deactivation timer timing out and the terminal device having configured a DRX short cycle.

[0118] The following situations indicate that a terminal device enters a long DRX cycle: the terminal device receives a DRX command MAC CE and a short DRX cycle is not configured; the DRX deactivation timer times out and the terminal device has not configured a short DRX cycle; the DRX short cycle timer times out; or the terminal device receives a long DRX command MAC CE.

[0119] III. AI Operation

[0120] With the development of networks, AI technology can be introduced into networks to achieve network intelligence. AI-related operations can include data collection (e.g., collecting AI model training data and / or AI model inference data), AI model training, AI model inference, and AI model performance monitoring.

[0121] Currently, in future mobile communications, there may be scenarios where AI operations and communication coexist. That is, terminal devices need to perform both communication services and AI operations. Since the power of terminal devices is limited, how to reduce the power consumption of terminal devices in scenarios where AI operations and communication coexist is an urgent technical problem to be solved.

[0122] In view of this, embodiments of this application provide a communication method for reducing the power consumption of terminal devices.

[0123] In the embodiments of this application, "when," "if," and "if" all refer to the device taking corresponding actions under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" can be substituted, and "when" and "in the case of" can be substituted. "When" and "if" / "if" can be substituted.

[0124] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0125] In this document, "used for indication" can include both direct and indirect indication. For example, when descriptive information I is used to indicate information J, it can mean that information I directly indicates information J or indirectly indicates information J, but it does not necessarily mean that information I carries information J.

[0126] Let information J, indicated by information I, be called the information to be indicated. In practice, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information itself or its index. It can also be indirectly indicated by indicating other information, where there is a relationship between the other information and the information to be indicated. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the indication of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) order of various pieces of information, thereby reducing indication overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and indicated uniformly to reduce the indication overhead caused by individually indicating the same information.

[0127] Furthermore, the specific instruction method can also be any existing instruction method, such as, but not limited to, the above-mentioned instruction methods and their various combinations. As described above, for example, when multiple pieces of information of the same type need to be indicated, the instruction methods for different pieces of information may differ. In specific implementation, the required instruction method can be selected according to specific needs. This application embodiment does not limit the selected instruction method. Therefore, the instruction methods involved in this application embodiment should be understood to cover various methods that enable the party to be instructed to obtain the information to be indicated.

[0128] In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission via the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY via the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0129] Information may undergo necessary processing, such as encoding and modulation, between the source and destination ends, but the destination end can understand the valid information from the source end. Similar statements in the embodiments of this application can be understood in a similar way, and will not be repeated here.

[0130] In this application embodiment, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " can indicate that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0131] In this application, the ordinal numbers such as "first" and "second" are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For a technical feature, the technical features within that technical feature are distinguished by "A", "B", "C", and "D", and there is no sequential or size order among the technical features described by "A", "B", "C", and "D".

[0132] The solutions provided in the embodiments of this application are described in detail below with reference to the accompanying drawings. In the following description, the communication method provided in the embodiments of this application is used as an example applied to the communication systems shown in Figures 1-3. The communication systems and application scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. Those skilled in the art will understand that with the evolution of communication systems and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0133] The communication method provided in this application is described below using an example of a terminal device and a network device. The terminal device can be the terminal equipment shown in Figures 1-3, or it can be a component (such as a chip, processing unit, or processor module) within the terminal equipment shown in Figures 1-3. The network device can be the network equipment shown in Figures 1-3, or it can be a component (such as a chip, processing unit, or processor module) within the network equipment shown in Figures 1-3.

[0134] When this communication method is implemented by components in a terminal device and a network device, the receiving and transmitting steps can be understood as the component communicating with other components, such as communication between a baseband chip and a radio frequency circuit. In the embodiments of this application, the processing performed by a single execution entity can also be divided into multiple execution entities, which can be logically and / or physically separated. For example, the processing performed by the network device can be divided into execution by at least one of a CU and a DU.

[0135] Referring to Figure 5, which is a flowchart illustrating a communication method provided in an embodiment of this application, the communication method includes the following steps, as shown in Figure 5.

[0136] S501, The terminal device determines a first time period, which is used to perform a first AI operation. The first time period includes at least two non-contiguous time periods.

[0137] S502, The terminal device performs the first AI operation in at least two non-contiguous time periods.

[0138] In the embodiments of this application, the first AI operation may include one or more AI operations, and the first time period may include multiple time periods for performing AI operations. The embodiments of this application do not limit this.

[0139] It is understandable that when the first time period includes multiple time periods used to perform AI operations, these multiple time periods used to perform AI operations are not consecutive.

[0140] It is understandable that the first time period can also include a time period for performing AI operations, and this time period for performing AI operations is used to perform the first AI operation.

[0141] It is understood that the time period used to perform AI operations can be called an AI-time period, or an AI-DRX activation period, or an AI-DRX activation period, etc. The time period used to perform communication services can be called a communication-time period, or a communication period, or a communication-DRX activation period, or a communication-DRX activation period. This application does not limit the names of the time periods used to perform AI operations and the time periods used to perform communication services. For ease of explanation, the following examples will use "AI-time period" for the time period used to perform AI operations and "communication-time period" for the time period used to perform communication services.

[0142] It is understandable that the terminal device can perform AI operations only during the AI-time period and not perform AI operations outside of the AI-time period. In other words, the terminal device can perform AI operations in stages to reduce the power consumption of the terminal device.

[0143] To facilitate understanding of this application, the following description uses the example of a first time period that may include one or more AI-time periods. The first section will first introduce the one or more AI-time periods included in the first time period.

[0144] The first time period may include one or more AI-time periods, which may belong to one cycle, multiple cycles, or not belong to any cycle.

[0145] For example, Figure 6 is a schematic diagram of a first time period provided in an embodiment of this application.

[0146] As shown in Figure 6(1), the first time period includes AI-time period a1, AI-time period a2, and AI-time period a3. The terminal device can perform corresponding AI operations in AI-time period a1, AI-time period a2, and AI-time period a3 respectively. Among them, AI-time period a1, AI-time period a2, and AI-time period a3 belong to period a.

[0147] It can be understood that AI-time period a1, AI-time period a2, and AI-time period a3 repeat according to a predefined period 'a'. In other words, AI-time period a1, AI-time period a2, and AI-time period a3 are not independent time periods, but rather periodic time periods that follow a periodic pattern.

[0148] It is understood that there can be one or more cycles 'a', and the terminal device can perform the corresponding AI operation in each AI-time period included in multiple cycles 'a'.

[0149] Alternatively, as shown in Figure 6(2), the first time period includes AI-time period b1, AI-time period b2, and AI-time period b3, and the terminal device can perform corresponding AI operations in AI-time period b1, AI-time period b2, and AI-time period b3 respectively. Among them, AI-time period b1 belongs to period b1, AI-time period b2 belongs to period b2, and AI-time period b3 belongs to period b3.

[0150] It can be understood that AI-time period b1 repeats according to a predefined cycle b1, AI-time period b2 repeats according to a predefined cycle b2, and AI-time period b3 repeats according to a predefined cycle b3. In other words, AI-time periods b1, b2, and b3 are not independent time periods, but rather periodic time periods that follow a periodic pattern.

[0151] It can be understood that there can be one or more cycles b1, and the terminal device can execute the corresponding AI operation in each AI-time period included in multiple cycles b1. There can be one or more cycles b2, and the terminal device can execute the corresponding AI operation in each AI-time period included in multiple cycles b2. There can be one or more cycles b3, and the terminal device can execute the corresponding AI operation in each AI-time period included in multiple cycles b2.

[0152] It is understandable that the periods b1, b2 and b3 can be the same period or different periods. Figure 6(2) takes the period b1, b2 and b3 as different periods as an example.

[0153] Alternatively, as shown in Figure 6(3), the first time period includes AI-time period c1, AI-time period c2, and AI-time period c3, and the terminal device can perform corresponding AI operations in AI-time period c1, AI-time period c2, and AI-time period c3 respectively. Among them, AI-time period c1, AI-time period c2, and AI-time period c3 do not belong to any one cycle.

[0154] It is understandable that AI-time periods c1, c2, and c3 do not repeat according to any predefined period. In other words, AI-time periods c1, c2, and c3 are independent, non-periodic time periods that do not follow a periodic pattern.

[0155] Regardless of whether the multiple AI-time periods included in the first time period belong to one cycle, multiple cycles, or not any cycle, each of the multiple AI-time periods included in the first time period can have its own corresponding start time, duration, end time, and AI operation.

[0156] In other words, the start time, duration, end time, and AI operation of one AI-segment within the first time period can be the same as or different from one or more of the start time, duration, end time, and AI operation of other AI-segments within the first time period. Therefore, it can be understood that the start time, duration, and end time of the first time period can be determined based on the start time, duration, and end time of each AI-segment within the first time period.

[0157] As shown in Figure 6(1), the start time of AI-segment a1 is time 1, the end time is time 2, and the duration is duration 1. AI-segment a1 corresponds to AI operation 1. The start time of AI-segment a2 is time 3, the end time is time 4, and the duration is duration 2. AI-segment a2 corresponds to AI operation 2 and AI operation 3. The start time of AI-segment a3 is time 5, the end time is time 6, and the duration is duration 3. AI-segment a3 corresponds to AI operation 4. Among these, time 1, time 3, and time 5 can be different. Time 2, time 4, and time 6 can be different. Duration 1, duration 2, and duration 3 can be different. AI operation 1, AI operation 2, AI operation 3, and AI operation 4 can be different.

[0158] It is understood that an AI-time period can correspond to at least one AI operation, and an AI operation can also correspond to at least one AI-time period. This application embodiment does not limit this. The correspondence between AI-time periods and AI operations can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0159] In practice, the terminal device can determine the first time period using the following methods, which will be described below.

[0160] Scenario 1: The first time period and the third time period are unrelated.

[0161] The third time period may include one or more communication time periods. It is understood that when the third time period includes multiple communication time periods, these multiple communication time periods are not consecutive.

[0162] The third time period may include one or more communication time periods that belong to one cycle, or multiple cycles, or may not belong to any cycle. This application does not limit this.

[0163] It is understandable that the network device independently configures one or more AI-time periods for the terminal device. In other words, when configuring one or more AI-time periods for the terminal device, the network device does not consider the configuration of one or more communication-time periods.

[0164] In one possible implementation, as shown in FIG7a, the present application may perform the following steps to determine a first time period.

[0165] S701, the network device sends the first information to the terminal device.

[0166] Accordingly, the terminal device receives first information from the network device. This first information can be used to determine a first time period.

[0167] S702, the terminal device determines the first time period based on the first information.

[0168] In the embodiments of this application, the first information may be encapsulated or carried in a wake-up signal (WUS), downlink control information (DCI), MAC CE, RRC message, or other messages, or the first information may be the aforementioned WUS, DCI, MAC CE, or RRC message. The embodiments of this application do not limit this.

[0169] The first information may be sent by the network device when it determines that the terminal device needs to perform the first AI operation, or it may be sent by the network device when it receives a request from the terminal device. This application embodiment does not limit this. For example, as shown in FIG7a, before executing S701, this application may also perform the following steps.

[0170] S700, the terminal device sends a first request message to the network device.

[0171] Accordingly, the network device receives a first request message from the terminal device. This first request message can be used to request a first time period.

[0172] In the embodiments of this application, the first request information may be encapsulated or carried in the physical uplink control channel (PUCCH) or the physical uplink shared channel (PUSCH), or other messages, or the first request information may be the aforementioned PUCCH or PUSCH. The embodiments of this application do not limit this.

[0173] It is understood that the first request information may be sent by the terminal device when it determines that the terminal device needs to perform a first AI operation. Optionally, the first request information may include an identifier of the first AI operation.

[0174] The first information may include first instruction information and / or second instruction information. This application does not limit this. The following is a description.

[0175] 1) The first information includes first indication information. The first indication information can be used to determine one or more of the start time, end time, or duration of the first time period.

[0176] It is understood that the first indication information may indicate one or more of the start time, end time, or duration of all AI-time periods within the first time period. Optionally, the first indication information may directly indicate the start time of all AI-time periods within the first time period, or it may indirectly indicate the offset of the start time of all AI-time periods within the first time period. This application embodiment does not limit this.

[0177] For example, the first indication information can indicate the first time period by the start and end times of all AI-time periods in the first time period. As shown in (1) of Figure 7b, the first indication information can indicate time 1, time 2, time 3, time 4, time 5 and time 6, and the terminal device can determine AI-time period d1, AI-time period d2 and AI-time period d3 based on time 1, time 2, time 3, time 4, time 5 and time 6.

[0178] Alternatively, the first indication information can also indicate the first time period by the start time and duration of all AI-time periods in the first time period. As shown in (1) of Figure 7b, the first indication information can indicate time 1, duration 1, time 3, duration 2, time 5 and duration 3, and the terminal device can determine AI-time period d1, AI-time period d2 and AI-time period d3 based on time 1, duration 1, time 3, duration 2, time 5 and duration 3.

[0179] Alternatively, the first indication information can also indicate the first time period by the end time and duration of all AI-time periods in the first time period. As shown in (1) of Figure 7b, the first indication information can indicate duration 1, time 2, duration 2, time 4, duration 3 and time 6, and the terminal device can determine AI-time period d1, AI-time period d2 and AI-time period d3 based on duration 1, time 2, duration 2, time 4, duration 3 and time 6.

[0180] Alternatively, the first indication information can also indicate the first time period by the offset and duration of the start time of all AI-time periods in the first time period. As shown in (1) of Figure 7b, the first indication information can be indicated by the indication offset 1, duration 1, offset 2, duration 2, offset 3, and duration 3. Among them, offset 1 represents the time difference between the time when the terminal device receives the first indication information and the start time of AI-time period d1, offset 2 represents the time difference between the end time of AI-time period d1 and the start time of AI-time period d2, and offset 3 represents the time difference between the end time of AI-time period d2 and the start time of AI-time period d3. The terminal device can determine AI-time period d1, AI-time period d2, and AI-time period d3 based on offset 1, duration 1, offset 2, duration 2, offset 3, and duration 3.

[0181] Alternatively, the first indication information can also indicate the first time period by the offset and end time of the start time of all AI-time periods in the first time period. As shown in (1) of Figure 7b, the first indication information can be indicated by the offset 1, time 2, offset 3, time 4, offset 5, and time 6. Among them, offset 1 represents the time difference between the time when the terminal device receives the first indication information and the start time of AI-time period d1, offset 2 represents the time difference between the end time of AI-time period d1 and the start time of AI-time period d2, and offset 3 represents the time difference between the end time of AI-time period d2 and the start time of AI-time period d3. The terminal device can determine AI-time period d1, AI-time period d2, and AI-time period d3 based on offset 1, time 2, offset 3, time 4, offset 5, and time 6.

[0182] Optionally, the first indication information may also indicate the number of cycles corresponding to the first time period.

[0183] For example, as shown in (1) of Figure 6, when the AI-time period a1, AI-time period a2 and AI-time period a3 included in the first time period belong to one cycle (i.e. cycle a), the first indication information can indicate that the number of cycles corresponding to the first time period is 1.

[0184] Alternatively, as shown in Figure 6(2), when the AI-time period b1, AI-time period b2, and AI-time period b3 included in the first time period belong to three different cycles (i.e., cycle b1, cycle b2, and cycle b3), the first indication information can indicate that the number of cycles corresponding to the first time period is 3. Alternatively, as shown in Figure 7b(2), when the AI-time period e1, AI-time period e2, and AI-time period e3 included in the first time period belong to three identical cycles (i.e., cycle e), the first indication information can indicate that the number of cycles corresponding to the first time period is 3.

[0185] Alternatively, as shown in Figure 6(3), when the first time period including AI-time period c1, AI-time period c2, and AI-time period c3 does not belong to any cycle, the first indication information can indicate that the number of cycles corresponding to the first time period is 0. Alternatively, as shown in Figure 7b(1), when the AI-time period d1, AI-time period d2, and AI-time period d3 included in the first time period does not belong to any cycle, the first indication information can indicate that the number of cycles corresponding to the first time period is 0.

[0186] It is understood that if the AI-time period included in the first indication information belongs to one or more cycles (the multiple cycles can be the same cycle or different cycles), the first indication information can indicate one or more of the start time, end time or duration of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period.

[0187] The period identifier, also known as the period index, can be used to indicate the length of the period.

[0188] Optionally, the first indication information may also indicate one or more of the start time, end time, or duration of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle length corresponding to the first time period. This application embodiment does not limit this.

[0189] For example, the first indication information can indicate the first time period by the start and end times of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period. As shown in (2) of Figure 7b, the first indication information can indicate time 1, time 2, the number of cycles is 3, and the cycle identifier is cycle e. The terminal device can determine AI-time period e1, AI-time period e2, and AI-time period e3 based on time 1, time 2, the number of cycles is 3, and the cycle identifier is cycle e.

[0190] Alternatively, the first indication information can also indicate the first time period by the start time and duration of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period. As shown in (2) of Figure 7b, the first indication information can indicate time 1, duration 1, number of cycles 3, and cycle identifier as cycle e. The terminal device can determine AI-time period e1, AI-time period e2, and AI-time period e3 based on time 1, duration 1, number of cycles 3, and cycle identifier as cycle e.

[0191] Alternatively, the first indication information can also indicate the first time period by the end time and duration of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period. As shown in (2) of Figure 7b, the first indication information can indicate the AI-time period e1, AI-time period e2, and AI-time period e3 by indicating duration 1, time 2, number of cycles 3, and cycle identifier e. The terminal device can determine AI-time period e1, AI-time period e2, and AI-time period e3 based on duration 1, time 2, number of cycles 3, and cycle identifier e.

[0192] Alternatively, the first indication information can also indicate the first time period by the offset and duration of the start time of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period. As shown in (2) of Figure 7b, the first indication information can be indicated by the indication offset 1, duration 1, number of cycles of 3, and cycle identifier as cycle e. Among them, offset 1 represents the time difference between the time when the terminal device receives the first indication information and the start time of AI-time period e1. The terminal device can determine AI-time period e1, AI-time period e2, and AI-time period e3 based on offset 1, duration 1, number of cycles of 3, and cycle identifier as cycle e.

[0193] Alternatively, the first indication information can also indicate the first time period by the offset and end time of the start time of a portion of the AI-time period in the first time period, the number of cycles corresponding to the first time period, and the cycle identifier corresponding to the first time period. As shown in (2) of Figure 7b, the first indication information can be indicated by the indication offset 1, time 2, the number of cycles being 3, and the cycle identifier being cycle e. Among them, the offset 1 represents the time difference between the time when the terminal device receives the first indication information and the start time of AI-time period e1. The terminal device can determine AI-time period e1, AI-time period e2, and AI-time period e3 based on the offset 1, time 2, the number of cycles being 3, and the cycle identifier being cycle e.

[0194] It is understood that the first indication information may include multiple sub-information, which may be encapsulated or carried in different WUS, DCI, MAC CE, RRC messages, or other messages, or multiple sub-information may be the aforementioned WUS, DCI, MAC CE, or RRC messages. This application embodiment does not limit this.

[0195] When the first indication information indicates one or more of the start time, end time, or duration of all AI-time periods within the first time period, the multiple sub-information pieces can respectively indicate the start time, end time, and duration of all AI-time periods within the first time period. For example, sub-information encapsulated or carried in WUS indicates the start time of all AI-time periods within the first time period, sub-information encapsulated or carried in DCI indicates the end time of all AI-time periods within the first time period, and sub-information encapsulated or carried in RRC messages indicates the duration of all AI-time periods within the first time period.

[0196] Alternatively, some of the multiple sub-information pieces may indicate one or more of the start time, end time, or duration of a portion of the AI-time period within the first time period, and the remaining sub-information pieces may indicate one or more of the start time, end time, or duration of the remaining AI-time period within the first time period. For example, the first time period includes two AI-time periods, where the sub-information encapsulated or carried in WUS indicates one or more of the start time, end time, or duration of the first AI-time period within the first time period, and the sub-information encapsulated or carried in DCI indicates one or more of the start time, end time, or duration of the second AI-time period within the first time period.

[0197] When the first indication information indicates one or more of the start time, end time, or duration of a portion of the AI-segment within the first time period, the number of cycles corresponding to the first time period, and the cycle identifier (or cycle length) corresponding to the first time period, the multiple sub-information pieces can respectively indicate the start time, end time, duration, number of cycles, and cycle identifier (or cycle length) of a portion of the AI-segment within the first time period. For example, sub-information encapsulated or carried in WUS indicates the start time of a portion of the AI-segment within the first time period; sub-information encapsulated or carried in DCI indicates the end time of a portion of the AI-segment within the first time period; sub-information encapsulated or carried in RRC messages indicates the duration of a portion of the AI-segment within the first time period; and sub-information encapsulated or carried in other messages indicates the number of cycles and the cycle identifier (or cycle length) corresponding to the first time period.

[0198] 2) The first information includes the second indication information, wherein the second indication information can be used to indicate the first time period and the first reference signal.

[0199] It is understood that the first reference signal may include one or more reference signals. One or more AI-time periods in the first time period may correspond one-to-one with one or more reference signals in the first reference signal.

[0200] The reference signals can be channel state information reference signals (CSI-RS), synchronization signal and physical broadcast channel block (SS / PBCH Block), phase tracking reference singular (PT-RS), PDCCH-demodulation reference singular (PDCCH-DMRS), physical downlink shared channel-demodulation reference singular (PDSCH-DMRS), physical broadcast channel-demodulation reference singular (PBCH-DMRS), remote interference management reference singular (RIM-RS), positioning reference signal (PRS), etc., and this application embodiment does not limit the specific reference signals. The aforementioned SS / PBCH Block can also be referred to as SSB.

[0201] One or more AI-time periods in the first time period correspond one-to-one with one or more reference signals in the first reference signal. This can be understood as follows: if the terminal device receives a reference signal from the network device, it means that the terminal device can execute the AI ​​operation corresponding to the AI-time period corresponding to the reference signal.

[0202] For example, taking a first time period that includes an AI-time period and a first reference signal that includes a reference signal as an example, the terminal device can determine the start time of the first time period through the following steps.

[0203] Step a1: The network device sends a first reference signal to the terminal device.

[0204] Accordingly, the terminal device receives the first reference signal from the network device.

[0205] The embodiments of this application do not limit the transmission time of the first reference signal. For example, the first reference signal can be transmitted simultaneously with the second indication information, or it can be transmitted before or after the second indication information.

[0206] It can be understood that if the terminal device receives the first reference signal from the network device, it means that the terminal device can execute the first AI operation corresponding to the first time period corresponding to the first reference signal.

[0207] For example, the first reference signal is CSI-RS. If the terminal device receives CSI-RS from the network device, it means that the terminal device can perform AI operations related to channel quality measurement and time-frequency offset tracking, such as training an AI model for channel quality measurement and time-frequency offset tracking.

[0208] Alternatively, the first reference signal is the SSB. If the terminal device receives the SSB from the network device, it indicates that the terminal device can perform AI operations related to cell search and measurement, such as training an AI model for cell search and measurement.

[0209] Alternatively, the first reference signal is PT-RS. If the terminal device receives PT-RS from the network device, it means that the terminal device can perform AI operations related to phase tracking, such as training an AI model for phase tracking. This AI model can track phase fluctuations within a transmission cycle (e.g., a slot) based on the downlink PT-RS.

[0210] Alternatively, the first reference signal is PDCCH-DMRS. If the terminal device receives PDCCH-DMRS from the network device, it means that the terminal device can perform AI operations related to demodulating PDCCH, such as training an AI model for demodulating PDCCH.

[0211] Alternatively, the first reference signal is PDSCH-DMRS. If the terminal device receives PDSCH-DMRS from the network device, it means that the terminal device can perform AI operations related to PDSCH demodulation, such as training an AI model for PDSCH demodulation.

[0212] Alternatively, the first reference signal is PBCH-DMRS. If the terminal device receives PBCH-DMRS from the network device, it means that the terminal device can perform AI operations related to PBCH demodulation, such as training an AI model for PBCH demodulation.

[0213] Alternatively, the first reference signal is RIM-RS. If the terminal device receives RIM-RS from the network device, it means that the terminal device can perform AI operations related to remote interference management, such as training an AI model for remote interference management. This AI model can determine whether atmospheric ducting occurs and determine the number of uplink symbols causing interference.

[0214] Alternatively, the first reference signal is the PRS. If the terminal device receives the PRS from the network device, it indicates that the terminal device can perform location-related AI operations, such as training an AI model for location. For example, in downlink time difference of arrival (DL-TDOA) positioning, the AI ​​model can determine the terminal device's location information by measuring the downlink time difference between two sets of transmission reception points (TRPs) based on the downlink PRS. As another example, in multi-TRP-round trip time (multi-TRP-RTT) positioning, the AI ​​model can determine the terminal device's location information by measuring the round-trip time between two sets of TRPs using the uplink sounding reference signal (SRS) and the downlink PRS. Yet another example, in downlink angle-of-departure (DL-AoD) positioning, the AI ​​model can determine the terminal device's location information by measuring the DL-AoD of multiple TRPs based on the downlink PRS.

[0215] Step a2: The terminal device determines the start time of the first time period based on the time when the terminal device receives the first reference signal.

[0216] In this embodiment, the time difference between the time when the terminal device receives the first reference signal and the start time of the first time period can be referred to as the first offset. The first offset can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device; this embodiment does not limit this.

[0217] For example, as shown in (1) of Figure 7c, if the terminal device receives the first reference signal from the network device at time 1, the terminal device can determine the start time of the first time period as time 2, and the time difference between time 1 and time 2 is offset 1.

[0218] Alternatively, if the terminal device receives a first reference signal from the network device, it can send a first report corresponding to the first reference signal (e.g., a CSI report corresponding to CSI-RS) to the network device. The time difference between the time the terminal device sends the first report and the start time of the first time period can be called the second offset. The second offset can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device. This application does not limit this specific provision.

[0219] As shown in Figure 7c(2), the terminal device receives the first reference signal from the network device at time 1 and sends the first report corresponding to the first reference signal to the network device at time 2. Then the terminal device can determine that the start time of the first time period is time 3, and the time difference between time 3 and time 2 is offset 1.

[0220] It is understood that if the terminal device has configured the duration of the first time period, the terminal device can determine the end time of the first time period based on the duration of the first time period and the start time of the first time period determined in steps a1-a2 above. The duration of the first time period can be pre-configured, defined by a standard, or negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This embodiment of the application does not limit this.

[0221] If the terminal device does not configure the duration of the first time period, the terminal device can determine the end time of the first time period through the following steps.

[0222] Step b1: The network device sends the second information to the terminal device.

[0223] Accordingly, the terminal device receives second information from the network device. This second information can be used to indicate the first reference signal corresponding to the first time period within the second time period.

[0224] In the embodiments of this application, the second information may be encapsulated or carried in WUS, or DCI, or MAC CE, or RRC message, or other messages, or the second information may be the aforementioned WUS, DCI, MAC CE, or RRC message. The embodiments of this application do not limit this.

[0225] The embodiments of this application do not limit the time of transmission of the second information. For example, the second information can be transmitted simultaneously with the first reference signal, or it can be transmitted before or after the first reference signal.

[0226] The first time period corresponds to the first reference signal in the second time period. This can be understood as follows: the terminal device can initiate the correspondence (or binding relationship) between the first time period and the first reference signal at the start time of the second time period. After initiating the correspondence between the first time period and the first reference signal, if the terminal device receives the first reference signal from the network device, it will determine the start time of the first time period according to step a2 above. The terminal device can de-correspond to the first time period and the first reference signal at the end time of the second time period. After de-corresponding to the first time period and the first reference signal, if the terminal device receives the first reference signal from the network device, it will not determine the start time of the first time period according to step a2 above.

[0227] The start time of the second time period can be equal to or later than the time when the terminal device receives the second information. When the start time of the second time period is later than the time when the terminal device receives the second information, the time difference between the start time of the second time period and the time when the terminal device receives the second information can be a first preset offset. The second preset offset can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device; this embodiment does not limit this.

[0228] The duration of the second time period can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0229] Optionally, the second information may include third indication information. The third indication information is used to instruct the start of a first bond timer. The first bond timer corresponds to a first time period. The terminal device can initiate the correspondence between the first time period and the first reference signal at the start time of the first bond timer, and de-correspond to the first time period and the first reference signal at the end time of the first bond timer. In other words, the running time of the first bond timer is the second time period.

[0230] It is understood that the correspondence between the first time period and the first binding timer can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this. The duration of the first binding timer can also be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0231] Step b2: The terminal device determines the end time of the first time period based on the end time of the second time period.

[0232] In this embodiment, the end time of the second time period can be equal to or later than the end time of the first time period. When the end time of the second time period is later than the end time of the first time period, the time difference between the end time of the second time period and the end time of the first time period can be a second preset offset. This second preset offset can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device; this embodiment does not limit this.

[0233] For example, as shown in Figure 7c(3), if the terminal device receives the second information from the network device at time 1 and the first reference signal from the network device at time 2, then the terminal device can determine that the start time of the second time period is time 1, the start time of the first time period is time 3, the end time of the first time period is time 4, and the end time of the second time period is time 5. The time difference between time 3 and time 2 is offset 1, and the time difference between time 4 and time 5 is offset 2.

[0234] 3) The first information includes first indication information and second indication information. The first indication information can be used to determine one or more of the start time, end time, or duration of the first time period. The second indication information can be used to indicate the first time period and the first reference signal.

[0235] It is understood that if the first indication information can be used to determine the end time and / or duration of the first time period, the terminal device can determine the start time of the first time period according to steps a1-a2 above; or, if the first indication information can be used to determine the start time and / or duration of the first time period, the terminal device can determine the end time of the first time period according to steps b1-b2 above. Further details are omitted here.

[0236] Scenario 2: The first time period is related to the third time period.

[0237] The third time period may include one or more communication time periods. It is understood that when the third time period includes multiple communication time periods, these multiple communication time periods are not consecutive.

[0238] The third time period may include one or more communication time periods that belong to one cycle, or multiple cycles, or may not belong to any cycle. This application does not limit this.

[0239] It can be understood that the network device binds and configures one or more AI-time periods and one or more communication-time periods for the terminal device. In other words, when configuring one or more AI-time periods for the terminal device, the network device considers the configuration of one or more communication-time periods. Alternatively, the network device configures one or more communication-time periods for the terminal device, and the terminal device can determine one or more AI-time periods based on the one or more communication-time periods. Or, the terminal device can determine one or more AI-time periods based on one or more pre-configured or standard-defined communication-time periods.

[0240] In one possible implementation, as shown in FIG8a, the present application may perform the following steps to determine a first time period.

[0241] S801, the terminal device determines the first time period based on the third time period.

[0242] In the embodiments of this application, the third time period may be pre-configured, or it may be defined by a standard, or it may be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. The embodiments of this application do not limit this.

[0243] The first time period and the third time period may not overlap or may partially overlap.

[0244] It is understandable that all AI-time periods in the first time period can be non-overlapping with all communication-time periods in the third time period. For example, the first time period includes AI-time period 1 and AI-time period 2, and the third time period includes communication-time period 1 and communication-time period 2. AI-time period 1, AI-time period 2, communication-time period 1, and communication-time period 2 do not overlap.

[0245] Alternatively, a portion of the AI-time period in the first time period may partially overlap with a portion of the communication-time period in the third time period, while the remaining portion of the AI-time period in the first time period may not overlap with the remaining portion of the communication-time period in the third time period. For example, the first time period includes AI-time period 1 and AI-time period 2, and the third time period includes communication-time period 1 and communication-time period 2. AI-time period 1, communication-time period 1, and communication-time period 2 do not overlap, while AI-time period 2 and communication-time period 2 partially overlap.

[0246] Alternatively, all AI-time periods in the first time period may partially overlap with all communication-time periods in the third time period. For example, the first time period includes AI-time period 1 and AI-time period 2, and the third time period includes communication-time period 1 and communication-time period 2, with AI-time period 1 and communication-time period 1 partially overlapping, and AI-time period 2 and communication-time period 2 partially overlapping.

[0247] It is understood that the non-overlapping or partial overlap between the first and third time periods can be pre-configured, or defined by a standard, or negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this. For example, as shown in FIG8a, before executing S801, this application may also perform the following steps.

[0248] S800, the network device sends third information to the terminal device.

[0249] Accordingly, the terminal device receives third information from the network device. This third information indicates that the first time period and the third time period do not overlap or only partially overlap.

[0250] In the embodiments of this application, the third information may be encapsulated or carried in WUS, or DCI, or MAC CE, or RRC message, or other messages. Alternatively, the third information may be WUS, DCI, MAC CE, or RRC message. The embodiments of this application do not limit this.

[0251] It is understandable that the third information can indicate that all communication-time periods in the third time period do not overlap or partially overlap with all AI-time periods in the first time period, or it can indicate that some communication-time periods in the third time period do not overlap or partially overlap with some AI-time periods in the first time period.

[0252] The third information is used to indicate whether the first and third time periods do not overlap or partially overlap. For ease of explanation, the following example uses the case where all AI-time periods in the first time period do not overlap with all communication-time periods in the third time period, or where all AI-time periods in the first time period partially overlap with all communication-time periods in the third time period.

[0253] For example, the first time can be defined as the start time of an AI-segment (e.g., AI-segment 1 or AI-segment 2) within the first time period, the second time as the end time of a communication-segment (e.g., communication-segment 1 or communication-segment 2) within the third time period, the third time as the end time of an AI-segment (e.g., AI-segment 1 or AI-segment 2) within the first time period, and the fourth time as the start time of a communication-segment (e.g., communication-segment 1 or communication-segment 2) within the third time period.

[0254] When the third information is used to indicate that the first time period and the third time period do not overlap, the third information can be used to indicate that the first time, the second time, the third time and the fourth time satisfy one or more of the following relationships, which will be introduced below.

[0255] 1) The third information can be used to indicate that the first time is equal to the second time. For example, as shown in (1) of Figure 8b, communication-time period 1 is the first communication-time period configured by the terminal device, and the start time of communication-time period 1 can be equal to the end time of communication-time period 1. Communication-time period 2 is the second communication-time period configured by the terminal device, and the start time of communication-time period 2 can be equal to the end time of communication-time period 2.

[0256] It is understandable that the end time of AI-time period 1 can be earlier than or equal to the start time of communication-time period 2. Figure 8b (1) takes the example where the end time of AI-time period 1 is equal to the start time of communication-time period 2.

[0257] It is understandable that the terminal device can perform AI operations after the first communication time period and before the second communication time period, with no time difference between the start time of the AI ​​operation and the end time of the first communication time period, and no time difference between the end time of the AI ​​operation and the start time of the second communication time period. Similarly, the terminal device can also perform AI operations after the second communication time period and before the third communication time period, with no time difference between the start time of the AI ​​operation and the end time of the second communication time period, and no time difference between the end time of the AI ​​operation and the start time of the third communication time period.

[0258] 2) The third information can be used to indicate that the third time is equal to the fourth time. For example, as shown in (2) of Figure 8b, communication-time period 1 is the first communication-time period configured by the terminal device, and the end time of AI-time period 1 can be equal to the start time of communication-time period 1. Communication-time period 2 is the second communication-time period configured by the terminal device, and the end time of AI-time period 2 can be equal to the start time of communication-time period 2.

[0259] It is understandable that the start time of AI-time period 2 can be later than or equal to the end time of communication-time period 1. Figure 8b (2) takes the example where the start time of AI-time period 2 is equal to the end time of communication-time period 1.

[0260] It is understandable that the terminal device can perform AI operations before the first communication-time period, and the time when the AI ​​operation ends is not different from the start time of the first communication-time period. Similarly, the terminal device can also perform AI operations after the first communication-time period and before the second communication-time period, and the time when the AI ​​operation starts is not different from the end time of the first communication-time period, and the time when the AI ​​operation ends is not different from the start time of the second communication-time period.

[0261] 3) The third information can be used to indicate that the first time is later than the second time, and the time difference between the first time and the second time can be a third offset. The third offset can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device. This application embodiment does not limit this. For example, as shown in (3) of Figure 8b, communication-time period 1 is the first communication-time period configured by the terminal device. The start time of AI-time period 1 can be later than the end time of communication-time period 1, and the time difference between the start time of AI-time period 1 and the end time of communication-time period 1 can be offset a1. Communication-time period 2 is the second communication-time period configured by the terminal device. The start time of AI-time period 2 is later than the end time of communication-time period 2, and the time difference between the start time of AI-time period 2 and the end time of communication-time period 2 can be offset a2. It can be understood that offset a1 and offset a2 can be the same or different.

[0262] It is understandable that the end time of AI-time period 1 can be earlier than or equal to the start time of communication-time period 2. Figure 8b (3) takes the example that the end time of AI-time period 1 is earlier than the start time of communication-time period 2.

[0263] It is understood that the duration of AI-Time Segment 1 and AI-Time Segment 2 can be pre-configured, or defined by a standard, or negotiated between the network device and the terminal device, such as configured by the network device to the terminal device. This embodiment of the application does not limit this. That is, after determining the start time of AI-Time Segment 1 based on the end time of Communication-Time Segment 1 and the offset a1, the terminal device can determine the end time of AI-Time Segment 1 based on its start time and duration. Similarly, after determining the start time of AI-Time Segment 2 based on the end time of Communication-Time Segment 2 and the offset a2, the terminal device can determine the end time of AI-Time Segment 2 based on its start time and duration.

[0264] It is understandable that the terminal device can perform AI operations after the first communication period and before the second communication period, with a time difference between the start time of the AI ​​operation and the end time of the first communication period, and a possible time difference between the end time of the AI ​​operation and the start time of the second communication period. Similarly, the terminal device can also perform AI operations after the second communication period and before the third communication period, with a time difference between the start time of the AI ​​operation and the end time of the second communication period, and a possible time difference between the end time of the AI ​​operation and the start time of the third communication period.

[0265] 4) The third information can be used to indicate that the third time is earlier than the fourth time, and the time difference between the third time and the fourth time is the second offset. The second offset can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device. This embodiment does not limit this. For example, as shown in (4) of Figure 8b, communication-time period 1 is the first communication-time period configured by the terminal device. The end time of AI-time period 1 can be earlier than the start time of communication-time period 1, and the time difference between the end time of AI-time period 1 and the start time of communication-time period 1 can be offset b1. Communication-time period 2 is the second communication-time period configured by the terminal device. The end time of AI-time period 2 can be earlier than the start time of communication-time period 2, and the time difference between the end time of AI-time period 2 and the start time of communication-time period 2 can be offset b2. It can be understood that offset a1 and offset a2 can be the same or different.

[0266] It is understandable that the start time of AI-time period 2 can be later than or equal to the end time of communication-time period 1. Figure 8b (4) takes the example where the start time of AI-time period 2 is later than the end time of communication-time period 1.

[0267] It is understood that the duration of AI-Time Segment 1 and AI-Time Segment 2 can be pre-configured, or defined by a standard, or negotiated between the network device and the terminal device, such as configured by the network device to the terminal device. This embodiment of the application does not limit this. That is, after determining the end time of AI-Time Segment 1 based on the start time and offset b1 of Communication-Time Segment 1, the terminal device can determine the start time of AI-Time Segment 1 based on its end time and duration. Similarly, after determining the end time of AI-Time Segment 2 based on the start time and offset b2 of Communication-Time Segment 2, the terminal device can determine the start time of AI-Time Segment 2 based on its end time and duration.

[0268] It is understandable that the terminal device can perform AI operations before the first communication-time period, and the time when the AI ​​operation ends is different from the start time of the first communication-time period. Similarly, the terminal device can also perform AI operations after the first communication-time period and before the second communication-time period, and the time when the AI ​​operation starts may or may not be different from the end time of the first communication-time period, and the time when the AI ​​operation ends is different from the start time of the second communication-time period.

[0269] When the third information is used to indicate that the first time period and the third time period partially overlap, the third information can be used to indicate that the first time, the second time, the third time and the fourth time satisfy one or more of the following relationships, which will be introduced below.

[0270] 1) The third information can be used to indicate that the first time is earlier than the second time, and the terminal device does not perform communication services during the time between the first time and the second time. For example, as shown in (5) of Figure 8b, communication-time period 1 is the first communication-time period configured for the terminal device. The start time of communication-time period 1 can be earlier than the end time of communication-time period 1, and the terminal device may not perform communication services during the time between the start time and the end time of communication-time period 1. Communication-time period 2 is the second communication-time period configured for the terminal device. The start time of communication-time period 2 can be earlier than the end time of communication-time period 2, and the terminal device may not perform communication services during the time between the start time and the end time of communication-time period 2.

[0271] It is understandable that the time overlap between AI-time period 1 and communication-time period 1 is actually the time during which the terminal device does not perform communication services in communication-time period 1, and the time overlap between AI-time period 2 and communication-time period 2 is actually the time during which the terminal device does not perform communication services in communication-time period 2.

[0272] It is understandable that the end time of AI-time period 1 can be earlier than or equal to the start time of communication-time period 2. Figure 8b (5) takes the example where the end time of AI-time period 1 is equal to the start time of communication-time period 2.

[0273] It is understood that the duration of AI-Time Period 1 and AI-Time Period 2 can be pre-configured, or defined by a standard, or negotiated between the network device and the terminal device, such as configured by the network device to the terminal device. This embodiment of the application does not limit this. That is, after determining the start time of AI-Time Period 1 based on the time during which the terminal device does not perform communication services in Communication-Time Period 1, the terminal device can determine the end time of AI-Time Period 1 based on its start time and duration. Similarly, after determining the start time of AI-Time Period 2 based on the time during which the terminal device does not perform communication services in Communication-Time Period 2, the terminal device can determine the end time of AI-Time Period 2 based on its start time and duration.

[0274] It is understandable that the terminal device can perform AI operations after the first communication time period and before the second communication time period, and the start time of the AI ​​operation can be the time when the communication service ends within the first communication time period. Similarly, the terminal device can also perform AI operations after the second communication time period and before the third communication time period, and the start time of the AI ​​operation can be the time when the communication service ends within the second communication time period.

[0275] 2) The third information can be used to indicate that the third time is later than the fourth time, and the terminal device does not perform communication services during the time between the fourth time and the third time. For example, as shown in (6) of Figure 8b, communication-time period 1 is the first communication-time period configured by the terminal device. The end time of AI-time period 1 can be later than the start time of communication-time period 1, and the terminal device may not perform communication services during the time between the start time of communication-time period 1 and the end time of AI-time period 1. Communication-time period 2 is the second communication-time period configured by the terminal device. The end time of AI-time period 2 can be later than the start time of communication-time period 2, and the terminal device may not perform communication services during the time between the start time of communication-time period 2 and the end time of AI-time period 2.

[0276] It is understandable that the time overlap between AI-time period 1 and communication-time period 1 is actually the time during which the terminal device does not perform communication services in communication-time period 1, and the time overlap between AI-time period 2 and communication-time period 2 is actually the time during which the terminal device does not perform communication services in communication-time period 2.

[0277] It is understandable that the start time of AI-time period 2 can be later than or equal to the end time of communication-time period 1. Figure 8b (6) takes the example where the start time of AI-time period 1 is equal to the end time of communication-time period 2.

[0278] It is understood that the duration of AI-Time Period 1 and AI-Time Period 2 can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This embodiment of the application does not limit this. That is, after the terminal device determines the end time of AI-Time Period 1 based on the time during which the terminal device does not perform communication services in Communication-Time Period 1, it can determine the start time of AI-Time Period 1 based on the end time of AI-Time Period 1 and the duration of AI-Time Period 1; after the terminal device determines the end time of AI-Time Period 2 based on the time during which the terminal device does not perform communication services in Communication-Time Period 1, it can determine the start time of AI-Time Period 2 based on the end time of AI-Time Period 2 and the duration of AI-Time Period 2.

[0279] It is understandable that the terminal device can perform AI operations before the first communication time period, and the time when the AI ​​operation ends can be the time when communication services begin within the first communication time period. Similarly, the terminal device can also perform AI operations after the first communication time period and before the second communication time period, and the time when the AI ​​operation begins can be the time when communication services begin within the second communication time period.

[0280] It is understandable that, whether at least one AI-time period and at least one communication-time period do not overlap as shown in (1), (2), (3) and (4) of Figure 8b, or at least one AI-time period and at least one communication-time period partially overlap as shown in (5) and (6) of Figure 8b, the execution of AI operations by the terminal device and the execution of communication services by the terminal device do not affect each other, thereby ensuring the performance of AI operations and communication services as much as possible in the scenario where AI operations and communication coexist.

[0281] In one possible implementation, before determining the first time period based on the third time period, the terminal device may activate the relationship between the first time period and the third time period (i.e., the first time period and the third time period do not overlap or partially overlap), so that the terminal device can determine the first time period based on the third time period.

[0282] Specifically, if the first AI operation is triggered by the terminal device, the terminal device and the network device can activate the relationship between the first time period and the third time period by executing steps c1-c2.

[0283] Step c1: The terminal device sends a second request message to the network device.

[0284] Accordingly, the network device receives a second request message from the terminal device. This second request message can be used to request activation of the relationship between the first time period and the third time period. The second request message can be encapsulated or carried in a PUCCH or PUSCH, or other messages, or the second request message can be the aforementioned PUCCH or PUSCH; this embodiment of the application does not limit this.

[0285] Step c2: The network device sends the fourth instruction information to the terminal device.

[0286] Accordingly, the terminal device receives fourth indication information from the network device. This fourth indication information can be used to indicate the relationship between the activation of the first time period and the third time period. The fourth indication information can encapsulate or carry a WUS, DCI, MAC CE, RRC message, or other message; alternatively, the fourth indication information may be any of the aforementioned WUS, DCI, MAC CE, or RRC messages. This application embodiment does not limit this specific to any particular message.

[0287] If the first AI operation is triggered by a network device, the terminal device and the network device can activate the relationship between the first time period and the third time period by executing step d1.

[0288] Step d1: The network device sends the fifth instruction information to the terminal device.

[0289] Accordingly, the terminal device receives fifth indication information from the network device. This fifth indication information can be used to indicate the relationship between the activation of the first time period and the third time period. The fifth indication information can encapsulate or carry a WUS, DCI, MAC CE, RRC message, or other message; alternatively, the fifth indication information may be any of the aforementioned WUS, DCI, MAC CE, or RRC messages. This application embodiment does not limit this specific to any particular message.

[0290] In one possible implementation, regardless of whether the terminal device determines the first time period in the manner described in Case 1 or Case 2, after the terminal device determines the first time period, the terminal device or the network device can update the first time period according to the needs of the terminal device when performing the first AI operation, thereby ensuring the performance of the AI ​​operation.

[0291] Alternatively, if the first time period is configured by the network device for the terminal device, such as the independent configuration in Case 1 above, or the binding configuration in Case 2 above, the network device can configure the first time period for the terminal device according to the needs of the terminal device when performing the first AI operation, thereby ensuring the performance of the AI ​​operation.

[0292] Specifically, the terminal device and the network device can update the first time period by executing step e1 or e2.

[0293] Step e1: The terminal device sends the fourth information to the network device.

[0294] Accordingly, the network device receives fourth information from the terminal device. This fourth information is used to request updates to the first time period and / or the third time period. The fourth information may be encapsulated or carried in a PUCCH or PUSCH, or other messages, or the fourth information may be the aforementioned PUCCH or PUSCH; this embodiment of the application does not limit this.

[0295] Step e2: The network device sends the fifth information to the terminal device.

[0296] Accordingly, the terminal device receives fifth information from the network device. This fifth information is used to indicate updates to the first time period and / or the third time period. The fifth information may be encapsulated or carried in a WUS, DCI, MAC CE, RRC message, or other message, or the fifth information may be one of the aforementioned WUS, DCI, MAC CE, or RRC messages; this application embodiment does not limit this.

[0297] It is understandable that the fourth piece of information can be sent by the terminal device under the condition that the first condition is met, and the fifth piece of information can also be sent by the network device under the condition that the first condition is met. That is, the first condition is the condition that determines the first time period that needs to be updated.

[0298] The first condition includes one or more of the following: the first time difference is less than or equal to the second time difference; the first time difference is less than or equal to the second time difference; and the priority of the first AI operation is greater than or equal to the first priority threshold; the target performance of the first AI operation is greater than or equal to the first target performance; and the end time of the first time period is later than the time when the terminal device finishes executing the first AI operation. This will be described below.

[0299] 1) The first time difference is less than or equal to the second time difference. Wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the first time period ends, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

[0300] It is understandable that if the first time difference is less than or equal to the second time difference, the first time period needs to be updated. Alternatively, if the first time difference is greater than the second time difference, the first time period does not need to be updated.

[0301] For example, as shown in (1) of Figure 8c, the time difference between the time when the terminal device starts executing AI operation 1 and the end time of AI-time period 1 is time difference 1, and the time difference between the time when the terminal device starts executing AI operation 1 and the time when it ends executing AI operation 1 is time difference 2. If time difference 1 is less than time difference 2, it means that the terminal device cannot complete AI operation 1 within AI-time period 1. Therefore, in order to meet the requirements of AI operation 1, it is determined that AI-time period 1 needs to be updated, that is, AI-time period 1 is increased, which is also the communication-time period 2 is decreased.

[0302] 2) The first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to the first priority threshold. The first priority threshold can be pre-configured, standard-defined, or negotiated between the network device and the terminal device, such as being configured by the network device for the terminal device. This embodiment does not limit this specific requirement.

[0303] It is understandable that if the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to the first priority threshold, then the first time period is determined to need updating. Optionally, if the first time difference is less than or equal to the second time difference, but the priority of the first AI operation is less than the first priority threshold, then the first time period is determined not to need updating. If the first time difference is greater than the second time difference, regardless of whether the priority of the first AI operation is greater than or equal to the first priority threshold, then the first time period is determined not to need updating.

[0304] For example, as shown in Figure 8c(1), if time difference 1 is less than time difference 2, and the priority of AI operation 1 is greater than or equal to priority 1, it means that the terminal device cannot complete the higher-priority AI operation 1 within AI-time period 1. Since AI operation 1 has a higher priority, the terminal device needs to meet the requirements of AI operation 1, and thus the terminal device determines that AI-time period 1 needs to be updated, i.e., AI-time period 1 is increased. If time difference 1 is less than time difference 2, but the priority of AI operation 1 is less than priority 1, it means that the terminal device cannot complete the lower-priority AI operation 1 within AI-time period 1. Since AI operation 1 has a lower priority, the terminal device does not need to meet the requirements of AI operation 1, and thus the terminal device determines that AI-time period 1 does not need to be updated.

[0305] 3) The target performance of the first AI operation is greater than or equal to the first target performance. The first target performance may be pre-configured, or it may be defined by a standard, or it may be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0306] It is understandable that if the target performance of the first AI operation is greater than or equal to the first target performance, then it is determined that an update is needed for the first time period. Optionally, if the target performance of the first AI operation is less than the first target performance, then it is determined that an update is not needed for the first time period.

[0307] Alternatively, if the first time difference is less than or equal to the second time difference, and the target performance of the first AI operation is greater than or equal to the first target performance, then the first time period needs to be updated. Optionally, if the first time difference is less than or equal to the second time difference, and the target performance of the first AI operation is less than the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is greater than the second time difference, and the target performance of the first AI operation is greater than or equal to the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is greater than the second time difference, and the target performance of the first AI operation is less than the first target performance, then the first time period does not need to be updated.

[0308] Alternatively, if the first time difference is less than or equal to the second time difference, the priority of the first AI operation is greater than or equal to the first priority threshold, and the target performance of the first AI operation is greater than or equal to the first target performance, then the first time period needs to be updated. Optionally, if the first time difference is less than or equal to the second time difference, the priority of the first AI operation is greater than or equal to the first priority threshold, and the target performance of the first AI operation is less than the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is less than or equal to the second time difference, the priority of the first AI operation is less than the first priority threshold, and the target performance of the first AI operation is less than the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is less than or equal to the second time difference, the priority of the first AI operation is less than the first priority threshold, and the target performance of the first AI operation is greater than or equal to the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is greater than the second time difference, the priority of the first AI operation is greater than or equal to the first priority threshold, and the target performance of the first AI operation is greater than or equal to the first target performance, then the first time period does not need to be updated. Optionally, if the first time difference is greater than the second time difference, the priority of the first AI operation is greater than or equal to the first priority threshold, and the target performance of the first AI operation is less than the first target performance, then it is determined that the first time period does not need to be updated.

[0309] For example, if the target performance of AI operation 1 is greater than or equal to target performance 1, it means that the time required for the terminal device to execute AI operation 1 is relatively long, and the terminal device cannot complete AI operation 1 within AI-time period 1. Therefore, in order to meet the requirements of AI operation 1, the terminal device determines that AI-time period 1 needs to be updated, that is, the AI-time period 1 is increased. If the target performance of AI operation 1 is less than target performance 1, it means that the time required for the terminal device to execute AI operation 1 is relatively short, and the terminal device can complete AI operation 1 within AI-time period 1. Therefore, the terminal device determines that AI-time period 1 does not need to be updated.

[0310] 4) The end time of the first time period is later than the time when the terminal device finishes executing the first AI operation.

[0311] For example, as shown in (2) of Figure 8c, if the end time of AI-time period 1 is later than the time when the terminal device finishes executing AI operation 1, it means that the terminal device does not execute AI operation 1 for part of the time within AI-time period 1. Therefore, in order to improve the utilization of resources, the terminal device can use the part of the time within AI-time period 1 when it does not execute AI operation 1 to perform communication services. The terminal device determines that AI-time period 1 needs to be updated, that is, the AI-time period 1 is reduced.

[0312] It is understandable that the fourth or fifth information can indicate an update to the first time period, which can be understood as a direct indication. For example, when it is necessary to increase or decrease the first time period, the fourth information can indicate an increase or decrease in one or more of the following: the DRX activation period timer, the DRX deactivation timer, the DRX hybrid automatic repeat request round-trip time timer, the DRX retransmission timer, the DRX long-period timer, or the DRX short-period timer.

[0313] For example, as shown in (1) of Figure 8c, the fourth or fifth information can directly indicate the increase of AI-time period 1, wherein the end time of the increased AI-time period 1 is later than the end time of the AI-time period 1 before the increase, and the time difference between the end time of the increased AI-time period 1 and the end time of the AI-time period 1 before the increase is the offset 1.

[0314] As shown in Figure 8c (2), the fourth or fifth information can directly indicate the reduction of AI-time period 1, wherein the end time of the reduced AI-time period 1 is earlier than the end time of the AI-time period 1 before reduction, and the time difference between the end time of the reduced AI-time period 1 and the end time of the AI-time period 1 before reduction is the bias 2.

[0315] Alternatively, the fourth or fifth information can indicate an update to the third time period, which can be understood as an indirect indication. For example, when it is necessary to increase or decrease the first time period, the fourth or fifth information can indicate to decrease or increase one or more of the following time periods: the DRX activation timer, the DRX deactivation timer, the DRX hybrid automatic repeat request round-trip timer, the DRX retransmission timer, the DRX long-period timer, or the DRX short-period timer.

[0316] For example, as shown in (1) of Figure 8c, the fourth or fifth information can indirectly indicate to reduce the communication-time period 2 to increase the AI-time period 1, wherein the start time of the reduced communication-time period 2 is later than the start time of the communication-time period 2 before reduction, and the time difference between the start time of the reduced communication-time period 2 and the start time of the communication-time period 2 before reduction is the bias 1.

[0317] As shown in (2) of Figure 8c, the fourth or fifth information can indirectly indicate to increase the communication-time period 2 to decrease the AI-time period 1, wherein the start time of the increased communication-time period 2 is earlier than the start time of the communication-time period 2 before the increase, and the time difference between the start time of the increased communication-time period 2 and the start time of the communication-time period 2 before the increase is the bias 2.

[0318] Alternatively, the fourth or fifth information may indicate the updating of the first and third time periods. For example, when it is necessary to increase or decrease the first time period, the fourth or fifth information may indicate increasing or decreasing one or more of the following time periods: the DRX activation period timer, the DRX deactivation timer, the DRX hybrid auto repeat request round-trip timer, the DRX retransmission timer, the DRX long-period timer, or the DRX short-period timer; and decreasing or increasing one or more of the following time periods: the DRX activation period timer, the DRX deactivation timer, the DRX hybrid auto repeat request round-trip timer, the DRX retransmission timer, the DRX long-period timer, or the DRX short-period timer.

[0319] For example, as shown in Figure 8c(1), the fourth or fifth information can indicate a reduction in communication-time period 2 and an increase in AI-time period 1. The start time of the reduced communication-time period 2 is later than the start time of the original communication-time period 2, and the end time of the increased AI-time period 1 is later than the end time of the original AI-time period 1. The time difference between the start time of the reduced communication-time period 2 and the start time of the original communication-time period 2 is offset 1a. The time difference between the end time of the increased AI-time period 1 and the end time of the original AI-time period 1 is offset 1b. The sum of offset 1a and offset 1b is offset 1.

[0320] As shown in Figure 8c(2), the fourth information can also indirectly indicate increasing the communication-time period 2 and decreasing the AI-time period 1. The start time of the increased communication-time period 2 is earlier than the start time of the original communication-time period 2, and the end time of the decreased AI-time period 1 is earlier than the end time of the original AI-time period 1. The time difference between the start time of the increased communication-time period 2 and the start time of the original communication-time period 2 is offset 2a. The time difference between the end time of the decreased AI-time period 1 and the end time of the original AI-time period 1 is offset 2b. The sum of offset 2a and offset 2b is offset 2.

[0321] In one possible implementation, regardless of whether the terminal device determines the first time period using either the method described in Case 1 or Case 2, it can determine whether the first time period is active after determining it and before performing the first AI operation within that time period. If the terminal device determines that the first time period is active, it can perform the first AI operation during that time period. If the terminal device determines that the first time period is not active, it cannot perform the first AI operation during that time period.

[0322] Specifically, if the first AI operation is triggered by the terminal device, the terminal device and the network device can activate the first time period corresponding to the first AI operation by executing steps f1-f2.

[0323] Step f1: The terminal device sends a third request message to the network device.

[0324] Accordingly, the network device receives a third request from the terminal device. This third request can be used to request activation of the first time period.

[0325] In this embodiment, the third request information may be encapsulated or carried in PUCCH or PUSCH, or other messages, or the third request information may be the aforementioned PUCCH or PUSCH; this embodiment does not limit this. The third request information may include an identifier of the first time period.

[0326] In step f2, the network device sends the sixth information to the terminal device.

[0327] Accordingly, the terminal device receives a sixth piece of information from the network device. This sixth piece of information can be used to indicate the activation of the first time period.

[0328] In this embodiment, the sixth information may be encapsulated or carried in WUS, DCI, MAC CE, RRC message, or other messages, or the sixth information may be the aforementioned WUS, DCI, MAC CE, or RRC message. This embodiment does not limit this. The sixth information may include an identifier of the first time period.

[0329] If the first AI operation is triggered by a network device, step f1 can be skipped, meaning that step f1 can be omitted.

[0330] In one possible implementation, regardless of whether the terminal device determines the first time period in the manner described in Case 1 or Case 2, after the terminal device determines the first time period, if the first time period belongs to one or more cycles, the terminal device or network device can update the duration of one or more cycles to which the first time period belongs, thereby dynamically adjusting resources and improving resource utilization.

[0331] Specifically, if the first AI operation is triggered by the terminal device, the terminal device and the network device can update the duration of one or more cycles to which the first time period belongs by executing steps g1-g2.

[0332] Step g1: The terminal device sends a fourth request message to the network device.

[0333] Accordingly, the network device receives a fourth request from the terminal device. This fourth request can be used to request an update on the duration of one or more periods to which the first time period belongs.

[0334] In this embodiment, the fourth request information may be encapsulated or carried in PUCCH or PUSCH, or other messages, or the third request information may be the aforementioned PUCCH or PUSCH; this embodiment does not limit this. The fourth request information may include one or more period identifiers corresponding to the first time period.

[0335] Step g2: The network device sends the fifth instruction information to the terminal device.

[0336] Accordingly, the terminal device receives a fifth instruction from the network device. This fifth instruction may update the duration of one or more periods to which the first time period belongs.

[0337] In this application example, the fifth indication information may be encapsulated or carried in WUS, DCI, MAC CE, RRC message, or other messages, or the fifth indication information may be the aforementioned WUS, DCI, MAC CE, or RRC message. This application embodiment does not limit this. The fifth indication information may include one or more period identifiers and durations corresponding to the first time period.

[0338] If the first AI operation is triggered by a network device, step g2 can be skipped, meaning step g2 can be omitted.

[0339] In one possible implementation, regardless of whether the terminal device determines the first time period in the manner described in Case 1 or Case 2, after the terminal device determines the first time period, the terminal device can start the first timer corresponding to the first time period and perform the first AI operation within the running time of the first timer if the first time difference is less than or equal to the second time difference.

[0340] The first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the first time period ends, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

[0341] The first timer can also be called a deactivation timer, and the name of the first timer is not limited in this application embodiment. The duration of the first timer can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0342] It can be understood that when the terminal device runs the first timer, it is equivalent to extending the first time period, and the running time of the first timer is the extended time.

[0343] For example, as shown in Figure 9a(1), the time difference between the time when the terminal device starts executing AI operation 1 and the end time of AI-segment 1 is time difference 1, and the time difference between the time when the terminal device starts executing AI operation 1 and the time when it ends executing AI operation 1 is time difference 2. If time difference 1 is less than time difference 2, it means that the terminal device cannot complete AI operation 1 within AI-segment 1. Therefore, in order to meet the requirements of AI operation 1, the terminal device starts the first timer 1 corresponding to AI-segment 1. The end time of the first timer 1 can be later than or equal to the end time of executing AI operation 1. Figure 9a(1) takes the example where the end time of the first timer 1 is later than the end time of executing AI operation 1.

[0344] As shown in Figure 9a(2), after the terminal device starts the first timer 1 corresponding to AI-time period 1, AI-time period 1 increases, and duration 1 is greater than duration 2. The terminal device can complete AI operation 1 within AI-time period 1.

[0345] If the first AI operation is triggered by the terminal device, the terminal device can start the first timer through the following steps h1-h2.

[0346] In step h1, if the first time difference is less than or equal to the second time difference, the terminal device sends a fifth request message to the network device.

[0347] Accordingly, the network device receives a fifth request from the terminal device. This fifth request can be used to request the activation of a first timer corresponding to the first time period.

[0348] In this embodiment, the fifth request information may be encapsulated or carried in PUCCH or PUSCH, or other messages, or the fifth request information may be the aforementioned PUCCH or PUSCH; this embodiment does not limit this. The fifth request information may include an identifier of the first time period and / or an identifier of the first timer.

[0349] In step h2, the network device sends the sixth instruction information to the terminal device.

[0350] Accordingly, the terminal device receives a sixth instruction from the network device. This sixth instruction can be used to instruct the activation of a first timer corresponding to the first time period.

[0351] In this embodiment, the sixth indication information may be encapsulated or carried in a WUS, DCI, MAC CE, RRC message, or other message, or the sixth indication information may be the aforementioned WUS, DCI, MAC CE, or RRC message. This embodiment does not limit this. The sixth indication information may include the identifier of the first time period and / or the identifier of the first timer.

[0352] If the first AI operation is triggered by a network device, step h1 can be skipped, meaning step h1 can be omitted.

[0353] In one possible implementation, the first AI operation may include an AI operation, which may include multiple sub-AI operations (e.g., a first sub-operation and a second sub-operation). The terminal device may start a second timer corresponding to the first sub-operation when the terminal device finishes executing the first sub-AI operation, enter a sleep state or execute communication services during the running time of the second timer, and start executing the second sub-AI operation when the second timer ends.

[0354] The second timer can also be called a pause timer, and the name of the second timer is not limited in this application embodiment. The duration of the second timer can be pre-configured, or it can be defined by a standard, or it can be negotiated between the network device and the terminal device, such as being configured by the network device to the terminal device. This application embodiment does not limit this.

[0355] For example, as shown in Figure 9b, AI operation 1 includes sub-AI operation 1, sub-AI operation 2, and sub-AI operation 3. Sub-AI operation 1 corresponds to second timer 1, and sub-AI operation 2 corresponds to second timer 2. The terminal device starts the second timer 1 corresponding to sub-AI operation 1 at the end time of sub-AI operation 1, and starts the second timer 2 corresponding to sub-AI operation 2 at the end time of sub-AI operation 2. The terminal device can be in a sleep state during the running time of second timer 1 and second timer 2 to reduce the power consumption of the terminal device. Alternatively, the terminal device can also perform communication services during the running time of second timer 1 and second timer 2 to improve resource utilization.

[0356] The methods provided in this application are described above using terminal devices and network devices as examples. In this application, each embodiment can be implemented independently or in combination based on certain inherent connections; in each embodiment, different implementation methods can be implemented in combination or independently. To achieve the functions of the methods provided in the above-described embodiments, the steps executed by the terminal device can be implemented by different functional entities constituting the terminal device. The steps executed by the network device can be implemented by different functional entities constituting the network device. To achieve the functions of the methods provided in the above-described embodiments, the terminal device and network device can include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0357] The methods provided by the embodiments of this application have been described above with reference to the accompanying drawings. The apparatus provided by the embodiments of this application will be described below with reference to the accompanying drawings.

[0358] Based on the same technical concept, embodiments of this application provide a communication device, which includes a module / unit / means for executing the method performed by the device in the above-described method embodiments. This module / unit / means can be implemented in software, or in hardware, or implemented by hardware executing corresponding software.

[0359] For example, referring to Figure 10, which is a schematic diagram of a communication device 1000, the device includes a transceiver module 1001 and a processing module 1002. This device can be the aforementioned terminal device or network device. For example, the transceiver module can be implemented using a transceiver or interface circuit, and the processing module can be implemented using a processor.

[0360] When the device 1000 is a terminal device, the functions of each module of the device 1000 are as follows:

[0361] The processing module 1002 is configured to determine a first time period, the first time period being used to perform a first AI operation, the first time period including at least two non-contiguous time periods; and to perform the first AI operation in the at least two non-contiguous time periods.

[0362] In one possible implementation, the transceiver module 1001 is configured to receive first information from the network device, the first information being used to determine the first time period.

[0363] In one possible implementation, the first information includes one or more of the following: first indication information, which is used to determine one or more of the start time, end time, or duration of the first time period; and second indication information, which is used to indicate that the first time period corresponds to a first reference signal.

[0364] In one possible implementation, the first indication information further indicates the number of cycles corresponding to the first time period.

[0365] In one possible implementation, the first information includes the second indication information; the transceiver module 1001 is used to receive the first reference signal from the network device; and the processing module 1002 is used to determine the start time of the first time period based on the time when the terminal device receives the first reference signal.

[0366] In one possible implementation, the time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or, the time difference between the time when the terminal device sends the first report and the start time of the first time period is a second offset, the first report corresponds to the first reference signal, and the time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

[0367] In one possible implementation, the transceiver module 1001 is configured to receive second information from the network device, the second information being configured to indicate that the first time period corresponds to the first reference signal in the second time period; the processing module 1002 is configured to determine the end time of the first time period based on the end time of the second time period.

[0368] In one possible implementation, the processing module 1002 is configured to determine the first time period based on a third time period, wherein the third time period is used to perform communication services.

[0369] In one possible implementation, the transceiver module 1001 is configured to receive third information from a network device, the third information being used to indicate that the first time period and the third time period do not overlap or partially overlap.

[0370] In one possible implementation, the start time of the first time period is equal to the end time of the third time period; or, the end time of the first time period is equal to the start time of the third time period; or, the start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, the end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, the start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, the end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

[0371] In one possible implementation, the transceiver module 1001 is configured to send fourth information to the network device, the fourth information being used to request updates to the first time period and / or the third time period, the third time period being used to perform communication services, the first time period and the third time period not overlapping or partially overlapping; and / or, to receive fifth information from the network device, the fifth information being used to instruct updates to the first time period and / or the third time period, the third time period being used to perform communication services, the first time period and the third time period not overlapping or partially overlapping.

[0372] In one possible implementation, the fourth information is sent by the terminal device when a first condition is met, and the fifth information is sent by the network device when a first condition is met. The first condition includes one or more of the following: a first time difference is less than or equal to a second time difference; or, the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to a first priority threshold; or, the target performance of the first AI operation is greater than or equal to a first target performance; or, the end time of the first time period is later than the time when the terminal device ends the execution of the first AI operation; wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends the execution of the first AI operation.

[0373] In one possible implementation, the start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

[0374] In one possible implementation, before the first AI operation is performed in the at least two non-contiguous time periods, the processing module 1002 is used to determine that the first time period has been activated.

[0375] In one possible implementation, the transceiver module 1001 is configured to receive sixth information from the network device, the sixth information being used to indicate activation of the first time period.

[0376] In one possible implementation, the processing module 1002 is configured to, when the first time difference is less than or equal to the second time difference, start a first timer corresponding to the first time period, and execute the first AI operation within the running time of the first timer; wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

[0377] In one possible implementation, the first AI operation includes a first sub-AI operation and a second sub-AI operation; the processing module 1002 is configured to start a second timer corresponding to the first sub-AI operation when the terminal device finishes executing the first sub-AI operation, enter a sleep state or execute communication services during the running time of the second timer, and start executing the second sub-AI operation when the second timer ends.

[0378] Alternatively, when the device 1000 is a network device, the functions of each module of the device 1000 are as follows:

[0379] The transceiver module 1001 is used to send first information or third information to the terminal device. The first information is used to determine a first time period, and the third information is used to indicate that the first time period and the third time period do not overlap or partially overlap. The first time period is used to perform a first AI operation, and the third time period is used to perform communication services.

[0380] In one possible implementation, the first information includes one or more of the following: first indication information, which is used to determine one or more of the start time, end time, or duration of the first time period; and second indication information, which is used to indicate that the first time period corresponds to a first reference signal.

[0381] In one possible implementation, the first indication information further indicates the number of cycles corresponding to the first time period.

[0382] In one possible implementation, the first information includes the second indication information; the transceiver module 1001 is used to send the first reference signal to the terminal device, and the time when the terminal device receives the first reference signal is related to the start time of the first time period.

[0383] In one possible implementation, the time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or, the time difference between the time when the terminal device sends the first report and the start time of the first time period is a second offset, the first report corresponds to the first reference signal, and the time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

[0384] In one possible implementation, the transceiver module 1001 is used to send second information to the terminal device, the second information being used to indicate that the first time period corresponds to the first reference signal in the second time period, and the end time of the second time period is related to the end time of the first time period.

[0385] In one possible implementation, the start time of the first time period is equal to the end time of the third time period; or, the end time of the first time period is equal to the start time of the third time period; or, the start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, the end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, the start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, the end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

[0386] In one possible implementation, the transceiver module 1001 is configured to receive fourth information from the terminal device, the fourth information being used to request updates to the first time period and / or the third time period; and / or to send fifth information to the terminal device, the fifth information being used to instruct updates to the first time period and / or the third time period.

[0387] In one possible implementation, the fourth information is sent by the terminal device when a first condition is met, and the fifth information is sent by the network device when the first condition is met. The first condition includes one or more of the following: a first time difference is less than or equal to a second time difference; or, the first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to a first priority threshold; or, the target performance of the first AI operation is greater than or equal to a first target performance; or, the end time of the first time period is later than the time when the terminal device ends the execution of the first AI operation; wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the end time of the first time period, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends the execution of the first AI operation.

[0388] In one possible implementation, the start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

[0389] In one possible implementation, the transceiver module 1001 is used to send a sixth message to the terminal device, the sixth message being used to indicate the activation of the first time period.

[0390] In practical implementation, the above-mentioned device 1000 can have various product forms. Several possible product forms are introduced below.

[0391] Referring to Figure 11, which is a schematic diagram of another communication device, the communication device 1100 includes a processor 1101, which implements the method executed by the communication device or terminal device in the above method embodiments through logic circuits or execution instructions.

[0392] Optionally, the communication device 1100 may further include an interface circuit 1102, which is used to receive signals from other communication devices outside the communication device and transmit them to the processor 1101, or to send signals from the processor 1101 to other communication devices outside the communication device. The processor 1101 and the interface circuit 1102 are coupled to each other. It is understood that the interface circuit 1102 can be a transceiver or an input / output interface.

[0393] Optionally, the communication device 1100 may also include a memory 1103 for storing instructions executed by the processor 1101, or storing input data required by the processor 1101 to execute instructions, or storing data generated after the processor 1101 executes instructions.

[0394] It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0395] For example, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), microprocessor units (MPUs), microcontroller units (MCUs), graphics processing units (GPUs), field-programmable gate arrays (FPGAs), artificial intelligence processors (AI processors) or neural processing units (NPUs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0396] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be cache or random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0397] It is understandable that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0398] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0399] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, causes the methods executed by the terminal device and the network device in the above method embodiments to be implemented.

[0400] Based on the same technical concept, this application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, cause the methods executed by the terminal device and the network device in the above method embodiments to be implemented.

[0401] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0402] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0403] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0404] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

Claims

1. A communication method, characterized in that, Applied to terminal devices, including: A first time period is determined, which is used to perform a first artificial intelligence (AI) operation. The first time period includes at least two non-contiguous time periods. The first AI operation is performed during at least two non-contiguous time periods.

2. The method according to claim 1, characterized in that, Determining the first time period includes: Receive first information from the network device, the first information being used to determine the first time period.

3. The method according to claim 2, characterized in that, The first information includes one or more of the following: The first indication information is used to determine one or more of the start time, end time, or duration of the first time period; The second indication information is used to indicate the first reference signal corresponding to the first time period.

4. The method according to claim 3, characterized in that, The first indication information also indicates the number of cycles corresponding to the first time period.

5. The method according to claim 3, characterized in that, The first information includes the second indication information, and the method further includes: Receive the first reference signal from the network device; The start time of the first time period is determined based on the time when the terminal device receives the first reference signal.

6. The method according to claim 5, characterized in that, The time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or... The time difference between the time when the terminal device sends the first report and the start time of the first time period is the second offset. The first report corresponds to the first reference signal. The time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

7. The method according to claim 5 or 6, characterized in that, The method further includes: Receive second information from the network device, the second information being used to indicate that the first time period corresponds to the first reference signal in the second time period; The end time of the first time period is determined based on the end time of the second time period.

8. The method according to claim 1, characterized in that, Determining the first time period includes: The first time period is determined based on the third time period, and the third time period is used to perform communication services.

9. The method according to claim 8, characterized in that, The method further includes: Receive third information from a network device, the third information being used to indicate that the first time period and the third time period do not overlap or partially overlap.

10. The method according to claim 8 or 9, characterized in that, The start time of the first time period is equal to the end time of the third time period; or, The end time of the first time period is equal to the start time of the third time period; or, The start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, The end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, The start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, The end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

11. The method according to any one of claims 1-10, characterized in that, The method further includes: Send a fourth message to the network device, the fourth message being used to request updates to the first time period and / or the third time period, the third time period being used for performing communication services, the first time period and the third time period not overlapping or only partially overlapping; and / or, The network device receives fifth information, which is used to indicate the updating of the first time period and / or the third time period, the third time period being used to perform communication services, and the first time period and the third time period do not overlap or partially overlap.

12. The method according to claim 11, characterized in that, The fourth information is sent by the terminal device when the first condition is met, and the fifth information is sent by the network device when the first condition is met, wherein the first condition includes one or more of the following: The first time difference is less than or equal to the second time difference; or... The first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to the first priority threshold; or, The target performance of the first AI operation is greater than or equal to the first target performance; or, The end time of the first time period is later than the time when the terminal device finishes executing the first AI operation; Wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the first time period ends, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

13. The method according to any one of claims 1-12, characterized in that, The start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

14. The method according to any one of claims 1-13, characterized in that, Before performing the first AI operation in the at least two non-contiguous time periods, the method further includes: It has been confirmed that the first time period has been activated.

15. The method according to claim 14, characterized in that, The method further includes: A sixth message is received from the network device, the sixth message indicating the activation of the first time period.

16. The method according to any one of claims 1-15, characterized in that, The method further includes: If the first time difference is less than or equal to the second time difference, start the first timer corresponding to the first time period, and execute the first AI operation during the running time of the first timer; Wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the first time period ends, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

17. The method according to any one of claims 1-16, characterized in that, The first AI operation includes a first sub-AI operation and a first sub-AI operation, and the method further includes: When the terminal device finishes executing the first sub-AI operation, it starts the second timer corresponding to the first sub-AI operation, enters a sleep state or executes communication services during the running time of the second timer, and starts executing the second sub-AI operation when the second timer ends.

18. A communication method, characterized in that, Applied to network devices, including: Send first information or third information to the terminal device. The first information is used to determine a first time period, and the third information is used to indicate that the first time period and the third time period do not overlap or partially overlap. The first time period is used to perform a first AI operation. The first time period includes at least two non-contiguous time periods, and the third time period is used to perform communication services.

19. The method according to claim 18, characterized in that, The first information includes one or more of the following: The first indication information is used to determine one or more of the start time, end time, or duration of the first time period; The second indication information is used to indicate the first reference signal corresponding to the first time period.

20. The method according to claim 19, characterized in that, The first indication information also indicates the number of cycles corresponding to the first time period.

21. The method according to claim 19, characterized in that, The first information includes the second indication information, and the method further includes: The first reference signal is sent to the terminal device, and the time at which the terminal device receives the first reference signal is related to the start time of the first time period.

22. The method according to claim 21, characterized in that, The time difference between the time when the terminal device receives the first reference signal and the start time of the first time period is a first offset; or... The time difference between the time when the terminal device sends the first report and the start time of the first time period is the second offset. The first report corresponds to the first reference signal. The time when the terminal device sends the first report is later than the time when the terminal device receives the first reference signal.

23. The method according to claim 22, characterized in that, The method further includes: Send a second message to the terminal device, the second message indicating that the first time period corresponds to the first reference signal in the second time period, and the end time of the second time period is related to the end time of the first time period.

24. The method according to claim 18, characterized in that, The start time of the first time period is equal to the end time of the third time period; or, The end time of the first time period is equal to the start time of the third time period; or, The start time of the first time period is later than the end time of the third time period, and the time difference between the start time of the first time period and the end time of the third time period is a third offset; or, The end time of the first time period is earlier than the start time of the third time period, and the time difference between the end time of the first time period and the start time of the third time period is a fourth offset; or, The start time of the first time period is earlier than the end time of the third time period, and the terminal device does not perform communication services during the time between the start time of the first time period and the end time of the third time period; or, The end time of the first time period is later than the start time of the third time period, and the terminal device does not perform communication services during the time between the start time of the third time period and the end time of the first time period.

25. The method according to any one of claims 18-24, characterized in that, The method further includes: Receive fourth information from the terminal device, the fourth information being used to request updates to the first time period and / or the third time period; and / or, A fifth message is sent to the terminal device, the fifth message being used to instruct the updating of the first time period and / or the third time period.

26. The method according to claim 25, characterized in that, The fourth information is sent by the terminal device when the first condition is met, and the fifth information is sent by the network device when the first condition is met. The first condition includes one or more of the following: The first time difference is less than or equal to the second time difference; or... The first time difference is less than or equal to the second time difference, and the priority of the first AI operation is greater than or equal to the first priority threshold; or, The target performance of the first AI operation is greater than or equal to the first target performance; or, The end time of the first time period is later than the time when the terminal device finishes executing the first AI operation; Wherein, the first time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the first time period ends, and the second time difference is the time difference between the time when the terminal device starts executing the first AI operation and the time when the terminal device ends executing the first AI operation.

27. The method according to any one of claims 18-26, characterized in that, The start time, duration, end time, or corresponding AI operation of the at least two non-contiguous time periods are different.

28. The method according to any one of claims 18-27, characterized in that, The method further includes: A sixth message is sent to the terminal device, the sixth message being used to indicate the activation of the first time period.

29. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1 to 17, or a module for performing the method as described in any one of claims 18 to 28.