Communication method and apparatus

Abstract

A communication method and apparatus. The method comprises: a terminal device receiving first information, which is used for instructing the terminal device to execute a first task; and the terminal device executing the first task, wherein when a first model or function is in a first state, compared with the situation where the first model or function is in a second state, at least one of the following corresponding to the first task is different: a latency requirement, a usage time period of the first model or function, a memory cell occupancy time period of the first model or function, and a computing unit occupancy time period of the first model or function, and the first model or function corresponds to the first task. The requirement corresponding to a first task can match the state of a first model or function corresponding to the first task, such that a terminal device can smoothly execute the first task.

Description

Communication method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on April 3, 2024, with application number 202410408519.7 and application name “A Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0003] Artificial intelligence (AI) has been widely used in many application scenarios of air interface technology, such as channel state information (CSI) feedback scenarios, CSI prediction scenarios, beam management scenarios, positioning scenarios, etc.

[0004] In various AI application scenarios, when models are deployed on the terminal device side, the network device may not be able to know the status of the model in the terminal device, which may prevent the task from being successfully executed. For example, Model 1 deployed in the terminal device is used to predict CSI. The network device instructs the terminal device to activate Model 1 and perform a CSI report. The terminal device activates Model 1 and then uses Model 1 for CSI calculation and CSI reporting. After a period of time, the terminal device deactivates Model 1. However, the network device believes that Model 1 has been activated. When it instructs the terminal device to report CSI again, it does not reserve time for Model 1 to activate. As a result, the terminal device cannot complete the CSI calculation at the specified reporting time, and thus cannot complete the CSI report. Summary of the Invention

[0005] The embodiments of the present application provide a communication method and apparatus, which facilitate matching the requirements corresponding to the first task with the state of the first model or function corresponding to the first task, thereby facilitating the terminal device to smoothly execute the first task.

[0006] In a first aspect, an embodiment of the present application provides a communication method, which can be executed by a terminal device. The terminal device here can refer to the terminal device itself, or a processor, module, chip, or chip system that implements the method in the terminal device. In this method, the terminal device receives first information, and the first information is used to instruct the terminal device to perform a first task; the terminal device performs the first task. Wherein, when the first model or function is in the first state relative to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, computing unit occupancy time period of the first model or function, and the first model or function corresponds to the first task.

[0007] It can be seen that in the embodiment of the present application, when the first model or function corresponding to the first task is in the first state, relative to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function. This method is beneficial for the terminal device to determine the state of the first model or function after receiving the first information, and to determine at least one of the following items corresponding to the first task based on the state of the first model or function: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function, and then execute the first task based on the determined at least one item, which is beneficial for the demand corresponding to the first task to match the state of the first model or function corresponding to the first task, thereby facilitating the terminal device to smoothly execute the first task.

[0008] Optionally, the "indication" in the first information being used to instruct the terminal device to perform the first task can be understood as "triggering" or "configuration". For example, the first information is used to trigger the terminal device to perform the first task. For another example, the first information is used to configure the terminal device to perform the first task. Optionally, the storage unit can be replaced with "storage resources" and the computing unit can be replaced with "computing resources". Thus, the storage unit occupancy time period of the first model or function can be replaced with "the storage resource occupancy time period of the first model or function", and the computing unit occupancy time period of the first model or function can be replaced with "the computing resource occupancy time period of the first model or function".

[0009] Optionally, the first model or function corresponds to the first task, which can be one of the following: the terminal device adopts the first model or function to perform the first task, the first task is performed using the first model or function, the first task is a task supported by the first function, the first task is one of one or more tasks supported by the first function, the first task is a task performed using the first model or function, and the first task is one of one or more tasks performed using the first model or function.

[0010] In one optional embodiment, the first state of the second model or function lasts from a first moment to a second moment, the second model or function corresponds to a second task, and the start time of the second task is earlier than the start time of the first task. The second moment is later than the first moment. In other words, during the period from the first moment to the second moment, the second model or function corresponding to the second task is in the first state.

[0011] In one optional embodiment, the first state of the second model or function is expected to last from a first moment to a second moment, the second model or function corresponds to a second task, and the start time of the second task is earlier than the start time of the first task. The second moment is later than the first moment. The first state of the second model or function is expected to last from the first moment to the second moment, which means that, without considering the first task, based on the second task, it can be expected that the second model or function corresponding to the second task is in the first state during the time period from the first moment to the second moment.

[0012] In an optional embodiment, the first moment corresponds to one of the following: a start moment of the first downlink signal, an end moment of the first downlink signal, a start moment of the first uplink signal, an end moment of the first uplink signal, a first offset moment, or a second offset moment. Both the first downlink signal and the first uplink signal are related to the second task.

[0013] The time interval between the first offset time and the start time or end time of the first downlink signal corresponds to the first time offset, and the time interval between the second offset time and the start time or end time of the first uplink signal corresponds to the second time offset. The first downlink signal can be a downlink signal or a downlink channel; the first uplink signal can be an uplink channel. The value of the first time offset can be positive or negative; the value of the second time offset can be positive or negative.

[0014] In an optional implementation, the first time offset and / or the second time offset is reported by the terminal device, or is preset by a protocol, or is configured or indicated by a network device.

[0015] In addition, the first moment corresponds to the starting moment of the first downlink signal, which can be: the first moment is the starting moment of the first downlink signal, or it can be: the first moment is determined based on the starting moment of the first downlink signal. The first moment is determined based on the starting moment of the first downlink signal, which can be: the first moment is the starting moment or ending moment of the time unit in which the starting moment of the first downlink signal is located, or it can be: the first moment is the starting moment of the first time unit after the time unit in which the starting moment of the first downlink signal is located. Similarly, the first moment corresponds to other moments and has the same meaning, which will not be repeated here.

[0016] Optionally, the first moment corresponds to one of the following: the starting moment of the usage time period of the second model or function corresponding to the second task, the starting moment of the storage unit occupation time period of the second model or function, the starting moment of the computing unit occupation time period of the second model or function, the end moment of the usage time period of the second model or function corresponding to the second task, the end moment of the storage unit occupation time period of the second model or function, and the end moment of the computing unit occupation time period of the second model or function.

[0017] In an optional embodiment, the time interval between the first moment and the second moment is a first time length. Alternatively, the second moment can be determined based on the first moment and the first time length. The first time length is configured or indicated by the network device, or is preset by the protocol.

[0018] In an optional embodiment, in which the time interval between the first moment and the second moment is a first time length, the second task is a periodic task or a semi-persistent task. The second task being a periodic task or a semi-persistent task can be understood as: the second task is a task in a period among multiple periods of the periodic task or semi-persistent task to which the second task belongs.

[0019] In other words, the terminal device can determine the time characteristics of the second task. When the terminal device determines that the second task is a periodic task or a semi-persistent task, the terminal device determines a second time based on the first time and the first time duration. The second time is the duration of the first state of the second model or function corresponding to the second task. In other words, the first state of the second model or function can continue until the second time.

[0020] Optionally, in an embodiment where the time interval between the first moment and the second moment is a first time length, the second task may also be a dynamically scheduled task. That is, when the terminal device determines that the second task is a dynamically scheduled task, it may also determine the second moment based on the first moment and the first time length. Dynamically scheduled tasks may also be referred to as non-periodic tasks.

[0021] In an optional implementation, the first moment is determined based on the sixth moment and the sixth time length. The implementation of the sixth moment and the sixth time length is similar to the implementation of the first moment and the first time length, and will not be repeated.

[0022] In an optional embodiment, when the second task is a periodic task or a semi-continuous task, the first moment corresponds to the start moment of the first cycle among N cycles, and the second moment corresponds to the end moment of the Nth cycle among N cycles. N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1. In other words, when the second task is a periodic task or a semi-continuous task, the first state of the second model or function lasts from the start moment of the first cycle among the N cycles to which the second task belongs to to the end moment of the Nth cycle among the N cycles, that is, within the N cycles to which the second task belongs, the second model or function is in the first state.

[0023] In an optional embodiment, when the second task belongs to a periodic task or a semi-continuous task, the first moment corresponds to the start moment of the first cycle in N cycles, and the second moment corresponds to the end moment of the Nth cycle in N cycles. N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1. Within the N cycles to which the second task belongs, the second model or function periodically switches between the first state and the third state. At the end moment of each cycle except the Nth cycle in the N cycles, the second model or function switches from the third state to the first state, and at the start moment of each cycle except the first cycle in the N cycles, the second model or function switches from the first state to the third state. In particular, at the start moment of the first cycle in the N cycles, the second model or function switches from the first state to the third state, or, the second model or function switches from the second state to the third state. In particular, at the end of the Nth cycle among the N cycles, the terminal device switches the third state of the second model or function to the second state, or in other words, after the end of the Nth cycle among the N cycles, the second model or function is in the second state, or in other words, the second state of the second model or function starts from the end of the Nth cycle among the N cycles. The third state is a state in which the model or function is activated and used, or in other words, the time period when the second model or function is in the third state is the time period when the terminal device uses the second model or function to perform model reasoning, or in other words, when the second model or function is in the third state, the terminal device is using the second model or function to perform model reasoning.

[0024] In an optional implementation, when the second task is a periodic task or a semi-continuous task, if the second task is not the last cycle in N cycles, the first moment corresponds to the end moment of the cycle in which the second task is located, and the second moment corresponds to the start moment of the next cycle of the cycle in which the second task is located; if the second task is the last cycle in N cycles, the first moment corresponds to the end moment of the cycle in which the second task is located, and the second moment corresponds to the end moment of the cycle in which the second task is located. Wherein, N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1. In other words, when the second task is a periodic task or a semi-continuous task, the first state of the second model or function periodically continues from the end moment of each cycle to the start moment of the next cycle. That is, within the N cycles to which the second task belongs, the second model or function is periodically in the first state.

[0025] Optionally, the third state of the second model or function begins at the second moment, or in other words, the second moment is the moment when the terminal device switches the first state of the second model or function to the third state. The third state is a state in which the model or function is activated and used, or in other words, the time period when the second model or function is in the third state is the time period in which the terminal device uses the second model or function for model reasoning, or in other words, when the second model or function is in the third state, the terminal device is using the second model or function for model reasoning. When the second model or function is in the third state, tasks other than the second task cannot use the second model or function for model reasoning.

[0026] Optionally, the first moment is the moment when the terminal device switches the third state of the second model or function to the first state, or in other words, the second model or function is in the third state for a period of time before the first moment.

[0027] Optionally, the second model or function is in the second state after the end moment of the Nth cycle in N cycles, or in other words, the end moment of the Nth cycle in N cycles is the moment when the terminal device switches the third state of the second model or function to the second state, or in other words, the second state of the second model or function starts from the end moment of the Nth cycle in N cycles.

[0028] In an optional implementation manner, in an implementation manner in which the time interval between the first moment and the second moment is a first time length, the second task is a task that does not require reporting of information.

[0029] In other words, when the terminal device determines that no information needs to be reported for the second task, the second moment is determined based on the first moment and the first time length. The second task is a task that does not require reporting information, or the second task does not require reporting information, which means that the result obtained by the terminal device when executing the second task does not need to be reported directly through an uplink channel or an uplink signal. The result obtained by the terminal device when executing the second task can be applied to other tasks, and the results obtained by the terminal device when executing other tasks can be reported directly through an uplink channel or an uplink signal. Alternatively, the second task is a task that does not require reporting information, and the second task does not require reporting information, which means that the network device does not configure an uplink channel or an uplink signal for the terminal device for the second task for result feedback.

[0030] In another optional embodiment, the second moment corresponds to one of the following: the starting moment or ending moment of the channel carrying the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located.

[0031] The second moment corresponds to the start moment or end moment of the channel carrying the report information of the second task. The second moment may be the start moment or end moment of the channel carrying the report information of the second task, or the second moment may be determined based on the start moment or end moment of the channel carrying the report information of the second task. Similarly, the second moment corresponds to other moments and has the same meaning, which is not further described.

[0032] Optionally, the second moment corresponds to one of the following: the starting moment or ending moment of the channel carrying the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located, which is applicable to the task scenario where the second task is dynamically scheduled.

[0033] In other words, the terminal device can determine the time characteristics of the second task. When the terminal device determines that the second task belongs to a dynamically scheduled task, it determines that the second moment corresponds to one of the following: the starting moment or ending moment of the channel carrying the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located.

[0034] In an optional embodiment, when the second function or model corresponding to the second task lasts from the first moment to the second moment, the first model or function corresponding to the first task is in the first state, including: the starting moment of the first task is between the first moment and the second moment.

[0035] In other words, the terminal device can determine the state of the first model or function corresponding to the first task based on the first moment, the second moment and the starting moment of the first task; when the starting moment of the first task is between the first moment and the second moment, the terminal device determines that the first model or function is in the first state.

[0036] In one optional embodiment, when the first model or function corresponding to the first task is in the first state, the first state of the first model or function persists until a third moment, the third moment corresponding to the first task, and the third moment being later than the second moment. The third moment corresponding to the first task can be understood as: the third moment is the duration of the first state of the first model or function corresponding to the first task; that is, the first state of the first model or function can persist until the third moment.

[0037] It can be seen that when the first model or function corresponding to the first task is in the first state and the third moment is later than the second moment, the first state of the first model or function can continue until the third moment. In other words, the first state of the first model or function corresponding to the first task continues from the start moment of the first task to the third moment. In one possible scenario, the third moment is the end moment of the first model or function, or in other words, the third moment is the moment when the terminal device switches the first state of the first model or function to the second state.

[0038] In one optional embodiment, the third time is applied to at least one of the following items corresponding to the third task: a latency requirement, a usage period of the third model or function, a storage unit occupancy period of the third model or function, or a computing unit occupancy period of the third model or function. The third model or function corresponds to the third task, and the start time of the third task is later than the start time of the first task.

[0039] In other words, the third moment can be used to determine at least one of the following items corresponding to the third task: latency requirement, usage period of the third model or function, storage unit occupancy period of the third model or function, and computing unit occupancy period of the third model or function. Specifically, the third moment is used to determine the status of the third model or function corresponding to the third task, and the status of the third model or function is used to determine at least one of the following items corresponding to the third task: latency requirement, usage period of the third model or function, storage unit occupancy period of the third model or function, and computing unit occupancy period of the third model or function.

[0040] In an optional embodiment, when the first function or model corresponding to the first task lasts from the starting moment of the first task to a third moment, the third model or function corresponding to the third task is in a first state, including: the starting moment of the third task is between the starting moment of the first task and the third moment.

[0041] In other words, the terminal device can determine the state of the third model or function corresponding to the third task based on the starting time of the first task, the third time and the starting time of the third task; when the starting time of the third task is between the starting time of the first task and the third time, the terminal device determines that the third model or function is in the first state.

[0042] In an optional embodiment, when the first model or function is in the first state, the first state of the first model or function continues until the second moment, or in other words, the first state of the first model or function ends at the second moment, or in other words, the second moment is the moment when the terminal device switches the first state of the first model or function to the second state.

[0043] In an optional embodiment, when the first state of the first model or function continues until a second moment, the second state of the first model or function starts from the second moment, or the time period corresponding to the second state of the first model or function includes time outside the time period corresponding to the first state.

[0044] It can be seen that when the first state of the first model or function lasts until the second moment, the terminal device can complete the switching of the first model or function from the first state to the second state at the second moment, so that the second state of the first model or function starts from the second moment.

[0045] Optionally, when the first state of the first model or function continues until the second moment, the terminal device completes the switching of the first model or function from the first state to the second state within a certain time period after the second moment, then the time period corresponding to the second state of the first model or function is outside the time period corresponding to the first state.

[0046] In an optional embodiment, when the first state of the second model or function continues until the second moment, the first model or function is in the second state, including: the first model or function is not in the first state; or the start time of the first task is after the second moment.

[0047] It can be seen that when the first state of the second model or function continues until the second moment, if the first model or function is not in the first state, the terminal device determines that the first model or function is in the second state. Alternatively, when the first state of the second model or function continues until the second moment, if the start time of the first task is after the second moment, the terminal device determines that the first model or function is in the second state.

[0048] In an optional implementation, when the first model or function corresponding to the first task is in the first state, the first state of the first model or function continues until the seventh moment, or in other words, the first state of the first model or function ends at the seventh moment, or in other words, the seventh moment is the moment when the terminal device switches the first state of the first model or function to the third state. The seventh moment corresponds to the first task. Optionally, the seventh moment corresponds to the starting moment of the first task. The seventh moment corresponds to the starting moment of the first task, which can be: the seventh moment is the starting moment of the first task, or it can be: the seventh moment is determined based on the starting moment of the first task.

[0049] Optionally, after the seventh moment, the first state of the first model or function begins again at an eighth moment, or in other words, the eighth moment is the moment when the terminal device switches the third state of the first model or function to the first state. The eighth moment corresponds to the first task. Optionally, the eighth moment corresponds to the end moment of the first task. The eighth moment corresponding to the end moment of the first task can be: the eighth moment is the end moment of the first task, or it can be: the eighth moment is determined based on the end moment of the first task.

[0050] Optionally, when the first model or function corresponding to the first task is in the first state, the first state of the first model or function begins at a ninth moment, or in other words, the ninth moment is the moment when the first model or function switches from the third state to the first state. Optionally, the ninth moment corresponds to the end moment of the second task. The ninth moment corresponding to the end moment of the second task may be: the ninth moment is the end moment of the second task, or it may be: the ninth moment is determined based on the end moment of the second task.

[0051] Optionally, the third state of the first model or function continues until the eighth moment, or in other words, the third state of the first model or function ends at the eighth moment, or in other words, the eighth moment is the moment when the terminal device switches the third state of the first model or function to the second state. The eighth moment corresponds to the first task, or the eighth moment is the second moment. Optionally, the eighth moment corresponds to the end moment of the first task. The eighth moment corresponds to the end moment of the first task, which can be: the eighth moment is the end moment of the first task, or it can be: the eighth moment is determined based on the end moment of the first task.

[0052] In an optional embodiment, the start time of the first task corresponds to one of the following: the start time of the second downlink signal, the end time of the second downlink signal, the third offset time, the start time of the usage time period of the first model or function, the start time of the storage unit occupancy time period of the first model or function, and the start time of the computing unit occupancy time period of the first model or function. The time interval between the third offset time and the start time or end time of the second downlink signal corresponds to a third time offset. The second downlink signal is related to the first task, and the second downlink signal can be a downlink signal or a downlink channel. The value of the third time offset is a positive number or a negative number.

[0053] Among them, the starting moment of the first task corresponds to the starting moment of the second downlink signal, which can be: the starting moment of the first task is the starting moment of the second downlink signal, or it can be: the starting moment of the first task is determined based on the starting moment of the second downlink signal. The starting moment of the first task is determined based on the starting moment of the second downlink signal, which can be: the starting moment of the first task is the starting moment or end moment of the time unit where the starting moment of the second downlink signal is located, or it can be: the starting moment of the first task is the starting moment of the first time unit after the time unit where the starting moment of the second downlink signal is located. Similarly, the starting moment of the first task corresponds to other moments, has similar meanings, and will not be repeated.

[0054] In an optional implementation manner, the third time offset is reported by the terminal device, or is preset, or is configured or indicated by the network device.

[0055] In an optional embodiment, the second model or function is the same as the first model or function. The second model or function is the same as the first model or function, which can be: the second model or function and the first model or function are used to implement the same function, such as both are used to implement CSI prediction, etc., or the second model or function and the first model or function have the same physical model. In addition, the second model or function has the same structure and all parameters as the first model or function, or the second model or function has the same structure as the first model or function but some parameters are different, such as the number of layers, width, and inter-layer connection relationship of the neural network, and the parameters such as the weight value and bias of the neural network.

[0056] In an optional embodiment, the latency requirement is one of the following: the time interval requirement between the second downlink signal and the second uplink signal; the time interval requirement between the second downlink signal and the end of the usage period of the first model or function; the time interval requirement between the second downlink signal and the end of the storage unit occupation period of the first model or function; and the time interval requirement between the second downlink signal and the end of the computing unit occupation period of the first model or function. The second downlink signal and the second uplink signal are both related to the first task. It can be understood that the latency requirement is the time interval requirement between the second downlink signal and the second uplink signal, which means that the time interval between the second downlink signal and the second uplink signal needs to be greater than or equal to a certain time length, or in other words, the terminal device expects the time interval between the second downlink signal and the second uplink signal to be greater than or equal to a certain time length. When the time interval between the second downlink signal and the second uplink signal is less than this time length, the latency requirement is not met, and the terminal device can ignore the first task. Ignoring a task can also be understood as not executing the task, not reporting the corresponding reporting information of the task, not updating the corresponding reporting information of the task, or ceasing to execute the task. Similarly, "not ignoring a task" can be understood as executing the task, reporting the corresponding report information, updating the corresponding report information, or continuing the task. Optionally, "ignore" can be replaced with "not retain," and "not ignoring" can be replaced with "retain." The meaning is similar when the latency requirement is other than "latency requirement."

[0057] In an optional embodiment, when the first model or function is in the first state, the delay requirement corresponding to the first task is smaller than when the first model or function is in the second state. When the first model or function is in the first state, the delay requirement corresponding to the first task includes the time requirement for model reasoning, that is, the time required for the terminal device to perform model reasoning using the first model or function; when the first model or function is in the second state, the delay requirement corresponding to the first task includes the time requirement for model activation and model reasoning, that is, the time required for the terminal device to activate the first model or function and the time required to perform reasoning using the first model or function. Therefore, when the first model or function is in the first state, the delay requirement corresponding to the first task is smaller than when the first model or function is in the second state. This method allows the terminal device to determine different delay requirements based on the state of the first model or function when performing the first task, so that the terminal device can smoothly perform the first task.

[0058] In an optional embodiment, when the first model or function is in a first state, the usage time period of the first model or function corresponding to the first task starts from the start time or end time of the second downlink signal corresponding to the first task; when the first model or function is in a second state, the start time of the usage time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task. This approach allows the terminal device to execute the first task based on the state of the first model or function, allowing the terminal device to smoothly execute the first task.

[0059] In an optional embodiment, when the first model or function is in the first state, the time period occupied by the computing unit of the first model or function corresponding to the first task starts from the start moment or end moment of the second downlink signal corresponding to the first task; when the first model or function is in the second state, the start moment of the time period occupied by the computing unit of the first model or function corresponding to the first task is later than the start moment or end moment of the second downlink signal corresponding to the first task. In this manner, the time period occupied by the computing unit of the first model or function does not always start from the start moment or end moment of the second downlink signal corresponding to the first task, but is adaptively changed based on the state of the first model or function. Therefore, when the first model or function is in the second state, the start moment of the time period occupied by the computing unit of the first model or function can be postponed, thereby making full use of idle computing units and reducing the occupation of unnecessary computing resources.

[0060] In an optional embodiment, when the first model or function corresponding to the first task is in a first state, the storage unit occupancy time period of the first model or function corresponding to the first task starts from the start or end time of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal or a downlink channel. When the first model or function corresponding to the first task is in the first state, the terminal device does not need to activate the first model or function, so that the storage unit occupancy time period of the first model or function corresponding to the first task can start from the start or end time of the second downlink signal corresponding to the first task.

[0061] In an optional embodiment, when the first model or function corresponding to the first task is in the second state, the starting moment of the time period occupied by the storage unit of the first model or function corresponding to the first task is earlier than the starting moment or the ending moment of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal. When the first model or function corresponding to the first task is in the second state, the terminal device activates the first model or function from a moment earlier than the starting moment or the ending moment of the second downlink signal corresponding to the first task in order to successfully complete the first task within the resources scheduled by the network device, so that the starting moment of the time period occupied by the storage unit of the first model or function corresponding to the first task is earlier than the starting moment or the ending moment of the second downlink signal corresponding to the first task.

[0062] In another optional embodiment, when the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink channel.

[0063] In another optional embodiment, when the first model or function corresponding to the first task is in the second state, the starting time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the starting time or end time of the second uplink signal corresponding to the first task, and the starting time of the storage unit occupancy time period of the first model or function corresponding to the first task is determined by the starting time or end time of the second uplink signal corresponding to the first task, and the second uplink signal is an uplink channel.

[0064] When the first model or function corresponding to the first task is in the second state, in order to successfully complete the first task before the start time or end time of the second uplink signal scheduled by the network device, the terminal device activates the first model or function from a moment earlier than the start time or end time of the second uplink signal, so that the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task. Furthermore, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task, and the time interval between the start time of the storage unit occupancy time period of the first model or function corresponding to the first task and the start time or end time of the second uplink signal corresponding to the first task needs to be greater than or equal to the sum of the model activation time and the time when the first task uses the model for reasoning.

[0065] Optionally, when the first model or function corresponding to the first task is in the second state, the starting moment of the usage time period of the first model or function is earlier than the moment when the first model or function is in the first state, and the starting moment of the time period occupied by the computing unit of the first model or function is earlier than the moment when the first model or function is in the first state. In other words, the starting moment of the usage time period of the first model or function is earlier than the starting moment or end moment of the second uplink signal corresponding to the first task, and the starting moment of the time period occupied by the computing unit of the first model or function is earlier than the starting moment or end moment of the second uplink signal corresponding to the first task.

[0066] In an optional implementation, the first state is an activated state, and the second state is a deactivated state.

[0067] In another optional embodiment, the first state is an active and idle state, and the second state is a deactivated state. The first state is an active and idle state, indicating that the model or function is in an active state and not in use. In this embodiment, the state of the model or function also includes a third state.

[0068] In an optional implementation manner, the first moment is configured by the network device or is preset.

[0069] In an optional embodiment, the first time length is determined based on at least one of the following: an index or identifier corresponding to the first time length; 1 / M times the reporting period of the second task, where M is a positive integer; or a time characteristic of the second task. The time characteristic of the second task may include: the second task being a periodic task, the second task being a semi-persistent task, or the second task being a dynamically scheduled task.

[0070] On the second aspect, an embodiment of the present application also provides a communication method, which can be executed by a terminal device, where the terminal device can refer to the terminal device itself, or a processor, module, chip, or chip system that implements the method in the terminal device. In this method, the terminal device receives a first message, and the first message is used to instruct the terminal device to perform a first task; the terminal device performs the first task. The computing unit of the first model or function corresponding to the first task occupies a time period starting at a fourth moment, and the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, or the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task. The second downlink signal can be a downlink signal or a downlink channel.

[0071] It can be seen that in the embodiment of the present application, the starting moment of the time period occupied by the calculation unit of the first model or function corresponding to the first task is later than the starting moment of the second downlink signal corresponding to the first task. Compared with the case where the starting moment of the time period occupied by the calculation unit of the first model or function starts at the starting moment of the second downlink signal corresponding to the first task, the time period occupied by the calculation unit of the model or function can be saved, thereby facilitating the terminal device to utilize the redundant calculation units of the model or function to perform other tasks, thereby improving resource utilization. Alternatively, the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task. Compared with the case where the starting moment of the time period occupied by the calculation unit of the first model or function starts at the starting moment of the second downlink signal corresponding to the first task, the terminal device can utilize sufficient resources to activate the first model or function when the first model or function corresponding to the first task is in the second state, thereby facilitating the smooth execution of the first task.

[0072] In an optional implementation, the time interval between the fourth moment and the start moment of the second downlink signal is a second time length, wherein the second time length is reported by the terminal device or preset.

[0073] In one optional embodiment, the fourth moment is earlier than the start moment or end moment of the second uplink signal corresponding to the first task, and the time interval between the fourth moment and the start moment or end moment of the second uplink signal is a third time length. The third time length is reported by the terminal device or is preset. The second uplink signal is an uplink channel.

[0074] In an optional implementation, the time period occupied by the calculation unit of the first model or function ends at a fifth moment, and the fifth moment is earlier than the end moment of the second uplink signal corresponding to the first task.

[0075] In an optional implementation, the time interval between the fifth moment and the start or end moment of the second downlink signal is a fourth time length, wherein the fourth time length is reported by the terminal device or is preset.

[0076] In an optional implementation, the time interval between the fifth moment and the start or end moment of the second uplink signal is a fifth time length, wherein the fifth time length is reported by the terminal device or is preset.

[0077] In a third aspect, an embodiment of the present application further provides a communication device. The communication device has the function of implementing some or all of the functions of the terminal device described in the first aspect above, or implements some or all of the functions of the terminal device described in the second aspect above. For example, the functions of the communication device may have the functions of some or all of the embodiments of the terminal device described in the first aspect of the embodiment of the present application, or may have the function of implementing any one of the embodiments of the present application alone. The functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the above functions.

[0078] In one possible design, the communication device may include a processing unit and a communication unit. The processing unit is configured to support the communication device in performing the corresponding functions in the above method. The communication unit is configured to support communication between the communication device and other communication devices. The communication device may also include a storage unit, which is coupled to the processing unit and the communication unit and stores program instructions and data necessary for the communication device.

[0079] In one embodiment, the communication device includes: a processing unit and a communication unit, and the device is applied to a terminal device;

[0080] The communication unit is configured to receive first information, where the first information is configured to instruct the terminal device to perform a first task;

[0081] The processing unit is configured to execute the first task;

[0082] Among them, when the first model or function is in the first state compared to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function; the first model or function corresponds to the first task.

[0083] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the first aspect above and will not be described in detail here.

[0084] In another embodiment, the communication device includes: a processing unit and a communication unit, and the device is applied to a terminal device;

[0085] The communication unit is configured to receive first information, where the first information is configured to instruct the terminal device to perform a first task;

[0086] The processing unit is configured to execute the first task;

[0087] The computing unit occupies a time period of the first model or function corresponding to the first task starting at a fourth moment; the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, or the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task.

[0088] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the second aspect above and will not be described in detail here.

[0089] As an example, the communication unit may be a transceiver or a communication interface, the storage unit may be a memory, and the processing unit may be a processor.

[0090] In one embodiment, the communication device includes: a processor and a transceiver, and the device is applied to a terminal device;

[0091] The transceiver is used for first information, wherein the first information is used to instruct the terminal device to perform a first task;

[0092] The processor is configured to perform the first task;

[0093] Among them, when the first model or function is in the first state compared to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function; the first model or function corresponds to the first task.

[0094] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the first aspect above and will not be described in detail here.

[0095] In another embodiment, the communication device includes: a processor and a transceiver, and the device is applied to a terminal device;

[0096] The transceiver is configured to receive first information, where the first information instructs the terminal device to perform a first task;

[0097] The processor is configured to execute the first task;

[0098] The computing unit occupies a time period of the first model or function corresponding to the first task starting at a fourth moment; the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, or the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task.

[0099] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the second aspect above and will not be described in detail here.

[0100] In another embodiment, the communication device is a chip or a chip system. The processing unit may also be embodied as a processing circuit or a logic circuit; and the communication unit may be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit on the chip or chip system.

[0101] During implementation, the processor can be used to perform, for example, but not limited to, baseband-related processing, and the transceiver can be used to perform, for example, but not limited to, radio frequency transceiver processing. The aforementioned devices can be provided on separate chips, or at least partially or entirely on the same chip. For example, the processor can be further divided into an analog baseband processor and a digital baseband processor. The analog baseband processor can be integrated with the transceiver on the same chip, while the digital baseband processor can be provided on a separate chip. With the continuous development of integrated circuit technology, more and more devices can be integrated on the same chip. For example, a digital baseband processor can be integrated with multiple application processors (such as, but not limited to, a graphics processor, a multimedia processor, etc.) on the same chip. Such a chip can be called a system on a chip (SoC). Whether each device is provided independently on different chips or integrated on one or more chips often depends on the needs of the product design. The embodiments of the present application do not limit the implementation form of the aforementioned devices.

[0102] In a fourth aspect, an embodiment of the present application further provides a processor for executing the various methods described above. In the process of executing these methods, the process of sending the above-mentioned information and receiving the above-mentioned information in the above-mentioned methods can be understood as the process of the processor outputting the above-mentioned information and the process of the processor receiving the above-mentioned information input. When outputting the above-mentioned information, the processor outputs the above-mentioned information to the transceiver so that the transceiver can transmit it. After being output by the processor, the above-mentioned information may also need to undergo other processing before reaching the transceiver. Similarly, when the processor receives the above-mentioned information input, the transceiver receives the above-mentioned information and inputs it into the processor. Furthermore, after the transceiver receives the above-mentioned information, the above-mentioned information may need to undergo other processing before being input into the processor.

[0103] For the sending and receiving operations involved in the processor, unless otherwise specified, or unless they conflict with their actual functions or internal logic in the relevant descriptions, they can be more generally understood as processor output, reception, input and other operations, rather than sending and receiving operations directly performed by the RF circuit and antenna.

[0104] During implementation, the processor may be a processor specifically configured to execute these methods, or may be a processor that executes computer instructions in a memory to execute these methods, such as a general-purpose processor. The memory may be a non-transitory memory, such as a read-only memory (ROM), which may be integrated with the processor on the same chip or disposed on separate chips. The embodiments of the present application do not limit the type of memory or the configuration of the memory and the processor.

[0105] In a fifth aspect, an embodiment of the present application further provides a communication system, which includes a terminal device and a network device. In another possible design, the system may also include other devices / functional network elements that interact with the terminal device and the network device.

[0106] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium for storing instructions, which, when executed by a computer, implements the method described in the first or second aspect above.

[0107] In a seventh aspect, an embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, implements the method described in the first or second aspect above.

[0108] In an eighth aspect, an embodiment of the present application provides a chip system, which includes a processor and an interface, wherein the interface is used to obtain a program or instruction, and the processor is used to call the program or instruction to implement or support the terminal device to implement the functions involved in the first aspect, or to implement or support the terminal device to implement the functions involved in the second aspect. For example, determining or processing at least one of the data and information involved in the above method. In one possible design, the chip system also includes a memory, which is used to store program instructions and data necessary for the terminal. The chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0109] In the ninth aspect, an embodiment of the present application provides a communication device, comprising a processor for executing a computer program or executable instructions stored in a memory, so that when the computer program or executable instructions are executed, the device executes the methods in each possible implementation of the first aspect or the second aspect.

[0110] In one possible implementation, the processor and memory are integrated;

[0111] In another possible implementation, the memory is located outside the communication device.

[0112] The beneficial effects of the third to ninth aspects can refer to the beneficial effects of the first or second aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0113] Figure 1 is a schematic diagram of an application framework;

[0114] FIG2 is a schematic diagram of another application framework;

[0115] FIG3 is a schematic diagram of a communication system;

[0116] FIG4 is a schematic diagram of another communication system;

[0117] FIG5 is a schematic diagram of CSI reporting;

[0118] FIG6 is a schematic diagram of a communication method provided in an embodiment of the present application;

[0119] FIG7 is a schematic diagram of a periodic CSI reporting provided in an embodiment of the present application;

[0120] FIG8 is a schematic diagram of an aperiodic CSI reporting method according to an embodiment of the present application;

[0121] FIG9 is a schematic diagram of another periodic CSI reporting provided in an embodiment of the present application;

[0122] FIG10 is a schematic diagram of another periodic CSI reporting provided in an embodiment of the present application;

[0123] FIG11a is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0124] FIG11b is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0125] FIG11c is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0126] FIG11d is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0127] FIG11e is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0128] FIG12 is a schematic diagram of another CSI reporting provided in an embodiment of the present application;

[0129] FIG13 is a schematic diagram of another CSI reporting provided in an embodiment of the present application;

[0130] FIG14a is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0131] FIG14b is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0132] FIG15a is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0133] FIG15b is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0134] FIG16 is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0135] FIG17 is a schematic diagram of interaction between a network device and a terminal device provided in an embodiment of the present application;

[0136] FIG18 is an interactive diagram of another communication method provided in an embodiment of the present application;

[0137] FIG19 is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0138] FIG20 is a schematic diagram of another CSI reporting method provided in an embodiment of the present application;

[0139] FIG21 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0140] Figure 22 is a structural diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0141] The technical solution in this application will be described below with reference to the accompanying drawings.

[0142] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, such as sixth generation (6G) mobile communication systems, or a fusion system of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0143] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the network element as an example for description. For example, the communication system may include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It is understandable that the terminal device in the present disclosure can be replaced by the first network element, and the network device can be replaced by the second network element, and the two perform the corresponding communication methods in the present disclosure.

[0144] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0145] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0146] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0147] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0148] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip that is set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0149] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0150] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0151] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0152] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0153] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0154] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0155] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0156] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0157] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0158] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, and therefore the demands that need to be met are becoming increasingly diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as network functionality becomes increasingly powerful, such as supporting higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new demands, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0159] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0160] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0161] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0162] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0163] An AI node can be an AI network element or an AI module.

[0164] Figure 1 is a schematic diagram of an application framework. As shown in Figure 1, network elements in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more devices of these network element nodes, such as core network equipment, access network nodes or devices (RAN nodes or devices), terminals or OAMs (for clarity, only one is shown in Figure 1). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0165] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0166] 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 on the same node or device.

[0167] Figure 2 is a schematic diagram of another application framework. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 1, which is used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real time RIC, near-RT RIC) and a non-real-time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0168] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near real-time RIC delivers the reasoning result to the DU, and the DU sends it to the RU.

[0169] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0170] The near real-time RIC and non-real-time RIC may also be separately configured as a network element. Optionally, the near real-time RIC and non-real-time RIC may also be part of other devices. For example, the near real-time RIC is configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network device.

[0171] Figure 3 is a schematic diagram of a communication system. As shown in Figure 3, communication system 100 may include at least one network device, such as network device 110 shown in Figure 3; communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 3. Network device 110 and terminal devices (such as terminal device 120 and terminal device 130) may communicate via wireless links. Communication devices in the communication system, such as network device 110 and terminal device 120, may communicate using multi-antenna technology.

[0172] Figure 4 is a schematic diagram of another communication system. Compared to the communication system 100 shown in Figure 3, the communication system 200 shown in Figure 4 also includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building a training data set or training an AI model.

[0173] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0174] It should be understood that Figure 4 illustrates only the example of a direct connection between AI network element 140 and network device 110. In other scenarios, AI network element 140 may also be connected to a terminal device. Alternatively, AI network element 140 may be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 may be connected to network device 110 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0175] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG3 .

[0176] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0177] The embodiments disclosed herein will present various aspects, embodiments, or features of the present invention centered around a system comprising multiple devices, components, modules, etc. It should be understood that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these solutions may also be used.

[0178] To facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0179] (1) AI, machine learning, and models:

[0180] AI (artificial intelligence) allows machines to possess human intelligence, for example, by using computer hardware and software to simulate certain intelligent human behaviors. Machine learning (ML) is a key technological approach to AI. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0181] In machine learning methods, a machine uses training data to learn (or train) a model, which represents the mapping from input to output. The model can be used for reasoning (or prediction), that is, the model can be used to predict the output corresponding to a given input. The output can also be called an inference result (or prediction result). The model can also be called an AI model, an ML model, a rule, a function, or other names. The AI ​​model can be considered as a specific method to implement a certain AI function, so the model and the function have the same meaning and can be replaced. The type of AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q learning model, or other machine learning models.

[0182] (2) Activation state of a model or function, deactivation state of a model or function:

[0183] The activation state of a model or function refers to at least one of the following: the terminal device supports the use of the model or function, the terminal device is capable of executing or running the model or function, the terminal device supports the execution or operation of the model or function, the terminal device has the ability to execute or run the model or function, the terminal device supports the execution (or operation or reasoning) of the model or function, the model or function in the terminal device is in a state where it can be used or executed (or run or reasoned), etc. The model or function in the terminal device is in an activated state, for example, including the terminal device having locally loaded a configuration file or model file for the model or function, or the model or function in the terminal device can be immediately executed (or run or reasoned).

[0184] Accordingly, the deactivated state of a model or function refers to at least one of the following: the terminal device does not support the use of the model or function, the terminal device cannot execute or run the model or function, the terminal device does not support the execution or operation of the model or function, the terminal device does not have the ability to execute the model or function, the terminal device does not support the execution (or operation or reasoning) of the model or function, the model or function in the terminal device is not in a state where it can be used or executed (or run or reasoned), the model or function in the terminal device is in a state where it cannot be used or executed (or run or reasoned), etc. The model or function in the terminal device is in a deactivated state, for example, the terminal device does not load the configuration file or model file of the model or function locally, or the model or function in the terminal device cannot be executed (or run or reasoned) immediately, or the model or function in the terminal device requires a certain amount of preparation time before it can be executed (or run or reasoned).

[0185] When a model or function is in an activated state, the terminal device can switch the activated state of the model or function to a deactivated state. Similarly, when a model or function is in a deactivated state, the terminal device can switch the deactivated state of the model or function to an activated state.

[0186] There may or may not be a delay when a terminal device switches a model or function from an active state to a deactivated state. If there is a delay when a terminal device switches a model or function from an active state to a deactivated state, the terminal device may switch the model or function from an active state to a deactivated state after a certain period of time. If there is no delay when a terminal device switches a model or function from an active state to a deactivated state, the terminal device may switch the model or function from an active state to a deactivated state directly at a certain moment.

[0187] Similarly, when a terminal device switches a model or function from a deactivated state to an activated state, there may or may not be a delay. If there is a delay when a terminal device switches a model or function from a deactivated state to an activated state, the terminal device will have to wait for a period of time before switching the activation state of the model or function to the activated state. If there is no delay when a terminal device switches a model or function from a deactivated state to an activated state, the terminal device can directly switch the model or function from the deactivated state to the activated state at a certain moment.

[0188] If there is a delay in the process of the terminal device switching the activation state of a model or function to the deactivation state, the terminal device will not process the activation or configuration of the model or function during the time period corresponding to the delay; if there is a delay in the process of the terminal device switching the deactivation state of a model or function to the activation state, the terminal device will not process the deactivation of the model or function during the time period corresponding to the delay.

[0189] (3) Channel state information (CSI) and CSI feedback:

[0190] CSI is a type of channel information that reflects channel characteristics and quality. In communication systems (such as LTE or NR), network equipment uses CSI to determine the resources, modulation and coding scheme (MCS), and precoding configuration for the downlink data channel of a terminal device.

[0191] In a time division duplex (TDD) system, due to the reciprocity of uplink and downlink channels, network equipment can obtain uplink CSI by measuring uplink reference signals, and then infer more accurate downlink CSI, for example, using uplink CSI as downlink CSI. In a frequency division duplex (FDD) system, uplink and downlink reciprocity cannot be guaranteed. Downlink CSI is obtained by the terminal device by measuring downlink reference signals, such as the channel state information reference signal (CSI RS) or the synchronization signal block (SSB). Therefore, the terminal device needs to generate a CSI report in accordance with the protocol pre-defined or network device configuration method, and feed back the downlink CSI to the network device through the CSI report. That is, the terminal device needs to feed back the downlink CSI to the network device.

[0192] In NR, the configuration and reporting process of downlink CSI includes: the network device sends a CSI reporting configuration (CSI-ReportConfig) to the terminal device, where the CSI reporting configuration is used to specify the reporting type (reportConfigType), reporting quantity (reportQuantity), etc., where the reporting type can be periodic reporting, semi-persistent reporting or aperiodic reporting, and the reporting quantity can be rank indicator (RI), channel quality indicator (CQI) and precoding matrix index (PMI), reference signal received power (RSRP), etc.; the network device sends CSI-RS to the terminal device; the terminal device performs channel measurement and interference measurement based on the CSI-RS to obtain measurement results; the terminal device determines the reporting quantities configured for reporting based on the measurement results, and reports the downlink CSI to the network device, where the downlink CSI includes information such as RI, CQI, PMI, RSRP measured by the terminal.

[0193] The RI indicates the number of downlink transmission layers recommended by the terminal device, the CQI indicates the modulation and coding scheme supported by the current channel conditions as determined by the terminal device, and the PMI indicates the precoding recommended by the terminal device. The number of precoding layers indicated by the PMI corresponds to the RI.

[0194] It should be understood that the RI, CQI, and PMI indicated in the above CSI report are only recommended values ​​for the terminal device, and the network device may perform downlink transmission according to part or all of the information indicated in the CSI report. Alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

[0195] In addition, if the reporting type in the CSI reporting configuration is configured as periodic, the terminal device performs periodic reporting according to the period specified in the radio resource control (RRC) signaling, and the network device does not need to send signaling to trigger the terminal device to report every time; if the reporting type in the CSI reporting configuration is configured as semi-persistent, the initial reporting of the terminal device needs to be triggered by signaling, and once triggered, the terminal device performs periodic reporting according to the specified period; if the reporting type in the CSI reporting configuration is configured as aperiodic, the network device needs to trigger the report through downlink control information (DCI). In the semi-statically configured CSI reporting trigger, when the CSI is carried on the physical uplink control channel (PUCCH) for reporting, the network device can trigger the terminal device to report CSI through the media access control layer control element (MAC-CE) signaling; when the CSI is carried on the physical uplink shared channel (PUSCH) for reporting, the network device can trigger the terminal device to report CSI through DCI.

[0196] (4) Number of CSI processing units (CPUs) and CSI calculation time:

[0197] The number of CSI processing units N available for the terminal device to report CSI CPU , indicating that the terminal device supports N CPU Calculation of CSI reports, N CPU Is a positive integer. At a certain symbol, if the calculation of the CSI report occupies L CPUs, the terminal device has N CPU -L unused CPUs, where L is less than N CPU A positive integer. For a certain symbol, N CPU - If L CPUs are not occupied, if there are N CSI reports, they need to occupy their respective CPUs starting from this symbol, where the number of CPUs corresponding to each CSI report is The terminal device does not need to update the NM lowest priority CSI reports, where 0≤M≤N, and M is the number of CSI reports that meet The maximum value of N is a positive integer. That is, when the unoccupied CPU is insufficient for the terminal device to process all CSI reports, the terminal device may not process some CSI reports according to priority.

[0198] Among them, the number of CPUs required for each CSI report processing It is related to the configured reporting amount and the number of reference signal resources used for channel measurement. For example, when the reporting amount is configured as RSRP, When the reporting amount is configured as PMI and the number of CPUs currently occupied is not 0, then where K s The number of CSI RS resources in the CSI RS resource set used for channel measurement. In addition, the CPU will continue to occupy several symbols for processing each CSI report.

[0199] When the reporting type (reportConfigType) is not set to 'none', the number of CPU symbols occupied is determined according to the following rules: Rule a, the periodic CSI report or semi-persistent CSI report (excluding the initial semi-persistent CSI report on the PUSCH after the physical downlink control channel (PDCCH) triggers the report) occupies the CPU for the time from the first symbol of the earliest reference signal resource used for channel measurement to the last symbol of the PUSCH / PUCCH carrying the report. Among them, each latest measurement resource is no later than the corresponding CSI reference resource. Rule b, the non-periodic CSI report occupies the CPU for the time from the first symbol after the PDCCH that triggers the CSI report to the last symbol of the PUSCH carrying the CSI report. Rule c, after the PDCCH triggers the CSI report, the initial semi-persistent CSI report on the PUSCH occupies the CPU for the time from the first symbol after the PDCCH to the last symbol of the PUSCH carrying the CSI report.

[0200] In addition, when triggering CSI reporting, the network device needs to reserve enough time for the terminal device to perform CSI calculation, that is, reserve CSI calculation time. For CSI reporting on PUSCH triggered by DCI, the terminal device will only report a valid CSI report when the following two conditions are met:

[0201] Condition 1: The first uplink symbol carrying the corresponding CSI report (including the effect of timing advance) starts no earlier than symbol Z ref ;

[0202] Condition 2: The first uplink symbol carrying the nth CSI report (including the effect of timing advance) starts no earlier than symbol Z'ref (n), where n is a positive integer.

[0203] Among them, Z ref For an uplink symbol, the interval between the start time of its cyclic prefix (CP) and the end time of the last symbol of the PDCCH that triggers the CSI report is greater than or equal to T proc,CSI =(Z)(2048+144)·κ2 -μ ·T C , and it is the earliest uplink symbol that meets this condition. Z is the value obtained according to the table in the protocol; T C is the basic time unit in NR, T c =1 / (Δf max ·N f ), where Δf max =480·10 3 Hz, N f =4096;κ=64;μ=min(μ PDCCH ,μ CSI-RS ,μ UL ), μ PDCCH is the subcarrier spacing configuration of the PDCCH that transmits DCI, μ CSI-RS is the minimum subcarrier spacing configuration of CSI-RS, μ UL It is the subcarrier spacing configuration of PUSCH for transmitting CSI reports.

[0204] When the aperiodic CSI RS is used for channel measurement of the nth triggered CSI report, Z' ref (n) is defined as an uplink symbol whose CP start time and the end time of the last symbol of the resource that ends the latest among the resources used for measurement are greater than or equal to T′ proc,CSI =(Z′)(2048+144)·κ2 -μ ·T C , and is the earliest uplink symbol that meets this condition. The values ​​of Z and Z′ are determined according to the table and principles given by the protocol.

[0205] Please refer to Figure 5, which is a schematic diagram of a CSI report. As shown in Figure 5, the time interval between the first symbol of the PUSCH carrying the CSI report and the end time of the last symbol of the PDCCH triggering the CSI report is greater than or equal to the specified time parameter T proc,CSI , and the time interval between the first PUSCH symbol carrying the CSI report and the end time of all reference resources used for channel measurement is greater than or equal to the specified time parameter T′ proc,CSI .

[0206] When conditions 1 and 2 are not met, the terminal device does not need to update the reported CSI. In addition, for non-DCI triggered reporting (i.e., periodic reporting and semi-continuous reporting), the network device can limit the CSI calculation time by defining CSI reference resources to ensure that the terminal device only needs to update the reported CSI when there is sufficient calculation time. The CSI reference resource is defined as a block of time-frequency resources. In the frequency domain, the CSI reference resource is defined by a set of downlink physical resource blocks corresponding to the frequency band related to the calculation of CSI; in the time domain, the CSI reference resource is defined as a valid time slot before the uplink time slot of the CSI report, and the number of symbols between the time slot where the CSI reference resource is located and the CSI reporting time slot needs to be greater than the specified value. The CSI RS used to calculate the CSI report cannot be later than the CSI reference resource. If there is no valid downlink time slot corresponding to a certain CSI reporting configuration, the terminal device may not report the CSI. In other words, the time interval between the CSI RS used to calculate the CSI report and the CSI reporting time slot is greater than or equal to the specified time parameter.

[0207] (5) Air interface AI

[0208] AI has been widely used in many air interface technology scenarios, such as CSI feedback, CSI prediction, beam management, and positioning. For example, when applying AI in CSI feedback scenarios, an autoencoder architecture can be used for CSI feedback. This architecture typically includes an AI encoder and an AI decoder. The AI ​​encoder can be deployed in the terminal device, while the AI ​​decoder can be deployed in the network equipment. Compared to traditional CSI feedback technologies, AI-based CSI feedback can reduce air interface feedback overhead and terminal device computational complexity while maintaining the same CSI feedback performance, offering greater application prospects. For example, when applying AI in CSI prediction scenarios, the terminal device or network equipment can use a prediction model to leverage historical CSI to predict future CSI and feed it back to the network equipment. The AI ​​model can be located in either the terminal device or the network equipment. Accurately predicting future CSI can address the issue of inaccurate CSI feedback due to channel time variations. For example, when AI is applied in a beam management scenario, the terminal device or network device can use the AI ​​model to efficiently and accurately identify the best beam. The AI ​​model can be located only in the terminal device or only in the network device. For example, when the AI ​​model is applied in a positioning scenario, three-point positioning can be used for positioning. The terminal device obtains the location information of the three surrounding network devices and inputs it into the corresponding AI model. The AI ​​model then obtains the location of the terminal device based on information such as the distance, direction, and channel from the terminal device to the three network devices.

[0209] The lifecycle of an AI model during use involves the following steps: data collection, model training (or model learning), model information release, model activation / deactivation, model inference (also known as model reasoning, inference, or prediction), model monitoring or model verification, model updates, or the release of inference results. Air interface AI model lifecycle management (LCM) can be based on model identification (model ID) or functionality. A model ID is an identifier assigned in some way to identify a model. In model ID-based LCM, model operations such as activation / deactivation / selection / fallback / switching are indicated by the model ID. Functionality refers to a configuration-related AI feature, or in other words, a functionality corresponds to a specific configuration under an AI feature, where the configuration is supported based on conditions indicated by the terminal device's capabilities. AI features refer to features that can use AI, such as AI-based CSI feedback and AI-based beam management. In functionality-based LCM, network equipment can instruct terminal devices on operations of AI functions, such as activation / deactivation / selection / fallback / switching, through 3rd generation partnership project (3GPP) signaling (e.g., RRC, media access control element (MAC-CE), DCI).

[0210] Specifically, an AI feature may include one or more functions. For each function, one model or multiple models may be used to implement it. Furthermore, a single model can be used to implement multiple functions. For example, one functionality corresponds to one AI feature. For example, functionality 1 is AI-based time-domain beamforming prediction, and functionality 2 is AI-based spatial beamforming prediction.

[0211] Exemplarily, one functionality corresponds to one AI feature + a set of specific RRC configurations, for example: functionality 1 is AI-based time domain beam prediction under configuration 1, and functionality 2 is AI-based time domain beam prediction under configuration 2, where configuration 1 and configuration 2 include at least one of the following: CSI RS resource configuration, CSI reporting configuration, beam set configuration, or prediction window configuration, etc.

[0212] Exemplarily, one functionality corresponds to one AI feature + a set of specific RRC configurations + scenario / site identifiers. For example, functionality 1 is AI-based time domain beam prediction under configuration 1 and scenario 1, and functionality 2 is AI-based time domain beam prediction under configuration 1 and scenario 2, where configuration 1 includes at least one of the following: CSI RS resource configuration, CSI reporting configuration, beam set configuration, or prediction window configuration, and scenario 2 can be at least one of the following: urban area, suburbs, urban macrocell (UMa), urban microcell (UMi), indoor hotspot cell (InH) or highway, etc.

[0213] When model parallelization is supported, multiple processes can run concurrently on a single model or function. This means that multiple processes can run concurrently on the same model or function, each performing independent reasoning. In this case, "model or function" in this application can be replaced with "a process of a model or function."

[0214] When the model is deployed on the terminal device side, the network device may not be able to know the specific model it is using and the model status. In the functionality-based LCM, the network device can instruct the terminal device to activate / deactivate the AI ​​function through 3GPP signaling. However, there may be multiple models corresponding to one functionality, and multiple functions may be implemented by one model. Therefore, the network device cannot accurately know the activation / deactivation status of the model for a certain function, which may cause the task to fail to be executed smoothly.

[0215] Furthermore, even if the terminal device can perform tasks normally, it will result in a waste of resources. For example, if the terminal device's corresponding functions 1 and 2 are both implemented using Model 1, the network device first activates Functionality 1, instructing the terminal to perform a CSI report for beam prediction. The terminal device then activates Model 1 for inference. Some time later, the network device activates Functionality 2 and instructs the terminal device to perform another CSI report for beam prediction. The terminal device can then directly use Model 1 for inference without activating Model 1. However, the network device assumes that the model corresponding to Functionality 2 requires activation time and reserves model activation time for the second CSI report, resulting in a waste of CSI computing resources.

[0216] It can be seen that if the network device and the terminal device do not align the activation / deactivation status of a model, the terminal device may not be able to perform the task smoothly when using the model again, or it may cause a waste of resources when executing the task.

[0217] It should be understood that the above description uses the AI ​​model for CSI reporting for beam prediction as an example. The AI ​​model can also be used in other scenarios in CSI feedback. For example, the AI ​​model can be used for CSI prediction. The embodiments of this application do not limit the specific use of the AI ​​model in the CSI feedback scenario.

[0218] It should be understood that, in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication of information A refers to including information A; implicit indication of information A refers to indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0219] It should be understood that, in this application, information C is used to determine information D, which includes both information D being determined solely based on information C and information D being determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0220] In addition, in each embodiment of the present application, "network element A sends information A to network element B" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0221] In the embodiment of the present application, the terminal device may be a terminal device configured with one or more models or functions. For example, the terminal device may be the terminal device shown in FIG1 .

[0222] In the embodiment of the present application, the first task is one of a periodic task, a semi-persistent task, and a dynamically scheduled task. The second task is also one of a periodic task, a semi-persistent task, and a dynamically scheduled task. The third task is also one of a periodic task, a semi-persistent task, and a dynamically scheduled task. The embodiment of the present application does not limit the time characteristics of the first task, the second task, and the third task. For example, the first task is a dynamically scheduled task, the second task is a periodic task, and the third task is a dynamically scheduled task. For another example, the first task, the second task, and the third task are all periodic tasks.

[0223] In the embodiment of the present application, the first downlink signal and the first uplink signal are signals related to the second task. For example, the first downlink signal is a downlink signal used to trigger the second task. In another example, the first uplink signal is an uplink signal that carries reporting information corresponding to the second task. The first downlink signal can be a downlink signal or a downlink channel, and the first uplink signal is an uplink channel.

[0224] In the embodiment of the present application, the second downlink signal and the second uplink signal are signals related to the first task. For example, the second downlink signal is a downlink signal used to trigger the first task. In another example, the second uplink signal is an uplink signal that carries reporting information corresponding to the first task. The second downlink signal can be a downlink signal or a downlink channel, and the first uplink signal is an uplink channel.

[0225] Among them, the downlink signal can be a reference signal or a physical broadcast channel block (synchronization signal and physical broadcast channel block, SSB), and the reference signal can be one of the CSI RS, tracking reference signal (TRS), phase tracking reference signal (PTRS), and positioning reference signal (PRS). The downlink channel can be PDCCH, and the uplink channel can be PUSCH or PUCCH. For example, the first task is a dynamically scheduled CSI reporting task, and the second downlink signal can be a PDCCH for triggering the terminal device to perform the CSI reporting task, or it can be a reference signal or SSB for measuring CSI, and the second uplink signal is PUSCH or PUCCH carrying the CSI report.

[0226] In the embodiment of the present application, the moment also includes a time unit, which can refer to a second (s), a millisecond (ms), a microsecond (us), a time slot (slot), a symbol (symbol), or at least one consecutive symbol. The embodiment of the present application does not limit the specific method of the time unit.

[0227] The present application proposes a communication method, and Figure 6 is a schematic diagram of the communication method. The communication method is described from the perspective of interaction between a network device and a terminal device, and includes but is not limited to the following steps:

[0228] S601. A network device sends first information to a terminal device, the first information being used to instruct the terminal device to perform a first task, wherein, when a first model or function is in a first state, at least one of the following items corresponding to the first task is different from when the first model or function is in a second state: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, computing unit occupancy time period of the first model or function, and the first model or function corresponds to the first task. Accordingly, the terminal device receives the first information from the network device.

[0229] Optionally, the "indication" in which the first information is used to instruct the terminal device to perform the first task can be understood as "trigger" or "configuration". For example, the first information is used to trigger the terminal device to perform the first task. For another example, the first information is used to configure the terminal device to perform the first task.

[0230] In an embodiment of the present application, the first task is a task performed by running the first model or function, or in other words, the first task requires the use of the first model or function to perform model reasoning. When the first model or function is in the first state (activated state), model reasoning can be performed directly. When the first model or function is in the second state (deactivated state), the model or function needs to be activated first so that the model or function is switched to the first state (activated state) before model reasoning is performed. Therefore, the first information is used to instruct the terminal device to perform the first task, which can be understood as implicitly instructing the terminal device to perform the activation and reasoning of the first model or function corresponding to the first task. In other words, the network device can indicate the activation of the first model or function through the first information, and the terminal device determines whether it is necessary to perform the actual model activation operation based on the state of the first model or function.

[0231] When the first task is a periodic task, the first information can be carried in the RRC signaling; when the first task is a semi-persistent task, the first information can be carried in the MAC-CE or PDCCH; when the first task is a dynamically scheduled task, that is, a non-periodic task, the first information can be carried in the DCI, and the DCI is carried in the PDCCH. Among them, the first task is a periodic task, indicating that the terminal device needs to perform the first task periodically. The first task is a semi-persistent task, indicating that when the terminal device is triggered to perform the first task, it needs to perform the first task periodically. The first task is a dynamically scheduled task, indicating that the terminal device performs the first task once when it is triggered to perform the first task.

[0232] For example, when the first task is a periodic CSI reporting task, the first information may be CSI reporting configuration information, which is carried in RRC signaling, and is used to configure the period and reporting amount of the terminal device's periodic CSI reporting. For another example, when the first task is a semi-continuous CSI reporting task, the first information may be CSI reporting trigger information, which is carried in MAC-CE, and is also used to configure the period and reporting amount of the terminal device's CSI reporting. For another example, when the first task is a dynamically scheduled CSI reporting task, the first information may also be CSI reporting trigger information, which is carried in DCI, which is carried in PDCCH, and is used to configure the resources and reporting amount for the terminal device to report CSI.

[0233] In addition, the first model or function corresponds to the first task, which can be one of the following: the model or function required for the terminal device to perform the first task is the first model or function, the terminal device uses the first model or function to perform the first task, the first task is performed using the first model or function, the first task is a task supported by the first function, the first task is one of one or more tasks supported by the first function, the first task is a task performed using the first model or function, and the first task is one of one or more tasks performed using the first model or function. For example, the first task is a CSI reporting task, and the first model or function corresponding to the first task is model or function 1, then the model used by the terminal device to perform model inference to obtain CSI is model or function 1. Similarly, the second model or function corresponds to the second task, and the third model or function corresponds to the third task, which have similar understandings and will not be repeated.

[0234] Optionally, the first state is an activated state, and the second state is a deactivated state. The activation state of the model or function and the deactivated state of the model or function can be referred to as described above and will not be repeated here.

[0235] Optionally, the first state is an active and idle state, and the second state is a deactivated state. The first state is an active and idle state, indicating that the model or function is in an active state and not in use. In this method, the state of the model or function also includes a third state, which is an active and occupied state, indicating that the model or function is in an active state and is occupied / used. In other words, the third state is the state when the model or function is used for model reasoning.

[0236] Optionally, the phrase "the first model or function is in the first state" can be replaced by the phrase "the first task is in the first state, and the first task is in the first state," indicating that the first model or function used by the terminal device to perform the first task is in the first state. Accordingly, the phrase "the first model or function is in the second state" can be replaced by the phrase "the first task is in the second state, and the first task is in the second state," indicating that the first model or function used by the terminal device to perform the first task is in the second state.

[0237] In an optional implementation, the delay requirement is the time interval requirement between the second downlink signal and the second uplink signal, and the second downlink signal and the second uplink signal are both related to the first task. The second downlink signal and the second uplink signal are both related to the first task, indicating that: the second downlink signal is a downlink channel used to trigger the terminal device to perform the second task, or is a downlink signal used by the terminal device to perform the second task, and the second uplink signal is an uplink channel that carries the report information corresponding to the second task. For example, the first task is a CSI reporting task, the second downlink signal is the RRC signaling or PDCCH or MAC-CE used to trigger CSI reporting, or the second downlink signal is a reference signal or SSB used to measure CSI during CSI reporting, and the second uplink signal is the PUSCH or PUCCH that carries the CSI report.

[0238] For example, the first task is the CSI reporting task, the second downlink signal is the PDCCH used to trigger the CSI reporting, and the second uplink signal is the PUSCH carrying the CSI report. The delay requirement is the time interval requirement between the PDCCH and the PUSCH. For example, in this case, the delay requirement is: the first uplink symbol carrying the corresponding CSI report (including the effect of timing advance) starts no earlier than symbol Z ref , or the first uplink symbol carrying the nth CSI report (including the effect of timing advance) starts no earlier than symbol Z' ref (n), n is a positive integer. Among them, Z ref For an uplink symbol, the interval between the start time of its CP and the end time of the last symbol of the PDCCH that triggers the CSI report is greater than or equal to the specified time length, Z' ref(n) is defined as an uplink symbol whose CP start time and the end time of the last symbol of the resource that ends the latest among the resources used for measurement are greater than or equal to the specified time length.

[0239] For example, the first task is a CSI reporting task, the second downlink signal is a CSI RS for measuring CSI, and the second uplink signal is a PUSCH for carrying CSI reports. The delay requirement is the time interval requirement between the CSI RS and the PUSCH, or the delay requirement is the time interval requirement between the CSI reference resource and the PUSCH.

[0240] In another optional implementation manner, the delay requirement is a time interval requirement between the second downlink signal and the end moment of the usage time period of the first model or function.

[0241] The usage period of the first model or function refers to the period of time during which the terminal device uses the first model or function for model inference. For example, if the first task is a CSI reporting task and the second downlink signal is a CSI RS used to measure CSI, the latency requirement is the required time interval between the CSI RS and the end of the period during which the terminal device uses the first model or function for CSI prediction.

[0242] In another optional implementation, the delay requirement is a time interval requirement between the second downlink signal and the end moment of the storage unit occupancy time period of the first model or function.

[0243] Optionally, the first model or function occupies the storage unit when it is in the first state, occupies the storage unit for the time period when the first model or function switches from the first state to the second state, and occupies the storage unit for the time period when the first model or function switches from the second state to the first state, and does not occupy the storage unit when the first model or function is in the second state.

[0244] Then, the delay requirement is the time interval requirement between the second downlink signal and the end moment of the storage unit occupation time period of the first model or function, which can be: the delay requirement is the time interval between the second downlink signal and the start moment of the first model or function being in the second state.

[0245] In another optional implementation, the delay requirement is a time interval requirement between the second downlink signal and the end moment of the computing unit occupation time period of the first model or function.

[0246] Optionally, the first model or function occupies the computing unit when it is in the first state. Optionally, the first model or function occupies the computing unit when it is used for model reasoning.

[0247] Optionally, the first model or function does not occupy the computing unit when it is in the second state, the time period when the first model or function switches from the first state to the second state does not occupy the computing unit, and the time period when the first model or function switches from the second state to the first state does not occupy the computing unit.

[0248] Optionally, when the first model or function is in the first state relative to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function. This can be replaced by: when the first model or function corresponding to the first task is in the first state, at least one of the following items corresponding to the first task is different from when the first model or function corresponding to the first task is in the second state: latency requirement, method for determining the usage time period of the first model or function, method for determining the storage unit occupancy time period of the first model or function, and method for determining the computing unit occupancy time period of the first model or function. Or it can be replaced by: when the first model or function corresponding to the first task is in the first state relative to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different from when the first model or function is in the first state: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function.

[0249] Optionally, the storage unit can be replaced with "storage resource" and the computing unit can be replaced with "computing resource." For example, the storage unit occupation time period of the first model or function can be replaced with "storage resource occupation time period of the first model or function," and the computing unit occupation time period of the first model or function can be replaced with "computing resource occupation time period of the first model or function." Similarly, the storage unit occupation time period of other models or functions can be replaced with "storage resource occupation time period," and the computing unit occupation time period of other models or functions can be replaced with "computing resource occupation time period." These details will not be repeated here.

[0250] It can be seen that when the first function or model used by the terminal device to perform the first task is in the first state and the second state, at least one of the following items of the first task differs: the latency requirement, the usage period of the first model or function, the storage unit occupancy period of the first model or function, and the computing unit occupancy period of the first model or function. Therefore, after receiving the first information, the terminal device can determine the state of the first model or function, and then, based on the state of the first model or function, determine at least one of the following items corresponding to the first task: the latency requirement, the usage period of the first model or function, the storage unit occupancy period of the first model or function, and the computing unit occupancy period of the first model or function, and then perform the first task based on the determined at least one item. The at least one item corresponding to the first task: the latency requirement, the usage period of the first model or function, the storage unit occupancy period of the first model or function, and the computing unit occupancy period of the first model or function can be considered as the requirement corresponding to the first task. This approach facilitates matching the requirement corresponding to the first task with the state of the first model or function, thereby facilitating the terminal device to smoothly execute the first task, or in other words, facilitates the smooth execution of model reasoning corresponding to the first model or function.

[0251] S602. The terminal device executes the first task.

[0252] When the first model or function corresponding to the first task is in different states, at least one of the following items of the first task differs: latency requirement, usage period of the first model or function, storage unit occupancy period of the first model or function, and computing unit occupancy period of the first model or function. Therefore, the terminal device must execute the first task in conjunction with the state of the first model or function corresponding to the first task to ensure that the requirements corresponding to the first task match the state of the first model or function, thereby ensuring the smooth execution of the first task, or in other words, ensuring the smooth execution of model reasoning corresponding to the first model or function.

[0253] In an optional embodiment, a terminal device performs a first task, including: determining a state of a first model or function; based on the state of the first model or function, determining at least one of the following items corresponding to the first task: a latency requirement, a usage period of the first model or function, a storage unit occupancy period of the first model or function, and a computing unit occupancy period of the first model or function; and performing the first task based on the at least one item determined. This approach ensures that at least one item of the determined first task matches the state of the first model or function, thereby ensuring that the terminal device can successfully perform the first task, or in other words, ensuring that model reasoning for the first model or function is successfully performed.

[0254] In an optional implementation, the terminal device determines the state of the first model or function, including: determining a second moment corresponding to the second model or function; and determining the state of the first model or function based on the second moment and the start moment of the first task.

[0255] The second model or function corresponds to the second task. The second model or function corresponds to the second task, meaning that the model or function used by the terminal device to execute the second task is the second model or function. The start time of the second task is earlier than the start time of the first task, or in other words, the trigger time / start time of the second task is earlier than the trigger time or start time of the first task.

[0256] The starting time of the second task corresponds to one of the following: the starting time of the first downlink signal, the ending time of the first downlink signal, the fourth offset time, the starting time of the usage time period of the second model or function, the starting time of the storage unit occupation time period of the second model or function, and the starting time of the calculation unit occupation time period of the second model or function. Among them, the time interval between the fourth offset time and the starting time or the ending time of the first downlink signal corresponds to the seventh time offset. The first downlink signal is related to the second task. Specifically, the first downlink signal can be a channel used to trigger the terminal device to perform the second task, such as PDCCH or DCI, or it can be a signal used by the terminal device to perform the second task, such as one of CSI RS, TRS, PTRS, PRS, and SSB.

[0257] The starting moment of the second task corresponds to the starting moment of the first downlink signal, which can be: the starting moment of the second task is the starting moment of the first downlink signal, or it can be: the starting moment of the second task is determined based on the starting moment of the first downlink signal. The starting moment of the second task is determined based on the starting moment of the first downlink signal, which can be: the starting moment of the second task is the starting moment or end moment of the time unit where the starting moment of the first downlink signal is located, or it can be: the starting moment of the second task is the starting moment of the first time unit after the time unit where the starting moment of the first downlink signal is located. Similarly, the starting moment of the second task corresponds to other moments, and has a similar understanding, so it will not be repeated.

[0258] The second model or function corresponding to the second task is the same as the first model or function corresponding to the first task. The second model or function is the same as the first model or function, which can be understood as follows: the second model or function and the first model or function are used to implement the same function, such as both are used to predict CSI or predict beam, or the second model or function and the first model or function have the same physical model. The second model or function has the same structure and all parameters as the first model or function, or the second model or function has the same structure as the first model or function but some parameters are different, such as the number of layers, width, and inter-layer connection relationship of the neural network, and the parameters are such as the weights and bias of the neural network. For example, the first model or function and the second model or function are both used to implement CSI prediction, and the first model or function has the same structure as the second model or function but some weight values ​​are different.

[0259] Optionally, the second moment corresponding to the second model or function can be understood as the duration of the first state of the second model or function. In other words, the first state of the second model or function may continue until the second moment, or the second model or function may not be in the first state after the second moment.

[0260] It can be seen that the terminal device can determine the state of the first model or function based on the duration of the first state of the second model or function and the start time of the first task. In other words, the duration of the first state of the second model or function can be used to determine the state of the first model or function.

[0261] In an optional implementation, the terminal device determines the second time corresponding to the second model or function, including: determining the second time according to the first time and the first time length, wherein the second time is later than the first time.

[0262] Optionally, the first moment may also be referred to as a timing start, and the first time length may also be referred to as a timing duration (timer).

[0263] In an optional embodiment, the first moment corresponds to one of the following: the start moment of the first downlink signal, the end moment of the first downlink signal, the start moment of the first uplink signal, the end moment of the first uplink signal, a first offset moment, and a second offset moment. The time interval between the first offset moment and the start moment or end moment of the first downlink signal corresponds to the first time offset, and the time interval between the second offset moment and the start moment or end moment of the first uplink signal corresponds to the second time offset.

[0264] The first downlink signal and the first uplink signal are both related to the second task. The first uplink signal can be a channel that carries reporting information when the terminal device performs the first task, such as PUCCH or PUSCH.

[0265] The first moment corresponds to the starting moment of the first downlink signal, which can be: the first moment is the starting moment of the first downlink signal, or it can indicate: the first moment is determined based on the starting moment of the first downlink signal, for example, the first moment is determined based on the starting moment of the first downlink signal and the first time offset, or the first moment is the starting moment or ending moment of the time unit in which the starting moment of the first downlink signal is located, or the first moment is the starting moment of the first time unit after the time unit in which the starting moment of the first downlink signal is located. Similarly, the first moment corresponds to other moments, has the same meaning, and is not further described.

[0266] For example, the first task belongs to a periodic CSI reporting task, and Figure 7 is a schematic diagram of a periodic CSI reporting. As shown in Figure 7, the first moment is the starting moment of the CSI RS used to measure CSI. For another example, the first task belongs to a dynamically scheduled CSI reporting task, and Figure 8 is a schematic diagram of a non-periodic CSI reporting. As shown in Figure 8, the network device triggers the terminal device to perform non-periodic CSI reporting through DCI at time t1, and the first moment is the starting moment or end moment of the DCI. For another example, the first task belongs to a periodic CSI reporting task, and Figure 9 is a schematic diagram of another periodic CSI reporting. As shown in Figure 9, the first moment is the starting moment of the PUSCH carrying the CSI report.

[0267] In addition, the first time offset and / or the second time offset may be reported by the terminal device, preset, or configured or indicated by the network device. The value of the first time offset and the value of the second time offset may be positive or negative.

[0268] When the value of the first time offset is a positive number, the time interval between the first offset moment and the start moment or end moment of the first downlink signal corresponds to the first time offset, indicating that the first offset moment is the moment when the start moment or end moment of the first downlink signal is delayed by the first time offset. For example, Figure 10 is another schematic diagram of periodic CSI reporting. As shown in Figure 10, the first moment is the first offset moment t3, and t3 is the moment when the start moment t2 of the CSI RS used to measure CSI is delayed by the first time offset, that is, the first time offset is a positive number. When the value of the first time offset is a negative number, the time interval between the first offset moment and the start moment or end moment of the first downlink signal corresponds to the first time offset, indicating that the first offset moment is the moment corresponding to the start moment or end moment of the first downlink signal being advanced by the absolute value of the first time offset.

[0269] Similarly, when the value of the second offset is a positive number, the time interval between the second offset moment and the start moment or end moment of the first uplink signal corresponds to the second time offset, indicating that the second offset moment is the moment when the start moment or end moment of the first uplink signal is delayed by the second time offset; when the value of the second offset is a negative number, the time interval between the second offset moment and the start moment or end moment of the first uplink signal corresponds to the second time offset, indicating that the second offset moment is the moment corresponding to the start moment or end moment of the first uplink signal being advanced by the absolute value of the second time offset. For example, Figure 11a is another CSI reporting schematic diagram. As shown in Figure 11a, the first moment is the second offset moment t3, and t3 is the moment when the start moment of the PUSCH carrying the CSI report is delayed by the second time offset, that is, the second time offset is a positive number. For another example, Figure 11b is another CSI reporting schematic diagram. As shown in Figure 11b, the first moment is the second offset moment t2, and t2 is the moment when the start moment of the PUSCH carrying the CSI report is advanced by the second time offset, that is, the second time offset is a negative number.

[0270] Optionally, multiple of the first time offset between the start moment of the first downlink signal and the first offset moment, the first time offset between the end moment of the first downlink signal and the first offset moment, the second time offset between the start moment of the first uplink signal and the second offset moment, and the second time offset between the end moment of the first uplink signal and the first offset moment may be equal or unequal, and this is not limited in the embodiments of the present application. For example, the first time offset between the start moment of the first downlink signal and the first offset moment is equal to or unequal to the first time offset between the end moment of the first downlink signal and the first offset moment. For another example, the first time offset between the start moment of the first downlink signal and the first offset moment is equal to or unequal to the second time offset between the end moment of the first uplink signal and the second offset moment.

[0271] In another optional embodiment, the first moment corresponds to one of the following: the starting moment of the usage time period of the second model or function, the starting moment of the storage unit occupation time period of the second model or function, and the starting moment of the computing unit occupation time period of the second model or function.

[0272] For example, if the second model or function is the model or function used for periodic CSI reporting in FIG7 , and the usage period of the model or function is the model reasoning period shown in FIG7 , then the first moment in FIG7 may not be t2, but may be t4, the starting moment of the time period occupied by the model reasoning in FIG7 . For another example, if the second model or function is the model or function used for periodic CSI reporting in FIG7 , and the starting moment of the storage unit occupation period of the model or function is t5, the starting moment of the model activation in FIG7 , then the first moment in FIG7 may not be t2, but may be t5, the starting moment of the model activation in FIG7 . For another example, if the second model or function is the model or function used for periodic CSI reporting in FIG7 , and the computing unit occupation period of the model or function is also the model reasoning period shown in FIG7 , then the first moment in FIG7 may not be t2, but may be t4, the starting moment of the time period occupied by the model reasoning in FIG7 .

[0273] In another optional embodiment, the first moment corresponds to one of the following: the end of a usage period of the second model or function, the end of a storage unit occupancy period of the second model or function, or the end of a computing unit occupancy period of the second model or function. In this embodiment, the first state is an active and idle state, and before the first moment, the second model or function is in a third state. The third state is an active and occupied state, i.e., the third state is a state in which the model or function is in model inference.

[0274] For example, Figure 11c is another schematic diagram of CSI reporting. As shown in Figure 11c, the first moment is t3, which means the first moment is the end of the usage period of the second model or function corresponding to the second task, and the first moment is the end of the model reasoning of the second model or function.

[0275] Optionally, the first moment corresponds to one of the following: the end moment of the usage time period of the second model or function, the end moment of the storage unit occupation time period of the second model or function, and the end moment of the computing unit occupation time period of the second model or function. The first state of the second model or function is expected to last from the first moment to the second moment, and the second moment is later than the first moment. The first state of the second model or function is expected to last from the first moment to the second moment, which means that without considering the first task, according to the second task, it can be expected that the second model or function corresponding to the second task is in the first state during the time period from the first moment to the second moment. For example, in Figure 11c, if the influence of the first task is not considered, the first state of the second model or function corresponding to the second task is expected to last from the first moment t3 to the second moment t5, that is, during the time period between t3 and t5, the second model or function is expected to be in both active and idle states.

[0276] Optionally, when the second task is a periodic task or a semi-continuous task, the first moment corresponds to one of the following: the starting moment or ending moment of the reference signal corresponding to the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located; the starting moment or ending moment of the reference resource corresponding to the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference resource corresponding to the second task is located; the starting moment or ending moment of the physical uplink shared channel PUSCH or physical uplink control channel PUCCH carrying the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the PUSCH or PUCCH carrying the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the PUSCH or PUCCH carrying the reporting information of the second task is located; the starting moment of the reference signal corresponding to the second task is advanced or delayed by the time offset The time at which the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located is advanced or delayed by the time offset; the time at which the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located is advanced or delayed by the time offset; the time at which the starting moment or ending moment of the reference resource corresponding to the second task is advanced or delayed by the time offset; the time at which the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference resource corresponding to the second task is located is advanced or delayed by the time offset; the time at which the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference resource corresponding to the second task is located is advanced or delayed by the time offset; The reference signal corresponding to the second task may be a first downlink signal, and the PUSCH or PUCCH carrying the reporting information of the second task may be a first uplink signal.

[0277] Optionally, when the second task belongs to a dynamically scheduled task, the first moment corresponds to one of the following: the starting moment or ending moment of the reference signal corresponding to the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located; the starting moment or ending moment of the PDCCH that triggers the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the PDCCH that triggers the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the PDCCH that triggers the second task is located; the starting moment or ending moment of the PUSCH or PUCCH that carries the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the PUSCH or PUCCH that carries the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the PUSCH or PUCCH that carries the reporting information of the second task is located; the moment when the starting moment or ending moment of the reference signal corresponding to the second task is advanced or delayed by the time offset; the reference signal corresponding to the second task The starting moment or ending moment of the time unit in which the starting moment or ending moment of the signal is located is advanced or delayed by the time offset; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the reference signal corresponding to the second task is located is advanced or delayed by the time offset; the starting moment or ending moment of the PDCCH that triggers the second task is advanced or delayed by the time offset; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the PDCCH that triggers the second task is advanced or delayed by the time offset; the starting moment or ending moment of the time unit in which the PDCCH that triggers the second task is advanced or delayed by the time offset; The moment after the time unit in which the start moment of the first time unit after the time unit is advanced or delayed by the time offset; the moment after the start moment or end moment of the PUSCH or PUCCH carrying the reporting information of the second task is advanced or delayed by the time offset; the moment after the start moment or end moment of the time unit in which the start moment or end moment of the PUSCH or PUCCH carrying the reporting information of the second task is advanced or delayed by the time offset; the moment after the start moment of the first time unit after the time unit in which the start moment or end moment of the PUSCH or PUCCH carrying the reporting information of the second task is advanced or delayed by the time offset. Among them, the reference signal corresponding to the second task and the PDCCH triggering the second task can be the first downlink signal, and the PUSCH or PUCCH carrying the reporting information of the second task can be the first uplink signal.

[0278] In an optional implementation, the first moment is determined based on the sixth moment and the sixth time length. The implementation of the sixth moment and the sixth time length is similar to the implementation of the first moment and the first time length, and will not be repeated.

[0279] In addition, the first time length may be an absolute time length that does not distinguish between sub-carrier intervals, such as the first time length is expressed in milliseconds (ms). Alternatively, the first time length may be a time length that distinguishes between sub-carrier intervals, such as the first time length is expressed in slots or symbols.

[0280] In an optional implementation, the first time length may be determined based on an index or identifier corresponding to the first time length. For example, if the network device configures the first time length for the terminal device using the index or identifier corresponding to the first time length, the terminal device may determine the first time length based on the index or identifier corresponding to the first time length.

[0281] For example, the network device determines that there are 8 selectable values ​​for the first time length, then each index from 0 to 7 corresponds to a specified time length, and the correspondence between each index and the time length is determined by protocol preset or configuration.

[0282] For another example, the network device determines that the first time length is a value of 16 integers from 0 to 15, where "0" represents that the second model or function remains in the first state, "16" represents that the second model or function is switched to the second state after use, and the remaining values ​​represent the values ​​of the first time length. Then, the terminal device can determine the first time length based on the value indicated by the network device. For example, if the value indicated by the network device is 6, the terminal device determines the first time length to be 6 time units.

[0283] In another optional implementation, when the second task is a periodic task or a semi-continuous task, the first time length can be determined based on the reporting period of the second task, for example, the first time length is 1 / M times the reporting period of the second task, where M is a positive integer.

[0284] In another optional embodiment, the first time length can be determined based on the time characteristics of the second task. For example, when the second task is a periodic task or a semi-persistent task, the first time length needs to be configured. For example, the first time length is 1 / M times the reporting period of the second task or is equal to the reporting period. For another example, when the second task is a dynamically scheduled task, the first time length is 0, that is, for a non-periodic task, the first time length does not need to be configured.

[0285] Optionally, the first moment and the first duration may be configured by the network device for the terminal device. For example, the network device configures the first moment and the first duration for the terminal device via first information, i.e., the first information includes the first moment and the first duration. Optionally, the first moment and the first duration may be preset, or may be pre-negotiated between the network device and the terminal device.

[0286] For each task, the first moment, the first time length and / or the second moment can be configured or set independently. For example: for periodic or semi-continuous tasks, the network device configures a set of first moment and first time length, and the second moment is determined based on the first moment and the first time length; for dynamically scheduled tasks, the network device configures another set of first moment and first time length, and the second moment is determined based on the first moment and the first time length. For another example: for periodic or semi-continuous tasks, the network device configures a set of first moment and first time length, and the second moment is determined based on the first moment and the first time length; for dynamically scheduled tasks, the network device configuration or protocol presets the second moment as the end moment of the task. For another example: for periodic or semi-continuous tasks, the network device configuration or protocol presets the first moment as the start moment of multiple cycles and the second moment as the end moment of multiple cycles; for dynamically scheduled tasks, the network device configures a set of first moment and first time length, and the second moment is determined based on the first moment and the first time length. For another example: for periodic or semi-continuous tasks, the network device configuration or protocol presets the first moment as the start moment of multiple cycles and the second moment as the end moment of multiple cycles; for dynamically scheduled tasks, the network device configuration or protocol presets the second moment as the end moment of the task.

[0287] After the terminal device determines the first moment and the first time duration, it can determine a second moment based on the first moment and the first time duration. The second moment is the moment after the first time duration, i.e., the time interval between the first moment and the second moment is the first time duration. For example, the second moment in Figures 7 to 9 is t3. For another example, the second moment in Figures 10 and 11a is t4.

[0288] In an optional implementation, the terminal device determines an implementation method for the second moment based on the first moment and the first time length. This is applicable to scenarios where the second task is a periodic task or a semi-persistent task, such as a periodic CSI reporting task or a semi-persistent CSI reporting task. Alternatively, the terminal device can determine the type of the second task, and when the second task is a periodic task or a semi-persistent task, determine the second moment based on the first moment and the first time length.

[0289] Optionally, the terminal device determines the implementation method of the second moment based on the first moment and the first time length, which can also be applied to the scenario where the second task is a dynamically scheduled task, such as the second task is a dynamically scheduled CSI reporting task.

[0290] In another optional embodiment, when the second task is a periodic task or a semi-continuous task, the first moment corresponds to the start moment of the first of N periods, the first time length corresponds to the length of the N periods, and N periods are the multiple periods to which the second task belongs. Thus, the second moment corresponds to the end moment of the Nth period of the N periods, where N is a positive integer greater than 1.

[0291] In other words, when the second task is a periodic task or a semi-persistent task, the first moment may be the start moment of the first of the N periods to which the second task belongs, and the second moment may be the end moment of the Nth period of the N periods. In other words, when the second task is a periodic task or a semi-persistent task, the first state of the second model or function lasts from the start moment of the first of the N periods to which the second task belongs to to the end moment of the Nth period of the N periods. In other words, when the second task is a periodic task or a semi-persistent task, the second model or function remains in the first state for the duration of the N periods to which the second task belongs.

[0292] This is because periodic tasks or semi-continuous tasks will last for multiple cycles. During the duration of multiple cycles, the second model or function is in the first state, which can avoid frequent switching between the first state and the second state, saving switching time and the overhead caused by switching. In addition, the terminal device does not need to judge the status every time, which can simplify the operation.

[0293] In addition, if the second task is a periodic task or a semi-continuous task, and the second task is a task within the first cycle, then when the second task is triggered, the terminal device needs to determine the state of the second model or function corresponding to the second task. Optionally, the terminal device determines the state of the second model or function based on the duration of the first state of the model or function corresponding to the task before the second task. For details, please refer to the following implementation method of determining the state of the first model or function based on the second moment. Optionally, in the multiple cycles corresponding to the second task, except for the first cycle, when the terminal device performs other tasks related to the second task, it is not necessary to determine the state of the model or function used. In the other cycles, the models or functions used by the terminal device are all in the first state.

[0294] In another optional implementation, when the second task is a periodic task or a semi-continuous task, if the second task is not the last cycle in N cycles, the first moment corresponds to the end moment of the cycle in which the second task is located, and the second moment corresponds to the start moment of the next cycle of the cycle in which the second task is located; if the second task is the last cycle in N cycles, the first moment corresponds to the end moment of the cycle in which the second task is located, and the second moment corresponds to the end moment of the cycle in which the second task is located. Among them, N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1. The end moment of the cycle in which the second task is located can also be understood as the end moment of the model reasoning of the second model or function corresponding to the second task; the start moment of the next cycle of the cycle in which the second task is located can also be understood as the start moment of the model reasoning of the first model or function corresponding to the first task.

[0295] In other words, when the second task is a periodic task or a semi-persistent task, the first state of the second model or function periodically persists from the end of each cycle to the start of the next cycle. That is, within the N cycles of the second task, the second model or function periodically remains in the first state, which is an active and idle state.

[0296] For example, Figure 11d is another CSI reporting diagram. If the second task is the second periodic CSI reporting task in Figure 11d, that is, the CSI reporting task corresponding to the second CSI RS in Figure 11d, the first time is t3 and the second time is t4, where t3 is the end time of the period in which the second task occurs, and t4 is the start time of the period following the period in which the second task occurs.

[0297] Optionally, when the second task is a periodic task or a semi-persistent task, the third state of the second model or function starts from the second moment, or in other words, the second moment is the moment when the terminal device switches the first state of the second model or function to the third state. The third state is a state in which the model or function is activated and used, or in other words, the time period when the second model or function is in the third state is the time period in which the terminal device uses the second model or function for model reasoning, or in other words, when the second model or function is in the third state, the terminal device is using the second model or function for model reasoning.

[0298] Optionally, the first moment is the moment when the terminal device switches the third state of the second model or function to the first state, or in other words, the second model or function is in the third state for a period of time before the first moment.

[0299] Optionally, the second model or function is in the second state after the end moment of the Nth cycle in N cycles, or in other words, the end moment of the Nth cycle in N cycles is the moment when the terminal device switches the third state of the second model or function to the second state, or in other words, the second state of the second model or function starts from the end moment of the Nth cycle in N cycles.

[0300] In another optional embodiment, when the second task belongs to a periodic task or a semi-continuous task, the first moment corresponds to the starting moment of the first cycle in N cycles, and the second moment corresponds to the ending moment of the Nth cycle in N cycles. N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1. Within the N cycles to which the second task belongs, the second model or function periodically switches between the first state and the third state. At the end of each cycle except the Nth cycle in the N cycles, the second model or function switches from the third state to the first state, and at the starting moment of each cycle except the first cycle in the N cycles, the second model or function switches from the first state to the third state. In particular, at the starting moment of the first cycle in the N cycles, the second model or function switches from the first state to the third state, or, the second model or function switches from the second state to the third state. In particular, at the end of the Nth cycle among the N cycles, the terminal device switches the third state of the second model or function to the second state, or in other words, after the end of the Nth cycle among the N cycles, the second model or function is in the second state, or in other words, the second state of the second model or function starts from the end of the Nth cycle among the N cycles. The third state is a state in which the model or function is activated and used, or in other words, the time period when the second model or function is in the third state is the time period when the terminal device uses the second model or function to perform model reasoning, or in other words, when the second model or function is in the third state, the terminal device is using the second model or function to perform model reasoning.

[0301] Exemplarily, Figure 11e is another CSI reporting schematic diagram. Figure 11e includes three cycles of CSI reporting tasks, wherein the second task is the CSI reporting task within the first cycle, and the first task is the CSI reporting task within the second cycle. As shown in Figure 11e, the first moment is the starting moment (t2) of the first cycle of the three cycles, and the second moment is the ending moment (t7) of the third cycle of the three cycles. In addition, as shown in Figure 11e, the second model or function corresponding to the second task periodically switches between the first state and the third state. Specifically, at the end moment t3 of the first cycle, the second model or function switches from the third state to the first state; at the starting moment t4 of the second cycle, the second model or function switches from the first state to the third state; at the end moment t5 of the second cycle, the second model or function switches from the third state to the first state; at the starting moment t6 of the third cycle, the second model or function switches from the first state to the third state. In addition, at the starting time t2 of the first cycle, the second model or function switches from the second state to the third state; at the ending time t7 of the third cycle, the second model or function switches from the third state to the second state.

[0302] Optionally, when the second task is a periodic task or a semi-persistent task, the second task is any one task in a plurality of periods.

[0303] In an optional implementation manner, in an implementation manner in which the time interval between the first moment and the second moment is a first time length, the second task is a task that does not require reporting of information.

[0304] In other words, the terminal device determines that there is no need to report information for the second task, and determines the second moment based on the first moment and the first time length. The second task is a task that does not require reporting information, or the second task does not require reporting information, which means that the result obtained by the terminal device when executing the second task does not need to be reported directly through an uplink channel or an uplink signal. The result obtained by the terminal device when executing the second task can be applied to other tasks, and the results obtained by the terminal device when executing other tasks can be reported directly through an uplink channel or an uplink signal. Alternatively, the second task is a task that does not require reporting information, and the second task does not require reporting information, which means that the network device does not configure an uplink channel or an uplink signal for the terminal device for the second task for result feedback.

[0305] In another optional implementation, the second moment may not be determined based on the first moment and the first time length, and the second moment may be preset, or configured or specified by the network device to the terminal device. In this case, the second moment may correspond to one of the following: the starting moment or ending moment of the channel carrying the reporting information of the second task, the starting moment or ending moment of the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located, and the starting moment of the first time unit after the starting moment or ending moment of the time unit in which the reporting information of the second task is located. Among them, the channel carrying the reporting information of the second task is, for example, PUSCH or PUCCH.

[0306] The second moment corresponds to the start moment or end moment of the channel carrying the report information of the second task. The second moment may be the start moment or end moment of the channel carrying the report information of the second task, or the second moment may be determined based on the start moment or end moment of the channel carrying the report information of the second task. Similarly, the second moment corresponds to other moments and has similar meanings, which are not further described.

[0307] In an optional implementation, the second moment corresponds to one of the following: the start moment or end moment of the channel carrying the reporting information of the second task, the start moment or end moment of the time unit in which the start moment or end moment of the channel carrying the reporting information of the second task is located, and the start moment of the first time unit after the time unit in which the start moment or end moment of the channel carrying the reporting information of the second task is located. This implementation is applicable to tasks in which the second task is dynamically scheduled, that is, the second task is a non-periodic task. This is because the DCI of non-periodic tasks has a probability of false alarm and missed detection. If the network device indicates the first time length to the terminal device through DCI, then when false alarms and missed detections occur, it will cause the network device and the terminal device to be unable to align the state of the first model or function. For example: the network device indicates to the terminal device through DCI that the first time length is 3 slots. When the first task is triggered within the first time length, the network device believes that the first model or function corresponding to the first task is in the first state. However, in the case of missed detection, the first model or function corresponding to the first task is actually in the second state, resulting in inconsistent understanding of the state of the first model or function between the network device and the terminal device.

[0308] Optionally, if the second moment determined by the terminal device is earlier than the start moment or end moment of the first uplink signal, the terminal device determines the second moment as the end moment of the first uplink signal. For example, the second task is a CSI reporting task, and the terminal device determines the second moment as earlier than the start moment of the PUSCH carrying the CSI report based on the first moment and the first time length, then the terminal device determines the second moment as the end moment of the PUSCH, that is, the first state of the second model or function corresponding to the second task continues until the end moment of the PUSCH carrying the CSI report. This is because if the second moment configured by the network device is too early, it is possible that the second model or function has not been used up on the terminal device side. At this time, if the second moment configured by the network device is followed, the second model or function may be switched to the second state too early, causing the second task to fail to execute normally.

[0309] In one optional embodiment, the first state of the second model or function persists from the first moment to the second moment, and the second model or function is identical to the first model or function. Then, when the terminal device is triggered to perform the first task, the state of the first model or function can be determined based on the state of the second model or function, that is, the state of the first model or function can be determined based on the second moment.

[0310] Specifically, the terminal device determines the state of the first model or function based on the second moment and the start moment of the first task, including: determining the state of the first model or function based on the first moment, the second moment, and the start moment of the first task. The terminal device determines the state of the first model or function based on the first moment, the second moment, and the start moment of the first task, including: determining that the first model or function is in the first state when the start moment of the first task is between the first moment and the second moment; and determining that the first model or function is in the second state when the start moment of the first task is later than the second moment.

[0311] The starting time of the first task corresponds to one of the following: the starting time of the second downlink signal, the ending time of the second downlink signal, the third offset time, the starting time of the usage time period of the first model or function, the starting time of the storage unit occupation time period of the first model or function, and the starting time of the calculation unit occupation time period of the first model or function. The time interval between the third offset time and the starting time or the ending time of the second downlink signal corresponds to the third time offset, which can be a positive number or a negative number. The third time offset can be configured or indicated by the network device to the terminal device, or it can be predefined or reported by the terminal device.

[0312] The start time of the first task corresponds to the start time of the second downlink signal. This can be understood as: the start time of the first task is the start time of the second downlink signal, or it can be understood as: the start time of the first task is determined based on the start time of the second downlink signal. Similarly, the second downlink signal corresponds to other times and has similar meanings, so it is not further explained.

[0313] It can be seen that the second model or function is in the first state between the first moment and the second moment. If the starting moment of the first task is between the first moment and the second moment, the first model or function is in the first state; if the starting moment of the first task is later than the second moment, the first model or function is in the second state.

[0314] For example, Figure 12 is a schematic diagram of another CSI reporting. As shown in Figure 12, the periodic CSI reporting task triggered at time t1 is the second task, and the non-periodic CSI reporting task triggered at time t4 is the first task. The first moment and the second moment corresponding to the second task are t3 and t5 respectively, and the first state of the second model or function corresponding to the second task lasts from t3 to t5. The starting moment of the first task is the starting moment of the second downlink signal used to schedule the terminal device to perform the first task, that is, time t4. If t4 is between t3 and t5, the terminal device determines that the first model or function corresponding to the first task is in an activated state.

[0315] For example, Figure 13 is another CSI reporting diagram. As shown in Figure 13, the periodic CSI reporting task triggered at time t1 is the second task, and the non-periodic CSI reporting task triggered at time t5 is the first task. The first moment and the second moment corresponding to the second task are t3 and t4 respectively, and the first state of the second model or function corresponding to the second task lasts from t3 to t4. The starting moment of the first task is the starting moment of the second uplink signal used to schedule the terminal device to perform the first task, that is, time t5. If t5 is later than t4, the terminal device determines that the first model or function corresponding to the first task is in a deactivated state.

[0316] It can be seen that the first model or function corresponding to the first task is in the first state, including: the start time of the first task is between the first time and the second time. The start time of the first task is between the first time and the second time, which can be: the start time of the first task is the first time, or the start time of the first task is later than the first time and earlier than the second time.

[0317] In an optional embodiment, the start moment and end moment of the first task are both between the first moment and the second moment. The end moment of the first task corresponds to one of the following: the start moment of the second uplink signal, the end moment of the second uplink signal, the end moment of the usage time period of the first model or function, the end moment of the storage unit occupation time period of the first model or function, and the end moment of the calculation unit occupation time period of the first model or function. The end moment of the first task corresponds to the start moment of the second uplink signal, which can be: the end moment of the first task is the start moment of the second uplink signal, or it can be: the end moment of the first task is determined based on the start moment of the second uplink signal. Similarly, the end moment of the first task has similar meanings corresponding to other moments and will not be repeated.

[0318] When the start time and end time of the first task are both between the first time and the second time, the start time of the first task is the first time, and the end time of the first task is earlier than the second time or is the second time. Alternatively, the start time of the first task is later than the first time, and the end time of the first task is earlier than the second time or is the second time. For example, in Figure 12, the first time is t3, the second time is t5, the start time of the first task is t4, t4 is between t3 and t5, the end time of the first task is t5, and the first function or model corresponding to the first task is in an activated state.

[0319] In another optional implementation, the starting moment of the first task is between the first moment and the second moment, and the ending moment of the first task is after the first moment and the second moment. In this way, the starting moment of the first task is the first moment, or the starting moment of the first task is later than the first moment and earlier than the second moment, and the ending moment of the first task is later than the second moment. For example, Figure 14a is another CSI reporting schematic diagram. In Figure 14a, the first moment is t3, the second moment is t5, the starting moment of the first task is t4, t4 is between t3 and t5, the ending moment of the first task is t6, t6 is later than t5, and the first function or model corresponding to the first task is in an activated state.

[0320] Similarly, the first model or function corresponding to the first task is in the second state, including: the first function or model is not in the first state; or the start time of the first task is after the second time, that is, the start time of the first task is later than the second time. For example, in Figure 13, the start time t5 of the first task is after the second time t4, and the first function or model corresponding to the first task is in the deactivated state.

[0321] Optionally, when the second moment is not determined based on the first moment and the first time length, the first state of the second model or function continues until the second moment, and the terminal device determines the state of the first model or function based on the second moment and the start time of the first task, including: when the start time of the first task is earlier than the second moment, determining that the first model or function is in the first state; when the start time of the first task is later than the second moment, determining that the first model or function is in the second state. In other words, the first model or function is in the first state, including: the start time of the first task is earlier than the second moment; the first model or function is in the second state, including: the start time of the first task is later than the second moment.

[0322] In an optional implementation, when the first state is an active and idle state and the first model or function corresponding to the first task is in the first state, the first state of the first model or function continues until the seventh moment, or the first state of the first model or function ends at the seventh moment, or the seventh moment is the moment when the terminal device switches the first state of the first model or function to the third state. The seventh moment corresponds to the first task. Optionally, the seventh moment corresponds to the starting moment of the first task. The seventh moment corresponds to the starting moment of the first task, which can be: the seventh moment is the starting moment of the first task, or it can be: the seventh moment is determined based on the starting moment of the first task, and the starting moment of the first task is the starting moment of the model reasoning of the first model or function.

[0323] For example, in Figure 11c, the first moment is the end moment (t3) of the usage period of the second model or function corresponding to the second task, the second moment is t5, and the seventh moment is the start moment (t6) of the first task. Based on the start moment of the first task, the first moment, and the second moment, the terminal device determines that the first model or function is in an active and idle state, and the first state of the first model or function continues until t6.

[0324] Optionally, after the seventh moment, the first state of the first model or function starts again at the eighth moment, or in other words, the eighth moment is the moment when the terminal device switches the third state of the first model or function to the first state. The eighth moment corresponds to the first task. Optionally, the eighth moment corresponds to the end moment of the first task. The eighth moment corresponds to the end moment of the first task, which may be: the eighth moment is the end moment of the first task, or it may be: the eighth moment is determined based on the end moment of the first task. For example, the eighth moment in Figure 11c is moment t7, and the first state of the first model or function starts again at moment t7, that is, moment t7 is the moment when the terminal device switches the third state of the first model or function to the first state.

[0325] Optionally, when the first model or function corresponding to the first task is in the first state, the first state of the first model or function starts at the ninth moment, or in other words, the ninth moment is the moment when the first model or function switches from the third state to the first state. Optionally, the ninth moment corresponds to the end moment of the second task or the ninth moment is the first moment. Wherein, the ninth moment corresponds to the end moment of the second task, which can be: the ninth moment is the end moment of the second task, or it can be: the ninth moment is determined based on the end moment of the second task, and the end moment of the second task is the end moment of the model reasoning of the second model or function. For example, the ninth moment in Figure 11c is moment t3, and moment t3 is the moment when the first model or function switches from the third state to the first state, that is, the first state of the first model or function starts at moment t3, and moment t3 is the first moment, which is also the end moment of the second task.

[0326] Optionally, the third state of the first model or function continues until the eighth moment, or in other words, the third state of the first model or function ends at the eighth moment, or in other words, the eighth moment is the moment when the terminal device switches the third state of the first model or function to the second state. The eighth moment corresponds to the first task or the eighth moment is the second moment. Optionally, the eighth moment corresponds to the end moment of the first task. The eighth moment corresponds to the end moment of the first task, which can be: the eighth moment is the end moment of the first task, or it can be: the eighth moment is determined based on the end moment of the first task, and the end moment of the first task refers to the end moment of the model reasoning.

[0327] For example, Figure 14b is another CSI reporting diagram. In Figure 14b, the third state of the first model or function lasts from time t5 to time t6, that is, the third state of the first model or function ends at time t6, and time t6 is the second time, which is also the end time of the first task.

[0328] It is understandable that when the first model or function is in the first state, at least one of the following items corresponding to the first task differs from when the first model or function is in the second state: latency requirement, time period for use of the first model or function, time period for storage unit occupancy of the first model or function, and time period for computing unit occupancy of the first model or function. The terminal device can then determine, based on the state of the first model or function, at least one of the following items differs: latency requirement, time period for use of the first model or function, time period for storage unit occupancy of the first model or function, and time period for computing unit occupancy of the first model or function, and execute the first task based on the determined at least one item.

[0329] The following are several implementations of the terminal device determining, based on the state of the first model or function, at least one of the following differences: a latency requirement, a usage time period of the first model or function, a storage unit occupancy time period of the first model or function, and a computing unit occupancy time period of the first model or function, and performing the first task based on the at least one determined difference:

[0330] Implementation method 1: The terminal device determines the delay requirement according to the state of the first model or function, and performs the first task according to the delay requirement.

[0331] In an optional embodiment, the delay requirement is the time interval requirement between the second downlink signal and the second uplink signal, and the terminal device determines the time interval requirement between the second downlink signal and the second uplink signal based on the state of the first model or function. When the first model or function is in the first state, the time interval requirement between the second downlink signal and the second uplink signal includes the time requirement for model reasoning, that is, the time it takes for the terminal device to perform model reasoning using the first model or function; when the first model or function is in the second state, the delay requirement includes the time requirement for model activation and model reasoning, that is, the time it takes for the terminal device to activate the first model or function and the time it takes to perform reasoning using the first model or function. Therefore, when the first model or function is in the first state, the delay requirement corresponding to the first task is different from when the first model or function is in the second state. Moreover, when the first model or function is in the first state, the delay requirement corresponding to the first task is smaller than when the first model or function is in the second state.

[0332] Furthermore, the terminal device performs the first task according to the determined delay requirement, including: when the first model or function is in the first state, based on the delay requirement, using the first model or function to perform model reasoning and obtain the reasoning result; when the first model or function is in the second state, based on the delay requirement, activating the first model or function, and using the activated first model or function to perform model reasoning and obtain the reasoning result.

[0333] It can be seen that when the first model or function is in the first state, compared with the first model or function being in the second state, when the terminal device performs the first task based on the latency requirement, there is no need to activate the first model or function, and the first model or function can be directly used for model reasoning, thereby saving resources.

[0334] For example, in Figure 12, the terminal device determines that the first model or function is in an activated state, and determines the delay requirement as the time interval requirement between the start time t6 of the CSI RS and the end time t5 of the PUSCH carrying the CSI report when the terminal device performs the first task. The delay requirement includes the time for the terminal device to perform model reasoning using the first model or function, and does not include the time for the terminal device to activate the first model or function. Then, when the terminal device performs the first task, based on the time interval requirement between t6 and t5, the first model or function is used to perform model reasoning to obtain the predicted CSI. The terminal device does not need to activate the first model or function, which can save resource overhead.

[0335] For example, in Figure 13, the terminal device determines that the first model or function is in a deactivated state, and determines the delay requirement as the time interval requirement between the start time t7 of the CSI RS and the end time t6 of the PUSCH carrying the CSI report when the terminal device performs the first task. The delay requirement includes the model activation time when the terminal device activates the first model or function and the time for performing model reasoning using the first model or function. Then, when the terminal device is triggered to perform the first task, based on the time interval requirement between t7 and t6, the first model or function is activated, and then the activated first model or function is used to perform model reasoning to obtain the predicted CSI.

[0336] In an optional implementation, the terminal device executes the first task according to the determined delay requirement, and may also include: when the first model or function is in the first state, determining that the time interval between the configured second downlink signal and the second uplink signal can meet the delay requirement, so the first task can be executed, or the first task is not ignored; when the first model or function is in the second state, determining that the delay requirement is greater, the time interval between the configured second downlink signal and the second uplink signal does not meet the delay requirement, and the first task cannot be executed, or the first task is ignored.

[0337] In an optional implementation, when the first model or function is in the first state, the terminal device uses the first model or function to perform model reasoning after receiving the signal or SSB for performing the first task. In this way, the time interval between the signal or SSB used to perform the first task and the PUSCH or PUCCH used to carry the reporting information is greater than the predefined first time interval by Δt3, where Δt3 is the value reported by the terminal device, or is a value predefined by the protocol. In other words, when the first model or function is in the first state, the network device schedules Δt3 more time resources for the terminal device to perform model reasoning than the predefined time. Optionally, the predefined first time interval corresponds to the time interval requirement between the signal or SSB used to perform the first task in non-AI mode and the PUSCH or PUCCH used to carry the reporting information, or corresponds to the first delay requirement for performing the task in non-AI mode. For example, the predefined first time interval is T′ proc,CSI , T′ proc,CSI Refer to the above description, it can be understood as T' proc,CSI Corresponding to the first delay requirement for performing CSI reporting in non-AI mode, Δt3 is the time increment of the time required to run the first AI model or function to perform model inference to perform CSI reporting relative to the first delay requirement for performing CSI reporting in the non-AI model. In another possible implementation, the predefined first time interval corresponds to the first reference delay requirement for performing the task in AI mode. For example, the predefined first time interval is the time interval requirement between the CSI-RS corresponding to the execution of CSI reporting by the AI ​​model or function defined in the protocol and the PUSCH or PUCCH used to carry the reporting information. The first reference delay requirement can be a minimum delay requirement or an average delay requirement, and Δt3 is the time increment of the time required to run the first AI model or function to perform model inference to perform the task relative to the first reference delay requirement. If the time required to run the first AI model or function to perform model inference to perform the task is less than the predefined first time interval, Δt3 can be 0. This method can ensure that after the terminal device receives the signal or SSB used to perform the first task, there is sufficient time to perform the reasoning of the first model or function, and thus can ensure that the terminal device can successfully use the first model or function to perform the first task, or in other words, can ensure that the model reasoning of the first model or function is carried out smoothly.

[0338] In an optional implementation, when the first model or function is in the second state, the terminal device activates the first model or function after receiving the signal or SSB for performing the first task. In this way, the time interval between the signal or SSB for performing the first task and the PUSCH or PUCCH for carrying the reporting information is greater than the predefined first time interval by Δt1, where Δt1 is the value reported by the terminal device or is a value predefined by the protocol. In other words, when the first model or function is in the second state, the network device schedules Δt1 more time resources for the terminal device for model activation and reasoning than the predefined first time interval. Optionally, the predefined first time interval corresponds to the time interval between the signal or SSB for performing the first task in the non-AI mode and the PUSCH or PUCCH for carrying the reporting information, or corresponds to the first delay requirement for performing the task in the non-AI mode. For example, the predefined first time interval is T′ proc,CSI , T′ proc,CSI Refer to the above description, it can be understood as T' proc,CSI Corresponding to the first delay requirement for performing CSI reporting in non-AI mode, Δt1 is the time increment of the time required to run the first AI model or function to perform CSI reporting relative to the first delay requirement for performing CSI reporting in the non-AI model. In another possible implementation, the predefined first time interval corresponds to the first reference delay requirement for performing a task in the AI ​​mode. For example, the predefined first time interval is the time interval requirement defined by the protocol between the CSI-RS corresponding to the CSI reporting performed by the AI ​​model or function and the PUSCH or PUCCH used to carry the reporting information. The first reference delay requirement can be a minimum delay requirement or an average delay requirement, and Δt1 is the time increment of the time required to run the first AI model or function to perform the task relative to the first reference delay requirement. The time required to run the first AI model or function to perform the task includes the time for model activation and model inference. If the time required to run the first AI model or function to perform the task is less than the predefined first time interval, Δt1 can be 0.

[0339] Optionally, if the first task is a dynamically scheduled task, then in this mode, the time interval between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information is greater than the predefined second time interval by Δt1. Optionally, the predefined second time interval corresponds to the time interval requirement between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information in the non-AI mode, or corresponds to the second delay requirement for executing the task in the non-AI mode. For example, the predefined second time interval is T proc,CSI , T proc,CSIAlternatively, the predefined time corresponds to the second reference delay requirement for executing the task in the AI ​​mode.

[0340] This method can ensure that after the terminal device receives the signal or SSB for performing the first task, there is sufficient time to activate the first model or function, thereby ensuring that the terminal device can successfully use the first model or function to perform the first task, or in other words, it can ensure that the model reasoning of the first model or function is carried out smoothly.

[0341] For example, in Figure 13, when the terminal device performs the first task, the time interval between the CSI RS used to measure CSI and the PUSCH used to carry the CSI report increases from t9 to t6 to t8 to t6, and the interval between t9 and t8 is Δt1. Thus, after receiving the CSI RS, the terminal device can complete activation of the first model or function within the time period t8 to t10, and can then use the activated first model or function to perform model inference, obtain predicted CSI, and complete CSI reporting.

[0342] In another optional implementation, when the first model or function is in the second state, the terminal device starts to activate the first model or function at a moment Δt1 before receiving the signal or SSB for performing the first task. In other words, the terminal device activates the first model or function before receiving the signal or SSB for performing the first task, and the time interval between the moment of activating the first model or function and receiving the signal or SSB for performing the first task is Δt1. In this way, the time interval between the signal or SSB for performing the first task and the PUSCH or PUCCH carrying the reporting information meets the predefined time interval, but does not meet the delay requirement of the first model or function in the second state, because the delay requirement of the first model or function in the second state is greater. Therefore, the terminal device can perform model activation Δt1 in advance.

[0343] Optionally, the predefined first time interval corresponds to the time interval requirement between the signal or SSB used to perform the first task in the non-AI mode and the PUSCH or PUCCH used to carry the reporting information, or corresponds to the first delay requirement for performing the task in the non-AI mode. For example, the predefined first time interval is T′ proc,CSI , T′ proc,CSI Refer to the above description, it can be understood as T' proc,CSICorresponding to the first delay requirement for performing CSI reporting in non-AI mode, Δt1 is the time increment of the time required to run the first AI model or function to perform CSI reporting relative to the first delay requirement for performing CSI reporting in the non-AI model. In another possible implementation, the predefined time corresponds to the first reference delay requirement for performing a task in AI mode. For example, the predefined first time interval is the first reference delay requirement corresponding to the CSI reporting performed by the AI ​​model or function defined in the protocol. The first reference delay requirement may be a minimum delay requirement or an average delay requirement, and Δt1 is the time increment of the time required to run the first AI model or function to perform the task relative to the first reference delay requirement. The time required to run the first AI model or function to perform the task includes the time for model activation and model inference. If the time required to run the first AI model or function to perform the task is less than the predefined first time interval, Δt1 may be 0.

[0344] In addition, the terminal device cannot fully activate the first model or function before receiving the signal or SSB for performing the first task. After the terminal device receives the signal or SSB for performing the first task, it activates the first model or function until the state of the first model or function is switched to the first state.

[0345] Optionally, if the first task is a dynamically scheduled task, then in this mode, the time interval between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information is greater than the predefined second time interval by Δt1. Optionally, the predefined second time interval corresponds to the time interval requirement between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information in the non-AI mode, or corresponds to the second delay requirement for executing the task in the non-AI mode. For example, the predefined time is T proc,CSI , T proc,CSI Please refer to the description above. Alternatively, the predefined second time interval corresponds to the second reference delay requirement for executing the task in AI mode. This method can also ensure that the terminal device can use sufficient resources to complete the activation of the first model or function, and then use the activated first model or function to perform model reasoning to ensure the smooth execution of the first task.

[0346] For example, Figure 15a is another CSI reporting diagram. In Figure 15a, the start time t5 of the first task is later than the second time t4, and the first model or function corresponding to the first task is in the second state. The terminal device starts model activation at a moment Δt1 before receiving the CSI RS. After receiving the CSI RS, the terminal device continues to activate the first model or function, and performs model reasoning using the activated first model or function from the moment t9 after the activation of the first model or function is completed. Compared with activating the first model or function after the terminal device receives the CSI RS, this method can ensure the smooth execution of the first task.

[0347] In another optional embodiment, when the first model or function is in the second state, the terminal device begins activating the first model or function at a time Δt2 before the configured PUSCH or PUCCH carrying the reporting information. In other words, the time interval between the terminal device activating the first model or function and the configured PUSCH or PUCCH carrying the reporting information is Δt2. Δt2 is a value reported by the terminal device or a value predefined by the protocol. In this approach, the terminal device can perform model activation Δt2 before the configured reporting time. It can be understood that Δt2 is the duration required to run the first AI model or function to perform the task, or that Δt2 includes the time for model activation and model inference. The terminal device performs model activation after receiving the signal used to trigger the first task. The terminal device may perform model activation before or after receiving the signal or SSB used to perform the first task. Based on this approach, it is ensured that the terminal device can utilize sufficient resources to complete the activation and inference of the first model or function before the configured PUSCH or PUCCH carrying the reporting information, thereby ensuring the smooth execution of the first task.

[0348] Optionally, if the first task is a dynamically scheduled task, then in this mode, the second time interval between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information needs to be greater than Δt2, or the time interval between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information is greater than the predefined second time interval by Δt4, where Δt4 is the value reported by the terminal device, or is a value predefined by the protocol. Optionally, Δt4 corresponds to the difference between Δt2 and the predefined second time interval. If Δt2 is less than the predefined second time interval, Δt4 can be 0. Optionally, the predefined second time interval corresponds to the time interval requirement between the PDCCH used to trigger the first task and the PUSCH or PUCCH used to carry the reporting information in non-AI mode, or corresponds to the second delay requirement for executing the task in non-AI mode. For example, the predefined time is T proc,CSI , T proc,CSIAlternatively, the predefined second time interval corresponds to a second reference delay requirement for executing the task in the AI ​​mode.

[0349] For example, Figure 15b is another CSI reporting schematic diagram. As shown in Figure 15b, the start time t5 of the first task is later than the second time t4, and the first model or function is in the second state. In Figure 15b, the terminal device starts to activate the first model or function at a moment Δt2 before the configured PUSCH carrying the reporting information (i.e., at a moment t8), to ensure that the terminal device can use sufficient resources to complete the activation and reasoning of the first model or function before the configured PUSCH carrying the reporting information, thereby ensuring the smooth execution of the first task.

[0350] Similarly, when the delay requirement is the time interval requirement between the second downlink signal and the end moment of the usage time period of the first model or function, or the delay requirement is the time interval requirement between the second downlink signal and the end moment of the storage unit occupation time period of the first model or function, or the delay requirement is the time interval requirement between the second downlink signal and the end moment of the computing unit occupation time period of the first model or function, if the first model or function is in the first state, the delay requirement includes the time of model inference; if the first model or function is in the second state, the delay requirement includes the time of model activation and the time of model inference. In this manner, the implementation method of the terminal device performing the first task according to the determined delay requirement can refer to the implementation method when the delay requirement is the time interval requirement between the second downlink signal and the second uplink signal, and will not be repeated.

[0351] Implementation method 2: The terminal device determines a usage time period of the first model or function according to a state of the first model or function, and executes the first task according to the usage time period of the first model or function.

[0352] Among them, when the first model or function is in the first state, the usage time period of the first model or function starts from the start moment or end moment of the second downlink signal corresponding to the first task. When the first model or function is in the first state, after the terminal device receives the second downlink signal corresponding to the first task, it can directly use the first model or function for model reasoning, then the usage time period of the first model or function can start from the start moment or end moment of the second downlink signal corresponding to the first task. For example, in Figure 12, the first model or function corresponding to the first task is in an activated state. When the terminal device executes the first task, there is no need to activate the first model or function. Then the usage time period of the first model or function starts from the start moment or end moment of the CSI RS corresponding to the first task.

[0353] When the first model or function is in the second state, the start time of the usage time period of the first model or function is later than the start time or end time of the second downlink signal corresponding to the first task. In other words, when the first model or function is in the second state, the time interval between the start time of the usage time period of the first model or function and the start time or end time of the second downlink signal corresponding to the first task corresponds to a fourth time offset, and the fourth time offset is a positive number. When the first model or function is in the second state, after the terminal device receives the second downlink signal corresponding to the first task, it needs to activate the first model or function, and then use the activated first model or function to perform model reasoning. Then, the start time of the usage time period of the first model or function is later than the start time or end time of the second downlink signal corresponding to the first task.

[0354] For example, in Figure 13, the first model or function corresponding to the first task is in a deactivated state. The terminal device needs to activate the first model or function, and then use the activated first model or function to perform model reasoning. The starting time of the usage time period of the first model or function is later than the starting time or end time of the CSI RS corresponding to the first task. For example, the starting time of the usage time period of the first model or function is t10.

[0355] The terminal device determines the usage time period of the first model or function based on the status of the first model or function. When the terminal device performs the first task, it can use the first model or function to perform reasoning within the determined usage time period of the first model or function to obtain the reasoning result.

[0356] Implementation method 3: The terminal device determines the time period occupied by the computing unit of the first model or function according to the state of the first model or function, and executes the first task according to the time period occupied by the computing unit of the first model or function.

[0357] In one possible implementation, the time period occupied by the computing unit of the first model or function may be the usage time period of the first model or function. Then, when the first model or function is in the second state, or in the time period of transition from the second state to the first state, the computing unit occupied by the first model or function is 0, or in other words, the first model or function does not occupy a computing unit. When the first model or function is in the first state, the time period occupied by the computing unit of the first model or function starts from the start or end time of the second downlink signal corresponding to the first task. When the first model or function is in the second state, the start time of the time period occupied by the computing unit of the first model or function is later than the start or end time of the second downlink signal corresponding to the first task; or, when the first model or function is in the second state, the time interval between the start time of the time period occupied by the computing unit of the first model or function and the start or end time of the second downlink signal corresponding to the first task corresponds to the fourth time offset.

[0358] The implementation method of the terminal device determining the time period occupied by the computing unit of the first model or function based on the status of the first model or function can refer to the above-mentioned implementation method of the terminal device determining the usage time period of the first model or function based on the status of the first model or function, and will not be repeated here.

[0359] Based on the state of the first model or function, the terminal device determines the time period occupied by the computing units of the first model or function. When the terminal device executes the first task, it can use the first model or function to perform reasoning and obtain reasoning results during the time period occupied by the computing units of the first model or function. Furthermore, the terminal device can determine that the computing units of the first model or function are not occupied by the first model or function during time periods outside of the time period occupied by the computing units of the first model or function. Thus, the terminal device can use these computing units to perform other tasks, thereby improving the utilization efficiency of the computing units.

[0360] Implementation method 4: The terminal device determines the storage unit occupancy time period of the first model or function according to the state of the first model or function, and executes the first task according to the storage unit occupancy time period of the first model or function.

[0361] The storage unit occupancy time period of the first model or function is calculated from the moment the first model or function is in the first state to the moment the first model or function is not in the first state; or, the storage unit occupancy time period of the first model or function is calculated from the moment the second state is converted to the first state to the moment the first model or function is not in the first state.

[0362] Therefore, when the first model or function corresponding to the first task is in the first state, the storage unit occupancy time period of the first model or function corresponding to the first task starts from the start time or end time of the second downlink signal corresponding to the first task, and the second downlink signal can be a downlink channel for triggering the first task, or can be a downlink signal for executing the first task. For example, in Figure 12, the first model or function corresponding to the first task is in the first state, then the storage unit occupancy time period of the first model or function can start from the start time t4 of the DCI for triggering CSI reporting, or can start from the start time t6 of the CSI RS for measuring CSI.

[0363] When the first model or function corresponding to the first task is in the second state, the starting moment of the time period occupied by the storage unit of the first model or function corresponding to the first task is earlier than the starting moment or the end moment of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal for executing the first task. For example, in Figure 15a, the first model or function corresponding to the first task is in the second state, and the terminal device activates the first model or function before receiving the CSI RS, then the starting moment of the time period occupied by the storage unit of the first model or function is earlier than the starting moment or the end moment of the CSI RS.

[0364] Optionally, when the first model or function corresponding to the first task is in the second state, the starting moment of the time period occupied by the storage unit of the first model or function corresponding to the first task is later than the starting moment or the ending moment of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal for triggering the first task. For example, in Figure 13, the first model or function corresponding to the first task is in the second state, and the terminal device activates the first model or function after receiving the CSI RS, then the starting moment of the time period occupied by the storage unit of the first model or function is later than the starting moment or the ending moment of the PDCCH that triggers the first task.

[0365] Optionally, when the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start or end time of the second uplink signal corresponding to the first task, and the start time of the storage occupancy time period of the first model or function corresponding to the first task is determined by the start or end time of the second uplink signal corresponding to the first task, where the second uplink signal is an uplink channel carrying reporting information, such as a PUSCH or PUCCH. For example, the time interval between the start time of the storage occupancy time period of the first model or function corresponding to the first task and the start or end time of the second uplink signal corresponding to the first task corresponds to a fifth time offset, and the value of the fifth time offset is a negative number. That is, the start time of the storage occupancy time period of the first model or function corresponding to the first task is the time corresponding to the start time or end time of the second uplink signal being advanced by the absolute value of the fifth time offset. The terminal device determines the start time of the storage unit occupancy time period of the first model or function based on the state of the first model or function. When the terminal device executes the first task, it can determine whether the first model or function needs to be activated based on the start time of the storage unit occupancy time period of the first model or function. For example, if the storage unit occupancy time period of the first model or function corresponding to the first task starts from the start time or end time of the second downlink signal corresponding to the first task, then when the terminal device executes the first task, it is not necessary to activate the first model or function, and the first model or function can be directly used to perform reasoning to obtain the reasoning result. For another example, if the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second downlink signal corresponding to the first task, or the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task, or the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task, and the start time of the storage occupancy time period of the first model or function corresponding to the first task is determined by the start time or end time of the second uplink signal corresponding to the first task, then when the terminal device executes the first task, it activates the first model or function, and then uses the activated first model or function to perform model reasoning to obtain the reasoning result.

[0366] When the first model or function corresponding to the first task is in the second state, in order to successfully complete the first task before the start time or end time of the second uplink signal scheduled by the network device, the terminal device activates the first model or function from a moment earlier than the start time or end time of the second uplink signal, so that the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task. Furthermore, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task, and the time interval between the start time of the storage unit occupancy time period of the first model or function corresponding to the first task and the start time or end time of the second uplink signal corresponding to the first task needs to be greater than or equal to the sum of the model activation time and the time when the first task uses the model for reasoning.

[0367] Optionally, when the first model or function corresponding to the first task is in the second state, the starting moment of the usage time period of the first model or function is earlier than the moment when the first model or function is in the first state, and the starting moment of the time period occupied by the computing unit of the first model or function is earlier than the moment when the first model or function is in the first state. In other words, the starting moment of the usage time period of the first model or function is earlier than the starting moment or end moment of the second uplink signal corresponding to the first task, and the starting moment of the time period occupied by the computing unit of the first model or function is earlier than the starting moment or end moment of the second uplink signal corresponding to the first task.

[0368] Exemplarily, in Figure 15b, the first model or function corresponding to the first task is in the second state, the starting time t8 of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the starting time of the PUSCH corresponding to the first task, and the starting time of the storage occupancy time period of the first model or function corresponding to the first task is determined by the starting or ending time of the PUSCH corresponding to the first task, for example, t8 is at a time Δt2 before the starting time t10 of the PUSCH.

[0369] It can be understood that when the first model or function is in the first state, the length of the storage unit occupation time period of the first model or function corresponding to the first task is longer than when the first model or function is in the second state. When the first model or function is in the first state, the first model or function corresponding to the first task does not need to be activated, so the storage unit occupation time period of the first model or function corresponding to the first task does not include the time of switching from the first state to the second state; when the first model or function is in the second state, the first model or function corresponding to the first task needs to be activated first, so the storage unit occupation time period of the first model or function corresponding to the first task also needs to include the time of switching from the first state to the second state.

[0370] The terminal device determines the storage unit occupancy time period of the first model or function based on the state of the first model or function. When the terminal device executes the first task, it can determine the storage unit occupancy requirement of the first model or function based on the storage unit occupancy time period of the first model or function, thereby ensuring the smooth execution of the first task. Furthermore, the terminal device can determine that during time periods outside the time periods during which the storage units of the first model or function are occupied, the first model or function does not occupy the computing units, allowing the terminal device to use these storage units to execute other tasks.

[0371] In another optional implementation, the usage time period of the first model or function may be the storage unit occupancy time period of the first model or function. The implementation method for the terminal device to determine the usage time period of the first model or function based on the status of the first model or function may refer to the above-mentioned implementation method for the terminal device to determine the storage occupancy time period of the first model or function based on the status of the first model or function, and will not be repeated here. The terminal device determines the usage time period of the first model or function based on the status of the first model or function. When the terminal device performs the first task, it can use the first model or function to perform reasoning within the determined usage time period of the first model or function to obtain an inference result.

[0372] In another optional implementation, the time period occupied by the computing unit of the first model or function may be the time period occupied by the storage unit of the first model or function. The implementation method for the terminal device to determine the time period occupied by the computing unit of the first model or function according to the status of the first model or function may refer to the implementation method for the terminal device to determine the time period occupied by the storage of the first model or function according to the status of the first model or function, and will not be repeated here. The terminal device determines the time period occupied by the computing unit of the first model or function according to the status of the first model or function. When the terminal device executes the first task, it can determine the occupancy requirement of the computing unit of the first model or function based on the time period occupied by the computing unit of the first model or function, thereby ensuring that the first task can be executed smoothly.

[0373] Implementation method 5: The terminal device determines at least two of the following based on the status of the first model or function: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function, and executes the first task based on the at least two determined items.

[0374] Among them, the implementation method of the terminal device determining any one of the delay requirement, the usage time period of the first model or function, the storage unit occupancy time period of the first model or function, and the computing unit occupancy time period of the first model or function according to the status of the first model or function can be referred to the above-mentioned implementation methods 1 to 4, which will not be repeated. Similarly, the implementation method of the terminal device performing the first task according to any one of the delay requirement, the usage time period of the first model or function, the storage unit occupancy time period of the first model or function, and the computing unit occupancy time period of the first model or function can be referred to the above-mentioned implementation methods 1 to 4, which will not be repeated.

[0375] It can be seen that the terminal device can determine the state of the first model or function corresponding to the first task, and determine at least one of the following based on the state of the first model or function: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function. Thus, the terminal device can execute the first task based on at least one of the determined items. When the first model or function is in the first state, compared with the terminal device being triggered to execute the first task directly, this method does not require the network device to schedule resources to activate the first model or function for the terminal device, thereby reducing resource waste. When the first task or function is in the second state, compared with the terminal device being triggered to execute the first task directly, this method can ensure that the terminal device uses sufficient resources to activate the first model or function, and uses the activated first model or function to perform model reasoning, thereby ensuring that the first task is smoothly executed by the terminal device.

[0376] Optionally, the terminal device uses the activated first model or function to perform model reasoning. After obtaining the reasoning result, it can also report the reasoning result or the reporting information obtained based on the reasoning result to the network device, such as reporting the reasoning result or the reporting information obtained based on the reasoning result to the network device in the form of a report.

[0377] In an optional implementation, the terminal device may also determine the third moment corresponding to the first task. The terminal device may determine the third moment corresponding to the first task based on the fourth moment and the second time length corresponding to the first task. The implementation of the fourth moment and the second time length is similar to the implementation of the first moment and the first time length and will not be repeated. Optionally, the third moment is configured or indicated by the network device, or is preset. For example, when the first task is a dynamically scheduled task, the third moment is the end moment of the terminal device's execution of the first task. The implementation of the third moment is similar to the implementation of the second moment and will not be repeated.

[0378] The third moment is used by the terminal device to determine the state of the third model or function corresponding to the third task, and further used by the terminal device to determine at least one of the following items corresponding to the third task: latency requirement, usage period of the third model or function, storage unit occupancy period of the third model or function, and computing unit occupancy period of the third model or function. In other words, the third moment acts on at least one of the following items corresponding to the third task: latency requirement, usage period of the third model or function, storage unit occupancy period of the third model or function, and computing unit occupancy period of the third model or function.

[0379] Among them, the starting time of the third task is later than the starting time of the first task. The third model or function corresponding to the third task is the same as the first model or function corresponding to the first task. The third model or function is the same as the first model or function, which means that the third model or function is used to implement the same function as the first model or function, or the third model or function is the same as the physical model corresponding to the first model or function. The third model or function is the same as the first model or function in structure and all parameters, or the third model or function is the same as the first model or function in structure but some parameters are different, such as the number of layers, width, and inter-layer connection relationship of the neural network, and the parameters such as the weight value and bias of the neural network.

[0380] Optionally, the starting time of the third task corresponds to one of the following: the starting time of the third downlink signal, the ending time of the third downlink signal, the fifth offset time, the starting time of the usage time period of the third model or function, the starting time of the storage unit occupation time period of the third model or function, and the starting time of the calculation unit occupation time period of the third model or function. Among them, the time interval between the fifth offset time and the starting time or the ending time of the third downlink signal corresponds to the eighth time offset. The third downlink signal is related to the third task. Specifically, the third downlink signal can be a channel used to trigger the terminal device to perform the third task, such as PDCCH or DCI, or it can be a signal used by the terminal device to perform the third task, such as one of CSI RS, TRS, PTRS, PRS, and SSB.

[0381] The starting moment of the third task corresponds to the starting moment of the third downlink signal, which can be: the starting moment of the third task is the starting moment of the third downlink signal, or it can be: the starting moment of the third task is determined based on the starting moment of the third downlink signal. The starting moment of the third task is determined based on the starting moment of the third downlink signal, which can be: the starting moment of the third task is the starting moment or end moment of the time unit where the starting moment of the third downlink signal is located, or it can be: the starting moment of the third task is the starting moment of the first time unit after the time unit where the starting moment of the third downlink signal is located. Similarly, the starting moment of the third task corresponds to other moments, and has a similar understanding, so it will not be repeated.

[0382] In an optional embodiment, when the first model or function corresponding to the first task is in the first state, the terminal device further determines the duration of the first state of the first model or function. Specifically, the terminal device determines that the first state of the first model or function persists until the second moment corresponding to the second task, or determines that the first state of the first model or function persists until the third moment corresponding to the first task.

[0383] In an optional embodiment, the terminal device determines the duration of the first state of the first model or function based on the priority of the first task and the priority of the second task. For example, when the priority of the first task is higher than the priority of the second task, the terminal device determines that the first state of the first model or function lasts until a third moment corresponding to the first task. For another example, when the priority of the first task is lower than the priority of the second task, the terminal device determines that the first state of the first model or function lasts until a second moment corresponding to the second task.

[0384] Optionally, the terminal device determines the duration of the first state of the first model or function based on the start time of the task. For example, when the start time of the first task is later than the start time of the second task, the terminal device determines that the first state of the first model or function lasts until a third time corresponding to the first task. For another example, when the start time of the first task is earlier than the start time of the second task, the terminal device determines that the first state of the first model or function lasts until a second time corresponding to the second task.

[0385] Optionally, the terminal device determines the duration of the first state of the first model or function based on the identifier of the task. For example, when the identifier of the first task is greater than the identifier of the second task, the terminal device determines that the first state of the first model or function lasts until a third moment. For another example, when the identifier of the second task is greater than the identifier of the first task, the terminal device determines that the first state of the first model or function lasts until a second moment corresponding to the second task. The identifier of the first task and the identifier of the second task may be identity identifiers used to identify the two tasks.

[0386] Optionally, when the first task is a reference task specified by the network device, the terminal device determines that the first state of the first model or function continues until a third moment corresponding to the first task. Optionally, when the second task is a reference task specified by the network device, the terminal device determines that the first state of the first model or function continues until a second moment corresponding to the second task.

[0387] Optionally, the terminal device determines the duration of the first state of the first model or function based on the time characteristics of the task, where the time characteristics of the task include periodicity, semi-permanence, and aperiodicity. For example, when the first task is an aperiodic task, the terminal device determines that the first state of the first model or function lasts until a third moment. For another example, when the first task is a periodic task, the terminal device determines that the first state of the first model or function lasts until a second moment.

[0388] In various implementations of the above-mentioned terminal device determining the duration of the first state of the first model or function, the third moment is later than the second moment, or the third moment is earlier than the second moment.

[0389] When the first state of the first model or function continues until the second moment, the second moment is the end moment of the first state of the first model or function; or, the first state of the first model or function ends at the second moment; or, the terminal device starts to switch the first state of the first model or function to the second state from the second moment; or, the terminal device can determine the first state of the first model or function based on the second moment, and before the second moment, the first model or function is in the first state. In an optional embodiment, after the second moment, the first model or function is in the second state, or, the second state of the first model or function starts from the second moment, or, the second moment is the starting moment of the second state of the first model or function. In another optional embodiment, the first model or function is in the second state at a moment delayed by the sixth time offset from the second moment, that is, the time period between the second moment and the moment delayed by the sixth time offset from the second time delay is the time period when the terminal device switches the first model or function from the first state to the second state, and the value of the sixth time offset is a positive number, that is, the time period corresponding to the second state of the first model or function is included in the time period outside the time period corresponding to the first state.

[0390] When the first state of the first model or function continues to the third moment, in one possible case, the third moment is the end moment of the first state of the first model or function; or, the first state of the first model or function ends at the third moment; or, the terminal device starts to switch the first state of the first model or function to the second state from the third moment; or, the terminal device can determine the first state of the first model or function based on the third moment, and before the third moment, the first model or function is in the first state. In an optional embodiment, after the third moment, the first model or function is in the second state, or, the second state of the first model or function starts from the third moment, or, the third moment is the starting moment of the second state of the first model or function. In another optional embodiment, the first model or function is in the second state at a moment after the third moment is delayed by the sixth time offset, that is, the time period between the third moment and the moment after the third moment is delayed by the sixth time offset is the time period when the terminal device switches the first model or function from the first state to the second state, that is, the time period corresponding to the second state of the first model or function is included in the time period outside the time period corresponding to the first state.

[0391] The sixth time offset is reported by the terminal device or is preset. In a possible implementation, the sixth time offset corresponds to a delay for the first model or function to switch from the first state to the second state.

[0392] For example, Figure 16 is another CSI reporting diagram. As shown in Figure 16, the third time corresponding to the first task is t5, and the second time corresponding to the second task is t6. If the terminal device determines that the activation state of the first model or function continues until t5, the terminal device will deactivate the first model or function starting at t5. That is, t5 is the end time of the first state of the first model or function. After t5, the first model or function is in the deactivated state, or the first model or function is in the deactivated state at a time delayed from t5.

[0393] It can be seen that when the duration of the first state of the first model or function corresponding to the first task overlaps with the duration of the first state of the second model or function corresponding to the second task, the terminal device can determine the duration of the first state of the first model or function based on one of the following: the priority of the task, the start time of the task, the identifier of the task, and the time characteristics of the task. Thus, the terminal device can transition the first state of the first model or function to the second state starting from the duration of the first state of the first model or function. The terminal device transitions the first state of the first model or function to the second state during the duration of the first model or function, or transitions the first state of the first model or function to the second state within a period of time after the duration of the first model or function.

[0394] It is understandable that regardless of whether the first state of the first model or function continues until the second moment or the third moment, the second moment is used to determine the state of the first model or function. In other words, regardless of whether the first state of the first model or function continues until the second moment or the third moment, the terminal device determines the state of the first model or function based on the second moment and the start time of the first task.

[0395] Optionally, when the duration of the first state of the first model or function corresponding to the first task overlaps with the duration of the first state of the second model or function corresponding to the second task, the network device may also determine the duration of the first state of the first model or function based on one of the following: the priority of the task, the start time of the task, the identifier of the task, or the time characteristics of the task. Thus, the network device and the terminal device can align the duration of the first model or function, allowing the terminal device to successfully use the first model or function during the duration of the first state of the first model or function.

[0396] In one optional embodiment, when the first function or model corresponding to the first task continues from the start time of the first task to the third time, the third model or function corresponding to the third task is in the first state, including: the start time of the third task is between the start time of the first task and the third time. In other words, the terminal device can determine the state of the third model or function corresponding to the third task based on the start time of the first task, the third time, and the start time of the third task; when the start time of the third task is between the start time of the first task and the third time, the terminal device determines that the third model or function is in the first state.

[0397] Optionally, since at least one of the following items corresponding to the first task is different when the first model or function is in the first state compared to when the first model or function is in the second state: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function, the network device may also determine the state of the first model or function corresponding to the first task before instructing the terminal device to perform the first task, or before sending the first information, and determine at least one of the following items based on the state of the first model or function: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function. Furthermore, the network device may schedule relevant resources for the terminal device to perform the first task based on the at least one item determined. For example, the network device may schedule resources for the second downlink signal used to perform the first task for the terminal device based on the determined delay requirement, or configure resources for the second uplink signal used to carry reported information for the terminal device.

[0398] Among them, the network device also determines the state of the first model or function based on the second moment and the starting moment of the first task. The specific implementation method can be found in the above-mentioned terminal device determining the implementation method of the first model or function based on the second moment and the starting moment of the first task, and will not be repeated here.

[0399] It can be seen that the network device can also determine the status of the first model or function corresponding to the first task, so that the network device and the terminal device can align the status of the first model or function, and then the network device and the terminal device can both determine the requirements corresponding to the first task based on the status of the first model or function, which can ensure that the terminal device can smoothly execute the first task.

[0400] In an embodiment of the present application, when the first model or function corresponding to the first task is in a first state, relative to when the first model or function is in a second state, at least one of the following items corresponding to the first task is different: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function. Therefore, when the terminal device receives the first information for instructing the execution of the first task, it determines the state of the first model or function, and based on the state of the first model or function, determines at least one of the following items corresponding to the first task: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function, and then executes the first task based on the determined at least one item. This method can enable the requirement corresponding to the first task to match the state of the first model or function corresponding to the first task, so that the terminal device can smoothly execute the first task, or enable the model reasoning of the first model or function to be smoothly executed.

[0401] The embodiment of the present application also takes the case where the second task belongs to the CSI measurement and reporting task of periodic beam prediction, the first task belongs to the CSI measurement and reporting task of dynamically scheduled beam prediction (i.e., the CSI measurement and reporting task of non-periodic beam prediction), the start time of the first task is later than the start time of the second task, the model or function adopted by the terminal device to perform the first task is the first model or function, and the model or function adopted by the terminal device to perform the second task is the second model or function as an example to illustrate the communication method shown in Figure 6 above. Figure 17 is a schematic diagram of the interaction between a network device and a terminal device. As shown in Figure 17, the interaction between the network device and the terminal device includes but is not limited to the following steps:

[0402] S1701. The network device sends CSI reporting trigger information to the terminal device, where the CSI reporting trigger information is used to trigger the terminal device to perform a first task. Correspondingly, the terminal device receives the CSI reporting trigger information from the network device.

[0403] Among them, the first task belongs to the CSI measurement and reporting of non-periodic beam prediction, and the CSI reporting trigger information also includes the resources for the terminal device to perform CSI measurement and reporting of non-periodic beam prediction, as well as the reporting amount.

[0404] In an embodiment of the present application, the first task is a task performed by running the first model or function, or in other words, the first task requires the use of the first model or function to perform model reasoning. When the first model or function is in the first state (activated state), model reasoning can be performed directly. When the first model or function is in the second state (deactivated state), the model or function needs to be activated first so that the model or function is switched to the first state (activated state) before model reasoning is performed. Therefore, the CSI reporting trigger information is used to trigger the terminal device to perform the first task, which can be understood as an implicit instruction to the terminal device to perform the activation and reasoning of the first model or function corresponding to the first task. In other words, the network device can indicate the activation of the first model or function through the CSI reporting trigger information, and the terminal device determines whether it is necessary to perform the actual model activation operation based on the state of the first model or function.

[0405] S1702. The terminal device determines the state of the first model or function corresponding to the first task.

[0406] In an optional implementation, the terminal device determines the state of the first model or function, including: determining a second moment corresponding to the second task, the second moment being the duration of the first state of the second model or function; and determining the state of the first model or function based on the second moment and the start moment of the first task.

[0407] The terminal device determines the second moment corresponding to the second task, including: determining the second moment based on the first moment and the first time length. The implementation method thereof can be found in the specific description of the communication method described in FIG6 above, and is not further described. Optionally, the first moment and the first time length are configured by the network device to the terminal device via CSI reporting trigger information, or are predefined by the protocol.

[0408] Optionally, the first moment corresponds to one of the following: the starting moment or the ending moment of the reference signal for measuring CSI; the starting moment or the ending moment of the time unit in which the starting moment or the ending moment of the reference signal for measuring CSI is located; the starting moment of the first time unit after the time unit in which the starting moment or the ending moment of the reference signal for measuring CSI is located; the starting moment or the ending moment of the PUSCH or PUCCH carrying the CSI report; the starting moment or the ending moment of the time unit in which the starting moment or the ending moment of the PUSCH or PUCCH carrying the CSI report is located; the first time unit after the starting moment or the ending moment of the time unit in which the PUSCH or PUCCH carrying the CSI report is located The starting time of the time unit; the starting time or ending time of the reference resource corresponding to the CSI report; the starting time or ending time of the time unit in which the starting time or ending time of the reference resource corresponding to the CSI report is located; the starting time of the first time unit after the time unit in which the starting time or ending time of the reference resource corresponding to the CSI report is located; the starting time or ending time of the PDCCH that triggers the CSI report; the starting time or ending time of the time unit in which the starting time or ending time of the PDCCH that triggers the CSI report; the starting time of the first time unit after the time unit in which the starting time or ending time of the PDCCH that triggers the CSI report; the starting time or ending time of the reference signal used to measure the CSI The moment when the end time is advanced or delayed by the time offset; the moment when the start time or end time of the time unit in which the reference signal for measuring CSI is located is advanced or delayed by the time offset; the moment when the start time of the first time unit after the time unit in which the reference signal for measuring CSI is located is advanced or delayed by the time offset; the moment when the start time or end time of the PUSCH or PUCCH carrying the CSI report is advanced or delayed by the time offset; the moment when the start time or end time of the time unit in which the PUSCH or PUCCH carrying the CSI report is located is advanced or delayed by the time offset; the moment when the start time or end time of the time unit in which the PUSCH or PUCCH carrying the CSI report is located is advanced or delayed by the time offset; The time interval after the start time of the first time unit after the time unit where the start time or end time of the PUSCH or PUCCH of the CSI reporting is located is advanced or delayed by the time offset; the time interval after the start time or end time of the reference resource corresponding to the CSI reporting is advanced or delayed by the time offset; the time interval after the start time or end time of the time unit where the start time or end time of the reference resource corresponding to the CSI reporting is located is advanced or delayed by the time offset; the time interval after the start time or end time of the first time unit after the time unit where the start time or end time of the reference resource corresponding to the CSI reporting is located is advanced or delayed by the time offset; the time interval after the start time or end time of the PDCCH that triggers the CSI reporting is advanced or delayed by the time offset;The time interval before or after the start or end time of the time unit containing the start or end time of the PDCCH that triggers CSI reporting; the time interval before or after the start time of the first time unit after the start or end time of the PDCCH that triggers CSI reporting. The reference signal used to measure CSI is RS or SSB.

[0409] Optionally, the first moment corresponds to the start moment of the first cycle among the N cycles, and the second moment corresponds to the end moment of the Nth cycle among the N cycles. The N cycles are multiple cycles to which the second task belongs, the second task is a task corresponding to one of the multiple cycles, and N is a positive integer greater than 1.

[0410] In addition, the implementation method of the terminal device determining the state of the first model or function according to the second moment and the start moment of the first task can be referred to the specific description in the communication method described in Figure 6 above, and will not be repeated here.

[0411] S1703. The terminal device determines at least one of the following based on the status of the first model or function: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function.

[0412] The implementation of S1703 can refer to the above-mentioned implementation modes 1 to 5, and will not be described in detail.

[0413] S1704: The network device sends a CSI RS to the terminal device. Correspondingly, the terminal device receives the CSI RS from the network device.

[0414] Among them, the CSI RS is used by the terminal device to perform CSI measurement for beam prediction.

[0415] In an optional implementation, in S1703, the terminal device determines the delay requirement, and the terminal device receives the CSI RS from the network device, including: receiving the CSI RS from the network device based on the determined delay requirement. For example, the terminal device receives the CSI RS at time t6 based on the delay requirement between the CSI RS corresponding to the first task in Figure 12 and the PUSCH. In other words, the terminal device determines to use the CSI RS received at time t6 for CSI measurement based on the delay requirement between the CSI RS corresponding to the first task in Figure 12 and the PUSCH. For another example, the terminal device receives the CSI RS at time t7 based on the delay requirement between the CSI RS corresponding to the first task in Figure 13 and the PUSCH. In other words, the terminal device determines to use the CSI RS received at time t7 for CSI measurement based on the delay requirement between the CSI RS corresponding to the first task in Figure 13 and the PUSCH. For another example, the terminal device receives the CSI RS at time t7 based on the delay requirement between the CSI RS corresponding to the first task in Figure 14a and the PUSCH. In other words, the terminal device determines to use the CSI RS received at time t7 to perform CSI measurement based on the delay requirement between the CSI RS and PUSCH corresponding to the first task in Figure 14a.

[0416] It is understandable that the CSI RS is sent according to the CSI RS configuration. Therefore, the configuration and transmission of the CSI RS and the CSI reporting configuration / trigger command are two independent processes. Therefore, the execution order of S1704 can be before the execution order of S1701 or after the execution order of S1701. In other words, the CSIRS used for CSI measurement by the terminal device may be the CSIRS sent before the execution of S1701 and / or the CSIRS sent after the execution of S1701.

[0417] S1705a. When the first model or function is in an activated state, the terminal device determines an optimal beam and an RSRP of the optimal beam based on the CSI RS and the first model or function.

[0418] The terminal device determines the optimal beam and the RSRP of the optimal beam based on the CSI RS and the first model or function, including: obtaining the first beam and the RSRP of the first beam based on the CSI RS; and performing model inference on the first beam and the RSRP of the first beam using the first model or function within a time period corresponding to the first model or function to obtain the optimal beam and the RSRP of the optimal beam. The time period corresponding to the first model or function includes at least one of the following determined by the terminal device: a usage time period of the first model or function, a storage unit occupancy time period of the first model or function, and a computing unit occupancy time period of the first model or function.

[0419] For example, in S1703, the terminal device determines the usage time period of the first model or function, then in S1705a: the terminal device obtains the first beam and the RSRP of the first beam based on the CSI RS; during the usage time period of the first model or function, the first model or function is used to perform model inference on the first beam and the RSRP of the first beam to obtain the optimal beam and the RSRP of the optimal beam.

[0420] S1705b. When the first model or function is in a deactivated state, the terminal device activates the first model or function, and determines the optimal beam and the RSRP of the optimal beam based on the CSI RS and the activated first model or function.

[0421] Wherein, when the first model or function is in a deactivated state, the terminal device activates the first model or function, and determines the optimal beam and the RSRP of the optimal beam based on the CSI RS and the activated first model or function, including: activating the first model or function based on the time period corresponding to the first model or function, and determining the optimal beam and the RSRP of the optimal beam based on the CSI RS and the activated first model or function. Wherein, the time period corresponding to the first model or function includes at least one of the following determined by the terminal device: the usage time period of the first model or function, the storage unit occupancy time period of the first model or function, and the computing unit occupancy time period of the first model or function.

[0422] For example, in S1703, the terminal device determines the usage time period of the first model or function, and the starting time of the usage time period of the first model or function is later than the starting time of the CSI RS, then in S1705b: after the terminal device receives the CSI RS, it activates the first model or function, and uses the first model or function to perform model inference on the first beam and the RSRP of the first beam during the usage time period of the first model or function to obtain the optimal beam and the RSRP of the optimal beam.

[0423] S1706. The terminal device sends a CSI report to the network device. The CSI report includes the optimal beam and the RSRP of the optimal beam.

[0424] Optionally, before sending CSI reporting trigger information to the terminal device, the network device further determines the state of the first model or function corresponding to the first task to align the state of the first model or function with that of the terminal device. The implementation method for the network device to determine the state of the first model or function can refer to the implementation method for the terminal device to determine the state of the first model or function, and will not be repeated here.

[0425] Optionally, the network device also determines at least one of the following based on the state of the first model or function: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function, and then configures the terminal device with relevant requirements corresponding to the first task based on the at least one determined item. For example, if the terminal device determines the delay requirement, resources for receiving CSI RS are scheduled for the terminal device based on the delay requirement, or resources for PUSCH for carrying CSI reports are scheduled for the terminal device based on the delay requirement. In this manner, the network device also determines at least one requirement corresponding to the first task based on the state of the first model or function. The at least one requirement corresponding to the first task determined by the network device and the at least one requirement corresponding to the first task determined by the terminal device are both determined based on the state of the first model or function, so the two are aligned, thereby ensuring that the terminal device can smoothly perform the first task, or saving resources for the terminal device to perform the first task.

[0426] It can be seen that after the terminal device receives the CSI reporting trigger information used to trigger the terminal device to perform the first task, it determines the state of the first model or function corresponding to the first task, and based on the state of the first model or function, determines at least one of the following items corresponding to the first task: delay requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and calculation unit occupancy time period of the first model or function, and then, based on at least one determined item, uses the activated first model or function to perform beam prediction to obtain the optimal beam and the RSRP of the optimal beam, and then reports the optimal beam and the RSRP of the optimal beam through the CSI report.

[0427] The present application also proposes another communication method. This communication method is also described from the perspective of the interaction between the network device and the terminal device. Figure 18 is a schematic diagram of the interaction of the communication method. As shown in Figure 18, the communication method includes but is not limited to the following steps:

[0428] S1801. A network device sends first information to a terminal device, the first information being used to instruct the terminal device to execute a first task, wherein a computing unit occupation time period of a first model or function corresponding to the first task begins at a fourth moment, and the fourth moment is later than a start moment of a second downlink signal corresponding to the first task, or the fourth moment is earlier than a start moment of the second downlink signal corresponding to the first task. Accordingly, the terminal device receives the first information from the network device.

[0429] S1802. The terminal device executes the first task.

[0430] The first information can be found in S601 above and will not be described in detail.

[0431] Optionally, the time period during which the computing unit of the first model or function corresponding to the first task occupies is replaced by the time period during which the first model or function corresponding to the first task is used.

[0432] In addition, the time period occupied by the calculation unit of the first model or function corresponding to the first task starts at the fourth moment, and the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal or a downlink channel. Compared with the fourth moment starting from the starting moment of the second downlink signal, this method can reduce the time occupied by the calculation unit of the model, and can enable the terminal device to have more idle calculation units to use other models to perform tasks. For example, as shown in Figure 13, the time period occupied by the calculation unit of the first model or function starts from moment t10, instead of from moment t7 or t8, thereby saving the time period occupied by the calculation unit of the first model or function. Therefore, there may be idle calculation units in the time period from t5 to t10, and the terminal device can use other models or functions for model reasoning.

[0433] For example, Figure 19 is another CSI reporting diagram. As shown in Figure 19, time t1 is the time for configuring the terminal device to perform periodic CSI reporting, and time t3 is the time for triggering the terminal device to perform non-periodic CSI reporting. The periodic CSI reporting task triggered at time t1 is the first task, and the non-periodic CSI reporting task triggered at time t3 is the second task. The terminal device is allowed to use up to 2 CPUs. The computing unit of the first model or function occupies the time period from t7 to t8, and occupies 2 computing unit CPUs. Then, there is no idle CPU in the time period from t7 to t8. The non-periodic CSI reporting task triggered at time T3 needs to occupy 1 CPU. Since the computing unit of the first model or function corresponding to the first task occupies the time period from t7 to t8, there are 2 idle CPUs from time t3 to time t7. Then the terminal device can use the idle CPU to perform the second task, that is, it can use the second model or function corresponding to the second task to perform model reasoning in the time period from t5 to t6 to obtain the reasoning result.

[0434] For example, Figure 20 is another CSI reporting diagram. As shown in Figure 20, time t1 is the time when the terminal device is configured to perform periodic CSI reporting, and time t3 is the time when the terminal device is triggered to perform aperiodic CSI reporting. The periodic CSI reporting task triggered at time t1 is the first task, and the aperiodic CSI reporting task triggered at time t3 is the second task. The terminal device is allowed to use up to 2 CPUs. The computing unit of the first model or function occupies the time period from t2 to t4, and occupies 1 computing unit CPU. Then, there is 1 idle CPU in the time period from t2 to t4. The second task triggered at time t3 needs to occupy 2 CPUs, but the CPU occupancy time period of the second task is from t5 to t6, that is, the CPU executing the second task only starts to be occupied from time t5. There are 2 idle CPUs between t5 and t6. Then, the terminal device can first perform model activation after receiving the trigger request of the second task, and then can use the second model or function corresponding to the second task to perform model reasoning between t5 and t6 to obtain the reasoning result.

[0435] Optionally, the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task, and the second downlink signal is a downlink signal. When the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task, it can be ensured that the terminal device can use sufficient resources to perform model reasoning based on the activated first model or function to obtain reasoning results. For example, in Figure 15a, if the time period occupied by the computing unit of the first model or function starts from t8, that is, computing resources are reserved for the first task at t8, then the terminal device can immediately use sufficient resources between t8 and t10 after the first model or function is switched from an activated state to a deactivated state, and smoothly perform model reasoning based on the activated first model or function to complete the execution of the first task.

[0436] In addition, the time interval between the fourth moment and the starting moment of the second downlink signal is a second time length, and the second time length is reported by the terminal device or preset.

[0437] Optionally, the fourth moment is earlier than the start moment or end moment of the second uplink signal corresponding to the first task, and the time interval between the fourth moment and the start moment or end moment of the second uplink signal is a third time length. The third time length is reported by the terminal device or is preset. For example, the start moment t7 of the time period occupied by the calculation unit of the first model or function corresponding to the first task in Figure 19 is earlier than the start moment t8 of the PUSCH carrying the CSI report, or earlier than the end moment t9 of the PUSCH carrying the CSI report.

[0438] Optionally, the time period occupied by the calculation unit of the first model or function ends at a fifth moment, and the fifth moment is earlier than the end moment of the second uplink signal corresponding to the first task. For example, in Figure 19, the time period occupied by the calculation unit of the first model or function corresponding to the first task ends at moment t8, and t8 is earlier than the end moment t9 of the PUSCH carrying the CSI report.

[0439] Optionally, the time interval between the fifth moment and the start or end moment of the second downlink signal is a fourth time length. The fourth time length is reported by the terminal device or is preset. For example, in Figure 19, there is a time interval between the end moment t8 of the computing unit occupation time period of the first model or function corresponding to the first task and the CSI RS corresponding to the first task.

[0440] Optionally, the time interval between the fifth moment and the start or end moment of the second uplink signal is a fifth time length. The fifth time length is reported by the terminal device or is preset. For example, in Figure 19, there is a time interval between the end moment t8 of the time period occupied by the calculation unit of the first model or function corresponding to the first task and the end moment t9 of the PUSCH carrying the CSI report corresponding to the first task.

[0441] Optionally, the terminal device executes the first task, including: executing the first task based on a time period during which a computing unit of a first model or function corresponding to the first task is occupied. Specifically, the terminal device performs model inference using the first model or function during the time period during which the computing unit of the first model or function is occupied, and obtains an inference result. Optionally, the terminal device also reports the inference result or reporting information generated based on the inference result to the network device.

[0442] It can be seen that in the embodiment of the present application, the time period occupied by the computing unit of the first model or function corresponding to the first task starts at the fourth moment, and the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, or the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task. Then, after receiving the first information for instructing the execution of the first task, the terminal device determines the time period occupied by the computing unit of the first model or function, and executes the first task according to the determined time period occupied by the computing unit of the first model or function.

[0443] The time period occupied by the computing unit of the first model or function corresponding to the first task begins at the fourth moment. When the fourth moment is later than the starting moment of the second downlink signal corresponding to the first task, the terminal device executes the first task according to the time period occupied by the computing unit of the determined first model or function, which can make more computing units idle, so that the terminal device can use the idle computing units to execute more tasks, or in other words, the terminal device can make full use of the idle computing unit resources to perform multiple parallel task processing. When the fourth moment is earlier than the starting moment of the second downlink signal corresponding to the first task, the terminal device executes the first task according to the time period occupied by the computing unit of the determined first model or function, which can make the terminal device use sufficient resources to perform model reasoning based on the first model or function when the first model or function is in the first state, and thus the terminal device can smoothly execute the first task.

[0444] With respect to the technical solutions described above, the corresponding device implementation solutions are further described below.

[0445] To implement the various functions of the methods provided in the embodiments of the present application, the terminal device and the network device may include hardware structures and / or software modules, and implement the aforementioned functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular one of the aforementioned functions is implemented 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.

[0446] As shown in Figure 21, an embodiment of the present application provides a communication device 2100. The communication device 2100 can be a component of a terminal device (e.g., an integrated circuit, a chip, etc.) or a component of a network device (e.g., an integrated circuit, a chip, etc.). The communication device 2100 can also be other communication units for implementing the method in the method embodiment of the present application. The communication device 2100 may include: a communication unit 2101 and a processing unit 2102. Optionally, a storage unit 2103 may also be included.

[0447] In one possible design, one or more units in FIG. 21 may be implemented by one or more processors, or by one or more processors and memories, or by one or more processors and transceivers, or by one or more processors, memories, and transceivers, which are not limited in this embodiment of the present application. The processors, memories, and transceivers may be provided separately or integrated.

[0448] The communication device 2100 has the functions of the terminal device described in the embodiment of the present application, or the functions of the network device. For example, the communication device 2100 includes a module or unit or means corresponding to the steps involved in the terminal device in the above-mentioned method embodiments. The functions or units or means can be implemented by software, or by hardware, or by hardware executing the corresponding software implementation, or by a combination of software and hardware. For details, please refer to the corresponding description in the above-mentioned corresponding method embodiment.

[0449] In one possible design, a communication apparatus 2100 may include: a processing unit 2102 and a communication unit 2101, wherein the apparatus is applied to a terminal device;

[0450] The communication unit 2101 is configured to receive first information, where the first information is used to instruct the terminal device to perform a first task;

[0451] The processing unit 2102 is configured to execute the first task;

[0452] Among them, when the first model or function is in the first state compared to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: latency requirement, usage time period of the first model or function, storage unit occupancy time period of the first model or function, and computing unit occupancy time period of the first model or function; the first model or function corresponds to the first task.

[0453] In an optional embodiment, the first state of the second model or function lasts from a first moment to a second moment; the second model or function corresponds to a second task, and the start moment of the second task is earlier than the start moment of the first task.

[0454] In an optional embodiment, the first moment corresponds to one of the following: the starting moment of the first downlink signal, the ending moment of the first downlink signal, the starting moment of the first uplink signal, the ending moment of the first uplink signal, the first offset moment, and the second offset moment; wherein, the time interval between the first offset moment and the starting moment or the ending moment of the first downlink signal corresponds to the first time offset, and the time interval between the second offset moment and the starting moment or the ending moment of the first uplink signal corresponds to the second time offset; or, the first moment corresponds to one of the following: the starting moment of the usage time period of the second model or function corresponding to the second task, the starting moment of the storage unit occupancy time period of the second model or function, the starting moment of the computing unit occupancy time period of the second model or function, the ending moment of the usage time period of the second model or function, the ending moment of the storage unit occupancy time period of the second model or function, and the ending moment of the computing unit occupancy time period of the second model or function; the first downlink signal and the first uplink signal are both related to the second task.

[0455] In an optional implementation manner, the time interval between the first moment and the second moment is a first time length, and the first time length is configured or indicated by the network device, or is preset.

[0456] In an optional implementation, the second task is a periodic task or a semi-persistent task.

[0457] In an optional embodiment, when the second task is a periodic task or a semi-continuous task, the first moment corresponds to the start moment of the first cycle among N cycles, and the second moment corresponds to the end moment of the Nth cycle among the N cycles; the N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1.

[0458] In an optional embodiment, the second moment corresponds to one of the following: the starting moment or ending moment of the channel carrying the reporting information of the second task; the starting moment or ending moment of the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located; the starting moment of the first time unit after the time unit in which the starting moment or ending moment of the channel carrying the reporting information of the second task is located.

[0459] In an optional implementation, the second task is a dynamically scheduled task.

[0460] In an optional implementation, the first model or function corresponding to the first task is in a first state, including: the start time of the first task is between the first time and the second time.

[0461] In an optional implementation, the first state of the first model or function continues until a third moment, the third moment corresponds to the first task, and the third moment is later than the second moment.

[0462] In an optional embodiment, the third moment acts on at least one of the following items corresponding to the third task: delay requirement, usage time period of the third model or function, storage unit occupancy time period of the third model or function, and computing unit occupancy time period of the third model or function; the third model or function corresponds to the third task, and the start moment of the third task is later than the start moment of the first task.

[0463] In an optional implementation, the first state of the first model or function ends at the second moment.

[0464] In an optional embodiment, the second state of the first model or function starts from the second moment, or the time period corresponding to the second state of the first model or function is included in a time period outside the time period corresponding to the first state.

[0465] In an optional implementation, the first model or function is in the second state, including: the first model or function is not in the first state; or the start time of the first task is after the second time.

[0466] In an optional embodiment, the starting time of the first task corresponds to one of the following: the starting time of the second downlink signal, the ending time of the second downlink signal, the third offset time, the starting time of the usage time period of the first model or function, the starting time of the storage unit occupancy time period of the first model or function, and the starting time of the computing unit occupancy time period of the first model or function; wherein the time interval between the third offset time and the starting time or ending time of the second downlink signal corresponds to a third time offset; and the second downlink signal is related to the first task.

[0467] In an optional embodiment, the second model or function is the same as the first model or function.

[0468] In an optional embodiment, the delay requirement is one of the following: the time interval requirement between the second downlink signal and the second uplink signal; the time interval requirement between the second downlink signal and the end moment of the usage time period of the first model or function; the time interval requirement between the second downlink signal and the end moment of the storage unit occupation time period of the first model or function; the time interval requirement between the second downlink signal and the end moment of the computing unit occupation time period of the first model or function; the second downlink signal and the second uplink signal are both related to the first task.

[0469] In an optional implementation, when the first model or function is in the first state, the latency requirement corresponding to the first task is smaller than when the first model or function is in the second state.

[0470] In an optional embodiment, when the first model or function is in the first state, the usage time period of the first model or function corresponding to the first task starts from the start time or end time of the second downlink signal corresponding to the first task; when the first model or function is in the second state, the start time of the usage time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task.

[0471] In an optional embodiment, when the first model or function is in the first state, the time period occupied by the computing unit of the first model or function corresponding to the first task starts from the start time or end time of the second downlink signal corresponding to the first task; when the first model or function is in the second state, the start time of the time period occupied by the computing unit of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task.

[0472] In an optional embodiment, when the first model or function corresponding to the first task is in the first state, the storage unit occupancy time period of the first model or function corresponding to the first task starts from the start or end time of the second downlink signal corresponding to the first task; when the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second downlink signal corresponding to the first task; or, when the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink channel corresponding to the first task; or, when the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second uplink signal corresponding to the first task, and the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is determined by the start time or end time of the second uplink signal corresponding to the first task.

[0473] In an optional implementation, the first state is an activated state, and the second state is a deactivated state.

[0474] In an optional implementation manner, the first moment is configured by the network device or is preset.

[0475] In an optional embodiment, the first time length is determined based on at least one of the following: an index or identifier corresponding to the first time length; 1 / M times the reporting period of the second task, where M is a positive integer; or a time characteristic of the second task.

[0476] In an optional implementation manner, the first time offset and / or the second time offset is reported by the terminal device or is preset.

[0477] In an optional implementation, the third time offset is reported by the terminal device or is preset.

[0478] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned embodiments, which will not be repeated here.

[0479] The present application also provides a communication device 2200. Figure 22 is a schematic diagram of the structure of the communication device 2200. The communication device 2200 can be a terminal device, or a chip, chip system, or processor that supports the terminal device to implement the above-mentioned method; or it can be a network device, or a chip, chip system, or processor that supports the network device to implement the above-mentioned method. This device can be used to implement the method described in the above-mentioned method embodiment. For details, please refer to the description of the above-mentioned method embodiment.

[0480] The communication device 2200 may include one or more processors 2201. The processor 2201 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or a central processing unit (CPU). The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control the communication device (e.g., a base station, a baseband chip, a terminal, a terminal chip, a DU or CU, etc.), execute software programs, and process data from the software programs.

[0481] Optionally, the communication device 2200 may include one or more memories 2202, on which instructions 2204 may be stored. The instructions may be executed on the processor 2201, causing the communication device 2200 to perform the method described in the above method embodiment. Optionally, the memory 2202 may also store data. The processor 2201 and memory 2202 may be provided separately or integrated together.

[0482] Optionally, the communication device 2200 may further include a transceiver 2205 and an antenna 2206. The transceiver 2205 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., and is configured to implement transceiver functions. The transceiver 2205 may include a receiver and a transmitter. The receiver may be referred to as a receiver or a receiving circuit, etc., and is configured to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., and is configured to implement a transmitting function.

[0483] In one possible design, the communication device 2200 can be applied to a terminal device. Specifically, the transceiver 2205 is used to execute S601 in the communication method described in Figure 6 and S1801 in the communication method described in Figure 18; the processor 2201 is used to execute S602 in the communication method described in Figure 6 and S1802 in the communication method described in Figure 18.

[0484] In another possible design, the communication device 2200 can be applied to a network device. Specifically, the transceiver 2205 is used to execute S601 in the communication method described in FIG. 6 and S1801 in the communication method described in FIG. 18 .

[0485] Optionally, the processor 2201 may store an instruction 2203. The instruction 2203 runs on the processor 2201, which may enable the communication device 2200 to perform the method described in the above method embodiment. The instruction 2203 may be fixed in the processor 2201. In this case, the processor 2201 may be implemented by hardware.

[0486] The embodiment of the present application and the method embodiment shown in the communication method described in Figure 6 above are based on the same concept, and the technical effects they bring are also the same. For specific principles, please refer to the description of the embodiment shown in the communication method described in Figure 6 above, and no further details will be given.

[0487] The embodiment of ...

Claims

1. A communication method, characterized in that: The method comprises: receiving first information, where the first information is used to instruct a terminal device to perform a first task; performing the first task; When the first model or function is in the first state, relative to when the first model or function is in the second state, at least one of the following items corresponding to the first task is different: a latency requirement, a usage period of the first model or function, a storage unit occupation period of the first model or function, and a computing unit occupation period of the first model or function; The first model or function corresponds to the first task.

2. The method according to claim 1, characterized in that The first model or function corresponding to the first task is in the first state, including: The starting time of the first task is between the first time and the second time.

3. The method according to claim 1 or 2, characterized in that said first state of a second model or function lasts from a first moment in time to a second moment in time; The second model or function corresponds to a second task, and a start time of the second task is earlier than a start time of the first task.

4. The method according to claim 3, characterized in that The first moment corresponds to one of the following: a start moment of a first downlink signal, an end moment of the first downlink signal, a start moment of a first uplink signal, an end moment of the first uplink signal, a first offset moment, and a second offset moment; wherein the time interval between the first offset moment and the start moment or the end moment of the first downlink signal corresponds to a first time offset, and the time interval between the second offset moment and the start moment or the end moment of the first uplink signal corresponds to a second time offset; Alternatively, the first moment corresponds to one of the following: a start moment of a usage time period of a second model or function corresponding to the second task, a start moment of a storage unit occupation time period of the second model or function, a start moment of a computing unit occupation time period of the second model or function, an end moment of a usage time period of the second model or function, an end moment of a storage unit occupation time period of the second model or function, or an end moment of a computing unit occupation time period of the second model or function; The first downlink signal and the first uplink signal are both related to the second task.

5. The method according to any one of claims 2 to 4, characterized in that The time interval between the first moment and the second moment is a first time length, and the first time length is configured or indicated by the network device, or is preset.

6. The method according to claim 3 or 4, characterized in that The second task is a periodic task or a semi-persistent task.

7. The method according to claim 3, characterized in that When the second task is a periodic task or a semi-persistent task, the first moment corresponds to the start moment of the first cycle of N cycles, and the second moment corresponds to the end moment of the Nth cycle of the N cycles; The N cycles are multiple cycles to which the second task belongs, and N is a positive integer greater than 1.

8. The method according to claim 3 or 4, characterized in that The second moment corresponds to one of the following: the start time or end time of the channel carrying the reporting information of the second task; The start time or end time of the time unit in which the start time or end time of the channel carrying the reporting information of the second task is located; The starting time of the first time unit after the starting time or ending time of the channel carrying the reporting information of the second task. The method according to claim 8 , wherein the second task is a dynamically scheduled task.

10. The method according to any one of claims 2 to 9, characterized in that The first state of the first model or function lasts until a third time, the third time corresponding to the first task, the third time being later than the second time.

11. The method according to claim 10, characterized in that The third moment acts on at least one of the following corresponding to the third task: latency requirement, a usage period of the third model or function, a storage unit occupancy period of the third model or function, and a computing unit occupancy period of the third model or function; The third model or function corresponds to the third task, and a start time of the third task is later than a start time of the first task.

12. The method according to any one of claims 2 to 9, characterized in that The first state of the first model or function ends at the second time.

13. The method according to any one of claims 2 to 9 or claim 12, characterized in that The second state of the first model or function starts from the second moment, or the time period corresponding to the second state of the first model or function includes time outside the time period corresponding to the first state.

14. The method according to any one of claims 1 to 13, characterized in that The first model or function is in a second state, comprising: the first model or function is not in the first state; Alternatively, the starting time of the first task is after the second time.

15. The method according to any one of claims 2 to 11, characterized in that include: The start time of the first task corresponds to one of the following: the start time of the second downlink signal, the end time of the second downlink signal, the third offset time, the start time of the usage time period of the first model or function, the start time of the storage unit occupation time period of the first model or function, and the start time of the calculation unit occupation time period of the first model or function; wherein the time interval between the third offset time and the start time or the end time of the second downlink signal corresponds to a third time offset; The second downlink signal is related to the first task.

16. The method according to any one of claims 2 to 15, characterized in that The second model or function is the same as the first model or function.

17. The method according to any one of claims 1 to 16, characterized in that The latency requirement is one of the following: The time interval requirement between the second downlink signal and the second uplink signal; A time interval requirement between the second downlink signal and the end time of the usage period of the first model or function; The time interval requirement between the second downlink signal and the end of the storage unit occupancy period of the first model or function; The time interval requirement between the second downlink signal and the end of the computing unit occupation time period of the first model or function; The second downlink signal and the second uplink signal are both related to the first task.

18. The method according to any one of claims 1 to 17, characterized in that When the first model or function is in the first state, the latency requirement corresponding to the first task is smaller than when the first model or function is in the second state.

19. The method according to any one of claims 1 to 18, characterized in that When the first model or function is in the first state, the usage time period of the first model or function corresponding to the first task starts from the start time or the end time of the second downlink signal corresponding to the first task; When the first model or function is in the second state, the start time of the usage time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task.

20. The method according to any one of claims 1 to 19, characterized in that When the first model or function is in the first state, the computing unit occupancy time period of the first model or function corresponding to the first task starts from the start time or the end time of the second downlink signal corresponding to the first task; When the first model or function is in the second state, the start time of the time period occupied by the calculation unit of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task.

21. The method according to any one of claims 1 to 20, characterized in that When the first model or function corresponding to the first task is in the first state, the storage unit occupancy time period of the first model or function corresponding to the first task starts from the start or end time of the second downlink signal corresponding to the first task; When the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the start time or end time of the second downlink signal corresponding to the first task; or When the first model or function corresponding to the first task is in the second state, the start time of the storage unit occupancy time period of the first model or function corresponding to the first task is later than the start time or end time of the second downlink signal corresponding to the first task; or When the first model or function corresponding to the first task is in the second state, the starting time of the storage unit occupancy time period of the first model or function corresponding to the first task is earlier than the starting time or the ending time of the second uplink signal corresponding to the first task, and the starting time of the storage unit occupancy time period of the first model or function corresponding to the first task is determined by the starting time or the ending time of the second uplink signal corresponding to the first task.

22. The method according to any one of claims 1 to 21, characterized in that The first state is an activated state, and the second state is a deactivated state.

23. The method according to any one of claims 2 to 22, characterized in that The first moment is configured by the network device or is preset.

24. The method according to claim 5, characterized in that The first time period is determined according to at least one of the following: An index or identifier corresponding to the first time length; 1 / M times the reporting period of the second task, where M is a positive integer; The temporal characteristics of the second task.

25. The method according to claim 4, wherein The first time offset and / or the second time offset are reported by the terminal device or are preset.

26. The method according to claim 15, wherein The third time offset is reported by the terminal device or is preset.

27. A communication device, characterized in that: The communication device comprises means for performing the method according to any one of claims 1 to 26.

28. A communication device, characterized in that: The communication device comprises a processor configured to perform the method according to any one of claims 1 to 26.

29. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store instructions, and when the instructions are run on a computer, the method according to any one of claims 1 to 26 is executed.

30. A computer program product comprising instructions, characterized in that When the method is executed on a computer, the method according to any one of claims 1 to 26 is performed.

Images