Demodulation method, communication device, communication system, and storage medium

Abstract

The present disclosure provides a demodulation method, a communication device, a communication system, and a storage medium. The method comprises: determining at least one of a first capability and a first delay, the first capability being used to indicate a processing capability of a terminal when performing demodulation on the basis of an artificial intelligence (AI) model, and the first delay being used to indicate a processing delay of the terminal when performing demodulation on the basis of the AI model; indicating to a network device at least one of the first capability supported by the terminal and the first delay supported by the terminal; receiving first information sent by the network device, the first information being used to indicate at least one of the following: whether the terminal is to perform demodulation on the basis of the AI model, the first capability to be used by the terminal, the first delay corresponding to the terminal, and information required when the terminal performs demodulation on the basis of the AI model; and on the basis of the first information, demodulating at least one of a channel and a signal. The present disclosure improves demodulation performance, demodulation accuracy, and demodulation efficiency, and ensures the stability of demodulation.

Description

Demodulation methods, communication equipment, communication systems, storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to demodulation methods, communication equipment, communication systems, and storage media. Background Technology

[0002] With the continuous development of artificial intelligence (AI) technology, its applications are becoming increasingly widespread. In communication systems, terminals typically rely on AI to handle communication tasks; for example, terminals may use AI models for demodulation.

[0003] Summary of the Invention

[0004] This disclosure provides demodulation methods, communication equipment, communication systems, and storage media.

[0005] According to a first aspect of the embodiments of this disclosure, a demodulation method is proposed, executed by a terminal, comprising:

[0006] Determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when demodulating based on an AI model.

[0007] Indicate to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0008] The network device receives first information, which indicates at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on the AI ​​model.

[0009] Demodulate at least one of the channel and the signal based on the first information.

[0010] According to a second aspect of the embodiments of this disclosure, a demodulation method is provided, performed by a network device, the method comprising:

[0011] Determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when demodulating based on an AI model.

[0012] Receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0013] Send first information to the terminal, the first information being used to indicate at least one of the following: whether the terminal is demodulating based on an AI model, a first capability used by the terminal, a first latency corresponding to the terminal, and information required by the terminal when demodulating based on an AI model.

[0014] According to a third aspect of the present disclosure, a demodulation method is provided for a communication system, the communication system including a network device and a terminal, the method comprising:

[0015] The terminal and / or the network device determine at least one of one or more first capabilities and one or more first delays, wherein the first capability is used to indicate the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay is used to indicate the processing delay of the terminal when demodulating based on an AI model.

[0016] The terminal sends to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0017] The network device sends first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, a first capability used by the terminal, a first latency corresponding to the terminal, and information required by the terminal when performing demodulation based on an AI model.

[0018] The terminal demodulates at least one of the channel and the signal based on the first information.

[0019] According to a fourth aspect of the embodiments of this disclosure, a terminal is provided, comprising:

[0020] A processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0021] A transceiver module is configured to indicate to a network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0022] The transceiver module is further configured to receive first information sent by the network device, the first information being configured to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0023] The processing module is further configured to demodulate at least one of the channel and the signal based on the first information.

[0024] According to a fifth aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0025] The processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0026] A transceiver module is configured to receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal, transmitted by the terminal.

[0027] The transceiver module is further configured to send first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0028] According to a sixth aspect of the present disclosure, a communication device is provided, comprising:

[0029] One or more processors;

[0030] The processor is configured to invoke instructions to cause the communication device to execute any of the demodulation methods described in the first or second aspect.

[0031] According to a seventh aspect of the present disclosure, a communication system is provided, including a network device and a terminal, wherein the terminal is configured to implement the demodulation method described in the first aspect, and the network device is configured to implement the demodulation method described in the second aspect.

[0032] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions which, when executed on a communication device, cause the communication device to perform a demodulation method as described in any of the first to second aspects.

[0033] In a ninth aspect, embodiments of this disclosure provide a program product, including a computer program that, when executed by a communication device, implements the demodulation method as described in the first and second aspects.

[0034] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the demodulation method as described in the first and second aspects.

[0035] It is understood that the aforementioned network devices, terminals, communication devices, communication systems, storage media, program products, and computer programs are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here. Attached Figure Description

[0036] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0037] Figure 1 is a schematic diagram of the architecture of some communication systems provided in the embodiments of this disclosure;

[0038] Figure 2 is a schematic flowchart of a demodulation method provided in an embodiment of this disclosure;

[0039] Figure 3 is a schematic flowchart of a demodulation method provided in another embodiment of this disclosure;

[0040] Figure 4 is a schematic flowchart of a demodulation method provided in another embodiment of this disclosure;

[0041] Figure 5 is a flowchart illustrating the demodulation method provided in another embodiment of this disclosure;

[0042] Figure 6A is a schematic diagram of the structure of a terminal provided in an embodiment of this disclosure;

[0043] Figure 6B is a schematic diagram of the structure of a network device provided in an embodiment of this disclosure;

[0044] Figure 7A is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure;

[0045] Figure 7B is a schematic diagram of the structure of a chip provided in an embodiment of this disclosure. Detailed Implementation

[0046] This disclosure provides demodulation methods, communication devices, communication systems, and storage media.

[0047] In a first aspect, embodiments of this disclosure propose a demodulation method, executed by a terminal, the method comprising:

[0048] Determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when demodulating based on an AI model.

[0049] Indicate to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0050] The network device receives first information, which indicates at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on the AI ​​model.

[0051] Demodulate at least one of the channel and the signal based on the first information.

[0052] In the above embodiments, the terminal can determine at least one of one or more first capabilities and one or more first delays. The first capability can indicate the terminal's processing capability when demodulating based on an AI model, and the first delay can indicate the processing delay when demodulating based on an AI model. The terminal sends at least one of the one or more first capabilities and one or more first delays supported by the terminal to the network device, so that the network device can instruct whether and how the terminal performs demodulation based on the AI ​​model based on the first capabilities and / or the first delays supported by the terminal. Therefore, the embodiments of this disclosure define first capabilities and / or first delays, enabling the terminal and network device to successfully achieve AI model-based demodulation based on the defined first capabilities and / or first delays, improving demodulation performance, accuracy, and efficiency. Furthermore, in the above embodiments, the terminal and network device can have a unified understanding of the first delay, allowing the network device to refrain from scheduling communication operations by the terminal within the first delay, ensuring that the terminal's demodulation operation is not interfered with within the first delay and guaranteeing demodulation stability.

[0053] In conjunction with some embodiments of the first aspect, in some embodiments, the first capability includes at least one of the following: AI model capability, data processing capability, and terminal hardware capability.

[0054] In conjunction with some embodiments of the first aspect, in some embodiments, the information required by the terminal when performing demodulation based on the AI ​​model includes at least one of the following: the AI ​​model capability used by the terminal when performing demodulation based on the AI ​​model, the data processing capability used by the terminal when performing demodulation based on the AI ​​model, and the terminal hardware capability used by the terminal when performing demodulation based on the AI ​​model.

[0055] In conjunction with some embodiments of the first aspect, in some embodiments, the AI ​​model capability includes at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0056] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0057] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0058] In the above embodiments, it is explained which specific capabilities the first capability may include, so that multiple first capabilities can be successfully defined based on these capabilities. This ensures that the terminal and network device can successfully perform AI model-based demodulation based on the defined first capabilities, thereby improving demodulation performance, demodulation accuracy, and demodulation efficiency. Furthermore, in the above embodiments, it is explained what specific information the terminal needs when performing demodulation based on the AI ​​model. The network device can instruct this information based on the first information, so that the terminal can successfully perform AI model-based demodulation based on the first information, thereby improving demodulation performance, demodulation accuracy, and demodulation efficiency.

[0059] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0060] Send the AI ​​processor status to the network device.

[0061] In conjunction with some embodiments of the first aspect, in some embodiments, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, AI processor task count, AI processor heat dissipation state, and AI processor operating speed.

[0062] In the above embodiments, the terminal can send the AI ​​processor status to the network device. The AI ​​processor status may include at least one of the following: AI processor runtime, AI processor load status, number of tasks on the AI ​​processor, AI processor heat dissipation status, and AI processor operating speed. Optionally, the network device can determine the pending tasks and / or available resources of the AI ​​processor based on the AI ​​processor status. Therefore, the network device can determine at least one of a first capability and a first latency that matches the terminal's AI processor status based on the pending tasks and / or available resources. For example, if the AI ​​processor has many pending tasks and / or few available resources, the network device can instruct the terminal to use the first capability corresponding to a shorter first latency, or directly instruct the terminal not to perform demodulation based on the AI ​​model. The processing latency is shorter when demodulation is not based on the AI ​​model. This avoids the situation where "when the AI ​​processor has many pending tasks and / or few available resources, the network device instructs the terminal to use the first capability corresponding to a longer first latency, resulting in a high AI processor load affecting other AI tasks," thus ensuring the execution efficiency of the AI ​​tasks.

[0063] In conjunction with some embodiments of the first aspect, in some embodiments, determining at least one of one or more first capabilities and one or more first delays includes:

[0064] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0065] In the above embodiments, it is explained how the terminal determines at least one of one or more first capabilities and one or more first delays, so that the terminal can successfully determine the first capability and / or the first delay, thereby facilitating the terminal to successfully perform demodulation based on the determined first capability and / or first delay, thereby improving demodulation performance, demodulation accuracy and demodulation efficiency.

[0066] In conjunction with some embodiments of the first aspect, in some embodiments, the first capability corresponds to the first latency.

[0067] In the above embodiments, there is a correspondence between the first capability and the first latency. Thus, the terminal can only report the first latency it supports to the network device. The network device can determine the first capability supported by the terminal based on the correspondence between the first capability and the first latency. At the same time, the network device can only indicate the first latency corresponding to the first capability used to the terminal. Then, the terminal can determine the first capability used by the terminal based on the correspondence between the first capability and the first latency. Since the first latency occupies fewer resources, communication resources can be greatly reduced.

[0068] In conjunction with some embodiments of the first aspect, in some embodiments, the demodulation of at least one of the channel and the signal based on the first information includes:

[0069] The first information instructs the terminal to perform demodulation based on an AI model, and to perform demodulation based on at least one of the following: a first capability supported by the terminal, a first capability indicated by the first information, a first capability corresponding to a first delay indicated by the first information, and information required by the terminal to perform demodulation based on the AI ​​model.

[0070] In the above embodiments, it is explained how the terminal demodulates at least one of the channel and the signal based on the first information, which can ensure that the terminal successfully achieves demodulation based on the AI ​​model, thereby improving demodulation performance, demodulation accuracy and demodulation efficiency.

[0071] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes at least one of the following:

[0072] The first information instructs the terminal to use a first AI model for demodulation. The first AI model is different from the second AI model. The terminal switches from the second AI model to the first AI model. The second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information.

[0073] The first information instructs the terminal to use a first data processing capability for demodulation. The first data processing capability is different from the second data processing capability. The terminal switches from the second data processing capability to the first data processing capability. The second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information.

[0074] The first information instructs the terminal to use the first terminal hardware capability for demodulation. The first terminal hardware capability is different from the second terminal hardware capability. The terminal switches from the second terminal hardware capability to the first terminal hardware capability. The second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information.

[0075] When the terminal does not perform demodulation based on the AI ​​model, if the first information indicates that the terminal performs demodulation based on the AI ​​model, the terminal switches from "not demodulating based on the AI ​​model" to "demodulating based on the AI ​​model".

[0076] When the terminal performs demodulation based on an AI model, if the first information indicates that the terminal does not perform demodulation based on an AI model, the terminal switches from "demodulation based on an AI model" to "demodulation without an AI model".

[0077] In conjunction with some embodiments of the first aspect, in some embodiments, the terminal is not scheduled to receive or process at least one of the signals or channels during at least one of the first handover delay, second handover delay, third handover delay, fourth handover delay, and fifth handover delay;

[0078] The first switching delay includes the switching delay of the terminal switching from the second AI model to the first AI model; the second switching delay includes the switching delay of the terminal switching from the second data processing capability to the first data processing capability; the third switching delay includes the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability; the fourth switching delay includes the switching delay of the terminal switching from "not demodulating based on AI model" to "demodulating based on AI model"; and the fifth switching delay includes the switching delay of the terminal switching from "demodulating based on AI model" to "not demodulating based on AI model".

[0079] In the above embodiments, the network device can instruct the terminal to switch AI models, or instruct the terminal to switch data processing capabilities, or instruct the terminal to switch terminal hardware capabilities, or instruct the terminal to switch from "not demodulating based on an AI model" to "demodulating based on an AI model," or instruct the terminal to switch from "demodulating based on an AI model" to "not demodulating based on an AI model," thereby improving the flexibility of AI model demodulation. Furthermore, in the above embodiments, when the terminal performs the above switching, the network device will not schedule the terminal to receive or process at least one of the signals or channels, thus ensuring that the switching process is not interfered with and guaranteeing switching efficiency and stability.

[0080] In conjunction with some embodiments of the first aspect, in some embodiments, during the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform Hybrid Automatic Repeat Request Response (HARQ-ACK) feedback.

[0081] In the above embodiments, during the processing delay of the terminal demodulation based on the first information, the network device will not schedule the terminal to perform Hybrid Automatic Retransmission Request Acknowledgement (HARQ-ACK) feedback, thereby ensuring that the AI ​​demodulation process is not interfered with and guaranteeing demodulation performance, demodulation stability, demodulation accuracy and demodulation efficiency.

[0082] In conjunction with some embodiments of the first aspect, in some embodiments, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capability are used to calculate the first delay corresponding to the first capability.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0084] Send a second capability supported by the terminal to the network device, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0085] In conjunction with some embodiments of the first aspect, in some embodiments, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0086] In the above embodiments, the calculation method of the first delay is explained, which makes it easier for the terminal and / or network device to successfully calculate the first delay. Then, the terminal and / or network device can subsequently achieve demodulation based on the AI ​​model based on the first delay, thereby improving demodulation performance, demodulation accuracy and demodulation efficiency.

[0087] Secondly, embodiments of this disclosure provide a demodulation method, executed by a network device, the method comprising:

[0088] Determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when demodulating based on an AI model.

[0089] Receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0090] Send first information to the terminal, the first information being used to indicate at least one of the following: whether the terminal is demodulating based on an AI model, a first capability used by the terminal, a first latency corresponding to the terminal, and information required by the terminal when demodulating based on an AI model.

[0091] In conjunction with some embodiments of the second aspect, in some embodiments, the first capability includes at least one of the following: AI model capability, data processing capability, and terminal hardware capability.

[0092] In conjunction with some embodiments of the second aspect, in some embodiments, the information required by the terminal when performing demodulation based on the AI ​​model includes at least one of the following: the AI ​​model capability used by the terminal when performing demodulation based on the AI ​​model, the data processing capability used by the terminal when performing demodulation based on the AI ​​model, and the terminal hardware capability used by the terminal when performing demodulation based on the AI ​​model.

[0093] In conjunction with some embodiments of the second aspect, in some embodiments, the AI ​​model capability includes at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0094] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0095] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0096] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0097] Receive the AI ​​processor status sent by the terminal.

[0098] In conjunction with some embodiments of the second aspect, in some embodiments, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, AI processor task count, AI processor heat dissipation state, and AI processor operating speed.

[0099] In conjunction with some embodiments of the second aspect, in some embodiments, determining at least one of one or more first capabilities and one or more first delays includes:

[0100] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0101] In conjunction with some embodiments of the second aspect, in some embodiments, the first capability corresponds to the first latency.

[0102] In conjunction with some embodiments of the second aspect, in some embodiments, the first information is used to indicate at least one of the following:

[0103] The terminal uses a first AI model for demodulation;

[0104] The terminal uses the first data processing capability for demodulation;

[0105] The terminal uses the hardware capabilities of the first terminal to perform demodulation;

[0106] The terminal demodulates based on an AI model;

[0107] The terminal does not perform demodulation based on an AI model.

[0108] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0109] During at least one of the first handover delay, the second handover delay, the third handover delay, the fourth handover delay, and the fifth handover delay, the terminal is not scheduled to receive or process at least one of the signals or channels.

[0110] The first switching delay includes: the switching delay of the terminal switching from the second AI model to the first AI model, where the second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information; the second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability, where the second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information; the third switching delay includes: the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability, where the second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information; the fourth switching delay includes: the switching delay of the terminal switching from "demodulation not based on AI model" to "demodulation based on AI model"; and the fifth switching delay includes: the switching delay of the terminal switching from "demodulation based on AI model" to "demodulation not based on AI model".

[0111] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0112] During the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform HARQ-ACK feedback.

[0113] In conjunction with some embodiments of the second aspect, in some embodiments, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capabilities are used to calculate the first delay corresponding to the first capability.

[0114] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0115] The terminal receives a second capability supported by the terminal, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0116] In conjunction with some embodiments of the second aspect, in some embodiments, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0117] Thirdly, embodiments of this disclosure provide a demodulation method for a communication system, the communication system including network devices and terminals, the method comprising:

[0118] The terminal and / or the network device determine at least one of one or more first capabilities and one or more first delays, wherein the first capability is used to indicate the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first delay is used to indicate the processing delay of the terminal when demodulating based on an AI model.

[0119] The terminal sends to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0120] The network device sends first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, a first capability used by the terminal, a first latency corresponding to the terminal, and information required by the terminal when performing demodulation based on an AI model.

[0121] The terminal demodulates at least one of the channel and the signal based on the first information.

[0122] Fourthly, embodiments of this disclosure provide a terminal, including:

[0123] A processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0124] A transceiver module is configured to indicate to a network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0125] The transceiver module is further configured to receive first information sent by the network device, the first information being configured to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0126] The processing module is further configured to demodulate at least one of the channel and the signal based on the first information.

[0127] In conjunction with some embodiments of the fourth aspect, in some embodiments, the first capability includes at least one of the following: AI model capability, data processing capability, and terminal hardware capability.

[0128] In conjunction with some embodiments of the fourth aspect, in some embodiments, the information required by the terminal when performing demodulation based on the AI ​​model includes at least one of the following: the AI ​​model capability used by the terminal when performing demodulation based on the AI ​​model, the data processing capability used by the terminal when performing demodulation based on the AI ​​model, and the terminal hardware capability used by the terminal when performing demodulation based on the AI ​​model.

[0129] In conjunction with some embodiments of the fourth aspect, in some embodiments, the AI ​​model capability includes at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0130] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0131] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0132] In conjunction with some embodiments of the fourth aspect, in some embodiments, the method further includes:

[0133] Send the AI ​​processor status to the network device.

[0134] In conjunction with some embodiments of the fourth aspect, in some embodiments, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, AI processor task count, AI processor heat dissipation state, and AI processor operating speed.

[0135] In conjunction with some embodiments of the fourth aspect, in some embodiments, determining at least one of one or more first capabilities and one or more first delays includes:

[0136] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0137] In conjunction with some embodiments of the fourth aspect, in some embodiments, the first capability corresponds to the first latency.

[0138] In conjunction with some embodiments of the fourth aspect, in some embodiments, the demodulation of at least one of the channel and the signal based on the first information includes:

[0139] The first information instructs the terminal to perform demodulation based on an AI model, and to perform demodulation based on at least one of the following: a first capability supported by the terminal, a first capability indicated by the first information, a first capability corresponding to a first delay indicated by the first information, and information required by the terminal to perform demodulation based on the AI ​​model.

[0140] In conjunction with some embodiments of the fourth aspect, in some embodiments, the method further includes at least one of the following:

[0141] The first information instructs the terminal to use a first AI model for demodulation. The first AI model is different from the second AI model. The terminal switches from the second AI model to the first AI model. The second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information.

[0142] The first information instructs the terminal to use a first data processing capability for demodulation. The first data processing capability is different from the second data processing capability. The terminal switches from the second data processing capability to the first data processing capability. The second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information.

[0143] The first information instructs the terminal to use the first terminal hardware capability for demodulation. The first terminal hardware capability is different from the second terminal hardware capability. The terminal switches from the second terminal hardware capability to the first terminal hardware capability. The second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information.

[0144] When the terminal does not perform demodulation based on the AI ​​model, if the first information indicates that the terminal performs demodulation based on the AI ​​model, the terminal switches from "not demodulating based on the AI ​​model" to "demodulating based on the AI ​​model".

[0145] When the terminal performs demodulation based on an AI model, if the first information indicates that the terminal does not perform demodulation based on an AI model, the terminal switches from "demodulation based on an AI model" to "demodulation without an AI model".

[0146] In conjunction with some embodiments of the fourth aspect, in some embodiments, the terminal is not scheduled to receive or process at least one of the signals or channels during at least one of the first handover delay, second handover delay, third handover delay, fourth handover delay, and fifth handover delay.

[0147] The first switching delay includes the switching delay of the terminal switching from the second AI model to the first AI model; the second switching delay includes the switching delay of the terminal switching from the second data processing capability to the first data processing capability; the third switching delay includes the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability; the fourth switching delay includes the switching delay of the terminal switching from "not demodulating based on AI model" to "demodulating based on AI model"; and the fifth switching delay includes the switching delay of the terminal switching from "demodulating based on AI model" to "not demodulating based on AI model".

[0148] In conjunction with some embodiments of the fourth aspect, in some embodiments, during the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform Hybrid Automatic Repeat Request Response (HARQ-ACK) feedback.

[0149] In conjunction with some embodiments of the fourth aspect, in some embodiments, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capabilities are used to calculate the first delay corresponding to the first capability.

[0150] In conjunction with some embodiments of the fourth aspect, in some embodiments, the method further includes:

[0151] Send a second capability supported by the terminal to the network device, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0152] In conjunction with some embodiments of the fourth aspect, in some embodiments, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0153] Fifthly, embodiments of this disclosure provide a network device, comprising:

[0154] The processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0155] A transceiver module is configured to receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal, transmitted by the terminal.

[0156] The transceiver module is further configured to send first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0157] In conjunction with some embodiments of the fifth aspect, in some embodiments, the first capability includes at least one of the following: AI model capability, data processing capability, and terminal hardware capability.

[0158] In conjunction with some embodiments of the fifth aspect, in some embodiments, the information required by the terminal when performing demodulation based on the AI ​​model includes at least one of the following: the AI ​​model capability used by the terminal when performing demodulation based on the AI ​​model, the data processing capability used by the terminal when performing demodulation based on the AI ​​model, and the terminal hardware capability used by the terminal when performing demodulation based on the AI ​​model.

[0159] In conjunction with some embodiments of the fifth aspect, in some embodiments, the AI ​​model capability includes at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0160] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0161] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0162] In conjunction with some embodiments of the fifth aspect, in some embodiments, the method further includes:

[0163] Receive the AI ​​processor status sent by the terminal.

[0164] In conjunction with some embodiments of the fifth aspect, in some embodiments, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, AI processor task count, AI processor heat dissipation state, and AI processor operating speed.

[0165] In conjunction with some embodiments of the fifth aspect, in some embodiments, determining at least one of one or more first capabilities and one or more first delays includes:

[0166] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0167] In conjunction with some embodiments of the fifth aspect, in some embodiments, the first capability corresponds to the first latency.

[0168] In conjunction with some embodiments of the fifth aspect, in some embodiments, the first information is used to indicate at least one of the following:

[0169] The terminal uses a first AI model for demodulation;

[0170] The terminal uses the first data processing capability for demodulation;

[0171] The terminal uses the hardware capabilities of the first terminal to perform demodulation;

[0172] The terminal demodulates based on an AI model;

[0173] The terminal does not perform demodulation based on an AI model.

[0174] In conjunction with some embodiments of the fifth aspect, in some embodiments, the method further includes:

[0175] During at least one of the first handover delay, the second handover delay, the third handover delay, the fourth handover delay, and the fifth handover delay, the terminal is not scheduled to receive or process at least one of the signals or channels.

[0176] The first switching delay includes: the switching delay of the terminal switching from the second AI model to the first AI model, where the second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information; the second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability, where the second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information; the third switching delay includes: the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability, where the second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information; the fourth switching delay includes: the switching delay of the terminal switching from "demodulation not based on AI model" to "demodulation based on AI model"; and the fifth switching delay includes: the switching delay of the terminal switching from "demodulation based on AI model" to "demodulation not based on AI model".

[0177] In conjunction with some embodiments of the fifth aspect, in some embodiments, the method further includes:

[0178] During the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform HARQ-ACK feedback.

[0179] In conjunction with some embodiments of the fifth aspect, in some embodiments, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capabilities are used to calculate the first delay corresponding to the first capability.

[0180] In conjunction with some embodiments of the fifth aspect, in some embodiments, the method further includes:

[0181] The terminal receives a second capability supported by the terminal, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0182] In conjunction with some embodiments of the fifth aspect, in some embodiments, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0183] In a sixth aspect, embodiments of this disclosure provide a communication device comprising: one or more processors; one or more memories for storing instructions; wherein the processors are configured to invoke the instructions to cause the communication device to perform the methods described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0184] In a seventh aspect, embodiments of this disclosure provide a communication system comprising: a network device and a terminal; wherein the terminal is configured to perform the method described in the first aspect and optional implementations thereof, and the network device is configured to perform the method described in the second aspect and optional implementations thereof.

[0185] Eighthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method described in the first aspect, an optional implementation of the first aspect, the second aspect, and an optional implementation of the second aspect.

[0186] In a ninth aspect, embodiments of this disclosure provide a program product including a computer program that, when executed by a processor, implements the methods described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0187] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in the first aspect, an optional implementation of the first aspect, the second aspect, and an optional implementation of the second aspect.

[0188] It is understood that the aforementioned network devices, terminals, communication devices, communication systems, storage media, program products, and computer programs are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0189] This disclosure provides demodulation methods, communication devices, communication systems, and storage media. In some embodiments, the terms demodulation method, information processing method, information transmission method, and information reception method can be used interchangeably; the terms communication device, information processing device, information transmission device, and information reception device can be used interchangeably; and the terms information processing system, communication system, information transmission system, and information reception system can be used interchangeably.

[0190] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0191] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0192] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0193] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0194] In the embodiments of this disclosure, "multiple" refers to two or more.

[0195] In some embodiments, the terms “at least one of”, “at least one of”, “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0196] The descriptions in this disclosure, such as "at least one of A, B, C..." or "A and / or B and / or C...", include the case where any one of A, B, C... exists alone, as well as the case where any combination of any of A, B, C... exists alone. Each case can exist alone. For example, "at least one of A, B, C" includes the cases of A alone, B alone, C alone, A and B combination, A and C combination, B and C combination, and A and B and C combination. For example, A and / or B includes the cases of A alone, B alone, and A and B combination.

[0197] In some embodiments, the notation "in one case A, in another case B" or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: A is executed regardless of B, i.e., A is executed in some embodiments; B is executed regardless of A, i.e., B is executed in some embodiments; A and B are selectively executed, i.e., A and B are selected for execution in some embodiments; A and B are both executed, i.e., A and B are executed in some embodiments. The same applies when there are more branches such as A, B, and C.

[0198] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0199] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0200] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0201] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0202] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0203] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0204] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0205] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0206] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures that replace communication between access network devices, core network devices, or network devices and terminals with communication between multiple terminals (e.g., also referred to as device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, uplink link, downlink link, etc., can be replaced with sidelink link.

[0207] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0208] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0209] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0210] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0211] The correspondences shown in the tables of this disclosure can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values; this disclosure is not limiting. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows of the tables in this disclosure may not be configured. Furthermore, appropriate modifications and adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the headers of the above tables can also use other names that the communication device can understand, and the values ​​or representations of the parameters can also be other values ​​or representations that the communication device can understand. In the implementation of the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or hash tables, etc.

[0212] The predefined terms in this disclosure can be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0213] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure. As shown in Figure 1, the communication system 100 may include network devices and terminals; wherein, the network devices may include at least one of access network devices and core network devices.

[0214] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things (IoT) device, narrowband Internet of Things (NB-IoT) device, car with communication capabilities, smart car, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0215] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), wireless backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a wireless fidelity (WiFi) system.

[0216] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0217] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0218] In some embodiments, the core network device may be a single device comprising one or more network elements, or multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC). Alternatively, the core network device may also be a location management function network element. Exemplarily, the location management function network element includes a location server, which may be implemented as any of the following: a Location Management Function (LMF), an Enhanced Serving Mobile Location Centre (E-SMLC), a Secure User Plane Location (SUPL), and a Secure User Plane Location Platform (SUPLLP).

[0219] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0220] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0221] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other demodulation methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0222] Optionally, the aforementioned demodulation based on the AI ​​model may include, for example, inputting the channel to be demodulated and / or the information to be demodulated into the AI ​​model, so that the AI ​​model outputs the demodulated channel and / or the demodulated information. In some embodiments, when demodulating based on the AI ​​model, the terminal and the network device typically need to define at least one of AI demodulation processing capability and AI demodulation processing latency. When at least one of AI demodulation processing capability and AI demodulation processing latency is defined, the terminal can send the AI ​​demodulation processing capability and / or AI demodulation processing latency supported by the terminal to the network device, so that the network device can instruct the terminal to use the AI ​​demodulation processing capability and / or AI demodulation processing latency based on the AI ​​demodulation processing capability and / or AI demodulation processing latency supported by the terminal. Thus, the terminal can perform demodulation based on the AI ​​model based on the AI ​​demodulation processing capability and / or AI demodulation processing latency indicated by the network device.

[0223] However, defining AI demodulation processing capabilities and AI demodulation processing latency are technical problems that urgently need to be solved.

[0224] Figure 2 is an interactive schematic diagram of a demodulation method according to an embodiment of the present disclosure. As shown in Figure 2, this embodiment of the disclosure relates to a demodulation method for a communication system 100; the method includes:

[0225] Step 2101: The terminal and / or network device determines at least one of one or more first capabilities and one or more first delays.

[0226] Optionally, in some embodiments, the first capability can be used to indicate the processing capability of the terminal when performing demodulation based on an AI model. For a detailed description of "demodulation based on an AI model," please refer to the description preceding the embodiment shown in Figure 2.

[0227] Optionally, the first capability may include at least one of the following: AI model capability, data processing capability, and terminal hardware capability.

[0228] In some embodiments, the AI ​​model capability may include at least one of the AI ​​model structure and the AI ​​model size; optionally, the AI ​​model structure may include at least one of the Convolutional Neural Network (CNN) model and the Deep Neural Network (DNN) model, and the AI ​​model size may include at least one of the large size, medium size, and low size.

[0229] In some embodiments, data processing capability may include at least one of data processing precision and data processing speed. Optionally, data processing precision may include floating-point precision, for example, at least one of 16-bit floating-point (FLOAT16), 32-bit floating-point (FLOAT32), and 64-bit floating-point (FLOAT64). Optionally, in some embodiments, the operation of the AI ​​model may be supported by an AI processor. For example, the AI ​​processor may be used to execute the AI ​​algorithm corresponding to the AI ​​model, or it may be used to store relevant data of the AI ​​model (such as historical input data, historical output data, etc.). In some embodiments, for the same AI processor, the data processing speed of the AI ​​model will also be different when the data processing precision of the AI ​​model is different. In some embodiments, for the same data processing precision, the data processing precision corresponding to different AI processors will also be different.

[0230] Optionally, in some embodiments, the aforementioned terminal hardware capabilities may include at least one of the following: the number of terminal hardware devices, the model of the terminal hardware, the design process of the terminal hardware, and the processing speed of the terminal hardware (e.g., the number of floating-point operations that the terminal hardware can process per second). Optionally, the terminal hardware may include at least one of the following: a graphics processing unit (GPU), a neural network processing unit (NPU), and a field-programmable gate array (FPGA).

[0231] Optionally, the aforementioned first latency can be used to indicate the processing latency (or processing speed) of the terminal when demodulating based on the AI ​​model. The unit of the first latency may include, for example, seconds, milliseconds, etc.

[0232] In some embodiments, a first capability can correspond to a first latency, and different first capabilities can correspond to the same or different first latencies. Optionally, the first latency corresponding to a first capability can be understood, for example, as the processing latency when the terminal's AI model uses the first capability for demodulation.

[0233] In some embodiments, the first latency will also be different when at least one of the AI ​​model capability, data processing precision, data processing rate, and terminal hardware capability is different. Optionally, for the same AI model, the first latency will be different when the data processing precision and / or terminal hardware capability are different; or, for the same data processing precision, the first latency will be different when the AI ​​model and / or terminal hardware capability are different; or, for the same data processing precision and the same AI model, the first latency will be different when the terminal hardware capability is different.

[0234] Optionally, in some embodiments, the first delay corresponding to the first capability can be calculated based on the first capability. For example, different first capabilities can correspond to different first parameters, and the first parameters corresponding to the first capability can be used to calculate the first delay corresponding to the first capability. Optionally, the first delay can be calculated based on the first parameters using the following formula: T proc,1 =(N 1_new +d 1,1 (2048+144)×k2 -μ ×T c ;

[0235] Optionally, the above T proc,1 This is the first time delay; the above N 1_new The first parameter is d; the above d 1,1 The T mentioned above can be determined based on at least one of the following: the first capability, the mapping type of the channel to be demodulated (e.g., the physical downlink shared channel mapping type, PDSCH mapping type), the mapping type of the signal to be demodulated, the number of symbols allocated to the channel to be demodulated (e.g., the number of PDSCH symbols allocated), and the number of symbols allocated to the signal to be demodulated. c =1 / (Δf) max ×N f ) = 1 / (480 × 10 3 ×4096); the above k=T s / T c =64,T s =1 / (Δf) ref ×N f,ref ) = 1 / (15 × 10 3 ×2048).

[0236] Optionally, in other embodiments, different first capabilities correspond to different first bias parameters, which can be positive or negative. Different second capabilities correspond to different second parameters. The second capability may include the processing capability of the terminal when demodulation is not based on an AI model. For example, the second capability may include PDSCH processing capability 1 and / or PDSCH processing capability 2. Optionally, the first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability can be used to calculate the first latency corresponding to the first capability. Optionally, the first latency can be calculated based on the first bias parameter and the second parameter using the following formula: T proc,1 =(N1+d) 1,1 +N2)(2048+144)×k2 -μ ×T c ;

[0237] Optionally, the above T proc,1 The first time delay is defined as N1, the second parameter is defined as N1, and the first bias parameter is defined as N2.

[0238] Optionally, in some embodiments, the terminal and / or network device may determine at least one of one or more first capabilities and one or more first delays based on protocol agreements.

[0239] Optionally, in some embodiments, the first capability may include AI model capability, data processing capability, and terminal hardware capability. Optionally, the protocol may define a first capability, wherein the first capability defined by the protocol corresponds to a first delay.

[0240] Optionally, in some embodiments, the first capability may include terminal hardware capabilities. Optionally, the protocol may define a first capability, wherein the first capability defined by the protocol corresponds to at least one of a first correspondence, a second correspondence, and a third correspondence; in some embodiments, the first correspondence may include: the correspondence between different AI model capabilities and different first latencies when the terminal uses the first capability; the second correspondence may include: the correspondence between different data processing capabilities and different first latencies when the terminal uses the first capability; the third correspondence may include: the correspondence between different AI model capabilities, different data processing capabilities, and different first latencies when the terminal uses the first capability.

[0241] Optionally, Tables 1 and 2 are schematic tables illustrating the first correspondence relationship shown in the embodiments of this disclosure.

[0242] Table 1

[0243] Table 2

[0244] As shown in Table 1 above, when the AI ​​model size is low, the corresponding first latency can be A milliseconds. As shown in Table 2 above, when the AI ​​model size is low and the AI ​​model structure is CNN, the corresponding first latency can be D milliseconds.

[0245] Optionally, Table 3 is a schematic table illustrating the second correspondence relationship shown in the embodiments of this disclosure.

[0246] Table 3

[0247] As shown in Table 3 above, when the floating-point precision is FLOAT16, the corresponding first delay can be A milliseconds.

[0248] Optionally, Tables 4, 5, and 6 are schematic tables illustrating the third correspondence relationship shown in the embodiments of this disclosure.

[0249] Table 4

[0250] Table 5

[0251] Table 6

[0252] Optionally, as shown in Table 4 above, when the floating-point precision is FLOAT16 and the AI ​​model structure is CNN, the first latency can be A milliseconds. As shown in Table 5 above, when the floating-point precision is FLOAT64 and the AI ​​model size is medium, the first latency can be B1 milliseconds. As shown in Table 6 above, when the floating-point precision is FLOAT16 and the AI ​​model structure is CNN, the first latency can be D milliseconds.

[0253] Optionally, in some embodiments, the first capability may include AI model capability, data processing capability, and terminal hardware capability; optionally, the protocol may agree on and define multiple first capabilities, wherein different first capabilities agreed on by the protocol correspond to a first latency; optionally, the terminal may support one first capability, and the first capabilities supported by different terminals are independent of each other. For example, if different terminals support different first capabilities, then the first latency supported by different terminals will also be different.

[0254] Optionally, in some embodiments, the first capability may include terminal hardware capabilities. Optionally, the protocol may define multiple first capabilities; wherein different first capabilities defined by the protocol correspond to at least one of a first correspondence, a second correspondence, and a third correspondence, and the first, second, and third correspondences corresponding to different first capabilities are different. Detailed descriptions of the first, second, and third correspondences can be found in the above description. Optionally, a terminal may support one first capability, and the first capabilities supported by different terminals are independent of each other.

[0255] For example, suppose the protocol stipulates a first capability #1 and a first capability #2, wherein the first capability #1 includes terminal hardware capability #1 (e.g., 1 GPU) and the first capability #2 includes terminal hardware capability #2 (e.g., 2 GPUs). Optionally, Table 7 is the third correspondence #1 corresponding to the terminal hardware capability #1 shown in the embodiments of this disclosure, and Table 8 is the third correspondence #2 corresponding to the terminal hardware capability #2 shown in the embodiments of this disclosure.

[0256] Table 7

[0257] Table 8

[0258] Referring to Tables 7 and 8 above, when the terminal uses terminal hardware capability #1, i.e., when the terminal uses one GPU for demodulation based on an AI model, the first latency can be A milliseconds if the floating-point precision is FLOAT16 and the AI ​​model structure is CNN. Optionally, when the terminal uses terminal hardware capability #2, i.e., when the terminal uses two GPUs for demodulation based on an AI model, the first latency can be D milliseconds if the floating-point precision is FLOAT16 and the AI ​​model structure is CNN.

[0259] Optionally, in some embodiments, when the first capability includes terminal hardware capabilities and the protocol stipulates multiple first capabilities, the terminal may have a fourth correspondence. This fourth correspondence may include, for example, the correspondence between at least one of different terminal hardware capabilities, different AI model capabilities, and different data processing capabilities and different first latency. For example, Tables 9 and 10 are schematic tables illustrating the fourth correspondence in embodiments of this disclosure.

[0260] Table 9

[0261] Table 10

[0262] Referring to Table 9 above, when the terminal uses 1 piece of terminal hardware, if the floating-point precision is FLOAT16 and the AI ​​model structure is CNN, the first latency can be D milliseconds. When the terminal uses 2 pieces of terminal hardware, if the floating-point precision is FLOAT32 and the AI ​​model structure is CNN, the first latency can be E milliseconds. Referring to Table 10 above, when the terminal uses 1 piece of terminal hardware, if the AI ​​model size is medium, the first latency can be A milliseconds.

[0263] Optionally, the indexes in the table above may uniquely indicate the corresponding first capability and / or first delay.

[0264] Optionally, in some embodiments, the first capability may include AI model capability, data processing capability, and terminal hardware capability. Optionally, the protocol may stipulate multiple first capabilities, wherein each of the multiple first capabilities stipulated in the protocol corresponds to a first latency. In some embodiments, the terminal may support multiple first capabilities, and the first capabilities supported by different terminals are independent of each other.

[0265] Optionally, in some embodiments, the first capability may include terminal hardware capabilities. Optionally, the protocol may stipulate multiple first capabilities; wherein different first capabilities stipulated by the protocol correspond to at least one of a first correspondence, a second correspondence, and a third correspondence, and the first, second, and third correspondences corresponding to different first capabilities are different. Detailed descriptions of the first, second, and third correspondences can be found in the above description. In some embodiments, the terminal may support multiple first capabilities, and the first capabilities supported by different terminals are independent of each other.

[0266] Optionally, in some embodiments, at least one of the above-mentioned first correspondence, second correspondence, third correspondence, and fourth correspondence can be agreed upon by a protocol; in other embodiments, at least one of the above-mentioned first correspondence, second correspondence, third correspondence, and fourth correspondence can be configured to the terminal by a network device.

[0267] Step 2102: The terminal indicates to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal.

[0268] Optionally, in some embodiments, when the protocol specifies a first capability, the terminal may send second information to the network device. This second information may indicate at least one of the following: the terminal mandatorily supports the first capability specified in the protocol; the terminal mandatorily supports the first capability specified in the protocol, corresponding to a first latency. Optionally, "the terminal mandatorily supports the first capability specified in the protocol" can be understood, for example, as the terminal supporting the first capability specified in the protocol, and "the terminal mandatorily supports the first capability specified in the protocol, corresponding to a first latency" can be understood, for example, as the terminal supporting the first capability specified in the protocol, corresponding to a first latency. In other embodiments, the terminal may send third information to the network device. This third information may indicate at least one of the following: the terminal optionally supports the first capability specified in the protocol; the terminal optionally supports the first capability specified in the protocol, corresponding to a first latency; whether the terminal supports the first capability specified in the protocol; and whether the terminal supports the first capability specified in the protocol, corresponding to a first latency. Optionally, "the terminal may optionally support the first capability stipulated in the protocol" can be understood as, for example, that the terminal may support the first capability stipulated in the protocol, or that the terminal may not support the first capability stipulated in the protocol. Similarly, "the terminal may optionally support the first delay corresponding to the first capability stipulated in the protocol" can be understood as, for example, that the terminal may support the first delay corresponding to the first capability stipulated in the protocol, or that the terminal may not support the first delay corresponding to the first capability stipulated in the protocol.

[0269] In some embodiments, when the protocol specifies a first capability, the terminal can directly mandate support for the first capability specified in the protocol, and / or the terminal can mandate support for the first delay corresponding to the first capability specified in the protocol. In this case, the terminal and network device can determine the first capability supported by the terminal and / or the first delay supported by the terminal based on the protocol, and there is no need to execute step 2102.

[0270] Optionally, in some embodiments, when the protocol specifies multiple first capabilities and the terminal supports one first capability, the terminal can send a first uplink signaling to the network device. This first uplink signaling can be used to indicate at least one of the following: the first capability supported by the terminal, or the first latency supported by the terminal. Optionally, when the first capability includes AI model capability, data processing capability, and terminal hardware capability, when the first uplink signaling indicates the first latency supported by the terminal, it can directly indicate the first latency corresponding to the first capability supported by the terminal. Optionally, when the first capability includes terminal hardware capability, the terminal can determine one or more first latencies supported by the terminal based on at least one of the terminal hardware capabilities supported by the terminal, a first correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, a second correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, a third correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, one or more AI model capabilities supported by the terminal, one or more data processing capabilities supported by the terminal, and a fourth correspondence relationship, and indicate the first latency supported by the terminal through the first uplink signaling.

[0271] For example, assuming the terminal supports hardware capabilities including one GPU, a floating-point precision of FLOAT16, and a CNN AI model structure, the terminal can determine, based on the third correspondence shown in Table 7, that the first latency when the terminal supports one GPU, FLOAT16, and CNN can be A milliseconds. Furthermore, based on the fourth correspondence shown in Table 9, the terminal can determine that the first latency when the terminal supports one GPU, FLOAT16, and CNN can be D milliseconds. Therefore, the terminal-supported first latency sent by the terminal to the network device can include at least one of A milliseconds and D milliseconds.

[0272] Optionally, in some embodiments, when the terminal supports multiple first capabilities, the terminal may send a second uplink signaling to the network device, the second uplink signaling may indicate at least one of the following: the highest first capability supported by the terminal, all first capabilities supported by the terminal, or some first capabilities supported by the terminal.

[0273] In some embodiments, when a network device receives the highest first capability supported by a terminal, it may assume that the terminal is also compatible with supporting first capabilities lower than the highest first capability. For example, assuming that the highest first capability supported by the terminal is FLOAT32 floating-point precision, the network device may assume that the terminal also supports floating-point precision below FLOAT32. For example, the network device may assume that the terminal is compatible with supporting FLOAT16 floating-point precision.

[0274] Optionally, in some embodiments, the aforementioned "second uplink signaling indicating part of the first capability supported by the terminal" can be understood as follows: the terminal does not send the highest first capability supported by the terminal to the network device, but instead sends a lower first capability supported by the terminal. For example, when the terminal supports a high data processing rate, the terminal may not send the highest data processing rate supported by the terminal to the network device, but instead send a lower data processing rate supported by the terminal. This is mainly to take into account factors such as terminal power consumption. Specifically, since the higher the first capability (e.g., the higher the data processing rate), the higher the terminal's power consumption, if the terminal sends the highest first capability supported by the terminal (e.g., the highest data processing rate) to the network device, the network device may instruct the terminal to perform AI demodulation based on that highest first capability, which would result in high terminal power consumption. Therefore, to avoid this situation, the terminal can send a lower first capability supported by the terminal (e.g., a lower data processing rate) to the network device, thereby ensuring that the first capability used by the network device when subsequently instructing the terminal to perform AI demodulation is lower, thus reducing terminal power consumption.

[0275] Optionally, in some embodiments, the aforementioned second uplink signaling can also be used to indicate one or more first delays supported by the terminal. In some embodiments, when the terminal supports multiple first capabilities, and the first capabilities include AI model capabilities, data processing capabilities, and terminal hardware capabilities, the aforementioned second uplink signaling can also indicate at least one of the following: the first delay corresponding to the highest first capability supported by the terminal, the first delay corresponding to all first capabilities supported by the terminal, and the first delay corresponding to some of the first capabilities supported by the terminal.

[0276] Optionally, in some embodiments, when the terminal supports multiple first capabilities, and the first capabilities include terminal hardware capabilities, the terminal can determine one or more first delays supported by the terminal based on at least one of the terminal hardware capabilities supported by the terminal, a first correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, a second correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, a third correspondence relationship corresponding to the terminal hardware capabilities supported by the terminal, one or more AI model capabilities supported by the terminal, one or more data processing capabilities supported by the terminal, and a fourth correspondence relationship, and indicate the first delays supported by the terminal through a second uplink signaling.

[0277] For example, assuming the terminal supports the following hardware capabilities: supporting 1 GPU, supporting 2 GPUs, and the terminal supports a floating-point precision of FLOAT16, and the AI ​​model structure supported by the terminal is CNN, then based on the third correspondence shown in Table 7 above, the terminal can determine that when the terminal supports 1 GPU, FLOAT16, and CNN, the corresponding first latency can be A milliseconds; based on the third correspondence shown in Table 8 above, the terminal can determine that when the terminal supports 2 GPUs, FLOAT16, and CNN, the corresponding first latency can be D milliseconds; based on the fourth correspondence shown in Table 9 above, the terminal can determine that when the terminal supports 1 GPU, FLOAT16, and CNN, the corresponding first latency can be D milliseconds; therefore, the terminal-supported first latency sent by the terminal to the network device can include at least one of A milliseconds and D milliseconds.

[0278] Optionally, in some embodiments, the terminal may send at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal to the network device via a bitmap. For example, the second information, third information, first uplink signaling, and second uplink signaling mentioned above may include a bitmap, in which bits in the bitmap may correspond to first capabilities and / or first delays, and the bit value carried by the bit may be used to indicate whether the terminal supports the first capability and / or first delay corresponding to the bit.

[0279] Optionally, in some embodiments, the terminal may send at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal to the network device via a sequence. For example, the second information, third information, first uplink signaling, and second uplink signaling mentioned above may include sequences, and different sequences are used to indicate at least one of different first capabilities and different first delays supported by the terminal.

[0280] Optionally, in some embodiments, the terminal may determine the index corresponding to the first capability supported by the terminal and / or the index corresponding to the first latency supported by the terminal based on at least one of the first correspondence, second correspondence, third correspondence, and fourth correspondence, and send these indexes to the network device through at least one of the second information, third information, first uplink signaling, and second uplink signaling. After receiving these indexes, the network device may determine the first capability supported by the terminal and / or the first latency supported by the terminal based on at least one of the first correspondence, second correspondence, third correspondence, and fourth correspondence.

[0281] Optionally, in some embodiments, the terminal can directly send to the network device the capabilities specifically included in the first capability supported by the terminal and the capabilities specifically included in the first latency supported by the terminal through at least one of the second information, the third information, the first uplink signaling, and the second uplink signaling. Alternatively, in some embodiments, the terminal can first determine the quantized value corresponding to the first latency supported by the terminal, and then send the quantized value corresponding to the first latency supported by the terminal to the network device through at least one of the second information, the third information, the first uplink signaling, and the second uplink signaling, thereby saving signaling overhead. Optionally, the aforementioned quantized value can be, for example, the integer value closest to the first latency supported by the terminal, or the quantized value can be, for example, the value closest to the first latency supported by the terminal in a preset dataset. Optionally, the preset dataset can be agreed upon by a protocol and / or configured by the network device. The preset dataset can include one or more integer values. For example, assuming the preset dataset includes {1s, 2s, 4s, 8s}, when the first latency supported by the terminal is 3.78s, the quantized value corresponding to the first latency supported by the terminal can be 4s.

[0282] Optionally, in some embodiments, a correspondence between different codepoints and the first capability and / or the first delay can be set. The terminal can send the codepoints corresponding to the first capability and / or the first delay supported by the terminal to the network device through at least one of the second information, the third information, the first uplink signaling, and the second uplink signaling.

[0283] Optionally, in some embodiments, the aforementioned second information, third information, first uplink signaling, and second uplink signaling may include at least one of the following: user equipment capability (UE capability) signaling, radio resource control (RRC) signaling, medium access control control element (MAC CE) signaling, uplink control indicator (UCI), UE assistance information (UAI) signaling, and AI layer-specific signaling.

[0284] Step 2103: The terminal indicates to the network device the second capability it supports.

[0285] For a detailed description of the second ability, please refer to step 2101 above.

[0286] Optionally, in some embodiments, step 2103 may be performed when the first latency is determined by the first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability. Optionally, the terminal indicates the second capability it supports to the network device so that the network device can determine one or more first latencies supported by the terminal based on the second parameter corresponding to the second capability supported by the terminal and the first bias parameter corresponding to the first capability supported by the terminal.

[0287] Step 2104: The terminal sends the fourth message to the network device.

[0288] Optionally, in some embodiments, the fourth information described above may be used to indicate at least one of the following: one or more data processing capabilities supported by the terminal, one or more AI model capabilities supported by the terminal, the highest data processing capability supported by the terminal, the highest AI model capability supported by the terminal, all data processing capabilities supported by the terminal, all AI model capabilities supported by the terminal, some data processing capabilities supported by the terminal, and some AI model capabilities supported by the terminal.

[0289] In some embodiments, step 2104 needs to be performed when the first capability includes terminal hardware capabilities. Optionally, the terminal sends fourth information to the network device so that the network device knows the data processing capabilities and / or AI model capabilities supported by the terminal. Thus, the network device can determine which hardware capability, data processing capability, or AI model capability the terminal specifically uses for demodulation by combining at least one of the terminal hardware capabilities, data processing capabilities, and AI model capabilities supported by the terminal.

[0290] Step 2105: The terminal sends the AI ​​processor status to the network device.

[0291] Optionally, in some embodiments, the AI ​​processor's operating state may include at least one of the following: AI processor runtime, AI processor load status (e.g., full load or idle), number of tasks on the AI ​​processor, AI processor heat dissipation status, and AI processor operating speed. Optionally, the AI ​​processor operating speed is related to the optimal performance of the AI ​​processor hardware design; for example, the AI ​​processor operating speed is related to whether accelerators such as tensor cores are enabled. In some embodiments, the terminal can send the AI ​​processor status to the network device in real time. In other embodiments, the terminal can send the AI ​​processor status to the network device semi-statically.

[0292] Optionally, the AI ​​processor status can reflect the tasks pending processing and / or the available resources of the AI ​​processor. Based on the AI ​​processor status, the network device can determine the current AI task density of the terminal. This allows the network device to subsequently determine at least one of the first capability and first latency that matches the terminal's current AI task density, thus avoiding a situation where "when the AI ​​processor has many tasks pending processing and / or few available resources, the network device instructs the terminal to use the first capability corresponding to a longer first latency, resulting in a high AI processor load that affects other AI tasks." This ensures the efficiency of AI task execution.

[0293] Step 2106: The network device sends the first information to the terminal.

[0294] In some embodiments, the network device may send first information to the terminal via dynamic signaling or semi-static signaling. The first information may indicate at least one of the following: whether the terminal is demodulating based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and information required by the terminal for demodulation based on the AI ​​model. In some embodiments, the first latency indicated by the first information is not lower than the lowest first latency supported by the terminal. In some embodiments, the first capability indicated by the first information is not higher than the highest first capability supported by the terminal.

[0295] Optionally, the "first latency corresponding to the terminal" mentioned above can be understood, for example, as the first latency corresponding to the first capability used by the terminal.

[0296] Optionally, in some embodiments, the "information required for the terminal to demodulate based on the AI ​​model" mentioned above may include at least one of the following: the AI ​​model capability used by the terminal to demodulate based on the AI ​​model, the data processing capability used by the terminal to demodulate based on the AI ​​model, and the terminal hardware capability used by the terminal to demodulate based on the AI ​​model.

[0297] In some embodiments, when the first capability includes AI model capability, data processing capability, and terminal hardware capability, the first capability used by the terminal includes the AI ​​model capability and / or data processing capability used by the terminal when performing demodulation based on the AI ​​model. Therefore, the first information may not indicate the information required by the terminal when performing demodulation based on the AI ​​model. In other embodiments, when the first capability includes terminal hardware capability, the first capability used by the terminal does not include the AI ​​model capability and / or data processing capability used by the terminal when performing demodulation based on the AI ​​model. In this case, the first information may indicate the information required by the terminal when performing demodulation based on the AI ​​model.

[0298] Optionally, in some embodiments, one or more of the above-mentioned "whether the terminal demodulates based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required when the terminal demodulates based on an AI model" can be determined by the network device based on at least one of the following: one or more first capabilities supported by the terminal, one or more first latencies supported by the terminal, the AI ​​processor status of the terminal, the data processing capability supported by the terminal, and the AI ​​model capability supported by the terminal.

[0299] Optionally, in some embodiments, when one or more first delays supported by the terminal are relatively long, such as exceeding a first threshold, it indicates that the processing delay required for demodulation based on the AI ​​model is long. In this case, to ensure communication efficiency, the network device can determine that the terminal does not perform demodulation based on the AI ​​model. In other embodiments, when one or more first delays supported by the terminal are relatively short, such as less than a first threshold, it indicates that the processing delay required for demodulation based on the AI ​​model is short. In this case, the network device can determine that the terminal performs demodulation based on the AI ​​model.

[0300] Optionally, in some embodiments, if the latency requirement of the demodulation service is high, but one or more first latencies supported by the terminal are long and do not meet the latency requirement of the demodulation service, the network device can determine that the terminal does not perform demodulation based on the AI ​​model. If the latency requirement of the demodulation service is high, and one or more first latencies supported by the terminal are short and meet the latency requirement of the demodulation service, the network device can determine that the terminal performs demodulation based on the AI ​​model.

[0301] Optionally, in some embodiments, when the network device determines that the load traffic of the AI ​​processor is large based on the AI ​​processor state, if one or more first delays supported by the terminal are all long, the network device can determine that the terminal does not perform demodulation based on the AI ​​model.

[0302] Optionally, in some embodiments, if the latency requirement of the demodulation service is high or the load traffic of the terminal AI processor is large, the first latency corresponding to the first capability used by the terminal determined by the network device should be low. In some embodiments, different first capabilities correspond to different first latencies. Specifically, the more complex the AI ​​model structure, the larger the model size, and the more layers the model has, the longer the corresponding first latency; or, the higher the data processing precision, the longer the corresponding first latency; or, the fewer the number of terminal hardware components, the longer the corresponding first latency. Therefore, if the latency requirement of the demodulation service is high or the load traffic of the terminal AI processor is large, the first capability used by the terminal determined by the network device may include at least one of the following: lower AI model capability, lower data processing precision, and higher terminal hardware capability. Similarly, the information required by the terminal for demodulation based on the AI ​​model, as determined by the network device, may also include at least one of the following: lower AI model capability, lower data processing precision, and higher terminal hardware capability.

[0303] Optionally, in some embodiments, the network device may carry an index corresponding to at least one of the following in the first information: AI model capability, terminal hardware capability, data processing capability, and first latency, to indicate to the terminal at least one of the following: the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal for demodulation based on the AI ​​model.

[0304] Optionally, in some embodiments, the first information can also be used to indicate AI model switching. For example, the first information can instruct the terminal to use a first AI model for demodulation, and indicate the model structure and / or model size corresponding to the first AI model. The first AI model is different from the second AI model, which can be the AI ​​model used by the terminal for demodulation before receiving the first information. In other embodiments, the first information can also be used to indicate data processing capability switching. For example, the first information can instruct the terminal to use a first data processing capability for demodulation, and indicate the data processing precision and / or data processing rate corresponding to the first data processing capability. The first data processing capability is different from the second data processing capability, which can be the data processing capability used by the terminal for demodulation before receiving the first information. In other embodiments, the first information can also be used to indicate terminal hardware capabilities. For example, the first information can instruct the terminal to use a first terminal hardware capability for demodulation, and indicate at least one of the following: the number of terminal hardware devices, the terminal hardware model, the terminal hardware design process, and the terminal hardware processing speed corresponding to the first terminal hardware capability. The first terminal hardware capability is different from the second terminal hardware capability, which can be the terminal hardware capability used by the terminal for demodulation before receiving the first information.

[0305] Step 2107: The terminal demodulates at least one of the channel and the signal based on the first information.

[0306] Optionally, the channel may include any channel that needs to be demodulated, such as a PDSCH, and the signal may include any signal that needs to be demodulated.

[0307] Optionally, in some embodiments, if the first information indicates that the terminal performs demodulation based on an AI model, then the terminal can perform demodulation based on at least one of the following: a first capability supported by the terminal, a first capability indicated by the first information, a first capability corresponding to a first delay indicated by the first information, and information required by the terminal to perform demodulation based on the AI ​​model.

[0308] Optionally, in some embodiments, if the protocol specifies a first capability, and the first information indicates that the terminal performs demodulation based on an AI model, and / or the first information indicates that the terminal uses the first capability, then the terminal can perform demodulation based on at least one of the first capability specified in the protocol, the data processing capability indicated by the first information, the AI ​​model capability indicated by the first information, and the terminal hardware capability indicated by the first information; or, the terminal can perform demodulation based on at least one of the first capability specified in the protocol, the data processing capability corresponding to the first delay indicated by the first information, the AI ​​model capability corresponding to the first delay indicated by the first information, and the terminal hardware capability corresponding to the first delay indicated by the first information.

[0309] Optionally, in some embodiments, if the terminal supports a first capability, and the first information indicates that the terminal performs demodulation based on an AI model, and / or the first information indicates that the terminal uses the first capability, then the terminal may perform demodulation based on at least one of the first capability supported by the terminal, the data processing capability indicated by the first information, the AI ​​model capability indicated by the first information, and the terminal hardware capability indicated by the first information; or, the terminal may perform demodulation based on at least one of the first capability supported by the terminal, the data processing capability corresponding to the first delay indicated by the first information, the AI ​​model capability corresponding to the first delay indicated by the first information, and the terminal hardware capability corresponding to the first delay indicated by the first information.

[0310] Optionally, in some embodiments, if the terminal supports multiple first capabilities, and the first information indicates that the terminal performs demodulation based on an AI model, and / or the first information indicates that the terminal uses a first capability, then the terminal can perform demodulation based on at least one of the first capability indicated by the first information, the data processing capability indicated by the first information, the AI ​​model capability indicated by the first information, and the terminal hardware capability indicated by the first information; or, the terminal can perform demodulation based on at least one of the first capability indicated by the first information, the data processing capability corresponding to the first delay indicated by the first information, the AI ​​model capability corresponding to the first delay indicated by the first information, and the terminal hardware capability corresponding to the first delay indicated by the first information.

[0311] Optionally, in some embodiments, if the first information instructs the terminal to use the first AI model for demodulation, the terminal can switch from the second AI model to the first AI model and perform demodulation based on the first AI model. Optionally, the switching delay for the terminal to switch from the second AI model to the first AI model can be a first switching delay.

[0312] Optionally, in some embodiments, if the first information instructs the terminal to use the first data processing capability for demodulation, the terminal can switch from the second data processing capability to the first data processing capability and perform demodulation based on the first data processing capability. Optionally, the switching delay for the terminal to switch from the second data processing capability to the first data processing capability can be the second switching delay.

[0313] Optionally, in some embodiments, when the terminal does not perform demodulation based on the AI ​​model, if the first information indicates that the terminal performs demodulation based on the AI ​​model, the terminal can switch from "not performing demodulation based on the AI ​​model" to "performing demodulation based on the AI ​​model". Optionally, the switching delay for the terminal to switch from "not performing demodulation based on the AI ​​model" to "performing demodulation based on the AI ​​model" can be a third switching delay.

[0314] Optionally, in some embodiments, when the terminal performs demodulation based on an AI model, if the first information indicates that the terminal does not perform demodulation based on an AI model, the terminal can switch from "demodulating based on an AI model" to "demodulating without an AI model". Optionally, the switching delay for the terminal to switch from "demodulating based on an AI model" to "demodulating without an AI model" can be a fourth switching delay.

[0315] In some embodiments, during at least one of the first, second, third, and fourth handover delays, the terminal is not scheduled to receive or process at least one of the signals or channels. In other words, during the first, second, third, or fourth handover delay, the network device will not schedule the terminal to receive or process at least one of the signals or channels, thereby ensuring that the handover process is not interfered with and guaranteeing handover efficiency and stability.

[0316] In some embodiments, at least one of the aforementioned first handover delay, second handover delay, third handover delay, and fourth handover delay can be determined by the terminal based on its handover capability and then sent to the network device. Optionally, in some embodiments, the terminal can also send its handover capability to the network device, so that the network device can determine at least one of the first handover delay, second handover delay, third handover delay, and fourth handover delay based on the terminal's handover capability. Optionally, different terminals can correspond to the same or different handover capabilities, and different handover capabilities can correspond to different handover delays. Optionally, a terminal can correspond to one handover capability, and the terminal can determine at least one of the first handover delay, second handover delay, third handover delay, and fourth handover delay based on that one handover capability. In this case, the first handover delay, second handover delay, third handover delay, and fourth handover delay can be the same. Optionally, in some embodiments, the terminal can correspond to multiple handover capabilities. For example, the terminal can correspond to four different handover capabilities, wherein the first handover capability can be used to determine the first handover delay, the second handover capability can be used to determine the second handover delay, the third handover capability can be used to determine the third handover delay, and the fourth handover capability can be used to determine the fourth handover delay. In this case, the first handover delay, the second handover delay, the third handover delay, and the fourth handover delay can be different.

[0317] In some embodiments, at least one of the first handover delay, second handover delay, third handover delay, and fourth handover delay described above may be agreed upon by a protocol.

[0318] In some embodiments, at least one of the first handover delay, second handover delay, third handover delay, and fourth handover delay described above can be configured by the network device.

[0319] Optionally, in some embodiments, during the processing delay of the terminal performing AI demodulation or non-AI demodulation based on the first information, the terminal is not scheduled to perform Hybrid Automatic Retransmission Request Acknowledgement (HARQ-ACK) feedback. In other words, during the processing delay of the terminal performing AI demodulation or non-AI demodulation based on the first information, the network device will not schedule the terminal to perform HARQ-ACK feedback. The delay between the time when the network device schedules the channel for the terminal and the time when the network device schedules the terminal to perform HARQ-ACK feedback on the channel is greater than the first delay indicated by the first information, or the delay between the time when the terminal receives the channel and the time when the terminal performs HARQ-ACK feedback on the channel is greater than the first delay indicated by the first information. This ensures that the AI ​​demodulation process is not interfered with, improving demodulation performance, demodulation stability, demodulation accuracy, and demodulation efficiency.

[0320] In summary, in the above embodiments, the terminal can determine at least one of one or more first capabilities and one or more first delays. The first capability can indicate the terminal's processing capability when demodulating based on an AI model, and the first delay can indicate the processing delay when demodulating based on an AI model. Furthermore, the terminal sends at least one of the one or more first capabilities and one or more first delays supported by the terminal to the network device, so that the network device can instruct whether and how the terminal performs demodulation based on the AI ​​model based on the first capabilities and / or the first delays supported by the terminal. Therefore, the embodiments of this disclosure define first capabilities and / or first delays, enabling the terminal and network device to successfully achieve AI model-based demodulation based on the defined first capabilities and / or first delays, improving demodulation performance, accuracy, and efficiency. Moreover, in the above embodiments, the terminal and network device can have a unified understanding of the first delay, allowing the network device to refrain from scheduling communication operations by the terminal within the first delay, ensuring that the terminal's demodulation operation is not interfered with within the first delay and guaranteeing demodulation stability.

[0321] The demodulation method involved in the embodiments of this disclosure may include at least one of steps 2101 to 2107. For example, step 2101 may be implemented as an independent embodiment, step 2102 may be implemented as an independent embodiment, step 2103 may be implemented as an independent embodiment, and step 2101+S2102 may be implemented as an independent embodiment, but is not limited thereto.

[0322] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0323] Figure 3 is an interactive schematic diagram of a demodulation method according to an embodiment of the present disclosure. As shown in Figure 3, this disclosure relates to a demodulation method for a terminal, the method comprising:

[0324] Step 3101: Determine at least one of one or more first capabilities and one or more first delays.

[0325] Step 3102: Indicate to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal.

[0326] Step 3103: Receive the first information sent by the network device.

[0327] Step 3104: Demodulate at least one of the channel and the signal based on the first information.

[0328] Optionally, the first capability is used to indicate the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first latency is used to indicate the processing latency of the terminal when performing demodulation based on an AI model.

[0329] Optionally, the first information is used to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required when the terminal performs demodulation based on an AI model;

[0330] Optionally, the first capability includes at least one of the following:

[0331] AI model capabilities;

[0332] Data processing capabilities;

[0333] Terminal hardware capabilities.

[0334] Optionally, the information required by the terminal for demodulation based on the AI ​​model includes at least one of the following:

[0335] The terminal uses AI model capabilities when demodulating based on an AI model;

[0336] The terminal uses data processing capabilities when demodulating based on an AI model;

[0337] The terminal hardware capabilities used by the terminal when performing demodulation based on the AI ​​model.

[0338] Optionally, the AI ​​model capabilities include at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0339] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0340] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0341] Optionally, the method further includes:

[0342] Send the AI ​​processor status to the network device.

[0343] Optionally, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, number of tasks on the AI ​​processor, AI processor heat dissipation state, and AI processor operating speed.

[0344] Optionally, determining at least one of one or more first capabilities and one or more first delays includes:

[0345] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0346] Optionally, the first capability corresponds to the first delay.

[0347] Optionally, demodulating at least one of the channel and the signal based on the first information includes:

[0348] The first information instructs the terminal to perform demodulation based on an AI model, and to perform demodulation based on at least one of the following: a first capability supported by the terminal, a first capability indicated by the first information, a first capability corresponding to a first delay indicated by the first information, and information required by the terminal to perform demodulation based on the AI ​​model.

[0349] Optionally, the method further includes at least one of the following:

[0350] The first information instructs the terminal to use a first AI model for demodulation. The first AI model is different from the second AI model. The terminal switches from the second AI model to the first AI model. The second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information.

[0351] The first information instructs the terminal to use a first data processing capability for demodulation. The first data processing capability is different from the second data processing capability. The terminal switches from the second data processing capability to the first data processing capability. The second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information.

[0352] The first information instructs the terminal to use the first terminal hardware capability for demodulation. The first terminal hardware capability is different from the second terminal hardware capability. The terminal switches from the second terminal hardware capability to the first terminal hardware capability. The second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information.

[0353] When the terminal does not perform demodulation based on the AI ​​model, if the first information indicates that the terminal performs demodulation based on the AI ​​model, the terminal switches from "not demodulating based on the AI ​​model" to "demodulating based on the AI ​​model".

[0354] When the terminal performs demodulation based on an AI model, if the first information indicates that the terminal does not perform demodulation based on an AI model, the terminal switches from "demodulation based on an AI model" to "demodulation without an AI model".

[0355] Optionally, in at least one of the first handover delay, the second handover delay, the third handover delay, the fourth handover delay, and the fifth handover delay, the terminal is not scheduled to receive or process at least one of the signals or channels;

[0356] Wherein, the first switching delay includes: the switching delay of the terminal switching from the second AI model to the first AI model;

[0357] The second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability;

[0358] The third handover delay includes: the handover delay when the terminal switches from the second terminal hardware capability to the first terminal hardware capability;

[0359] The fourth switching delay includes: the switching delay when the terminal switches from "not demodulated based on AI model" to "demodulated based on AI model";

[0360] The fifth switching delay includes the switching delay when the terminal switches from "demodulation based on AI model" to "demodulation without AI model".

[0361] Optionally, during the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform Hybrid Automatic Repeat Request (HARQ) ACK feedback.

[0362] Optionally, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capabilities are used to calculate the first delay corresponding to the first capability.

[0363] Optionally, the method further includes:

[0364] Send a second capability supported by the terminal to the network device, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0365] Optionally, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0366] For a detailed description of steps 3101-3104, please refer to the above embodiment description.

[0367] The demodulation method involved in the embodiments of this disclosure may include at least one of steps 3101 to 3104. For example, step 3101 may be implemented as an independent embodiment, step 3102 may be implemented as an independent embodiment, step 3103 may be implemented as an independent embodiment, and step 3101+S3102 may be implemented as an independent embodiment, but is not limited thereto.

[0368] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0369] Figure 4 is an interactive schematic diagram of a demodulation method according to an embodiment of the present disclosure. As shown in Figure 4, this disclosure relates to a demodulation method for use in a network device, the method comprising:

[0370] Step 4101: Determine at least one of one or more first capabilities and one or more first delays.

[0371] Step 4102: Receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal.

[0372] Step 4103: Send the first information to the terminal.

[0373] Optionally, the first capability is used to indicate the processing capability of the terminal when demodulating based on an artificial intelligence (AI) model, and the first latency is used to indicate the processing latency of the terminal when demodulating based on an AI model.

[0374] Optionally, the first information is used to indicate at least one of the following: whether the terminal demodulates based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required when the terminal demodulates based on an AI model.

[0375] Optionally, the first capability includes at least one of the following:

[0376] AI model capabilities;

[0377] Data processing capabilities;

[0378] Terminal hardware capabilities.

[0379] Optionally, the information required by the terminal for demodulation based on the AI ​​model includes at least one of the following:

[0380] The terminal uses AI model capabilities when demodulating based on an AI model;

[0381] The terminal uses data processing capabilities when demodulating based on an AI model;

[0382] The terminal hardware capabilities used by the terminal when performing demodulation based on the AI ​​model.

[0383] Optionally, the AI ​​model capabilities include at least one of the model structure of the AI ​​model and the model size of the AI ​​model;

[0384] The data processing capability includes at least one of data processing accuracy and data processing speed;

[0385] The terminal hardware capabilities include at least one of the following: number of terminal hardware devices, terminal hardware model, terminal hardware design process, and terminal hardware processing speed.

[0386] Optionally, the method further includes:

[0387] Receive the AI ​​processor status sent by the terminal.

[0388] Optionally, the AI ​​processor state includes at least one of the following: AI processor runtime, AI processor load state, number of tasks on the AI ​​processor, AI processor heat dissipation state, and AI processor operating speed.

[0389] Optionally, determining at least one of one or more first capabilities and one or more first delays includes:

[0390] Based on the agreement, at least one of one or more first capabilities and one or more first delays are determined.

[0391] Optionally, the first capability corresponds to the first delay.

[0392] Optionally, the first information is used to indicate at least one of the following:

[0393] The terminal uses a first AI model for demodulation;

[0394] The terminal uses the first data processing capability for demodulation;

[0395] The terminal uses the hardware capabilities of the first terminal to perform demodulation;

[0396] The terminal demodulates based on an AI model;

[0397] The terminal does not perform demodulation based on an AI model.

[0398] Optionally, the method further includes:

[0399] During at least one of the first handover delay, the second handover delay, the third handover delay, the fourth handover delay, and the fifth handover delay, the terminal is not scheduled to receive or process at least one of the signals or channels.

[0400] The first switching delay includes the switching delay of the terminal from the second AI model to the first AI model, wherein the second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information;

[0401] The second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability, wherein the second data processing capability is: the data processing capability used by the terminal when demodulating before receiving the first information;

[0402] The third switching delay includes: the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability, wherein the second terminal hardware capability is: the terminal hardware capability used by the terminal when demodulating before receiving the first information;

[0403] The fourth switching delay includes: the switching delay when the terminal switches from "not demodulated based on AI model" to "demodulated based on AI model";

[0404] The fifth switching delay includes the switching delay when the terminal switches from "demodulation based on AI model" to "demodulation without AI model".

[0405] Optionally, the method further includes:

[0406] During the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform HARQ-ACK feedback.

[0407] Optionally, different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capabilities are used to calculate the first delay corresponding to the first capability.

[0408] Optionally, the method further includes:

[0409] The terminal receives a second capability supported by the terminal, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

[0410] Optionally, different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

[0411] For a detailed description of steps 4101-4103, please refer to the above embodiment description.

[0412] The demodulation method involved in the embodiments of this disclosure may include at least one of steps 4101 to 4103. For example, step 4101 may be implemented as an independent embodiment, step 4102 may be implemented as an independent embodiment, step 4103 may be implemented as an independent embodiment, and step 4101+S4102 may be implemented as an independent embodiment, but is not limited thereto.

[0413] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0414] Figure 5 is an interactive schematic diagram of a demodulation method according to an embodiment of the present disclosure. As shown in Figure 5, the present disclosure relates to a demodulation method for a communication system, which includes a network device and a terminal. The method includes at least one of the following:

[0415] Step 5101: The terminal and / or network device determines at least one of one or more first capabilities and one or more first delays.

[0416] Step 5102: The terminal sends to the network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal.

[0417] Step 5103: The network device sends the first information to the terminal.

[0418] Step 5104: The terminal demodulates at least one of the channel and the signal based on the first information.

[0419] The optional implementation methods of steps 5101-5104 can be found in the above embodiments.

[0420] In some embodiments, the above methods may include the methods described in the embodiments of the communication system side, terminal side, network device side, etc., which will not be repeated here.

[0421] The demodulation method involved in the embodiments of this disclosure may include at least one of steps 5101 to 5104. For example, step 5101 may be implemented as a separate embodiment, and step 5102 may be implemented as a separate embodiment, but are not limited thereto.

[0422] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0423] The following is an exemplary description of the above method:

[0424] In 6G research, AI-based demodulation methods can be considered to obtain better demodulation performance. Traditional demodulation methods are sensitive to phase and fading caused by channel factors, especially in low SNR scenarios, where high-order modulation performance is poor. Considering that AI can handle some nonlinear problems better, AI-based demodulation methods can be considered to obtain better demodulation performance, especially in low SNR scenarios. AI-based demodulation methods have been studied in the IMT-2030 Wireless AI Subgroup and have attracted the attention of many companies.

[0425] AI model inference latency depends on the following factors:

[0426] The real-time computing speed of an AI processor is related to the optimal performance of the AI ​​processor hardware design (including whether accelerators such as tensor cores are enabled), as well as the AI ​​processor's operating status, heat dissipation, or load status.

[0427] AI models, including model structure, model size, etc.

[0428] The precision of data processing varies; different floating-point precisions result in different real-time processing speeds for the model.

[0429] For AI-based demodulation, considering that the implementation of AI models may be relatively complex compared to traditional hardware or software demodulation solutions, the terminal may experience increased processing latency while achieving a certain improvement in demodulation performance.

[0430] Therefore, one issue that needs to be considered is a new method for defining processing latency for AI-based demodulation.

[0431] Key Point 1: For AI-based Demodulation, define the first processing latency and / or the first processing capability.

[0432] 1-1: Optionally, the first processing latency and / or the first processing capability may be one or more.

[0433] 1-2: Different terminals can support one or more primary processing capabilities / primary processing latencies. Simultaneously, different terminals can support different processing capabilities / latencies.

[0434] 1-3: Based on 1-1, different processing latencies can be determined based on at least one of the following factors, or different processing latencies correspond to different at least one of the following factors (it is conceivable that different processing latencies could correspond to different AI models, different data precision, or different hardware capabilities, or different combinations of two or three of these factors):

[0435] - AI model (structure, scale)

[0436] - Data precision

[0437] - Hardware capabilities

[0438] It is conceivable that even for the same AI model / data precision, different devices may have different processing capabilities.

[0439] - The operating status of the AI ​​processing module; the reporting of processing capacity / processing latency determined by this factor allows the gNB to make real-time adjustments.

[0440] Key Point 2: The terminal reports the first processing latency and / or the first processing capability to the base station based on at least one of the following methods.

[0441] Method 1: Report processing latency and / or primary processing capability based on UE capability.

[0442] Method 2: Based on RRC signaling, MAC CE, or UCI, for example, based on UAI, MAC CE, or UCI, report the first processing latency / first processing capability in real time.

[0443] It is conceivable that the processing delay can be the quantized processing delay.

[0444] Alternatively, the terminal may report its processing capacity, with different processing capacities corresponding to different processing latency.

[0445] Key Point 3: The gNB determines the target processing capacity / latency corresponding to AI+Demodulation based on the terminal's supported processing capacity / latency. Simultaneously, the gNB configures / indicates the target processing capacity / latency to the terminal.

[0446] Key Point 4: For terminals with AI+Demodulation enabled, demodulation is performed based on the target processing capability. Simultaneously, the terminal does not expect HARQ-ACK feedback within the latency range determined based on the target processing capability. Alternatively, the gNB's scheduling latency requirement between PDSCH and HARQ-ACK must be greater than or equal to the processing latency determined based on the target processing capability.

[0447] Key Point 5: In the above method, defining a new processing latency can be achieved by introducing an additional bias parameter based on AI+demodulation. This bias parameter can be positive or negative, and the new processing latency is determined based on this bias parameter and the legacy processing latency (processing capability). The legacy processing latency can be the processing latency corresponding to PDSCH processing capability 1 or PDSCH processing capability 2 (that is, in this method, the terminal can also report the terminal processing capability under the legacy method). Alternatively, defining a new processing latency can also be achieved by introducing a new N1 value based on AI+demodulation, etc.

[0448] Example 1: AI demodulation model + floating-point arithmetic + AI hardware capabilities together form the AI ​​entity's AI+demodulation processing capability.

[0449] AI+demoulation processing capability based on AI entities defines a processing capability that corresponds to a processing latency preset by a protocol.

[0450] The terminal can either mandately support this capability, which can be reported to the gNB via RRC signaling such as UE capability signaling, or without RRC signaling such as UE capability signaling. Alternatively, the terminal can optionally support this capability, which can be reported to the gNB via RRC signaling such as UE capability signaling.

[0451] Whether to enable AI demodulation is configured / instructed to the UE by the gNB.

[0452] For terminals with AI+Demodulation enabled, this processing capability is always used for PDSCH processing. At the same time, when the gNB performs scheduling, it needs to ensure that the latency between the scheduled HARQ-ACK and PDSCH is greater than this processing latency.

[0453] Example 2: Determine AI processing latency based on AI demodulation model and / or floating-point precision.

[0454] A processing capability is defined based on the capabilities of AI hardware entities, and this capability can correspond to a processing speed preset by a protocol (quantized processing speed).

[0455] The terminal can mandate that it support this capability, which can be reported to the gNB via RRC signaling or without RRC signaling. Alternatively, the terminal can optionally support this hardware capability, which can be reported to the gNB via RRC signaling, such as UE capability signaling.

[0456] The terminal can simultaneously report the supported AI demodulation models and / or data precision, or the terminal can support all demodulation models and / or data precision.

[0457] The protocol predefines the correspondence between AI processing capabilities and different AI demodulation models and / or data accuracy and processing latency. One possible implementation is shown in the table in the aforementioned embodiment.

[0458] Whether to enable AI demodulation, and / or which AI demodulation model and / or data precision to enable, is configured / instructed to the UE by the gNB. Alternatively, the processing latency (index) corresponding to enabling AI demodulation, or the index in the table above, is indicated to the gNB.

[0459] The terminal determines the processing latency and / or AI demodulation model and / or data precision based on the table index indicated by the gNB, or directly determines the processing latency and / or AI demodulation model and / or data precision based on the indication signaling sent by the gNB, or determines the processing latency based on the AI ​​demodulation model and / or data precision indicated by the gNB and the protocol preset table, and simultaneously performs PDSCH processing based on the corresponding AI demodulation model and / or data precision. Furthermore, the gNB also determines the processing latency based on its own indicated model and / or data precision and the terminal's capabilities, and performs latency scheduling between PDSCH and HARQ feedback.

[0460] Example 3: The processing capability of AI + demodulation is determined by the AI ​​hardware entity, AI model, and floating-point calculation precision.

[0461] Based on the capabilities of AI hardware entities, various processing capabilities are defined, and different processing capabilities correspond to different processing latencies preset in the protocol.

[0462] The processing capabilities of different terminals are independent, and a specific terminal can support at most one type of processing capability.

[0463] The terminal reports its supported UE capabilities to the gNB via uplink signaling.

[0464] Whether to use this capability can be configured / indicated to the terminal directly by the gNB through display signaling (such as a capability indication field); or, it can be configured / indicated to the terminal through an indication of whether to enable the AI ​​demodulation model.

[0465] For terminals that have AI+Demodulation enabled, PDSCH processing is always performed using the capabilities corresponding to their own. At the same time, when the gNB performs scheduling, it needs to ensure that the latency between HARQ-ACK and PDSCH is greater than the latency corresponding to the UE's processing capabilities.

[0466] Optionally, this approach implies that different floating-point precisions and different AI models can be among the determining factors, along with the capabilities of the AI ​​hardware entity, all of which are part of the terminal's capabilities. Therefore, it is not necessary to determine the processing latency again through different floating-point precisions or AI models.

[0467] Example 4: Based on the AI ​​demodulation model, data accuracy, and the hardware capabilities reported by the terminal, determine the AI ​​processing latency.

[0468] Based on the capabilities of AI hardware entities, various processing capabilities are defined, and different processing capabilities correspond to the preset processing speed in the protocol (which can be the quantized processing speed).

[0469] The processing capabilities of different terminals are independent, and a specific terminal can support at most one type of processing capability.

[0470] The terminal reports its supported UE capabilities to the gNB via uplink signaling.

[0471] The protocol predetermines the correspondence between AI processing capabilities and different AI demodulation models and / or data accuracy and processing latency. One possible implementation is shown in the table above.

[0472] Whether to enable AI demodulation, and / or which AI demodulation model and / or data precision to enable, is configured / instructed to the UE by the gNB. Alternatively, the processing latency (index) corresponding to enabling AI demodulation, or the index in the table above, is indicated to the gNB.

[0473] For terminals that have AI+Demodulation enabled, PDSCH processing is always performed using the capabilities corresponding to their own. At the same time, when the gNB performs scheduling, it needs to ensure that the latency between HARQ-ACK and PDSCH is greater than the latency corresponding to the UE's processing capabilities.

[0474] Example 5: The processing capability of AI + demodulation is determined by the AI ​​hardware entity, AI model, and floating-point calculation precision.

[0475] Based on the capabilities of AI hardware entities, various processing capabilities are defined, and different processing capabilities correspond to different processing latencies.

[0476] The processing capabilities of different terminals are independent, and a specific terminal can support multiple processing capabilities.

[0477] The terminal can report one or more capabilities it supports to the gNB.

[0478] In other words, terminals that support high-speed computing can achieve a reduction in computing speed (taking into account factors such as terminal power consumption).

[0479] Specifically, the supported processing power can be indicated using either a bitmap or a sequence. Alternatively, the highest processing power can be indicated to the gNB (meaning that lower processing power can be supported).

[0480] Ultimately, the gNB can indicate to the terminal which processing capability to enable via explicit signaling.

[0481] For terminals with AI+Demodulation enabled, the capabilities configured / indicated by the gNB are always used for PDSCH processing. At the same time, when scheduling, the gNB needs to ensure that the latency between HARQ-ACK and PDSCH is greater than the latency corresponding to its own processing capabilities.

[0482] Optionally, this approach implies that different floating-point precisions and different AI models can be among the determining factors, along with the capabilities of the AI ​​hardware entity, all of which are part of the terminal's capabilities. There is no need to determine the processing latency again through different floating-point precisions or AI models. Example 6: AI hardware entity + AI model + computational precision jointly determine the processing capability of AI + demodulation.

[0483] Based on AI hardware capabilities, AI models, and data accuracy, various processing capabilities are defined, with different processing capabilities corresponding to different processing latencies. One possible implementation is shown in the figure below (including but not limited to the following different combinations).

[0484] The processing capabilities of different terminals are independent, and a specific terminal can support multiple processing capabilities.

[0485] The terminal can report one or more capabilities it supports to the gNB.

[0486] In other words, terminals that support high-speed computing can achieve a reduction in computing speed (taking into account factors such as terminal power consumption).

[0487] Specifically, the supported processing power can be indicated using either a bitmap or a sequence. Alternatively, the highest processing power can be indicated to the gNB (meaning that lower processing power can be supported).

[0488] Ultimately, the gNB can explicitly indicate to the terminal which processing capability to enable via signaling. For example, it can directly indicate the capability index, or specify the AI ​​model, data accuracy, etc.

[0489] For terminals with AI+Demodulation enabled, the capabilities configured / indicated by the gNB are always used for PDSCH processing. At the same time, when scheduling, the gNB needs to ensure that the latency between HARQ-ACK and PDSCH is greater than the latency corresponding to its own processing capabilities.

[0490] Optionally, this approach implies that different floating-point precisions and different AI models can be among the determining factors, along with the capabilities of the AI ​​hardware entity, all of which are part of the terminal's capabilities. Therefore, it is not necessary to determine the processing latency again through different floating-point precisions or AI models.

[0491] Example 7: Determining PDSCH Processing Latency Based on AI+demodulation Based on AI Model / Floating-Point Number Type and AI Hardware Entity Capabilities

[0492] Based on the capabilities of AI hardware entities, various processing capabilities are defined, and different processing capabilities correspond to different processing speeds.

[0493] The processing capabilities of different terminals are independent, and a specific terminal can support multiple processing capabilities.

[0494] The terminal can report one or more capabilities it supports to the gNB.

[0495] In other words, terminals that support high-speed computing can achieve a reduction in computing speed (taking into account factors such as terminal power consumption).

[0496] Specifically, the supported processing power can be indicated using either a bitmap or a sequence. Alternatively, the highest processing power can be indicated to the gNB (meaning that lower processing power can be supported).

[0497] The protocol predetermines the correspondence between AI processing capabilities and different AI demodulation models and / or data accuracy and processing latency. One possible implementation is shown in the table above.

[0498] The gNB configures / instructs the UE on whether to enable AI demodulation, and / or which AI demodulation model and / or data precision to enable, as well as which hardware capabilities to enable. Alternatively, the gNB may be instructed on the processing latency (index) corresponding to enabling AI demodulation, or by indexing the above table.

[0499] For terminals with AI+Demodulation enabled, PDSCH processing is always performed using the capabilities indicated by the gNB. At the same time, when scheduling, the gNB needs to ensure that the latency between HARQ-ACK and PDSCH is greater than the latency corresponding to the UE's processing capabilities.

[0500] Example 8

[0501] The protocol pre-sets several different levels of real-time processing capabilities, with different processing speeds or processing latency, as shown in the aforementioned embodiments.

[0502] Terminals can report their real-time processing capabilities based on RRC signaling, such as UAI.

[0503] Based on the protocol presets and the real-time processing capabilities reported by the terminal, the gNB determines whether to enable AI-based demodulation, and / or whether to perform model switching, and / or whether to perform data precision switching. Simultaneously, it instructs the terminal via dynamic or semi-static signaling to enable / disable AI+demodulation, and / or the model to be switched (model structure, model size, etc.), and / or the data precision.

[0504] Based on instructions from the gNB, the terminal performs model updates, data precision updates, or enables / disables AI demos. The specific gNB instructions depend on the scheduling implementation. For example, if the terminal reports a long processing delay, the AI ​​demo is disabled; or, if the terminal reports a specific processing delay, the network side determines whether to disable the AI ​​demo based on the service's delay requirement; or, if the terminal reports a specific processing delay, the network side determines whether to disable the AI ​​demo based on load and traffic conditions. The same applies to model switching and data precision switching; larger models, more complex models, or models with more layers introduce greater processing delays, as does higher data precision.

[0505] Optionally, in response to the terminal using the first AI model for PDSCH processing during the previous PDSCH reception, the UE receives a second model handover indication sent by the gNB, and the UE performs a handover from the first AI model to the second AI model. During the handover delay, the terminal does not expect to receive or process PDSCH. The handover delay can be reported by the terminal capability (optionally, different terminals may correspond to different handover capabilities) and / or configured / indicated by the gNB, or the handover delay can be preset by the protocol.

[0506] Optionally, in response to the terminal using legacy mode for PDSCH processing during the previous PDSCH reception, the UE receives an AI+demodulation enable signaling from the gNB, and the UE performs a handover from legacy mode to AI+demodulation. During the handover delay, the terminal does not expect to receive or process PDSCH. The handover delay can be reported by the terminal capability (optionally, different terminals correspond to different handover capabilities) and / or indicated by gNB configuration, or the handover delay can be preset by the protocol.

[0507] Optionally, in response to the terminal using AI+demodulation for PDSCH processing during the previous PDSCH reception, the UE receives an AI+demodulation disable signaling sent by the gNB, and the UE performs a handover from AI+demodulation to legacy mode. During the handover delay, the terminal does not expect to receive or process PDSCH. The handover delay can be reported by the terminal capability (optionally, different terminals correspond to different handover capabilities) and / or indicated by gNB configuration, or the handover delay can be preset by the protocol.

[0508] Optionally, the above three types of latency can be the same (including the same terminal capabilities) or independent (including independent terminal capabilities reported through different fields).

[0509] Other: In the above real-time examples, the signaling reported by the gNB and / or UE may also be AI layer-specific signaling, etc.

[0510] This disclosure proposes a method for defining and indicating the processing latency of AI demodulation, so that both the gNB and the terminal can align their understanding of the processing latency, enabling AI demodulation to be deployed in practical wireless communication systems.

[0511] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0512] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0513] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0514] Figure 6A is a schematic diagram of the structure of a terminal according to an embodiment of this disclosure. As shown in Figure 6A, it includes:

[0515] A processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0516] A transceiver module is configured to indicate to a network device at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal;

[0517] The transceiver module is further configured to receive first information sent by the network device, the first information being configured to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0518] The processing module is further configured to demodulate at least one of the channel and the signal based on the first information.

[0519] Optionally, the transceiver module described above is used to perform the communication steps such as sending and / or receiving performed by the terminal in any of the above methods. The processing module described above is used to perform other steps performed by the terminal in any of the above methods.

[0520] Figure 6B is a schematic diagram of the structure of a network device according to an embodiment of this disclosure. As shown in Figure 6B, it includes:

[0521] The processing module is configured to determine at least one of one or more first capabilities and one or more first delays, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model.

[0522] A transceiver module is configured to receive at least one of one or more first capabilities supported by the terminal and one or more first delays supported by the terminal, transmitted by the terminal.

[0523] The transceiver module is further configured to send first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

[0524] Optionally, the transceiver module described above can be used to perform the communication steps such as sending and / or receiving performed by the network device in any of the above methods. The processing module described above is used to perform other steps performed by the network device in any of the above methods.

[0525] Figure 7A is a schematic diagram of the structure of the communication device 7100 proposed in an embodiment of this disclosure. The communication device 7100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment or the aforementioned network device), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 7100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0526] As shown in Figure 7A, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. The processor 7101 is used to invoke instructions to cause the communication device 7100 to execute any of the above methods.

[0527] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memories 7102 may also be located outside the communication device 7100.

[0528] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the communication steps such as sending and receiving in the above method are performed by the transceivers 7103, and other steps are performed by the processor 7101.

[0529] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, sensing signal receiving end, receiving circuit, etc., may be used interchangeably.

[0530] Optionally, the communication device 7100 further includes one or more interface circuits 7104, which are connected to the memory 7102. The interface circuits 7104 can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuits 7104 can read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0531] The communication device 7100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 7100 described in this disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7a. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a sensing signal receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0532] Figure 7B is a schematic diagram of the structure of the chip 7200 according to an embodiment of this disclosure. For cases where the communication device 7100 can be a chip or a chip system, the schematic diagram of the chip 7200 shown in Figure 7B can be referenced, but is not limited thereto.

[0533] Chip 7200 includes one or more processors 7201, which are used to invoke instructions to cause chip 7200 to perform any of the above methods.

[0534] In some embodiments, chip 7200 further includes one or more interface circuits 7202 connected to memory 7203. Interface circuits 7202 can be used to receive signals from memory 7203 or other devices, and can also be used to send signals to memory 7203 or other devices. For example, interface circuit 7202 can read instructions stored in memory 7203 and send those instructions to processor 7201. Optionally, terms such as interface circuit, interface, transceiver pin, and transceiver can be used interchangeably.

[0535] In some embodiments, chip 7200 further includes one or more memories 7203 for storing instructions. Optionally, all or part of the memories 7203 may be located outside of chip 7200.

[0536] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 7100, cause the communication device 7100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0537] This disclosure also provides a program product that, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0538] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0539] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0540] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0541] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0542] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A demodulation method, characterized in that, The method, executed by a terminal, includes: Determine at least one of a first capability and a first delay, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model. Indicate to the network device at least one of a first capability supported by the terminal and a first latency supported by the terminal; The network device receives first information, which indicates at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on the AI ​​model. Demodulate at least one of the channel and the signal based on the first information.

2. The method as described in claim 1, characterized in that, The method further includes: Send the AI ​​processor status to the network device.

3. The method as described in claim 2, characterized in that, The AI ​​processor status includes at least one of the following: AI processor runtime, AI processor load status, number of tasks on the AI ​​processor, AI processor heat dissipation status, and AI processor operating speed.

4. The method according to any one of claims 1-3, characterized in that, The first capability corresponds to the first delay.

5. The method according to any one of claims 1-4, characterized in that, The demodulation of at least one of the channel and the signal based on the first information includes: The first information instructs the terminal to perform demodulation based on an AI model, and to perform demodulation based on at least one of the following: a first capability supported by the terminal, a first capability indicated by the first information, a first capability corresponding to a first delay indicated by the first information, and information required by the terminal to perform demodulation based on the AI ​​model.

6. The method according to any one of claims 1-5, characterized in that, The method further includes at least one of the following: The first information instructs the terminal to use a first AI model for demodulation. The first AI model is different from the second AI model. The terminal switches from the second AI model to the first AI model. The second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information. The first information instructs the terminal to use a first data processing capability for demodulation. The first data processing capability is different from the second data processing capability. The terminal switches from the second data processing capability to the first data processing capability. The second data processing capability is the data processing capability used by the terminal for demodulation before receiving the first information. The first information instructs the terminal to use the first terminal hardware capability for demodulation. The first terminal hardware capability is different from the second terminal hardware capability. The terminal switches from the second terminal hardware capability to the first terminal hardware capability. The second terminal hardware capability is the terminal hardware capability used by the terminal for demodulation before receiving the first information. When the terminal does not perform demodulation based on the AI ​​model, if the first information indicates that the terminal performs demodulation based on the AI ​​model, the terminal switches from "not demodulating based on the AI ​​model" to "demodulating based on the AI ​​model"; When the terminal performs demodulation based on an AI model, if the first information indicates that the terminal does not perform demodulation based on an AI model, the terminal switches from "demodulation based on an AI model" to "demodulation not based on an AI model".

7. The method as described in claim 6, characterized in that, In at least one of the first handover delay, the second handover delay, the third handover delay, the fourth handover delay, and the fifth handover delay, the terminal is not scheduled to receive or process at least one of the signals or channels; Wherein, the first switching delay includes: the switching delay of the terminal switching from the second AI model to the first AI model; The second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability; The third handover delay includes: the time it takes for the terminal to switch from the second terminal hardware capability to the first terminal hardware capability. Delay; The fourth switching delay includes the switching delay when the terminal switches from "not demodulated based on AI model" to "demodulated based on AI model"; The fifth switching delay includes the switching delay when the terminal switches from "demodulation based on AI model" to "demodulation without AI model".

8. The method according to any one of claims 1-7, characterized in that, During the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform Hybrid Automatic Repeat Request (HARQ) ACK feedback.

9. The method according to any one of claims 1-8, characterized in that, Different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capability are used to calculate the first delay corresponding to the first capability.

10. The method according to any one of claims 1-8, characterized in that, The method further includes: Send a second capability supported by the terminal to the network device, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

11. The method as described in claim 10, characterized in that, Different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

12. A demodulation method, characterized in that, Performed by a network device, the method includes: Determine at least one of a first capability and a first delay, wherein the first capability is used to indicate the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay is used to indicate the processing delay of the terminal when performing demodulation based on an AI model. Receive at least one of the first capability supported by the terminal and the first latency supported by the terminal sent by the terminal; Send first information to the terminal, the first information being used to indicate at least one of the following: whether the terminal is demodulating based on an AI model, a first capability used by the terminal, a first latency corresponding to the terminal, and information required by the terminal when demodulating based on an AI model.

13. The method as described in claim 12, characterized in that, The method further includes: Receive the AI ​​processor status sent by the terminal.

14. The method as described in claim 13, characterized in that, The AI ​​processor status includes at least one of the following: AI processor runtime, AI processor load status, number of tasks on the AI ​​processor, AI processor heat dissipation status, and AI processor operating speed.

15. The method according to any one of claims 12-14, characterized in that, The first capability corresponds to the first delay.

16. The method according to any one of claims 12-15, characterized in that, The first information is used to indicate at least one of the following: The terminal uses a first AI model for demodulation; The terminal uses the first data processing capability for demodulation; The terminal uses the hardware capabilities of the first terminal to perform demodulation; The terminal demodulates based on an AI model; The terminal does not perform demodulation based on an AI model.

17. The method as described in claim 16, characterized in that, The method further includes: Within at least one of the first handover delay, second handover delay, third handover delay, fourth handover delay, and fifth handover delay, not The terminal is scheduled to receive or process at least one of the signals and channels. The first switching delay includes the switching delay of the terminal from the second AI model to the first AI model, wherein the second AI model is the AI ​​model used by the terminal for demodulation before receiving the first information; The second switching delay includes: the switching delay of the terminal switching from the second data processing capability to the first data processing capability, wherein the second data processing capability is: the data processing capability used by the terminal when demodulating before receiving the first information; The third switching delay includes: the switching delay of the terminal switching from the second terminal hardware capability to the first terminal hardware capability, wherein the second terminal hardware capability is: the terminal hardware capability used by the terminal when demodulating before receiving the first information; The fourth switching delay includes the switching delay when the terminal switches from "not demodulated based on AI model" to "demodulated based on AI model"; The fifth switching delay includes the switching delay when the terminal switches from "demodulation based on AI model" to "demodulation without AI model".

18. The method according to any one of claims 12-17, characterized in that, The method further includes: During the processing delay of the terminal demodulating based on the first information, the terminal is not scheduled to perform HARQ-ACK feedback.

19. The method according to any one of claims 12-18, characterized in that, Different first capabilities correspond to different first parameters, and the first parameters corresponding to the first capability are used to calculate the first delay corresponding to the first capability.

20. The method according to any one of claims 12-18, characterized in that, The method further includes: The terminal receives a second capability supported by the terminal, the second capability including: the processing capability of the terminal when demodulation is not based on an AI model.

21. The method as described in claim 20, characterized in that, Different first capabilities correspond to different first bias parameters, and different second capabilities correspond to different second parameters. The first bias parameter corresponding to the first capability and the second parameter corresponding to the second capability are used to calculate the first delay corresponding to the first capability.

22. A demodulation method for a communication system, the communication system including a terminal and network equipment, the method comprising: The terminal and / or the network device determine at least one of a first capability and a first latency, wherein the first capability is used to indicate the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first latency is used to indicate the processing latency of the terminal when performing demodulation based on an AI model. The terminal sends at least one of the first capability supported by the terminal and the first latency supported by the terminal to the network device. The network device sends first information to the terminal, the first information being used to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model. The terminal demodulates at least one of the channel and the signal based on the first information.

23. A terminal, characterized in that, include: A processing module is configured to determine at least one of a first capability and a first latency, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first latency indicates the processing latency of the terminal when performing demodulation based on an AI model. The transceiver module is configured to indicate to the network device at least one of a first capability supported by the terminal and a first latency supported by the terminal; The transceiver module is further configured to receive first information sent by the network device, the first information being configured to indicate at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model. The processing module is further configured to demodulate at least one of the channel and the signal based on the first information.

24. A network device, characterized in that, include: The processing module is used to determine at least one of a first capability and a first delay, wherein the first capability indicates the processing capability of the terminal when performing demodulation based on an artificial intelligence (AI) model, and the first delay indicates the processing delay of the terminal when performing demodulation based on an AI model. The transceiver module is configured to receive at least one of the first capability supported by the terminal and the first latency supported by the terminal sent by the terminal; The transceiver module is further configured to send first information to the terminal, the first information indicating at least one of the following: whether the terminal performs demodulation based on an AI model, the first capability used by the terminal, the first latency corresponding to the terminal, and the information required by the terminal when performing demodulation based on an AI model.

25. A communication device, characterized in that, The communication device is used to perform the method according to any one of claims 1-11 and 12-21.

26. A communication system, characterized in that, The device includes a terminal and a network device, wherein the terminal is configured to implement the method of any one of claims 1-11, and the network device is configured to implement the method of any one of claims 12-21.

27. A storage medium storing instructions, characterized in that, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1-11 and 12-21.

28. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by a communication device, it implements the steps of the method according to any one of claims 1-11 and 12-21.

Images