Communication method, apparatus and system

By sending messages in the communication system to verify the applicability of AI features and the matching of configuration information, the problem of increased signaling overhead caused by AI feature verification tasks is solved, thereby improving the efficiency and reliability of the communication system.

WO2026233098A1PCT designated stage Publication Date: 2026-11-12HUAWEI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/091883
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-08
Filing Date
2026-04-21
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

As AI/ML models are increasingly used in communication systems, the task of verifying whether AI features are activated leads to increased signaling overhead, affecting the efficiency of communication systems.

Method used

The first communication device sends a message indicating the applicability of AI features to the second communication device, and sends a message indicating whether the configuration information matches or does not match after receiving a response. This allows the second communication device to indirectly determine the applicability of AI features, thereby reducing signaling overhead.

Benefits of technology

This effectively reduces signaling overhead between devices, improves the accuracy of AI feature activation status determination, and enhances the reliability of the communication system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026091883_12112026_PF_FP_ABST
    Figure CN2026091883_12112026_PF_FP_ABST
Patent Text Reader

Abstract

The present application relates to the field of communications, and discloses a communication method, apparatus and system. In the present application, a first communication apparatus sends a first message to a second communication apparatus; and when receiving a second message from the second communication apparatus, the first communication apparatus sends a third message to the second communication apparatus. In this way, the first communication apparatus sends, to the second communication apparatus, the first message indicating that applicability of a first AI characteristic is consistent with applicability of a second AI characteristic, and upon receiving the second message, sends, to the second communication apparatus, a third message indicating that the first AI characteristic matches or does not match a configuration information set, so that the second communication apparatus can indirectly determine the applicability of the first AI characteristic on the basis of the third message, and on the basis of the first message and the third message, determine whether the second AI characteristic has applicability. Therefore, when determining that the second AI characteristic has no applicability, the second communication apparatus gives up determination of an activation state of the second AI characteristic, thereby reducing signaling overhead between apparatuses.
Need to check novelty before this filing date? Find Prior Art

Description

Communication methods, devices and systems

[0001] This application claims priority to Chinese Patent Application No. 202510593524.4, filed on May 8, 2025, entitled "Communication Method, Apparatus and System", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods, apparatus and systems. Background Technology

[0003] With the continuous development of artificial intelligence (AI) and machine learning (ML) technologies, AI / ML models are increasingly being used in communication systems. For example, communication systems can use AI / ML models to achieve functions such as beam management and positioning. Before using an AI / ML model, a communication system typically needs to confirm whether the corresponding AI features can be activated. If the AI ​​features are activated, the AI / ML model can function normally. However, due to the increasing number of AI / ML models involved in communication systems, the task of confirming whether the AI ​​features can be activated has greatly increased, leading to higher signaling overhead. Summary of the Invention

[0004] This application provides a communication method, apparatus, and system that can save signaling overhead between devices.

[0005] In a first aspect, a communication method is provided. This method can be executed by a first communication device, which may include a first AI feature and a second AI feature. It can also be executed by a component of the first communication device (e.g., a processor, chip, or chip system), or by a logic node, logic module, or software capable of implementing all or part of the functions of the first communication device. The method includes: sending a first message to a second communication device, the first message indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, the first message being used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature; upon receiving a second message from the second communication device, sending a third message to the second communication device, the second message indicating first configuration information related to the first AI feature, the third message indicating whether the first AI feature matches or does not match the first configuration information.

[0006] The solution provided in the first aspect above involves the first communication device sending a first message to the second communication device indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and sending a third message to the second communication device after receiving the second message indicating whether the first AI feature matches or does not match the configuration information set. This allows the second communication device to indirectly determine the applicability of the first AI feature based on the third message, and to determine whether the second AI feature is applicable based on the first and third messages. Thus, when the second communication device determines that the second AI feature is not applicable, it abandons the determination of the activation state of the second AI feature, saving signaling overhead between devices.

[0007] In some examples, the first communication device can be a terminal device, and the second communication device can be a network device (such as a base station, network element, etc.).

[0008] In some examples, taking the first AI feature as an example, determining whether to activate the first AI feature can be understood as determining whether to determine the applicability of the first AI feature, whether to determine the applicability of the first configuration information of the first AI feature, and whether to activate the configuration information of the first AI feature (i.e., whether to instruct the activation of the first AI feature). Determining the activation status of the first AI feature can be understood as determining whether to activate the first AI feature or to activate the first AI feature.

[0009] In some examples, taking the first AI feature as an example, the applicability of the first AI feature can be understood as the resources of the first communication device itself (such as power, computing power, storage resources, etc., one or more) can support the normal operation of the AI / ML model corresponding to the first AI feature. In other words, the first AI feature is compatible with the resources of the first communication device itself. The determination of the activation state of the first AI feature by the second communication device can be understood as determining whether the first AI feature can be in an activated state (i.e., whether the first AI feature can be activated). The activation of the first AI feature can be considered from the following two points: 1. The first AI feature is applicable; 2. The first AI feature matches the first configuration information included in the second communication device, that is, when the second communication device is configured according to the first configuration information, the AI / ML model corresponding to the first AI feature can run normally. When the first AI feature is not applicable, the AI / ML model corresponding to the first AI feature cannot run normally regardless of how the second communication device is configured. In other words, when the first AI feature is not applicable, the first AI feature does not match the first configuration information. Therefore, when the third message indicates that the first AI feature matches the first configuration information, it can indirectly indicate that the first AI feature is applicable; when the third message indicates that the first AI feature does not match the first configuration information, it can indirectly indicate that the first AI feature is not applicable.

[0010] In some examples, the second communication device can set corresponding configuration information for different AI features. This configuration information can be used to ensure that the AI / ML model corresponding to the AI ​​feature operates normally under the communication environment (such as channel quality). The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. The network parameter configuration can be used to match the corresponding AI feature, and the auxiliary information can represent some privacy information of the base station. For example, the auxiliary information can implicitly express the downtilt angle of the base station beam. For instance, assuming the first AI feature is an AI beam management feature, the first configuration information may include a first network parameter configuration and first auxiliary information. The first network parameter configuration may be a CSI report configuration, and the first auxiliary information may represent the downtilt angle of the base station beam.

[0011] In some examples, there can be multiple types of first configuration information, each of which can be adapted to an AI / ML model corresponding to a first AI feature. For example, assuming the first AI feature is an AI beam management feature, the first AI feature corresponds to first configuration information 1 and first configuration information 2. First configuration information 1 can be adapted to an AI / ML model that performs inference through 32 beam scan results, and first configuration information 2 can be adapted to an AI / ML model that performs inference through 16 beam scan results. This allows the first communication device to select the appropriate first configuration information for matching based on the AI / ML model corresponding to its own first AI feature.

[0012] In some examples, the applicability relationship between AI features can be related to the relationship between the AI / ML models corresponding to the AI ​​features. For example, if multiple AI features can share an AI / ML model, then the applicability of the above multiple AI features can be consistent. Or, if the AI / ML models corresponding to multiple AI features have a successor relationship, that is, the input of the AI / ML model corresponding to one AI feature can be the output of the AI / ML model corresponding to another AI feature, then the applicability of the above multiple AI features can be consistent.

[0013] In some examples, the first message may indicate that the first AI feature and the second AI feature belong to the first AI set, and the applicability of AI features in the first AI set is consistent; or, the first message may indicate that the applicability of the first AI feature is consistent with the applicability of the second AI feature in the second AI set, and the first AI feature does not belong to the second AI set. Thus, by considering the correlation between the applicability of the first AI feature and the second AI feature under different AI set distributions, the diversity and accuracy of the correlation between the applicability of the first AI feature and the second AI feature can be improved.

[0014] In some examples, the first AI set can be represented as "{first AI feature, second AI feature}". Consistent applicability of AI features within the first AI set can mean that if the first AI feature is applicable, the second AI feature is also applicable, and vice versa. For example, suppose the first AI feature is the AI ​​reference signal receiving power (RSRP) prediction feature, and the second AI feature is the AI ​​signal to interference plus noise ratio (SINR) prediction feature. Since the AI ​​RSRP prediction feature and the AI ​​SINR prediction feature can share the same AI / ML model, if either the first AI feature or the second AI feature is applicable, the other AI feature is also applicable.

[0015] In some examples, the first AI feature and the second AI set can be represented as "first AI feature : {second AI feature}". The applicability of the first AI feature being consistent with the applicability of the second AI feature in the second AI set indicates that when the first AI feature is applicable, the second AI feature is also applicable. However, when the second AI feature is applicable, the first AI feature may not necessarily be applicable. For example, suppose the first AI feature is an AI channel state information (CSI) estimation feature, and the second AI feature is an AI CSI prediction feature. The input to AI CSI estimation can be the output of the AI / ML model corresponding to AI CSI prediction. In this case, when the first AI feature is applicable, the second AI feature is also applicable; however, when the second AI feature is applicable, the first AI feature may not necessarily be applicable.

[0016] In some examples, the first AI set and / or the second AI set may also have other AI features, such as a third AI feature, etc., which are not limited here.

[0017] In some examples, the first communication device may also include other AI sets, each of which may correspond to an identity document (ID). For example, the first communication device may also include a third AI set, which may include a fourth AI feature and a fifth AI feature. Or, the first communication device may also include a fourth AI set and a sixth AI feature, where the fourth AI set may include a seventh AI feature, and the sixth AI feature does not belong to the fourth AI set. This application does not limit the scope of the application.

[0018] In some examples, the content indicated by the third message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can determine whether the first AI feature matches the first configuration information based on the preset conditions and obtain the content indicated by the third message. This allows the second communication device to indirectly confirm the applicability of the first AI feature based on the third message, improving the accuracy of the applicability of the first AI feature and thereby enhancing the reliability of inter-device communication.

[0019] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0020] In one possible design, before sending the first message to the second communication device, the method further includes receiving a fourth message from the second communication device, the fourth message being used to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature. Thus, the first communication device can send the first message to the second communication device when the second communication device queries the relationship between the applicability of the first AI feature and the applicability of the second AI feature, enabling the second communication device to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature, and allowing the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature based on the first message, thereby improving the accuracy of the second communication device's decision-making.

[0021] In one possible design, the method further includes: receiving a fifth message from the second communication device, the fifth message being used to obtain the applicability of the first AI feature; and sending a sixth message to the second communication device, the sixth message indicating whether the first AI feature is applicable or not, the sixth message being used by the second communication device to determine whether to send a second message. Thus, the first communication device can enable the second communication device to obtain the applicability of the first AI feature by sending a sixth message to the second communication device. If the first AI feature is not applicable, the second communication device can choose not to send a second message to the first communication device, saving signaling overhead between devices.

[0022] In some examples, the content indicated by the sixth message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can confirm the applicability of the first AI feature based on the preset conditions and obtain the content indicated by the sixth message, enabling the second communication device to obtain the applicability of the first AI feature based on the sixth message, improving the accuracy of the applicability of the first AI feature, and thereby improving the reliability of inter-device communication.

[0023] In one possible design, after sending the first message, the method further includes sending a seventh message to the second communication device. The seventh message indicates that the relationship between the applicability of the first AI feature and the applicability of the second AI feature has failed. The seventh message is used by the second communication device to determine whether to switch the strategy for determining the activation state of the AI ​​feature. In this way, the first communication device can promptly notify the second communication device when the relationship between the applicability of the first and second AI features fails, thereby facilitating the second communication device to adjust the strategy for determining the activation state of the AI ​​feature in a timely manner, and thus improving the reliability of communication.

[0024] In one possible design, the method further includes: re-determining the relationship between the applicability of the first AI feature and the applicability of the second AI feature when the first communication device switches from an inactive state to a connected state; or, re-determining the relationship between the applicability of the first AI feature and the applicability of the second AI feature when the first communication device switches from a dormant state to a connected state; the aforementioned sending of the first message to the second communication device includes: sending the first message to the second communication device when the first communication device is in a connected state. Thus, the first communication device can re-confirm the applicability relationship between the first AI feature and the second AI feature when switching from another state to a connected state, improving the accuracy of the applicability relationship between the first AI feature and the second AI feature, thereby improving the reliability of inter-device communication.

[0025] In some examples, inactive state, connected state, and sleep state can refer to different states of the first communication device under the radio resource control (RRC) protocol. Inactive state can refer to RRC_INACTIVE state, in which the first communication device has not established an RRC connection, has no context storage, and cannot transmit data or messages. Sleep state can refer to RRC_IDLE state, in which the first communication device can retain part of the context and quickly restore the connection with the second communication device. Connected state can refer to RRC_CONNECTED state, in which the first communication device maintains a connection with the second communication device and can transmit data or messages.

[0026] In one possible design, the method further includes: deactivating the first AI feature and the second AI feature when the first AI feature is not applicable and is in an active state. Thus, the first communication device can deactivate both the first AI feature and the second AI feature, which has the same applicability as the first AI feature, when the first AI feature is not applicable, saving signaling overhead between devices for deactivating the second AI feature.

[0027] In some embodiments, the first communication device can detect the applicability of the first AI feature in real time, and then activate the first AI feature and the second AI feature when the first AI feature is not applicable and the first AI feature is in an active state.

[0028] In some embodiments, the first communication device may receive a message sent by the second communication device to deactivate the first AI feature and the second AI feature when the first AI feature is not applicable.

[0029] Secondly, a communication method is provided. This method can be executed by a first communication device, which may include a first AI feature and a second AI feature. It can also be executed by a component of the first communication device (e.g., a processor, chip, or chip system), or by a logic node, logic module, or software capable of implementing all or part of the functions of the first communication device. The method includes: receiving a fifth message from a second communication device, the fifth message being used to obtain the applicability of the first AI feature; and sending a sixth message to the second communication device, the sixth message indicating whether the first AI feature is applicable or not. The sixth message is used by the second communication device to determine whether to send a second message, the second message indicating first configuration information related to the first AI feature.

[0030] The solution provided in the second aspect above allows the first communication device to send a sixth message to the second communication device so that the second communication device can obtain the applicability of the first AI feature. When the first AI feature is not applicable, the second communication device abandons sending a second message to the first communication device, thus saving the signaling overhead between devices used to determine the activation state of the first AI feature.

[0031] In some examples, the first communication device can be a terminal device, and the second communication device can be a network device (such as a base station).

[0032] In some examples, taking the first AI feature as an example, the applicability of the first AI feature can be understood as the resources of the first communication device itself (such as power, computing power, storage resources, etc., one or more) being able to support the normal operation of the AI / ML model corresponding to the first AI feature. In other words, the first AI feature is compatible with the resources of the first communication device itself. The determination by the second communication device to determine the activation state of the first AI feature and / or the second AI feature can be understood as determining whether the first AI feature or the second AI feature is in an active state (i.e., whether the first AI feature or the second AI feature can be activated). Whether the first AI feature can be activated can be considered from the following two points: 1. The first AI feature is applicable; 2. The first AI feature matches the first configuration information included in the second communication device, that is, when the second communication device is configured according to the first configuration information, the AI / ML model corresponding to the first AI feature can run normally. Therefore, the first communication device first sends a sixth message to the second communication device to enable the second communication device to obtain the applicability of the first AI feature. This allows the second communication device to determine whether to send the first configuration information related to the first AI feature. If the first AI feature is not applicable, the signaling overhead corresponding to the second message can be reduced.

[0033] In some examples, the second communication device can set corresponding configuration information for different AI features. This configuration information can be used to ensure that the AI / ML model corresponding to the AI ​​feature operates normally under the communication environment (such as channel conditions). The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. For example, assuming the first AI feature is an AI beam management feature, the first configuration information may include a first network parameter configuration and first auxiliary information. The first network parameter configuration may be a CSI report configuration (CSI-reportconfig), etc., and the first auxiliary information may represent the downtilt angle of the base station beam, etc.

[0034] In some examples, there can be multiple types of first configuration information, each of which can be adapted to an AI / ML model corresponding to a first AI feature. For example, assuming the first AI feature is an AI beam management feature, the first AI feature corresponds to first configuration information 1 and first configuration information 2. First configuration information 1 can be adapted to an AI / ML model that performs inference through 32 beam scan results, and first configuration information 2 can be adapted to an AI / ML model that performs inference through 16 beam scan results. This allows the first communication device to select the appropriate first configuration information for matching based on the AI / ML model corresponding to its own first AI feature.

[0035] In some examples, the content indicated by the sixth message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can confirm the applicability of the first AI feature based on the preset conditions and obtain the content indicated by the sixth message, enabling the second communication device to obtain the applicability of the first AI feature based on the sixth message, improving the accuracy of the applicability of the first AI feature, and thereby improving the reliability of inter-device communication.

[0036] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0037] As an example, when the first communication device meets the preset conditions, the sixth message indicates that the first AI feature is not applicable; when the first communication device does not meet the preset conditions, the sixth message indicates that the first AI feature is not applicable.

[0038] In one possible design, the sixth message indicates that the first AI feature is applicable. The method further includes: receiving a second message from the second communication device; and sending a third message to the second communication device, the third message indicating that the first AI feature matches the first configuration information. Thus, the first communication device can receive the second message from the second communication device when the first AI feature is applicable, but cannot receive the second message from the second communication device when the first AI feature is not applicable, thereby reducing signaling overhead between devices when the first AI feature is not applicable.

[0039] Thirdly, a communication method is provided, which can be executed by a second communication device, a component of the second communication device (e.g., a processor, chip, or chip system), or a logic node, logic module, or software capable of implementing all or part of the functions of the second communication device. The method includes: receiving a first message from a first communication device, the first message indicating that the applicability of a first AI feature included in the first communication device is consistent with the applicability of a second AI feature; sending a second message to the first communication device, the second message indicating first configuration information related to the first AI feature; receiving a third message from the first communication device, the third message indicating whether the first AI feature matches or does not match the first configuration information; and abandoning the determination of the activation state of the second AI feature when the third message indicates that the first AI feature does not match the first configuration information.

[0040] The solution provided in the third aspect above allows the second communication device to indirectly determine the applicability of the first AI feature based on the third message after receiving a first message indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and a third message indicating whether the first AI feature matches or does not match the configuration information set. It can also determine the applicability of the second AI feature based on the first message and the applicability of the first AI feature. Thus, when the first AI feature does not match the first configuration information, the second communication device can determine that the second AI feature is not applicable and abandon the determination of the activation state of the second AI feature, saving signaling overhead between devices.

[0041] In some examples, the first communication device can be a terminal device, and the second communication device can be a network device (such as a base station, network element, etc.).

[0042] In some examples, taking the first AI feature as an example, the applicability of the first AI feature can be understood as the resources of the first communication device itself (such as power, computing power, storage resources, etc., one or more) can support the normal operation of the AI / ML model corresponding to the first AI feature. That is, the first AI feature is compatible with the resources of the first communication device itself. The determination of the second communication device to determine the activation state of the first AI feature and / or the second AI feature can be understood as determining whether the first AI feature or the second AI feature is in an active state (i.e., whether the first AI feature or the second AI feature can be activated). Whether the first AI feature can be activated can be considered from the following two points: 1. The first AI feature is applicable; 2. The first AI feature matches the first configuration information included in the second communication device, that is, when the second communication device is configured according to the first configuration information, the AI / ML model corresponding to the first AI feature can run normally. When the first AI feature is not applicable, the AI / ML model corresponding to the first AI feature cannot run normally regardless of how the second communication device is configured. In other words, the first AI feature does not match the first configuration information. Therefore, when the third message indicates that the first AI feature matches the first configuration information, it can indirectly indicate that the first AI feature is applicable; when the third message indicates that the first AI feature does not match the first configuration information, it can indirectly indicate that the first AI feature is not applicable.

[0043] In some examples, the second communication device can set corresponding configuration information for different AI features. This configuration information can be used to ensure that the AI / ML model for the corresponding AI feature operates normally under the communication environment (such as channel quality). The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. For example, assuming the first AI feature is an AI beam management feature, the first configuration information may include a first network parameter configuration and first auxiliary information. The first network parameter configuration may be a CSI report configuration (CSI-reportconfig), etc., and the first auxiliary information may represent the downtilt angle of the base station beam, etc.

[0044] In some examples, there can be multiple types of first configuration information, each of which can be adapted to an AI / ML model corresponding to a first AI feature. For example, assuming the first AI feature is an AI beam management feature, the first AI feature corresponds to first configuration information 1 and first configuration information 2. First configuration information 1 can be adapted to an AI / ML model that performs inference through 32 beam scan results, and first configuration information 2 can be adapted to an AI / ML model that performs inference through 16 beam scan results. This allows the first communication device to select the appropriate first configuration information for matching based on the AI / ML model corresponding to its own first AI feature.

[0045] In some examples, the applicability relationship between AI features can be related to the relationship between the AI / ML models corresponding to the AI ​​features. For example, if multiple AI features can share an AI / ML model, then the applicability of the above multiple AI features can be consistent. Or, if the AI / ML models corresponding to multiple AI features have a successor relationship, then the applicability of the above multiple AI features can be consistent, that is, the input of the AI / ML model corresponding to one AI feature can be the output of the AI / ML model corresponding to another AI feature.

[0046] In some examples, the first message may indicate that the first AI feature and the second AI feature belong to the first AI set, and the applicability of AI features in the first AI set is consistent; or, the first message may indicate that the applicability of the first AI feature is consistent with the applicability of the second AI feature in the second AI set, and the first AI feature does not belong to the second AI set. Thus, by considering the correlation between the applicability of the first AI feature and the second AI feature under different AI set distributions, the diversity and accuracy of the correlation between the applicability of the first AI feature and the second AI feature can be improved.

[0047] In some examples, the first AI set can be represented as "{first AI feature, second AI feature}". Consistent applicability of AI features within the first AI set can mean that if the first AI feature is applicable, the second AI feature is also applicable, and vice versa. For example, suppose the first AI feature is the AI ​​reference signal receiving power (RSRP) prediction feature, and the second AI feature is the AI ​​signal to interference plus noise ratio (SINR) prediction feature. Since the AI ​​RSRP prediction feature and the AI ​​SINR prediction feature can share the same AI / ML model, if either the first AI feature or the second AI feature is applicable, the other AI feature is also applicable.

[0048] In some examples, the first AI feature and the second AI set can be represented as "first AI feature : {second AI feature}". The applicability of the first AI feature being consistent with the applicability of the second AI feature in the second AI set indicates that when the first AI feature is applicable, the second AI feature is also applicable. However, when the second AI feature is applicable, the first AI feature may not necessarily be applicable. For example, suppose the first AI feature is an AI channel state information (CSI) estimation feature, and the second AI feature is an AI CSI prediction feature. The input to AI CSI estimation can be the output of the AI / ML model corresponding to AI CSI prediction. In this case, when the first AI feature is applicable, the second AI feature is also applicable; however, when the second AI feature is applicable, the first AI feature may not necessarily be applicable.

[0049] In some examples, the first AI set and / or the second AI set may also have other AI features, such as a third AI feature, etc., which are not limited here.

[0050] In some examples, the first communication device may also include other AI sets, each of which may correspond to an identity document (ID). For example, the first communication device may also include a third AI set, which may include a fourth AI feature and a fifth AI feature. Or, the first communication device may also include a fourth AI set and a sixth AI feature, where the fourth AI set may include a seventh AI feature, and the sixth AI feature does not belong to the fourth AI set. This application does not limit the scope of the application.

[0051] In some examples, the first message is sent when the first communication device is in a connected state. This ensures that the first communication device sends the first message to the second communication device only when it is connected, thus improving the accuracy of the first message.

[0052] In some examples, the content indicated by the third message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can determine whether the first AI feature matches the first configuration information based on the preset conditions and obtain the content indicated by the third message. This allows the second communication device to indirectly confirm the applicability of the first AI feature based on the third message, improving the accuracy of the applicability of the first AI feature and thereby enhancing the reliability of inter-device communication.

[0053] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0054] In one possible design, the method further includes: when a third message indicates that the first AI feature matches the first configuration information, sending an eighth message to the first communication device, the eighth message indicating second configuration information related to the second AI feature; and receiving a ninth message from the first communication device, the ninth message indicating that the second AI feature matches the second configuration information. In this way, the second communication device can determine the activation state of the second AI feature only when it determines that the first AI feature is applicable based on the third message, saving signaling overhead between devices.

[0055] In one possible design, before receiving the first message from the first communication device, the method further includes sending a fourth message to the first communication device. This fourth message is used to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature. Thus, the second communication device can obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature through the fourth message, and can determine whether to determine the activation state of the first AI feature and / or the second AI feature based on the first message, which helps improve the accuracy of the second communication device's decision-making.

[0056] In some examples, the relationship between the applicability of the first AI feature and the applicability of the second AI feature may include, but is not limited to, an association relationship, which can be understood as the applicability of the first AI feature being consistent with the applicability of the second AI feature.

[0057] In one possible design, before sending the second message to the first communication device, the method further includes: sending a fifth message to the first communication device, the fifth message being used to obtain the applicability of the first AI feature; receiving a sixth message from the first communication device, the sixth message indicating whether the first AI feature is applicable or not; the aforementioned sending the second message to the first communication device includes: sending the second message to the first communication device when the sixth message indicates that the first AI feature is applicable. Thus, the second communication device can proactively obtain the applicability of the first AI feature by sending the fifth message, and only sends the second message to the first communication device when the first AI feature is applicable, saving signaling overhead between devices.

[0058] In one possible design, the method further includes: abandoning the transmission of the second message to the first communication device when the sixth message indicates that the first AI feature is not applicable. Thus, the second communication device can proactively determine the applicability of the first AI feature by sending a fifth message. When the first AI feature is not applicable, the second communication device can abandon the transmission of the second message to the first communication device, saving signaling overhead between devices.

[0059] In some examples, the content indicated by the sixth message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can confirm the applicability of the first AI feature based on the preset conditions and obtain the content indicated by the sixth message, enabling the second communication device to obtain the applicability of the first AI feature based on the sixth message, improving the accuracy of the applicability of the first AI feature, and thereby improving the reliability of inter-device communication.

[0060] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0061] In one possible design, after receiving the first message from the first communication device, the method further includes: receiving a seventh message from the first communication device, the seventh message indicating that the relationship between the applicability of the first AI feature and the applicability of the second AI feature is invalid; and switching the strategy for determining the activation state of the AI ​​feature. Thus, the second communication device can promptly adjust the strategy for determining the activation state of the AI ​​feature after receiving the seventh message, thereby improving communication reliability.

[0062] In one possible design, the strategy for determining the activation state of the aforementioned AI feature includes: switching the strategy for determining the activation state of the AI ​​feature to: determining the activation state of the first AI feature and the second AI feature one by one. In this way, the second communication device can determine the activation state of the first AI feature and the second AI feature one by one, improving the accuracy of determining the activation state of the first AI feature and the second AI feature when the applicability relationship between the first AI feature and the second AI feature fails.

[0063] In some examples, when there is a correlation between the applicability of the first AI feature and the applicability of the second AI feature (i.e., the applicability of the first AI feature and the applicability of the second AI feature are consistent), the strategy for determining the activation state of the AI ​​feature can be: the second communication device determines the applicability of the first AI feature through a third message, and determines whether to determine the activation state of the second AI feature based on the first message and the applicability of the first AI feature (hereinafter referred to as "Strategy 1"); when the relationship between the applicability of the first AI feature and the applicability of the second AI feature fails, the strategy for determining the activation state of the AI ​​feature can be: a second determination strategy, which can be that the second communication device determines the activation state of the first AI feature and the second AI feature one by one (hereinafter referred to as "Strategy 2"). When the applicability relationship between the first AI feature and the second AI feature changes from the applicability of the first AI feature being consistent with that of the second AI feature to the applicability of the first AI feature being invalid, the strategy for determining the activation state of the AI ​​feature can be changed from strategy 1 to strategy 2; when the applicability relationship between the first AI feature and the second AI feature changes from the applicability of the first AI feature being invalid to the applicability of the first AI feature being consistent with that of the second AI feature, the strategy for determining the activation state of the AI ​​feature can be changed from strategy 2 to strategy 1.

[0064] In one possible design, the method further includes: when the first AI feature is not applicable, sending a tenth message to the first communication device, the tenth message instructing the first communication device to activate the first AI feature and the second AI feature. Thus, the second communication device can instruct the first communication device to activate both the first AI feature and the second AI feature, which is compatible with the first AI feature, when the first AI feature is not applicable, saving signaling overhead between devices for deactivating the second AI feature.

[0065] Fourthly, a communication method is provided. This method can be executed by a second communication device, by a component of the second communication device (e.g., a processor, chip, or chip system), or by a logic node, logic module, or software capable of implementing all or part of the functions of the second communication device. The method includes: sending a fifth message to a first communication device, the fifth message being used to obtain the applicability of a first AI feature included in the first communication device; receiving a sixth message from the first communication device, the sixth message indicating whether the first AI feature is applicable or not; and when the sixth message indicates that the first AI feature is not applicable, abandoning the sending of a second message to the first communication device, the second message indicating first configuration information related to the first AI feature.

[0066] The solution provided in the fourth aspect above allows the second communication device to obtain the applicability of the first AI feature by sending a fifth message to the first communication device. If the first AI feature is not applicable, the second communication device will not send a second message to the first communication device, thus saving the signaling overhead between devices for determining the activation status of the first AI feature.

[0067] In some examples, the first communication device can be a terminal device, and the second communication device can be a network device (such as a base station, network element, etc.).

[0068] In some examples, taking the first AI feature as an example, the applicability of the first AI feature can be understood as the resources of the first communication device itself (such as power, computing power, storage resources, etc., one or more) being able to support the normal operation of the AI / ML model corresponding to the first AI feature. In other words, the first AI feature is compatible with the resources of the first communication device itself. The determination by the second communication device to determine the activation state of the first AI feature and / or the second AI feature can be understood as determining whether the first AI feature or the second AI feature is in an active state (i.e., whether the first AI feature or the second AI feature can be activated). Whether the first AI feature can be activated can be considered from the following two points: 1. The first AI feature is applicable; 2. The first AI feature matches the first configuration information included in the second communication device, that is, when the second communication device is configured according to the first configuration information, the AI / ML model corresponding to the first AI feature can run normally. Therefore, the first communication device first sends a sixth message to the second communication device to enable the second communication device to obtain the applicability of the first AI feature. This allows the second communication device to determine whether to send the first configuration information related to the first AI feature. If the first AI feature is not applicable, the signaling overhead corresponding to the second message can be reduced.

[0069] In some examples, the second communication device can set corresponding configuration information for different AI features. This configuration information can be used to ensure that the AI / ML model for the corresponding AI feature operates normally under the communication environment (such as channel quality). The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. For example, assuming the first AI feature is an AI beam management feature, the first configuration information may include a first network parameter configuration and first auxiliary information. The first network parameter configuration may be a CSI report configuration (CSI-reportconfig), etc., and the first auxiliary information may represent the downtilt angle of the base station beam, etc.

[0070] In some examples, there can be multiple types of first configuration information, each of which can be adapted to an AI / ML model corresponding to a first AI feature. For example, assuming the first AI feature is an AI beam management feature, the first AI feature corresponds to first configuration information 1 and first configuration information 2. First configuration information 1 can be adapted to an AI / ML model that performs inference through 32 beam scan results, and first configuration information 2 can be adapted to an AI / ML model that performs inference through 16 beam scan results. This allows the first communication device to select the appropriate first configuration information for matching based on the AI / ML model corresponding to its own first AI feature.

[0071] In some examples, the content indicated by the sixth message may be related to whether the first communication device meets preset conditions. Thus, the first communication device can confirm the applicability of the first AI feature based on the preset conditions and obtain the content indicated by the sixth message, enabling the second communication device to obtain the applicability of the first AI feature based on the sixth message, improving the accuracy of the applicability of the first AI feature, and thereby improving the reliability of inter-device communication.

[0072] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0073] In one possible design, the method further includes sending a second message to the first communication device when the sixth message indicates that the first AI feature is applicable. In this way, the second communication device only sends the second message to the first communication device when the first AI feature is applicable, saving the signaling overhead between devices used to determine the activation state of the first AI feature.

[0074] Fifthly, a communication system is provided, comprising: a first communication device, configured to: send a first message to a second communication device, the first message indicating that the applicability of a first AI feature is consistent with the applicability of a second AI feature, the first message being used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature; a second communication device, configured to: receive the first message from the first communication device, and send a second message to the first communication device, the second message indicating first configuration information related to the first AI feature; the first communication device, configured to: send a third message to the second communication device, the second message indicating the first configuration information related to the first AI feature, the third message indicating whether the first AI feature matches or does not match the first configuration information; receive a third message from the first communication device, and when the third message indicates that the first AI feature does not match the first configuration information, abandon the determination of the activation state of the second AI feature.

[0075] A sixth aspect provides a communication system comprising: a second communication device configured to: send a fifth message to a first communication device, the fifth message being used to obtain the applicability of a first AI feature included in the first communication device; the first communication device configured to: receive the fifth message from the second communication device and send a sixth message to the second communication device, the sixth message indicating whether the first AI feature is applicable or not, the sixth message being used by the second communication device to determine whether to send a second message, the second message indicating first configuration information related to the first AI feature; and the second communication device configured to: receive the sixth message from the first communication device; and abandon sending the second message to the first communication device when the sixth message indicates that the first AI feature is not applicable.

[0076] A seventh aspect provides a communication apparatus. The communication apparatus includes a module for performing the communication method described in any one of the first, second, third, or fourth aspects.

[0077] It should be understood that the communication apparatus described in the seventh aspect includes modules, units, or means that implement the communication methods described in any of the first, second, third, or fourth aspects above. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units for performing the functions involved in the aforementioned communication methods.

[0078] Eighthly, a communication apparatus is provided. The communication apparatus includes a processor configured to execute computer instructions to perform the communication method described in any possible implementation of the first, second, third, or fourth aspect.

[0079] In one possible design, the communication device described in the eighth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the eighth aspect and other communication devices.

[0080] In one possible design, the communication device described in aspect eight may further include a memory. This memory may be integrated with the processor or disposed separately. The memory may be used to store computer instructions.

[0081] A ninth aspect provides a communication apparatus. The communication apparatus includes: a processor and an interface circuit, the interface circuit being configured to receive computer instructions and transmit them to the processor, the processor being configured to execute the computer instructions to perform the communication method as described in any possible implementation of the first, second, third, or fourth aspect.

[0082] In one possible design, the communication device described in the ninth aspect may further include a memory. This memory is used to store computer instructions.

[0083] A tenth aspect provides a communication apparatus, comprising: a processor and a memory; the memory for storing computer instructions, and the processor for executing the computer instructions to perform the communication method as described in any one of the first, second, third, or fourth aspects.

[0084] In one possible design, the communication device described in the tenth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the tenth aspect and other communication devices.

[0085] Eleventhly, a communication device is provided, comprising: a processor and a transceiver; the transceiver is used for information exchange between the communication device and other communication devices, and the processor is used to execute computer instructions to perform the communication method as described in any one of the first, second, third, or fourth aspects.

[0086] In one possible design, the communication device described in aspect eleven may further include a memory. This memory is used to store computer instructions.

[0087] In this application, the communication device described in any one of the seventh to eleventh aspects can be a terminal device or a network device, or a chip (system) or other component or assembly, or a device containing the terminal device or the network device. The aforementioned chip (system) or other component or assembly can all be disposed within the terminal device or the network device.

[0088] In a twelfth aspect, a processor is provided, wherein the processor is configured to execute the communication method described in any possible implementation of the first, second, third, or fourth aspect.

[0089] In a thirteenth aspect, a communication system is provided, comprising a first communication device for performing the method as described in the first aspect, and a second communication device for performing the method as described in the third aspect.

[0090] In a fourteenth aspect, a communication system is provided, wherein the communication system includes a first communication device for performing the method as described in the second aspect, and a second communication device for performing the method as described in the fourth aspect.

[0091] In a fifteenth aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a communication device, the communication device causes the communication device to perform the communication method described in any possible implementation of the first aspect, the second aspect, the third aspect, or the fourth aspect.

[0092] In a sixteenth aspect, a computer program product is provided, comprising a computer program or instructions that, when executed on a communication device, cause the communication device to perform the communication method described in any one of the possible implementations of the first, second, third, or fourth aspects.

[0093] Furthermore, the technical effects of the communication devices described in the seventh to eleventh aspects above can be referred to the technical effects of the communication methods described in the first, second, third, or fourth aspects above, and will not be repeated here. Attached Figure Description

[0094] Figure 1 is a flowchart of an AI feature activation process;

[0095] Figure 2 is a flowchart of another AI feature activation process;

[0096] Figure 3 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0097] Figure 4 is a schematic diagram of a communication scenario provided in an embodiment of this application;

[0098] Figure 5 is a flowchart of a communication method provided in an embodiment of this application;

[0099] Figure 6 is a flowchart of a design scheme provided in an embodiment of this application;

[0100] Figure 7 is a flowchart of another design scheme provided in the embodiment of this application;

[0101] Figure 8 is a flowchart of another design scheme provided in the embodiment of this application;

[0102] Figure 9 is a flowchart of another communication method provided in an embodiment of this application;

[0103] Figure 10 is a structural block diagram of a communication device provided in an embodiment of this application;

[0104] Figure 11 is a schematic diagram of the hardware structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0105] With the continuous development of AI / ML technology, it is increasingly being applied in communication systems, enabling devices within these systems to possess AI characteristics. This means that devices can perform related functions through AI / ML technology. For example, if a terminal device has AI beam management (BM) capabilities, it means that the terminal device has the ability to implement beam management functions using AI / ML technology. The implementation of AI characteristics can rely on corresponding AI / ML models. For instance, communication systems can use AI / ML models to implement functions such as beam management and positioning.

[0106] Taking BM based on AI / ML technology in a new radio (NR) communication system as an example, the NR communication system can use AI / ML technology to infer the scanning results of some beams and obtain the preferred beam. In contrast, traditional BM technology (i.e., BM technology without AI / ML technology) needs to scan all candidate beams. Therefore, BM based on AI / ML technology can obtain the preferred beam for communication with less beam scanning cost, thus saving overhead.

[0107] Taking AI / ML-based positioning in NR communication systems as an example, NR communication systems can use AI / ML technology to infer the measured channel information to obtain more accurate location information than traditional positioning technologies (i.e., positioning technologies not based on AI / ML technology). For example, channel information may include, but is not limited to, power information, phase information, time delay information, distance information, velocity information, channel scattering information, and non-line-of-sight (NLOS) information.

[0108] In the examples above, the implementation of AI / ML technology typically relies on AI / ML models. For instance, when a communication system needs to compress CSI based on AI / ML technology, both the network device and the terminal device in the communication system can each deploy an AI / ML model. The AI / ML model corresponding to the terminal device can be used to infer the original CSI to compress it, while the AI / ML model corresponding to the network device can be used to infer the compressed CSI to restore it. As another example, when a communication system needs to implement BM or positioning based on AI / ML technology, either the network device or the terminal device in the communication system can deploy an AI / ML model. By deploying an AI / ML model on one side, the entire inference process corresponding to BM or positioning can be completed.

[0109] In some embodiments, before using an AI / ML model to implement related functions, the communication system usually needs to confirm whether the AI ​​features corresponding to the AI / ML model can be activated. When the corresponding AI features are activated, the AI / ML model can run normally.

[0110] In some examples, taking the activation of AI features on a terminal device as an example, the following points can be considered when determining whether the AI ​​features of a terminal device can be activated:

[0111] 1. The compatibility between the network device's configuration information and the AI ​​model / supported functionality corresponding to the AI ​​features. For example, the configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. The network parameter configuration can be used to match the corresponding AI features. The network parameter configuration may include RRC configuration information, private configuration information (such as TX beam pattern), etc. The auxiliary information may represent some privacy information of the network device. For example, the auxiliary information may implicitly express the downtilt angle of the network device's beam.

[0112] 2. The adaptability of AI models / functions corresponding to AI characteristics to the communication environment (such as channel conditions).

[0113] 3. The compatibility between the AI ​​model / function corresponding to the AI ​​characteristics and the terminal device's own resources (such as remaining power, storage resources, computing power resources, etc.).

[0114] Network devices can confirm the first two points through relevant methods, but for the third point, network devices still need to interact with terminal devices to obtain confirmation results. In other words, network devices need to interact with terminal devices to confirm whether the AI ​​features of the terminal devices can be activated.

[0115] For example, taking BM based on AI / ML technology as an example, the activation process of the AI ​​beam management feature in the communication system can be shown in Figure 1. The network device of the communication system in Figure 1 can be a base station. The base station can send an AI feature acquisition request to the terminal device through step S101. After receiving the AI ​​feature acquisition request, the terminal device can send AI feature feedback information to the base station through step S102. For example, the AI ​​feature feedback information may include AI beam management features. Then, the base station can send the configuration information corresponding to the AI ​​beam management feature to the terminal device through step S103. The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary configuration. Auxiliary information, such as network parameter configuration (e.g., CSI report configuration), can be provided, and the auxiliary information can implicitly express the downtilt angle of the base station beam. Next, when the terminal device confirms that the configuration information matches the AI ​​beam management feature, the terminal device can send configuration feedback information to the base station in step S104. This configuration feedback information can be the network parameter configuration that the terminal device confirms from the received network parameter configuration, based on the auxiliary information and its own resources, is compatible with its own AI beam management feature. Then, the base station can send information to the terminal device in step S105 instructing the terminal device to activate the AI ​​beam management feature.

[0116] For example, taking AI / ML-based positioning as an example, the activation process of AI positioning features in a communication system can be shown in Figure 2. The network device in the communication system in Figure 2 can be a location management function (LMF) network element. The LMF network element can send an AI feature acquisition request to the terminal device in step S201. After receiving the AI ​​feature acquisition request, the terminal device can send AI feature feedback information to the LMF network element in step S202. For example, the AI ​​feature feedback information may include AI positioning features. Then, the LMF network element can send configuration information corresponding to the AI ​​positioning features to the terminal device in step S203. The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. For example, the network parameter configuration may be a positioning reference signal. The auxiliary information can be some privacy information of the LMF network element, such as signal (PRS) configuration. Then, when the terminal device confirms that the configuration information matches the AI ​​positioning feature, the terminal device can send configuration feedback information to the LMF network element through step S204. The configuration feedback information can be the network parameter configuration that the terminal device confirms from the received network parameter configuration that is compatible with its own AI positioning feature based on the auxiliary information and its own resources. Then, the LMF network element can send information to the terminal device through step S205 to instruct the terminal device to activate the AI ​​positioning feature.

[0117] As can be seen from the examples shown in Figures 1 and 2, network devices need to confirm whether AI features can be activated one by one. As the number of AI / ML models involved in the communication system increases, the task of confirming whether the AI ​​features of the communication system can be activated increases significantly, resulting in a large amount of signaling overhead.

[0118] To address this, this application provides a communication method comprising: a first communication device sending a first message to a second communication device, the first message indicating that the applicability of a first AI feature is consistent with the applicability of a second AI feature, the first message being used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature; upon receiving a second message from the second communication device, the first communication device sending a third message to the second communication device, the second message indicating first configuration information related to the first AI feature, the third message indicating whether the first AI feature matches or does not match the first configuration information. Through this method, by sending a first message indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and sending a third message indicating whether the first AI feature matches or does not match the configuration information set after receiving the second message, the first communication device can indirectly determine the applicability of the first AI feature based on the third message, and determine whether the second AI feature is applicable based on the first and third messages. Therefore, when the second communication device determines that the second AI feature is not applicable, it abandons the determination of the activation state of the second AI feature, saving signaling overhead between devices.

[0119] For example, Figure 3 is a schematic diagram of the architecture of a communication system 3000 provided in an embodiment of this application. As shown in Figure 3, the communication system 3000 includes a first communication device and a second communication device. The first communication device may be a terminal device as shown in Figure 3 (120a-120j in Figure 3, collectively referred to as 120), and the second communication device may be a network device as shown in Figure 3 (110a and 110b in Figure 3, collectively referred to as 110). It may also include at least one terminal device (120a-120j in Figure 3, collectively referred to as 120). The communication system 3000 may also include other devices, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 3). The terminal device 120 is wirelessly connected to the base station 110. Terminal devices and network devices can be interconnected via wired or wireless means.

[0120] In one application scenario, network equipment can be a base station (BS), an evolved NodeB (eNodeB / eNB), a next-generation eNodeB (ng-eNB), a transmission reception point (TRP), a generation NodeB (gNB) in a 5th generation (5G) mobile communication system, a future base station in a future communication network, or a base station in a future mobile communication system. Network equipment can be a macro base station (as shown in Figure 3, 110a), a micro base station or an indoor station (as shown in Figure 3, 110b), or a relay node or master node.

[0121] In another application scenario, multiple network devices can collaborate to help terminal devices achieve wireless access, with different network devices each implementing a portion of the base station's functions. For example, network devices can be central units (CUs), distributed units (DUs), or radio units (RUs). An RU can also be called a radio frequency unit. Here, the CU performs the functions of the base station's radio resource control protocol and packet data convergence protocol (PDCP), and can also perform the functions of the service data adaptation protocol (SDAP). The DU performs the functions of the base station's radio link control layer and medium access control (MAC) layer, and can also perform some or all of the physical layer functions. For specific descriptions of these protocol layers, refer to the relevant 3GPP technical specifications. The RU can be used to implement radio frequency signal transmission and reception. The CU and DU can be two independent network devices, or they can be integrated into the same network device, such as within a baseband unit (BBU). RUs can be included in radio frequency equipment, such as remote radio units (RRUs) or active antenna units (AAUs). CUs can be further divided into two types of radio access network equipment: CU-control plane and CU-user plane. In different systems, network equipment may have different names. For example, in an open radio access network (O-RAN) system, a CU can be called an open CU (O-CU), a DU can be called an open DU (O-DU), and an RU can be called an open RU (O-RU).

[0122] The network devices in the embodiments of this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules. For example, a network device can be a server loaded with corresponding software modules. The embodiments of this application do not limit the specific technology or device form used in the network devices. For ease of description, a base station is used as an example of a network device in the following description.

[0123] Terminal equipment is a device with wireless transceiver capabilities, capable of sending signals to or receiving signals from a base station. It can also be called a terminal, user equipment (UE), mobile station, or mobile terminal device. Terminal equipment can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, intelligent transportation, and smart cities. Terminal devices can be mobile phones, cellular phones, smartphones, tablets, wireless data cards, personal digital assistants (PDAs), wireless modems, handsets, laptop computers, machine-type communication (MTC) terminal devices, computers with wireless transceiver capabilities, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, smart home devices (e.g., refrigerators, televisions, air conditioners, electricity meters, etc.), intelligent robots, robotic arms, workshop equipment, wireless terminal devices in autonomous driving, wireless terminal devices in industrial control, wireless terminal devices in self-driving, wireless terminal devices in remote medical care, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, and smart homes. Wireless terminal devices (such as those in the home), vehicle-mounted terminal devices, roadside units (RSUs) with terminal device functions, and flying equipment (such as intelligent robots, hot air balloons, drones, and airplanes) are all examples of such devices. The terminal devices in this application can also be vehicle-mounted modules, vehicle-mounted components, vehicle-mounted chips, or vehicle-mounted units that are built into a vehicle as one or more components or units.The terminal device can also be other devices with terminal device functions. For example, the terminal device can also be a device that performs the terminal device function in D2D communication.

[0124] The embodiments of this application do not limit the form of the terminal device. The device used to implement the function of the terminal device can be the terminal device itself; it can also be a device that supports the terminal device in implementing the function, such as a chip system. The device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of this application, the chip system can be composed of chips or can include chips and other discrete components.

[0125] Base stations and terminal equipment can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the base stations and terminal equipment.

[0126] The roles of base stations and terminal devices can be relative. For example, the helicopter or drone 120i in Figure 3 can be configured as a mobile base station. For terminal devices 120j that access the wireless access network 100 through 120i, terminal device 120i is a base station; however, for base station 110a, 120i is a terminal device, meaning that 110a and 120i communicate via a wireless air interface protocol. Of course, 110a and 120i can also communicate via a base station-to-base station interface protocol. In this case, relative to 110a, 120i is also a base station. Therefore, both base stations and terminal devices can be collectively referred to as communication devices. 110a and 110b in Figure 3 can be called communication devices with base station functions, and 120a-120j in Figure 3 can be called communication devices with terminal device functions.

[0127] Communication between base stations and terminal devices, between base stations, and between terminal devices can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0128] In the embodiments of this application, the functions of the base station can be executed by modules (such as chips) within the base station, or by a control subsystem that includes base station functions. This control subsystem, including base station functions, can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of the terminal device can be executed by modules (such as chips or modems) within the terminal device, or by a device that includes terminal device functions.

[0129] A wireless communication system includes multiple communication devices that can communicate wirelessly using air interface resources. These communication devices may include network devices and terminal devices, and network devices may include, but are not limited to, the base stations mentioned above. Air interface resources may include at least one of time-domain resources, frequency-domain resources, code resources, and spatial resources. These communication devices may also be referred to as communication apparatuses.

[0130] The solutions provided in this application can be applied to wireless communication between communication devices. Wireless communication can include: wireless communication between a network-side device and a terminal-side device, wireless communication between two network-side devices, and wireless communication between two terminal devices. In this application, the term "wireless communication" can also be simply referred to as "communication," and the term "communication" can also be described as "data transmission," "information transmission," or "transmission."

[0131] It should be understood that the embodiments of this application exemplarily provide the names of nodes, modules, devices or network elements in different scenarios, architectures or systems, as well as the names of the communication interfaces between any two nodes, modules, devices or network elements, and do not exclude the possibility of name changes in future communication systems or scenarios or architectures.

[0132] For example, Figure 4 is a schematic diagram of a communication scenario provided by an embodiment of this application.

[0133] As shown in Figure 4, Figure 4 may include terminal device 410 and network device 420.

[0134] In some embodiments, terminal device 410 may send a first message to network device 420; network device 420 may receive the first message from terminal device 410 and send a second message to terminal device 410; terminal device 410 may send a third message to network device 420; network device 420 may receive the third message from terminal device 410, and when the third message indicates that the first AI feature does not match the first configuration information, it may abandon the determination of the activation state of the second AI feature.

[0135] In some examples, the first message may indicate that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and the first message is used by the network device 420 to determine whether to determine the activation status of the first AI feature and / or the second AI feature.

[0136] In some examples, the second message may indicate first configuration information related to the first AI feature.

[0137] In some examples, a third message may indicate whether the first AI feature matches or does not match the first configuration information.

[0138] In some embodiments, network device 420 may send a fifth message to terminal device 410; terminal device 410 may receive the fifth message from network device 420 and send a sixth message to network device 420; network device 420 may receive the sixth message from terminal device 410 and, when the sixth message indicates that the first AI feature is not applicable, abandon sending a second message to network device 420.

[0139] In some examples, the fifth message can be used to determine the applicability of the first AI features included in the terminal device 410.

[0140] In some examples, the sixth message can indicate whether the first AI feature is applicable or not.

[0141] The interaction process between devices in the above-mentioned communication system will be specifically described below with reference to Figures 5, 6, 7, 8, and 9 through method embodiments. The communication method provided in this application embodiment can be applied to, but is not limited to, the communication scenarios shown in Figures 3 and 4. This communication method can be applied to LTE, LTE frequency division duplex (FDD) systems, LTE TDD, 5G systems or NR systems, subsequent evolving communication systems (such as future communication systems), V2X, where V2X can include vehicle to network (V2N), vehicle to vehicle (V2V), vehicle to infrastructure (V2I), vehicle to pedestrian (V2P), long term evolution-vehicle (LTE-V), vehicle-to-everything (V2X), MTC, IoT, long term evolution-machine (LTE-M), machine to machine (M2M), D2D and other wireless communication scenarios. The following embodiments of this application will be described using the example of a second communication device sending a first message to a first communication device. The first communication device involved in the embodiments of this application may be a terminal device, and the second communication device may be a network device (such as a base station). This application does not limit this.

[0142] For example, Figure 5 is a flowchart of a communication method provided in an embodiment of this application. As shown in Figure 5, the communication method includes the following steps:

[0143] S501, The first communication device sends a first message to the second communication device.

[0144] Accordingly, the second communication device receives the first message.

[0145] In some examples, the first message may indicate that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and the first message may be used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature.

[0146] In some examples, taking the first AI feature as an example, the applicability of the first AI feature can be understood as the resources of the first communication device itself (such as power, computing power, storage resources, etc., one or more) can support the normal operation of the AI / ML model corresponding to the first AI feature. That is, the first AI feature is compatible with the resources of the first communication device itself. The determination of the second communication device to determine the activation state of the first AI feature and / or the second AI feature can be understood as determining whether the first AI feature or the second AI feature is in an active state (i.e., whether the first AI feature or the second AI feature can be activated). Whether the first AI feature can be activated can be considered from the following two points: 1. The first AI feature is applicable; 2. The first AI feature matches the first configuration information included in the second communication device, that is, when the second communication device is configured according to the first configuration information, the AI / ML model corresponding to the first AI feature can run normally. When the first AI feature is not applicable, the AI / ML model corresponding to the first AI feature cannot run normally regardless of how the second communication device is configured. In other words, the first AI feature does not match the first configuration information. Therefore, when the third message indicates that the first AI feature matches the first configuration information, it can indirectly indicate that the first AI feature is applicable; when the third message indicates that the first AI feature does not match the first configuration information, it can indirectly indicate that the first AI feature is not applicable.

[0147] In some examples, the second communication device can set corresponding configuration information for different AI features. This configuration information can be used to ensure that the AI / ML model corresponding to the AI ​​feature operates normally under the communication environment (such as channel quality). The configuration information may include, but is not limited to, network parameter configuration and / or auxiliary information. The network parameter configuration can be used to match the corresponding AI feature, and the auxiliary information can represent some privacy information of the base station. For example, the auxiliary information can implicitly express the downtilt angle of the base station beam. For instance, assuming the first AI feature is an AI beam management feature, the first configuration information may include a first network parameter configuration and first auxiliary information. The first network parameter configuration may be a CSI report configuration, and the first auxiliary information may represent the downtilt angle of the base station beam.

[0148] In some examples, there can be multiple types of first configuration information, each of which can be adapted to an AI / ML model corresponding to a first AI feature. For example, assuming the first AI feature is an AI beam management feature, the first AI feature corresponds to first configuration information 1 and first configuration information 2. First configuration information 1 can be adapted to an AI / ML model that performs inference through 32 beam scan results, and first configuration information 2 can be adapted to an AI / ML model that performs inference through 16 beam scan results. This allows the first communication device to select the appropriate first configuration information for matching based on the AI / ML model corresponding to its own first AI feature.

[0149] In some examples, the applicability relationship between AI features can be related to the relationship between the AI / ML models corresponding to the AI ​​features. For example, if multiple AI features can share an AI / ML model, then the applicability of the above multiple AI features can be consistent. Or, if the AI / ML models corresponding to multiple AI features have a successor relationship, then the applicability of the above multiple AI features can be consistent, that is, the input of the AI / ML model corresponding to one AI feature can be the output of the AI / ML model corresponding to another AI feature.

[0150] In some examples, the first message may indicate that the first AI feature and the second AI feature belong to the first AI set, and the applicability of AI features in the first AI set is consistent; or, the first message may indicate that the applicability of the first AI feature is consistent with the applicability of the second AI feature in the second AI set, and the first AI feature does not belong to the second AI set. Thus, by considering the correlation between the applicability of the first AI feature and the second AI feature under different AI set distributions, the diversity and accuracy of the correlation between the applicability of the first AI feature and the second AI feature can be improved.

[0151] In some examples, the first AI set can be represented as "{first AI feature, second AI feature}". Consistent applicability of AI features within the first AI set can mean that if the first AI feature is applicable, the second AI feature is also applicable, and vice versa. For example, suppose the first AI feature is the AI ​​reference signal receiving power (RSRP) prediction feature, and the second AI feature is the AI ​​signal to interference plus noise ratio (SINR) prediction feature. Since the AI ​​RSRP prediction feature and the AI ​​SINR prediction feature can share the same AI / ML model, if either the first AI feature or the second AI feature is applicable, the other AI feature is also applicable.

[0152] In some examples, the first AI feature and the second AI set can be represented as "first AI feature : {second AI feature}". The applicability of the first AI feature being consistent with the applicability of the second AI feature in the second AI set indicates that when the first AI feature is applicable, the second AI feature is also applicable. However, when the second AI feature is applicable, the first AI feature may not necessarily be applicable. For example, suppose the first AI feature is an AI channel state information (CSI) estimation feature, and the second AI feature is an AI CSI prediction feature. The input to AI CSI estimation can be the output of the AI / ML model corresponding to AI CSI prediction. In this case, when the first AI feature is applicable, the second AI feature is also applicable; however, when the second AI feature is applicable, the first AI feature may not necessarily be applicable.

[0153] In some examples, the first AI set and / or the second AI set may also have other AI features, such as a third AI feature, etc., which are not limited here.

[0154] In some examples, the first communication device may also include other AI sets, each of which may correspond to an identity document (ID). For example, the first communication device may also include a third AI set, which may include a fourth AI feature and a fifth AI feature. Or, the first communication device may also include a fourth AI set and a sixth AI feature, where the fourth AI set may include a seventh AI feature, and the sixth AI feature does not belong to the fourth AI set. This application does not limit the scope of the application.

[0155] In one possible implementation, the first communication device can actively send a first message to the second communication device.

[0156] In some examples, the first message may also indicate the applicability relationship between other AI features besides the first and second AI features, which is not limited herein. For example, the first message may also indicate a third AI set, a fourth AI set, etc.

[0157] In one possible implementation, before the first communication device sends the first message to the second communication device, the second communication device can send a fourth message to the first communication device through step S506, and the first communication device can send the first message to the second communication device after receiving the fourth message.

[0158] In some examples, the fourth message can be used to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature.

[0159] In some examples, the fourth message can also be used to obtain the applicability relationship between AI features other than the first and second AI features, which is not limited herein. For example, the fourth message can also be used to obtain the relationship between the applicability of the first AI feature and the applicability of the third AI feature, etc.

[0160] S502, the second communication device sends a second message to the first communication device.

[0161] Accordingly, the first communication device receives the second message.

[0162] In some examples, the second message may indicate first configuration information related to the first AI feature included in the second communication device.

[0163] In one possible implementation, the second communication device can determine the activation state of the first AI feature after receiving the first message, and then send a second message to the first communication device.

[0164] S503. When the first communication device receives the second message from the second communication device, it sends a third message to the second communication device.

[0165] Accordingly, the second communication device receives the third message.

[0166] In some examples, a third message can indicate whether the first AI feature matches or does not match the first configuration information. A mismatch between the first AI feature and the first configuration information may indicate that the first AI feature is not applicable, while a match between the first AI feature and the first configuration information may indicate that the first AI feature is applicable.

[0167] In one possible implementation, when the first communication device receives a second message from the second communication device, it can confirm whether it meets preset conditions, further determine the content indicated by the third message based on whether it meets the preset conditions, and then send the third message to the second communication device. In this way, the first communication device can confirm whether the first AI feature matches the first configuration information based on the preset conditions and obtain the content indicated by the third message. This allows the second communication device to indirectly confirm the applicability of the first AI feature based on the third message, improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0168] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0169] As an example, when the first communication device meets the preset conditions, the content indicated by the third message may be that the first AI feature does not match the first configuration information; when the first communication device does not meet the preset conditions, the content indicated by the third message may be that the first AI feature matches the first configuration information.

[0170] Optionally, when there are multiple types of first configuration information and the first communication device does not meet the preset conditions, the content indicated by the third message may also include the first configuration information that matches the first AI characteristic among the multiple types of first configuration information.

[0171] Optionally, the first communication device may not execute step S503 if it does not receive a second message from the second communication device.

[0172] S504a. When the third message indicates that the first AI feature does not match the first configuration information, the second communication device abandons the determination of the activation state of the second AI feature.

[0173] In one possible implementation, when the third message indicates that the first AI feature does not match the first configuration information, it can indicate that the second AI feature is not applicable. The second communication device can then abandon sending the eighth message to the first communication device, that is, abandon the determination of the activation state of the second AI feature. Thus, after receiving the first message indicating that the applicability of the first AI feature matches the applicability of the second AI feature, and the third message indicating whether the first AI feature matches or does not match the configuration information set, the second communication device can indirectly determine the applicability of the first AI feature based on the third message, and determine the applicability of the second AI feature based on the first message and the applicability of the first AI feature. Therefore, when the first AI feature does not match the first configuration information, the second communication device can determine that the second AI feature is not applicable and abandon the determination of the activation state of the second AI feature, saving signaling overhead between devices.

[0174] In some examples, the eighth message may indicate second configuration information related to the second AI feature, which can be used to enable the AI / ML model of the second AI feature to operate normally in a communication environment (such as channel quality), and the eighth message may be used to enable the first communication device to confirm whether there is configuration information in the second configuration information that matches the second AI feature.

[0175] S504b: When the third message indicates that the first AI feature matches the first configuration information, the second communication device sends an eighth message to the first communication device.

[0176] Accordingly, the first communication device receives the eighth message.

[0177] In one possible implementation, when the third message indicates that the first AI feature matches the first configuration information, it can indicate that the second AI feature is applicable, and the second communication device can determine the activation state of the second AI feature, that is, send an eighth message to the first communication device.

[0178] Optionally, when the third message indicates that the first AI feature matches the first configuration information, it can indicate that the first AI feature is activatable, and the second communication device can also send an eleventh message to the first communication device. The eleventh message can instruct the first communication device to activate the first AI feature, enabling the first communication device to run the AI / ML model corresponding to the first AI feature.

[0179] S505. When the first communication device receives the eighth message from the second communication device, it sends the ninth message to the second communication device.

[0180] Accordingly, the second communication device receives the ninth message.

[0181] In some examples, the ninth message can indicate that the second AI feature matches the second configuration information.

[0182] In one possible implementation, when the first communication device receives the eighth message from the second communication device, it can confirm whether there is configuration information in the second configuration information that matches the second AI feature, and if there is configuration information in the second configuration information that matches the second AI feature, it sends a ninth message to the second communication device.

[0183] Optionally, when there are multiple types of second configuration information, the content indicated by the ninth message may also include second configuration information that matches the second AI feature among the multiple types of second configuration information.

[0184] Optionally, when the ninth message indicates that the second AI feature matches the second configuration information, it can indicate that the second AI feature is activating, and the second communication device can also send a twelfth message to the first communication device. The twelfth message can instruct the first communication device to activate the second AI feature, enabling the first communication device to run the AI / ML model corresponding to the second AI feature.

[0185] Optionally, the first communication device may not execute step S505 if it does not receive the eighth message from the second communication device.

[0186] Optionally, in the embodiments of this application, the order of the sequence numbers of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. For example, the execution order of step S501 may be after step S502 and / or step S503.

[0187] In one possible design, when the applicability of the first AI feature and the second AI feature are consistent, the second communication device can directly obtain the applicability of the first AI feature before sending the second message to the first communication device. Thus, the second communication device can proactively obtain the applicability of the first AI feature by sending a fifth message. Only when the first AI feature is applicable will the second communication device send the second message to the first communication device. Conversely, if the sixth message indicates that the first AI feature is not applicable, the second communication device will abandon sending the second message to the first communication device, saving signaling overhead between devices.

[0188] For example, as shown in Figure 6, the design scheme may include the following steps:

[0189] S601, The first communication device sends a first message to the second communication device.

[0190] For details regarding the first communication device sending the first message to the second communication device, please refer to the description of the corresponding part of S501 in Figure 5 above, which will not be repeated here.

[0191] S602, the second communication device sends a fifth message to the first communication device.

[0192] Accordingly, the first communication device receives the fifth message.

[0193] In some examples, the fifth message can be used to determine the applicability of the first AI feature.

[0194] In one possible implementation, after receiving the first message, the second communication device can determine the applicability of the first AI feature and then send a fifth message to the first communication device. In this way, the second communication device can proactively obtain the applicability of the first AI feature by sending the fifth message. Only when the first AI feature is deemed applicable will the second communication device send a second message to the first communication device, thus saving signaling overhead between devices.

[0195] S603, The first communication device sends a sixth message to the second communication device.

[0196] In some examples, the sixth message can indicate whether the first AI feature is applicable or not.

[0197] In one possible implementation, when the first communication device receives the fifth message from the second communication device, it can confirm whether it meets preset conditions, further determine the content indicated by the sixth message based on whether it meets the preset conditions, and then send the sixth message to the second communication device. In this way, the first communication device can enable the second communication device to obtain the applicability of the first AI feature by sending the sixth message. If the first AI feature is not applicable, the second communication device can abandon sending the second message to the first communication device, saving signaling overhead between devices.

[0198] In some examples, the preset conditions may include, but are not limited to, at least one of the following: the remaining battery power of the first communication device is less than or equal to a preset battery power, the computing power resources of the first communication device are less than or equal to a preset computing power value, or the remaining storage space of the first communication device is less than or equal to a preset storage value. In this way, the first communication device can use its own resources to confirm the applicability of the first AI feature, that is, whether the resources of the first communication device itself can support the normal operation of the AI / ML model corresponding to the first AI feature, thereby improving the accuracy of the applicability of the first AI feature and thus improving the reliability of inter-device communication.

[0199] As an example, when the first communication device meets the preset conditions, the content indicated by the sixth message may indicate that the first AI feature is not applicable; when the first communication device does not meet the preset conditions, the content indicated by the sixth message may indicate that the first AI feature is applicable.

[0200] S604a. When the sixth message indicates that the first AI feature is not applicable, the second communication device abandons sending the second message to the first communication device.

[0201] As one possible approach, when the sixth message indicates that the first AI feature is not applicable, it can be shown that the first AI feature is inactive, and the second communication device can abandon sending the second message to the first communication device. In this way, the second communication device can avoid sending the second message to the first communication device when the first AI feature is not applicable, saving signaling overhead between devices.

[0202] Optionally, when the sixth message indicates that the first AI feature is not applicable, it can also indicate that the second AI feature is not applicable. Therefore, the second communication device can give up determining the activation state of the second AI feature, that is, give up sending the eighth message.

[0203] S604b: When the sixth message indicates that the first AI feature is applicable, the second communication device sends a second message to the first communication device.

[0204] When the sixth message indicates that the first AI feature is applicable, the process of the second communication device sending the second message to the first communication device and the process after sending the second message are similar to the process in S503 to S505 in Figure 5, and will not be described again here.

[0205] Optionally, step S602 can be an optional operation, meaning that the first communication device can actively send a sixth message to the second communication device.

[0206] In some embodiments, the applicability relationship between the first AI feature and the second AI feature may change. For example, when the first communication device changes from not meeting the preset conditions to meeting the preset conditions, in order to save its own resources, the first communication device may disable the relationship between the applicability of the first AI feature and the applicability of the second AI feature.

[0207] For example, assuming that the applicability of the first AI feature and the applicability of the second AI feature are the same at time t0, after a period of time, that is, at time t1, the remaining power of the first communication device is less than the preset power. In order to ensure that the AI / ML model corresponding to the first AI feature can run normally and save power, the first communication device can disable the correlation between the applicability of the first AI feature and the second AI feature, so that the first AI feature can be in an active state while the second AI feature cannot be activated.

[0208] In one possible design, when the applicability relationship between the first AI feature and the second AI feature changes, the second communication device can switch the strategy for determining the activation state of the AI ​​feature.

[0209] For example, as shown in Figure 7, taking the example of a relationship failure where the applicability of the first AI feature and the applicability of the second AI feature become the same, the design scheme may include the following steps:

[0210] S701, The first communication device sends a first message to the second communication device.

[0211] In one possible implementation, the first communication device can send a first message to the second communication device when it is in a connected state.

[0212] In some examples, the connected state can refer to the RRC_CONNECTED state of the first communication device under the RRC protocol. In this state, the first communication device maintains a connection with the second communication device and can transmit data or messages. Besides the connected state, the first device can also be in an inactive state or a dormant state. The inactive state can refer to the RRC_INACTIVE state, in which the first communication device has not established an RRC connection, has no context storage, and cannot transmit data or messages. The dormant state can refer to the RRC_IDLE state, in which the first communication device can retain some context and quickly restore the connection with the second communication device.

[0213] Optionally, when the first communication device switches from an inactive state to a connected state, it redetermines the relationship between the applicability of the first AI feature and the applicability of the second AI feature; or, when the first communication device switches from a dormant state to a connected state, it can redetermine the relationship between the applicability of the first AI feature and the second AI feature. In this way, the first communication device can reconfirm the relationship between the applicability of the first AI feature and the second AI feature when switching from other states to a connected state, improving the accuracy of the relationship between the applicability of the first AI feature and the second AI feature, thereby improving the reliability of communication between devices.

[0214] Optionally, when the first communication device re-determines the relationship between the applicability of the first AI feature and the applicability of the second AI feature to be consistent, the first communication device may send a first message to the second communication device; when the first communication device re-determines the relationship between the applicability of the first AI feature and the applicability of the second AI feature to be invalid, the first communication device may execute S702 and send a seventh message to the second communication device.

[0215] In some examples, the seventh message can indicate that the relationship between the applicability of the first AI feature and the applicability of the second AI feature is invalid.

[0216] Optionally, when the applicability of the first AI feature and the second AI feature is consistent, the strategy for determining the activation state of the AI ​​feature can be to determine whether to determine the activation state of the second AI feature based on the applicability of the first AI feature.

[0217] For further details regarding the first communication device sending the first message to the second communication device, please refer to the description of the corresponding part of S501 in Figure 5 above, which will not be repeated here.

[0218] When the applicability of the first AI feature and the applicability of the second AI feature are consistent, the implementation process of the second communication device determining the activation state of the first AI feature and / or the second AI feature is similar to the implementation process in S502 to S505 in Figure 5, and will not be described again here.

[0219] S702, The first communication device sends a seventh message to the second communication device.

[0220] In some examples, the seventh message can indicate that the relationship between the applicability of the first AI feature and the applicability of the second AI feature is invalid, and the seventh message can be used by the second communication device to determine whether to switch the strategy for determining the activation state of the AI ​​feature.

[0221] For example, the first AI feature, the first AI set, and the second AI set can each correspond to an ID. When the first AI feature and the second AI feature belong to the first AI set, the seventh message can indicate the ID corresponding to the first AI set. When the second AI feature belongs to the second AI set and the first AI feature does not belong to the first AI set, the seventh message can indicate the ID corresponding to the first AI feature and the ID corresponding to the second AI set.

[0222] In one possible implementation, the first communication device can send a seventh message to the second communication device when it meets preset conditions. In this way, the first communication device can promptly notify the second communication device when the applicability relationship between the first AI feature and the second AI feature fails, thereby facilitating the second communication device to adjust its strategy for determining the activation state of the AI ​​feature in a timely manner, and thus improving the reliability of communication.

[0223] S703, Strategy for determining the activation state of the AI ​​feature switching of the second communication device.

[0224] In one possible implementation, the second communication device can switch the strategy for determining the activation state of the AI ​​feature to: determining the activation state of the first AI feature and the second AI feature one by one. In this way, the second communication device can determine the activation state of the first AI feature and the second AI feature one by one, improving the accuracy of determining the activation state of the first AI feature and the second AI feature when the applicability relationship between the first AI feature and the second AI feature fails.

[0225] For example, when there is a correlation between the applicability of the first AI feature and the applicability of the second AI feature (i.e., the applicability of the first AI feature and the applicability of the second AI feature are consistent), the strategy for determining the activation state of the AI ​​feature can be: the second communication device determines the applicability of the first AI feature through a third message, and determines whether to determine the activation state of the second AI feature based on the first message and the applicability of the first AI feature (hereinafter referred to as "Strategy 1"); when the relationship between the applicability of the first AI feature and the applicability of the second AI feature fails, the strategy for determining the activation state of the AI ​​feature can be: a second determination strategy, which can be that the second communication device determines the activation state of the first AI feature and the second AI feature one by one (hereinafter referred to as "Strategy 2"). When the applicability relationship between the first AI feature and the second AI feature changes from the applicability of the first AI feature being consistent with that of the second AI feature to the applicability of the first AI feature being invalid, the strategy for determining the activation state of the AI ​​feature can be changed from strategy 1 to strategy 2; when the applicability relationship between the first AI feature and the second AI feature changes from the applicability of the first AI feature being invalid to the applicability of the first AI feature being consistent with that of the second AI feature, the strategy for determining the activation state of the AI ​​feature can be changed from strategy 2 to strategy 1.

[0226] In some embodiments, when the applicability of the first AI feature is consistent with the applicability of the second AI feature, the applicability of the first AI feature and / or the applicability of the second AI feature may change. For example, when the first communication device changes from not meeting the preset conditions to meeting the preset conditions, the first AI feature and / or the second AI feature may switch from having applicability to not having applicability.

[0227] For example, assuming that the applicability of the first AI feature is consistent with the applicability of the second AI feature, the first AI feature and the second AI feature are applicable at time t0. After a period of time, that is, at time t1, the remaining power of the first communication device is less than the preset power, the first AI feature and / or the second AI feature can switch from being applicable to not being applicable.

[0228] In one possible design, when the applicability of the first AI feature and the second AI feature is consistent, if the first AI feature is not applicable and is in an active state, the first communication device can deactivate both the first AI feature and the second AI feature. Thus, the first communication device can activate both the first AI feature and the second AI feature, which are compatible with the first AI feature, even when the first AI feature is not applicable, saving signaling overhead between devices for deactivating the second AI feature.

[0229] For example, as shown in Figure 8, taking the first AI feature and the second AI feature as being active and the first AI feature switching from having applicability to not having applicability as an example, the design scheme may include the following steps:

[0230] S801. When the first AI feature is not applicable, the second communication device sends a tenth message to the first communication device.

[0231] Accordingly, the first communication device receives the tenth message.

[0232] In some examples, the tenth message can instruct the first communication device to activate the first AI feature and the second AI feature.

[0233] In some possible embodiments, the first communication device can send a message indicating that the first AI feature is no longer applicable to the second communication device when the first AI feature switches from being applicable to being unapplicable. This allows the second communication device to send a tenth message to the first communication device when the first AI feature is no longer applicable. Thus, the second communication device can instruct the first communication device to activate the first AI feature and a second AI feature with the same applicability as the first AI feature when the first AI feature is no longer applicable, saving the signaling overhead between devices for deactivating the second AI feature.

[0234] S802, the first communication device deactivates the first AI feature and the second AI feature.

[0235] As one possible approach, the first communication device can simultaneously activate both the first AI feature and the second AI feature, thereby stopping the operation of the AI / ML models corresponding to the first AI feature and the second AI feature, respectively.

[0236] Optionally, after deactivating the first AI feature and the second AI feature, the first communication device may send a message to the second communication device indicating that the first AI feature and the second AI feature are inactive.

[0237] Optionally, when the first AI feature and the second AI feature are applicable, the second communication device may send a message to the first communication device instructing to activate the first AI feature or the second AI feature.

[0238] It should be noted that step S801 can be an optional operation. The first communication device can determine the applicability of the first AI feature on its own, and activate the first AI feature and the second AI feature when the first AI feature is not applicable and the first AI feature is in an active state.

[0239] In summary, when the first communication device can determine the applicability relationship between the first AI feature and the second AI feature, the first communication device can send a first message to the second communication device, and after receiving the second message, send a third message to the second communication device indicating whether the first AI feature matches or does not match the configuration information set. This allows the second communication device to indirectly determine the applicability of the first AI feature based on the third message, and determine whether the second AI feature is applicable based on the first and third messages. Thus, when the second communication device determines that the second AI feature is not applicable, it abandons the determination of the activation state of the second AI feature, saving signaling overhead between devices.

[0240] The communication method shown in Figure 5 involves a second communication device that, when the first communication device can determine the applicability relationship between the first AI feature and the second AI feature, can indirectly determine the applicability of the first AI feature based on the result of determining the activation state of the first AI feature. Then, based on the applicability of the first AI feature, it determines whether to determine the activation state of the second AI feature. In another communication method provided in this application, the second communication device can directly determine the applicability of the first AI feature. In the embodiments of this application, the first communication device can be a terminal device, and the second communication device can be a network device (such as a base station), which is not limited herein.

[0241] For example, as shown in Figure 9, the communication method may include the following steps:

[0242] S901, the second communication device sends a fifth message to the first communication device.

[0243] For details regarding the second communication device sending the fifth message to the first communication device, please refer to the description of the corresponding part of S602 in Figure 6 above, which will not be repeated here.

[0244] S902, The first communication device sends a sixth message to the second communication device.

[0245] Accordingly, the second communication device receives the sixth message.

[0246] For details regarding the first communication device sending the sixth message to the second communication device, please refer to the description of the corresponding part of S603 in Figure 6 above, which will not be repeated here.

[0247] S903a, when the sixth message indicates that the first AI feature is not applicable, the second communication device abandons sending the second message to the first communication device.

[0248] For details regarding the second communication device abandoning the transmission of the second message to the first communication device, please refer to the description of the corresponding part of S604a in Figure 6 above, which will not be repeated here.

[0249] S903b: When the sixth message indicates that the first AI feature is applicable, the second communication device sends a second message to the first communication device.

[0250] For details regarding the second communication device sending a second message to the first communication device, please refer to the description of the corresponding part of S604b in Figure 6 above, which will not be repeated here.

[0251] Optionally, step S901 can be an optional operation, meaning that the first communication device can actively send a sixth message to the second communication device.

[0252] In summary, the second communication device can obtain the applicability of the first AI feature by sending a fifth message to the first communication device. If the first AI feature is not applicable, it can abandon sending a second message to the first communication device, thus saving the signaling overhead between devices used to determine the activation status of the first AI feature.

[0253] It is understood that each of the above embodiments of this application can be implemented independently or in combination with each other; there is no absolute subordinate relationship between the embodiments, and they can be combined with each other under any conditions to obtain the corresponding effect.

[0254] It is understood that, in order to implement the functions in the above embodiments, the terminal device and network device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0255] Figures 10 and 11 are structural block diagrams and hardware structure diagrams of possible communication devices provided in the embodiments of this application, respectively. These communication devices can be used to implement the functions of terminal devices or network devices in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be a terminal device as shown in Figure 3, such as terminal device 120, or a network device as shown in Figure 3. For example, the network device can be a macro base station (110a in Figure 3), a micro base station or an indoor station (110b in Figure 3), or a module (such as a chip) applied to a terminal device or network device.

[0256] As shown in Figure 10, the communication device 1000 includes a processing unit 1010 and a transceiver unit 1020. The communication device 1000 is used to implement the functions of the first or second communication device in the method embodiments shown in Figure 5 or Figure 9.

[0257] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG5: the transceiver unit 1020 is used to send a first message to the second communication device, the first message indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, and the first message is used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature; when receiving a second message from the second communication device, a third message is sent to the second communication device, the second message indicating first configuration information related to the first AI feature, and the third message indicating whether the first AI feature matches or does not match the first configuration information; the processing unit 1010 is used to determine the content indicated by the third message.

[0258] For a more detailed description of the above-mentioned processing unit 1010 and transceiver unit 1020, please refer to the relevant description in the method embodiment shown in FIG5, which will not be repeated here.

[0259] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG9: the transceiver unit 1020 is used to receive a fifth message from the second communication device, the fifth message being used to obtain the applicability of the first AI feature; send a sixth message to the second communication device, the sixth message indicating whether the first AI feature has or does not have applicability, the sixth message being used by the second communication device to determine whether to send a second message, the second message indicating first configuration information related to the first AI feature; the processing unit 1010 is used to determine the content indicated by the sixth message.

[0260] For a more detailed description of the above-mentioned processing unit 1010 and transceiver unit 1020, please refer to the relevant description in the method embodiment shown in FIG9, which will not be repeated here.

[0261] When the communication device 1000 is used to implement the function of the network device in the method embodiment shown in FIG5: the transceiver unit 1020 is used to receive a first message from the first communication device, the first message indicating that the applicability of the first AI feature included in the first communication device is consistent with the applicability of the second AI feature; send a second message to the first communication device, the second message indicating the first configuration information related to the first AI feature; receive a third message from the first communication device, the third message indicating whether the first AI feature matches or does not match the first configuration information; the processing unit 1010 is used to abandon the determination of the activation state of the second AI feature when the third message indicates that the first AI feature does not match the first configuration information.

[0262] For a more detailed description of the above-mentioned processing unit 1010 and transceiver unit 1020, please refer to the relevant description in the method embodiment shown in FIG5, which will not be repeated here.

[0263] When the communication device 1000 is used to implement the function of the network device in the method embodiment shown in FIG9: the transceiver unit 1020 is used to send a fifth message to the first communication device, the fifth message being used to obtain the applicability of the first AI feature included in the first communication device; receive a sixth message from the first communication device, the sixth message indicating whether the first AI feature has or does not have applicability; the processing unit 1010 is used to abandon sending a second message to the first communication device when the sixth message indicates that the first AI feature does not have applicability, the second message indicating first configuration information related to the first AI feature.

[0264] For a more detailed description of the above-mentioned processing unit 1010 and transceiver unit 1020, please refer to the relevant description in the method embodiment shown in FIG9, which will not be repeated here.

[0265] The communication device 1000 may also include a memory (not shown in FIG10) for storing instructions executed by the processing unit 1010, or storing input data required for the running instructions of the processing unit 1010, or storing data generated after the running instructions of the processing unit 1010.

[0266] For a more detailed description of the above-mentioned processing unit 1010 and transceiver unit 1020, please refer to the relevant descriptions in the method embodiments shown in Figure 5 or Figure 9, which will not be repeated here.

[0267] As shown in Figure 11, the communication device 1100 includes a processor 1110 and an interface circuit 1120. The processor 1110 and the interface circuit 1120 are coupled to each other. It is understood that the interface circuit 1120 can be a transceiver or an input / output interface. Optionally, the communication device 1100 may also include a memory 1130 for storing instructions executed by the processor 1110, or storing input data required by the processor 1110 to execute instructions, or storing data generated after the processor 1110 executes instructions. Sometimes, the interface circuit 1120 can also be understood as part of the processor 1110, in which case the communication device 1100 includes the processor 1110.

[0268] When the communication device 1100 is used to implement the method shown in FIG5 or FIG9, the processor 1110 is used to implement the function of the processing unit 1010, and the interface circuit 1120 is used to implement the function of the transceiver unit 1020.

[0269] When the aforementioned communication device is a chip applied to a terminal device, the terminal device chip implements the functions of the terminal in the above method embodiments. The terminal device chip receiving information from a base station can be understood as the information being first received by other modules (such as an RF module or antenna) in the terminal device, and then sent to the terminal device chip by these modules. The terminal device chip sending information to the base station can be understood as the information being first sent to other modules (such as an RF module or antenna) in the terminal device, and then sent to the base station by these modules.

[0270] When the aforementioned communication device is a chip applied to a base station, the base station chip implements the functions of the base station in the above method embodiments. The base station chip receives information from the terminal device, which can be understood as the information being first received by other modules in the base station (such as an RF module or antenna), and then sent to the base station chip by these modules. The base station chip sends information to the terminal, which can be understood as the information being sent down to other modules in the base station (such as an RF module or antenna), and then sent to the terminal by these modules.

[0271] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal chip and other modules of the terminal, or between a base station chip and other modules of the base station.

[0272] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or one or more of other general-purpose processors, digital signal processors (DSPs), microprocessor units (MPUs), microcontroller units (MCUs), graphics processing units (GPUs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), artificial intelligence processors (AI processors), or neural processing units (NPUs); or, the processor mentioned in the embodiments of this application can be application-specific integrated circuits (ASICs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components (or parts), or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor, etc.

[0273] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in memory, such as volatile memory and / or non-volatile memory. The non-volatile memory can be flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), or electrically erasable programmable read-only memory (EEPROM). The volatile memory can be a cache or random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes a variety of forms, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). The memory can also be in registers, hard disks, portable hard disks, compact disc (CD) ROMs, or any other form of storage medium well known in the art.

[0274] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a communication device. The processor and storage medium can also exist as discrete components in the communication device.

[0275] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0276] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0277] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one item" means one or more, and "multiple items" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the related objects before and after are in an "or" relationship; in the formulas of this application, the character " / " indicates that the related objects before and after are in a "division" relationship. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.

[0278] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0279] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0280] The terms "first" and "second," etc., used in the specification and drawings of this application embodiments are used to distinguish different objects or to distinguish different processing of the same object. The terms "first," "second," etc., can distinguish identical or similar items with substantially the same function and effect. For example, "first message" and "second message" are merely to distinguish different messages and do not limit their order. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or execution order, and that "first," "second," etc., do not necessarily imply that they are different.

[0281] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0282] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0283] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of the embodiments of this application. Therefore, the various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of the embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0284] It is understood that in the embodiments of this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a time, nor do they require a judgment action during implementation, nor do they imply any other limitations.

[0285] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0286] In the embodiments of this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and in the various implementation methods / methods / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various implementation methods / methods / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various implementation methods / methods / implementations within each embodiment can be combined to form new embodiments, implementation methods, methods, or implementation approaches based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of the embodiments of this application.

Claims

1. A communication method, characterized in that, Applied to a first communication device, the first communication device including a first AI feature and a second AI feature, the method includes: Send a first message to the second communication device, the first message indicating that the applicability of the first AI feature is consistent with the applicability of the second AI feature, the first message being used by the second communication device to determine whether to determine the activation state of the first AI feature and / or the second AI feature. Upon receiving a second message from the second communication device, a third message is sent to the second communication device. The second message indicates first configuration information related to the first AI feature, and the third message indicates whether the first AI feature matches or does not match the first configuration information.

2. The method according to claim 1, characterized in that, The first message indicates that the first AI feature and the second AI feature belong to a first AI set, and the applicability of AI features in the first AI set is consistent; or, The first message indicates that the applicability of the first AI feature is consistent with the applicability of the second AI feature in the second AI set, and the first AI feature does not belong to the second AI set.

3. The method according to claim 1 or 2, characterized in that, Before sending the first message to the second communication device, the method further includes: A fourth message is received from the second communication device, the fourth message being used to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Receive a fifth message from the second communication device, the fifth message being used to obtain the applicability of the first AI feature; A sixth message is sent to the second communication device, the sixth message indicating whether the first AI feature has or does not have the applicability, and the sixth message is used by the second communication device to determine whether to send the second message.

5. The method according to any one of claims 1-4, characterized in that, After sending the first message, the method further includes: A seventh message is sent to the second communication device, the seventh message indicating that the relationship between the applicability of the first AI feature and the applicability of the second AI feature is invalid, and the seventh message is used by the second communication device to determine whether to switch the strategy for determining the activation state of the AI ​​feature.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: When the first communication device switches from an inactive state to a connected state, the applicability of the first AI feature and the applicability of the second AI feature are re-determined; or, When the first communication device switches from the sleep state to the connected state, the applicability of the first AI feature and the applicability of the second AI feature are re-determined. Sending the first message to the second communication device includes: When the first communication device is in a connected state, the first message is sent to the second communication device.

7. The method according to any one of claims 1-5, characterized in that, The method further includes: When the first AI feature is not applicable and the first AI feature is in the activated state, deactivate the first AI feature and the second AI feature.

8. The method according to any one of claims 1-7, characterized in that, The first communication device is a terminal device, and the second communication device is a network device.

9. A communication method, characterized in that, Applied to a first communication device, the first communication device including a first AI feature and a second AI feature, the method includes: Receive a fifth message from the second communication device, the fifth message being used to obtain the applicability of the first AI feature; A sixth message is sent to the second communication device, the sixth message indicating whether the first AI feature has or does not have the applicability, the sixth message being used by the second communication device to determine whether to send a second message, the second message indicating first configuration information related to the first AI feature.

10. The method according to claim 9, characterized in that, The sixth message indicates that the first AI feature has the applicability, and the method further includes: Receive a second message from the second communication device; A third message is sent to the second communication device, the third message indicating that the first AI feature matches the first configuration information.

11. The method according to claim 9 or 10, characterized in that, The first communication device is a terminal device, and the second communication device is a network device.

12. A communication method, characterized in that, Applied to a second communication device, the method includes: Receive a first message from a first communication device, the first message indicating that the applicability of a first AI feature included in the first communication device is consistent with the applicability of a second AI feature; Send a second message to the first communication device, the second message indicating first configuration information related to the first AI feature; Receive a third message from the first communication device, the third message indicating whether the first AI feature matches or does not match the first configuration information; When the third message indicates that the first AI feature does not match the first configuration information, the determination of the activation state of the second AI feature is abandoned.

13. The method according to claim 12, characterized in that, The method further includes: When the third message indicates that the first AI feature matches the first configuration information, an eighth message is sent to the first communication device, the eighth message indicating second configuration information related to the second AI feature; A ninth message is received from the first communication device, the ninth message indicating that the second AI feature matches the second configuration information.

14. The method according to claim 12 or 13, characterized in that, The first message indicates that the first AI feature and the second AI feature belong to a first AI set, and the applicability of AI features in the first AI set is consistent; or, the first message indicates that the applicability of the first AI feature is consistent with the applicability of the second AI feature in a second AI set, and the first AI feature does not belong to the second AI set.

15. The method according to any one of claims 12-14, characterized in that, Before receiving the first message from the first communication device, the method further includes: A fourth message is sent to the first communication device, the fourth message being used to obtain the relationship between the applicability of the first AI feature and the applicability of the second AI feature.

16. The method according to any one of claims 12-15, characterized in that, Before sending the second message to the first communication device, the method further includes: Send a fifth message to the first communication device, the fifth message being used to obtain the applicability of the first AI feature; Receive a sixth message from the first communication device, the sixth message indicating whether the first AI feature has or does not have the applicability; Sending the second message to the first communication device includes: When the sixth message indicates that the first AI feature has the applicability, the second message is sent to the first communication device.

17. The method according to claim 16, characterized in that, The method further includes: When the sixth message indicates that the first AI feature does not have the applicable nature, the sending of the second message to the first communication device is abandoned.

18. The method according to any one of claims 12-17, characterized in that, After receiving the first message from the first communication device, the method further includes: A seventh message is received from the first communication device, the seventh message indicating that the relationship between the applicability of the first AI feature and the applicability of the second AI feature is invalid; Determining the strategy for switching the activation state of AI features.

19. The method according to claim 18, characterized in that, The strategy for determining the activation state of the switching AI feature includes: The strategy for determining the activation state of the AI ​​feature is switched to: determining the activation state of the first AI feature and the second AI feature one by one.

20. The method according to any one of claims 13-17, characterized in that, The method further includes: When the first AI feature does not have the aforementioned applicability, a tenth message is sent to the first communication device, the tenth message instructing the first communication device to activate the first AI feature and the second AI feature.

21. The method according to any one of claims 12-20, characterized in that, The first communication device is a terminal device, and the second communication device is a network device.

22. A communication method, characterized in that, Applied to a second communication device, the method includes: Send a fifth message to the first communication device, the fifth message being used to obtain the applicability of the first AI feature included in the first communication device; Receive a sixth message from the first communication device, the sixth message indicating whether the first AI feature has or does not have the applicability; When the sixth message indicates that the first AI feature is not applicable, the sending of the second message to the second communication device is abandoned. The second message indicates the first configuration information related to the first AI feature.

23. The method according to claim 22, characterized in that, The method further includes: When the sixth message indicates that the first AI feature has the applicability, the second message is sent to the first communication device.

24. The method according to claim 22 or 23, characterized in that, The first communication device is a terminal device, and the second communication device is a network device.

25. A communication device, characterized in that, It includes a processor and an interface circuit, the interface circuit being used to communicate with other communication devices, and the processor being used to implement the method as described in any one of claims 1-8, 9-11, 12-21, or 22-24 through logic circuits and / or executing code instructions.

26. A communication system, characterized in that, It includes a first communication device and a second communication device, wherein the first communication device is used to implement the method as described in any one of claims 1-8 or 9-11; and the second communication device is used to implement the method as described in any one of claims 12-21 or 22-24.

27. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1-8, 9-11, 12-21, or 22-24.

28. A computer program product, characterized in that, Includes computer program code, which, when run on a communication device, implements the method as described in any one of claims 1-8, 9-11, 12-21, or 22-24.