Performance monitoring method and apparatus, device, and storage medium

Abstract

The present disclosure relates to the technical field of communications, and provides a performance monitoring method and apparatus, a device and a storage medium, applied to a terminal device. The method comprises: sending a performance monitoring request of an AI model to a network device on the basis of a trigger event; and receiving a response to the performance monitoring request sent by the network device, performing performance monitoring on the AI model on the basis of the response to the performance monitoring request. Communication resources for model monitoring are saved.

Description

Performance monitoring method, device, equipment and storage medium

[0001] This disclosure claims priority to Chinese patent application number 202410108832.9, filed with the Patent Office of China on January 25, 2024, entitled “Performance Monitoring Method, Device, Equipment and Storage Medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of communication technology, and more particularly to a performance monitoring method, apparatus, device, and storage medium. Background Art

[0003] With the development of artificial intelligence (AI) technology and machine learning (ML), AI and / or ML models (hereinafter referred to as AI models) can be used to improve the performance of communication systems. Among them, performance monitoring of AI models is particularly important.

[0004] Currently, base stations can periodically send reference signals related to AI models to terminal devices, thereby periodically enabling performance monitoring of the AI ​​models. However, during most periods of time, AI models do not require frequent performance monitoring, which results in a waste of communication resources. Summary of the Invention

[0005] The present disclosure relates to a performance monitoring method, apparatus, device, and storage medium, which solve the technical problem of wasted communication resources in performance monitoring of AI models.

[0006] In a first aspect, the present disclosure provides a performance monitoring method, applied to a terminal device, the method comprising:

[0007] Sending performance monitoring requests for AI models to network devices based on trigger events;

[0008] Receive a response to the performance monitoring request sent by the network device, and perform performance monitoring on the AI ​​model based on the response to the performance monitoring request.

[0009] In some embodiments, the performance monitoring request includes an identification of the AI ​​model and / or an identification of a function.

[0010] In some embodiments, the performance monitoring request includes an identifier of an applicable model, an identifier of an applicable function, and an identifier of an applicable scenario corresponding to the performance monitoring request.

[0011] In some embodiments, the performance monitoring request includes a start time of performance monitoring and / or an end time of performance monitoring.

[0012] In some embodiments, the performance monitoring request includes target information, which is related to the performance indicators of the AI ​​model and / or the measurement values ​​of the AI ​​model.

[0013] In some embodiments, the target information includes at least one of the following:

[0014] Intermediate key performance indicators related to the AI ​​model;

[0015] Final key performance indicators related to the AI ​​model;

[0016] Statistical information related to channel state information (CSI);

[0017] distribution information of the CSI-related information;

[0018] The reference signal received power related to the AI ​​model;

[0019] the reference signal reception quality associated with the AI ​​model;

[0020] signal-to-interference-plus-noise ratio;

[0021] Speed ​​information;

[0022] Location information.

[0023] In some embodiments, the trigger event includes a first event related to the AI ​​model and / or function and a second event related to the performance of the terminal device.

[0024] In some embodiments, when the AI ​​model is not activated, not selected, or not paired, the first event includes at least one of the following:

[0025] Send the identification of supported AI models and / or capabilities;

[0026] Receive the identifier of the AI ​​model and / or the identifier of the function supported by the cell currently covered by the base station.

[0027] In some embodiments, when the AI ​​model is activated, selected, or paired, the first event is an event determined based on at least one of the following information:

[0028] The final key performance indicators measured;

[0029] Statistical information and / or distribution information of measured CSI-related information;

[0030] Statistical information and / or distribution information of CSI-related information inferred by the AI ​​model;

[0031] The generalization metric of the AI ​​model;

[0032] The update information of the AI ​​model and / or the transfer information of the AI ​​model.

[0033] In some embodiments, the first event is an event determined based on a final key performance indicator of the measurement, and the first event includes at least one of the following:

[0034] A first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter, and the first parameter is proportional to the performance of the AI ​​model;

[0035] A second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter, and the second parameter is inversely proportional to the performance of the AI ​​model;

[0036] The number of times that the first parameter in the final key performance indicator is less than the threshold corresponding to the first parameter within the first time period is greater than the first threshold;

[0037] The number of times that the second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter within the first duration is greater than the first threshold;

[0038] A deviation between the parameter in the final key performance indicator and a first target value is greater than a second threshold, and the first target value is a target value corresponding to the parameter in the final key performance indicator.

[0039] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of measured CSI-related information, and the first event includes at least one of the following:

[0040] a third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than a threshold corresponding to the third parameter, and the third parameter is inversely proportional to the performance of the AI ​​model;

[0041] a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than a threshold corresponding to the fourth parameter, and the fourth parameter is proportional to the performance of the AI ​​model;

[0042] The number of times that a third parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is greater than a threshold corresponding to the third parameter is greater than the third threshold;

[0043] The number of times that a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is less than a threshold corresponding to the fourth parameter is greater than the third threshold;

[0044] A deviation between the parameter in the statistical information and / or distribution information of the measured CSI-related information and the second target value is greater than a fourth threshold, and the second target value is a target value corresponding to the parameter in the statistical information and / or distribution information of the measured CSI-related information.

[0045] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model, and the first event includes at least one of the following:

[0046] a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than a threshold corresponding to the fifth parameter, and the fifth parameter is inversely proportional to the performance of the AI ​​model;

[0047] a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than a threshold corresponding to the sixth parameter, and the sixth parameter is proportional to the performance of the AI ​​model;

[0048] The number of times that a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is greater than a threshold corresponding to the fifth parameter is greater than the fifth threshold;

[0049] The number of times a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is less than a threshold corresponding to the sixth parameter is greater than the fifth threshold;

[0050] A deviation between the parameters in the statistical information and / or distribution information of the inferred CSI-related information and the third target value is greater than a sixth threshold, and the third target value is a target value corresponding to the parameters in the statistical information and / or distribution information of the inferred CSI-related information.

[0051] In some embodiments, the first event is an event determined based on a generalization indicator of the AI ​​model, and the first event includes at least one of the following:

[0052] a duration during which a parameter in a performance indicator of the received reference signal is less than a seventh threshold and greater than an eighth threshold;

[0053] the number of times that the parameter in the performance indicator of the received reference signal is less than the seventh threshold within the fourth time duration is greater than the ninth threshold;

[0054] The quasi co-location information of the received reference signal changes;

[0055] The dataset label of the measured CSI-related information has changed;

[0056] The duration during which the parameter in the measured speed information is greater than the tenth threshold is greater than the eleventh threshold;

[0057] The number of times that the parameter in the measured speed information is greater than the tenth threshold within the fifth time period is greater than the twelfth threshold;

[0058] The distance difference between the two positions measured at the sixth time interval is greater than the thirteenth threshold;

[0059] The operating center frequency, subcarrier and / or bandwidth configuration changes.

[0060] In some embodiments, the first event is an event determined based on update information and / or model transfer information of the AI ​​model, and the first event includes at least one of the following:

[0061] receiving model update information and / or model transfer information sent by the network device;

[0062] After receiving the model update information and / or model transfer information sent by the network device, no performance monitoring related indication is received within a seventh time period.

[0063] In some embodiments, the second event is an event determined based on upper layer signaling, and the second event includes at least one of the following:

[0064] A handover occurs in the cell where the cell is located;

[0065] A first monitoring quantity is greater than a fourteenth threshold, and the first monitoring quantity is inversely proportional to the performance of the terminal device;

[0066] The second monitoring amount is less than a fifteenth threshold, and the first monitoring amount is proportional to the performance of the terminal device;

[0067] A first parameter of a final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is less than a threshold corresponding to the first parameter;

[0068] A second parameter of the final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is greater than a threshold corresponding to the second parameter.

[0069] In some embodiments, the threshold, duration, and target value are based on protocol pre-definition and / or network-side configuration and / or a mixture of protocol pre-definition and network-side configuration.

[0070] In some embodiments, the CSI-related information includes the CSI information, beam information and positioning information.

[0071] In some embodiments, the response to the performance monitoring request includes a reply or indication of the performance monitoring request.

[0072] In some embodiments, sending a performance monitoring request of an AI model to a network device includes:

[0073] Sending the performance monitoring request to the network device based on the scheduling request SR of uplink control information UCI;

[0074] or,

[0075] Sending the performance monitoring request to the network device based on media access control element MAC-CE signaling;

[0076] or,

[0077] The performance monitoring request is sent to the network device based on the physical uplink control channel PUCCH resources or the physical uplink shared channel PUSCH resources of the reserved period.

[0078] In a second aspect, the present disclosure provides another performance monitoring method, applied to a network device, the method comprising:

[0079] Receiving a performance monitoring request for an AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event;

[0080] Sending a response to the performance monitoring request to the terminal device.

[0081] In some embodiments, the sending of the response to the performance monitoring request to the terminal device includes:

[0082] Determine, based on the information contained in the performance monitoring request, whether the AI ​​model requires performance monitoring, and obtain a determination result;

[0083] Based on the determination result, a response to the performance monitoring request is sent to the terminal device.

[0084] In some embodiments, sending a response to the performance monitoring request to the terminal device includes:

[0085] Receiving a scheduling request SR sent by the terminal device;

[0086] A response to the scheduling request SR is sent to the terminal device, where the response to the scheduling request SR includes downlink control information DCI for uplink transmission resource allocation, and the downlink control information DCI is encrypted based on the radio network temporary identifier RNTI of the terminal device.

[0087] In a third aspect, the present disclosure provides a performance monitoring device, which is applied to a terminal device. The performance monitoring device includes a sending module, a receiving module, and a monitoring module, wherein:

[0088] The sending module is used to send a performance monitoring request of the AI ​​model to the network device according to the trigger event;

[0089] The receiving module is used to receive a response to the performance monitoring request sent by the network device;

[0090] The monitoring module is used to monitor the performance of the AI ​​model based on the response to the performance monitoring request.

[0091] In a fourth aspect, the present disclosure provides another performance monitoring device, applied to a network device, the performance monitoring device including a receiving module and a sending module, wherein:

[0092] The receiving module is configured to receive a performance monitoring request for an AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event;

[0093] The sending module is used to send a response to the performance monitoring request to the terminal device.

[0094] In a fifth aspect, the present disclosure provides a terminal device, including a memory, a transceiver, and a processor:

[0095] The memory is used to store computer programs;

[0096] The transceiver is used to send and receive data under the control of the processor;

[0097] The processor is configured to read the computer program in the memory and perform the following operations:

[0098] Sending performance monitoring requests for AI models to network devices based on trigger events;

[0099] Receive a response to the performance monitoring request sent by the network device, and monitor the performance of the AI ​​model based on the response to the performance monitoring request.

[0100] In a sixth aspect, the present disclosure provides a network device, including a memory, a transceiver, and a processor:

[0101] The memory is used to store computer programs;

[0102] The transceiver is used to send and receive data under the control of the processor;

[0103] The processor is configured to read the computer program in the memory and perform the following operations:

[0104] Receiving a performance monitoring request for an AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event;

[0105] Sending a response to the performance monitoring request to the terminal device.

[0106] In a seventh aspect, the present disclosure provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method described in the first aspect or the method described in the second aspect.

[0107] The present disclosure provides a performance monitoring method, apparatus, equipment and storage medium, in which a terminal device can send a performance monitoring request of an AI model to a network device based on a trigger event, receive a response to the performance monitoring request sent by the network device, and perform performance monitoring on the AI ​​model based on the response to the performance monitoring request. In the above method, since the performance monitoring of the AI ​​model can be enabled by the terminal device based on a trigger event, and the trigger event can be associated with the performance of the AI ​​model, the terminal device can avoid frequently (periodically or semi-periodically) enabling the performance monitoring of the AI ​​model, thereby reducing the communication resources required for monitoring the AI ​​model, and in the event of AI model failure, AI model performance degradation and other events, the terminal device can promptly enable the performance monitoring of the AI ​​model, thereby improving the timeliness of the AI ​​model performance monitoring, and thus improving the stability of the communication. This method can also be used in conjunction with a method for enabling model monitoring aperiodically, periodically or semi-periodically, to achieve the purpose of quickly and flexibly performing AI model performance monitoring based on the available communication resources in the system.

[0108] It should be understood that the contents described in the above summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easier to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0109] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0110] FIG1 is a schematic diagram of a communication scenario provided by an embodiment of the present disclosure;

[0111] FIG2 is a flow chart of a performance monitoring method provided by an embodiment of the present disclosure;

[0112] FIG3 is a schematic diagram of a method for monitoring the performance of an AI model provided by an embodiment of the present disclosure;

[0113] FIG4 is a schematic diagram of another method for monitoring the performance of an AI model provided by an embodiment of the present disclosure;

[0114] FIG5 is a schematic diagram of another method for monitoring the performance of an AI model provided by an embodiment of the present disclosure;

[0115] FIG6 is a schematic diagram of a method for triggering a first event provided by an embodiment of the present disclosure;

[0116] FIG7 is a schematic diagram of another method for triggering a first event provided by an embodiment of the present disclosure;

[0117] FIG8 is a schematic diagram of a method for sending a monitoring request provided by an embodiment of the present disclosure;

[0118] FIG9 is a schematic diagram of another method for sending a monitoring request according to an embodiment of the present disclosure;

[0119] FIG10 is a schematic diagram of another method for sending a monitoring request according to an embodiment of the present disclosure;

[0120] FIG11 is a schematic diagram of another method for sending a monitoring request according to an embodiment of the present disclosure;

[0121] FIG12 is a schematic diagram of another method for sending a monitoring request according to an embodiment of the present disclosure;

[0122] FIG13 is a schematic diagram of a method for sending a monitoring request according to an embodiment of the present disclosure;

[0123] FIG14 is a schematic diagram of a method for sending a response to a monitoring request to a terminal device according to an embodiment of the present disclosure;

[0124] FIG15 is a schematic structural diagram of a performance monitoring device provided by an embodiment of the present disclosure;

[0125] FIG16 is a schematic diagram of the structure of another performance monitoring device provided by an embodiment of the present disclosure;

[0126] FIG17 is a schematic structural diagram of a terminal device provided in an embodiment of the present disclosure;

[0127] FIG18 is a schematic structural diagram of a network device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0128] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0129] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0130] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0131] The embodiments of the present disclosure provide a performance monitoring method, apparatus, device, and storage medium. A terminal device can enable monitoring of an AI model based on a triggering event. This eliminates the need for network devices to frequently enable monitoring of the AI ​​model's performance, thereby reducing the consumption of communication resources and improving the timeliness of monitoring the AI ​​model's performance.

[0132] Among them, the method and the device are based on the same application concept. Since the principles of solving problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0133] The technical solutions provided by the embodiments of the present disclosure can be applicable to a variety of systems. For example, applicable systems may be long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, advanced long term evolution (LTE-A) systems, universal mobile telecommunication systems (UMTS), worldwide interoperability for microwave access (WiMAX) systems, 5G new radio (NR) systems and their evolved communication systems, etc. These various systems may include terminal devices and network devices. The system may also include a core network part, such as an evolved packet system (EPC), a 5G core network (5GC), etc.

[0134] The terminal device involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing device connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called User Equipment (UE). A wireless terminal device may be a USB storage device, other personal computer memory devices, and a dongle. It may also communicate with one or more core networks (CN) via a radio access network (RAN). A wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile device that exchanges language and / or data with a radio access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), personal computers, tablet computers, Machine-type Communication (MTC) terminal devices, etc. Wireless terminal devices may also be referred to as systems, subscriber units, subscriber stations, mobile stations, mobile stations, remote stations, access points, remote terminal devices, access terminal devices, user terminal devices, user agents, user devices, and wireless access points and routers / modems that meet the limitations of this definition, but are not limited in the embodiments of the present disclosure.

[0135] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to the terminal. Depending on the application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be an evolved network device (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation 5G network architecture, etc., or a home evolved Node B (HeNB), a relay node, a femto, a pico base station, a network test device, etc., which is not limited in the embodiments of the present disclosure. In some network structures, network devices may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0136] The communication scenario of the present disclosure is described below with reference to FIG1 .

[0137] Figure 1 is a schematic diagram of a communication scenario provided by an embodiment of the present disclosure. Please refer to Figure 1, including terminal devices and network devices, both of which can be used as AI model users. Among them, when the AI ​​model usage scenario is different from its training scenario, it is necessary to monitor the performance of the AI ​​model to determine whether the AI ​​model is applicable in the current scenario. The monitoring party of the AI ​​model can perform life cycle management (LCM) operations related to the AI ​​model based on the performance monitoring results of the AI ​​model. For example, when the current AI model is invalid, the monitoring party of the AI ​​model can perform operations such as model deactivation, model switching, model rollback and model update, thereby ensuring the stability of communication.

[0138] At present, the network equipment can send reference signals related to the AI ​​model to the terminal equipment, and then start monitoring the performance of the AI ​​model. For example, the AI ​​model is a model for processing channel state information (CSI). The network equipment can send CSI-related reference signals to the terminal equipment non-periodically, periodically or semi-periodically. The terminal equipment can measure the real CSI based on the reference signal and process (compress and restore) the real CSI through the AI ​​model, and then monitor the performance of the current AI model based on the real CSI and the CSI output by the AI ​​model. However, in most time periods, the performance of the AI ​​model is relatively stable. Therefore, the AI ​​model does not need to be frequently monitored for performance, which will result in a waste of communication resources. In addition, when an emergency occurs (such as failure of the AI ​​model or degradation of the AI ​​model performance), the network equipment cannot start performance monitoring of the AI ​​model in time, which leads to low communication stability.

[0139] In order to solve the technical problems in the related art, the embodiment of the present disclosure provides a performance monitoring method, wherein the terminal device can send a performance monitoring request of the AI ​​model to the network device according to the trigger event, wherein the performance monitoring request can include the identifier of the AI ​​model and / or the identifier of the function, and the trigger event can include events related to the AI ​​model and / or the function, and events related to the performance of the terminal device. The terminal device can receive the response to the performance monitoring request sent by the network device, and perform performance monitoring on the AI ​​model according to the response to the performance monitoring request. In this way, since the trigger event is related to the AI ​​model and / or the function, when the AI ​​model fails and the performance of the AI ​​model degrades, the terminal device can promptly start performance monitoring of the AI ​​model, thereby ensuring the stability of communication quality. Moreover, since the terminal device can start performance monitoring of the AI ​​model based on the trigger event, there is no need for the network device to frequently (periodically or semi-periodically) start performance monitoring of the AI ​​model, thereby saving communication resources.

[0140] The performance monitoring method provided by the present disclosure is described in detail below with reference to embodiments.

[0141] FIG2 is a flow chart of a performance monitoring method provided by an embodiment of the present disclosure. Referring to FIG2 , the method flow includes:

[0142] S201. The terminal device sends a performance monitoring request of the AI ​​model to the network device based on a trigger event.

[0143] The trigger event can be used to trigger the terminal device to send a performance monitoring request for the AI ​​model to the network device. For example, when the terminal device detects the occurrence of a trigger event, the terminal device can send a performance monitoring request for the AI ​​model to the network device.

[0144] Among them, the triggering event may include a first event related to the AI ​​model and / or function and a second event related to the performance of the terminal device. For example, if the user throughput is less than the preset throughput, the event may be the first event, if the block error rate is greater than the preset block error rate, the event may be the first event, wherein the first event may be any event related to the AI ​​model and / or function, and the embodiments of the present disclosure do not limit this. For example, if the power consumption of the terminal device increases, the event may be the second event, if the remaining computing power of the terminal device is less than the preset computing power, the event may be the second event, wherein the second event may be any event related to the performance of the terminal device, and the embodiments of the present disclosure do not limit this.

[0145] In some embodiments, the AI ​​model may be a model for processing CSI information, the AI ​​model may be a model for processing beam information, or the AI ​​model may be a model for processing positioning information, which is not limited in the embodiments of the present disclosure.

[0146] Among them, the performance monitoring request can be used to request performance monitoring of the AI ​​model. For example, the performance monitoring request can request performance monitoring of the AI ​​model, and the monitoring request can also trigger the activation of the performance monitoring of the AI ​​model. Among them, performance monitoring (performance monitoring) can include model-based monitoring (model based performance monitoring, i.e., performance monitoring) and function-based monitoring (functionality based) (the function can be the function of the AI ​​model or the AI ​​function in communication, which is not limited in the embodiment of the present disclosure). The terminal device can perform lifecycle management of the AI ​​model based on the results of performance monitoring.

[0147] The performance monitoring request may include an identifier of the AI ​​model and / or an identifier of the function. For example, the performance monitoring request may include an identification number (ID) of the AI ​​model, the performance monitoring request may include an ID of the function, or the performance monitoring request may include both an ID of the AI ​​model and an ID of the function, which is not limited in the present embodiment.

[0148] For example, if the performance monitoring request sent by the terminal device to the network device includes the identifier of AI model 1, the terminal device requests performance monitoring of AI model 1; if the performance monitoring request sent by the terminal device to the network device includes the identifier of AI model 2, the terminal device requests performance monitoring of AI model 2. For example, if the performance monitoring request sent by the terminal device to the network device includes the identifier of function A, the terminal device requests performance monitoring of function A; if the monitoring request sent by the terminal device to the network device includes the identifier of function B, the terminal device requests performance monitoring of function B. In this way, the terminal device can accurately perform performance monitoring on AI models and / or functions.

[0149] In some embodiments, the performance monitoring request may include an identifier indicating the applicable model, an identifier indicating the applicable function, and an identifier indicating the applicable scenario to which the performance monitoring request corresponds. For example, the performance monitoring request may include an identifier indicating the function of the AI ​​model to which the performance monitoring request corresponds, and an identifier indicating the applicable scenario to which the performance monitoring request corresponds.

[0150] In some embodiments, the performance monitoring request may include the start time of performance monitoring and / or the end time of performance monitoring. For example, the performance monitoring request may include the start time of performance monitoring, the performance monitoring request may also include the end time of performance monitoring, and the performance monitoring request may also include the start time of performance monitoring and the end time of performance monitoring. For example, if the performance monitoring request includes the start time of performance monitoring, the terminal device may start performance monitoring of the AI ​​model at the start time; if the performance monitoring request includes the end time of performance monitoring, the terminal device may stop performance monitoring of the AI ​​model at the end time; if the performance monitoring request includes the start time of performance monitoring and the end time of performance monitoring, the terminal device may perform performance monitoring on the AI ​​model during the period between the start time and the end time. In this way, the terminal device can flexibly perform performance monitoring on the AI ​​model.

[0151] It should be noted that if the performance monitoring request does not include the start time of performance monitoring, the network device can execute the performance monitoring process of the AI ​​model when it receives the performance monitoring request (the performance monitoring process of the AI ​​model starts when the network device sends a reference signal related to the AI ​​model, but in this disclosure, starting the performance monitoring process of the AI ​​model is determined by the performance monitoring request sent by the terminal device).

[0152] It should be noted that if the performance monitoring request does not include the end time of performance monitoring, the terminal device can stop performance monitoring after starting the performance monitoring for a preset period of time. The terminal device can also stop performance monitoring at any time. This embodiment of the present disclosure does not limit this.

[0153] It should be noted that the start time and the end time in the embodiment of the present disclosure may be absolute time or offset time, and the embodiment of the present disclosure is not limited to this.

[0154] In some embodiments, the performance monitoring request may include target information. The target information may be related to the performance indicators of the AI ​​model and / or the measurement values ​​of the AI ​​model. In some embodiments, the target information may include at least one of the following: intermediate key performance indicators related to the AI ​​model, final key performance indicators related to the AI ​​model, statistical information of information related to channel state information (CSI), distribution information of information related to CSI, speed information, and location information.

[0155] Among them, intermediate key performance indicators (KPIs) related to the AI ​​model can indicate the performance of the AI ​​model. For example, if the AI ​​model is a model for processing CSI, the terminal device can obtain real CSI, compress and restore the real CSI based on the AI ​​model, and obtain predicted CSI. The terminal device can calculate the intermediate KPI (performance metric calculation) of the AI ​​model based on the real CSI and the predicted CSI, and determine the inference precision and accuracy of the AI ​​model based on the intermediate KPI.

[0156] Among them, the final key performance indicators (Eventual KPIs) related to the AI ​​model can be used to indicate the performance of the AI ​​model. For example, the final KPIs may include parameters such as throughput, hypothetical throughput, hypothetical block error rate (hypothetical BLER), and block error rate. The above parameters can accurately reflect the quality of the communication system. The terminal device can determine the performance of the AI ​​model based on the quality of the communication system. For example, if the throughput is low, it means that the quality of the current communication system is poor and the performance of the AI ​​model is low.

[0157] Among them, the information related to the channel state information CSI may include CSI information, beam information and positioning information. The information related to the CSI may also include any information that may affect the CSI, which is not limited in the embodiments of the present disclosure.

[0158] Among them, the statistical information of CSI-related information may include average delay, delay spread, Doppler shift, Doppler spread and other information, and the CSI-related distribution information may include LOS (Line-of-Sight) distribution, NLOS (Non-Line-of-Sight) distribution, etc., which is not limited to the embodiments of the present disclosure.

[0159] The AI ​​model-related reference signal received power (RSRP) may be the power strength of a reference signal received by a terminal device. For example, RSRP may measure the signal strength of a terminal device or a cell. For example, if the AI ​​model processes CSI, the reference signal may be a CSI-related reference signal; if the AI ​​model processes beam information, the reference signal may be a beam-related reference signal; and if the AI ​​model processes positioning information, the reference signal may be a positioning-related reference signal.

[0160] The AI ​​model-related reference signal received quality (RSRQ) may be the quality of a reference signal received by the terminal device. For example, the terminal device may determine the signal quality based on the RSRQ.

[0161] The Signal to Interference plus Noise Ratio (SINR) ratio may be the ratio of the strength of the received useful signal to the strength of the received interference signal (noise plus interference). For example, based on the SINR, the terminal device can accurately determine the impact of interference other than noise on the signal.

[0162] The speed information may include the absolute value of the linear velocity, the absolute value of the angular velocity, the linear velocity acceleration, and the angular velocity acceleration of the terminal device. The speed information may include any information related to the speed of the terminal device, which is not limited in the embodiments of the present disclosure.

[0163] The location information may be information related to the location of the terminal device. For example, the location information may be the current location of the terminal device, or the location difference between two locations measured by the terminal device within a period of time, which is not limited in the present embodiment.

[0164] It should be noted that the performance indicators and metric values ​​of the above-mentioned target information may be L1 (layer 1) or L3 (layer 3) filtered, which is not limited in the embodiments of the present disclosure.

[0165] In this way, when the performance monitoring request of the AI ​​model includes target information, the network device can determine whether to enable performance monitoring of the AI ​​model based on the target information. Although the judgment process of whether the performance monitoring of the AI ​​model is enabled is determined by the network device, the initiation of the judgment process is determined by the performance monitoring request sent by the terminal device. Therefore, the network device does not need to frequently enable performance monitoring of the AI ​​model, thereby saving communication resources.

[0166] In some embodiments, the terminal device may send a performance monitoring request of the AI ​​model to the network device according to the following three feasible implementation methods:

[0167] A possible implementation:

[0168] A performance monitoring request (SR) based on the uplink control information (UCI) is sent to the network device. For example, if the terminal device uses UCI reporting, the terminal device can send the SR and the physical uplink shared channel (PUSCH) information required for uplink transmission (e.g., the number of reported quantities).

[0169] Another possible implementation:

[0170] The performance monitoring request is sent to the network device based on Media Access Control Element (MAC-CE) signaling. For example, the terminal device may send the performance monitoring request using MAC-CE signaling, and the MAC-CE signaling may also include target information.

[0171] Another possible implementation:

[0172] Based on the reserved period physical uplink control channel (PUCCH) resources or PUSCH resources, a performance monitoring request is sent to the network device. For example, the terminal device can report the performance monitoring request in the reserved period PUCCH resources or PUSCH resources based on L1 resource pre-configuration.

[0173] S202: The network device sends a response to the performance monitoring request to the terminal device.

[0174] Among them, after the network device receives the performance monitoring request sent by the terminal device, it can respond to the performance monitoring request. In some embodiments, the response to the performance monitoring request may include a reply or indication of the monitoring request. For example, the response to the performance monitoring request may include agreeing to turn on the performance monitoring of the AI ​​model and / or agreeing to activate the performance monitoring of the AI ​​model, and the response to the performance monitoring request may include refusing to turn on the performance monitoring of the AI ​​model and / or refusing to activate the performance monitoring of the AI ​​model.

[0175] After the network device determines the response to the monitoring request, it may send the response to the monitoring request to the terminal device.

[0176] Among them, the network device can send a response to the performance monitoring request to the terminal device according to the following feasible implementation method: receive a scheduling request SR sent by the terminal device, and send a response to the scheduling request SR sent by the terminal device.

[0177] Among them, the response to the scheduling request SR includes downlink control information (DCI) of uplink transmission resource allocation, and the downlink control information DCI is encrypted based on the radio network temporary identifier (RNTI) of the terminal device. For example, when the terminal device sends a performance monitoring request for the AI ​​model to the network device based on the UCI call request SR, the terminal device can send the SR on the PUCCH or random access channel (RACH). After receiving the SR, the network device can send an uplink grant as a response to the scheduling request SR, wherein the uplink grant may include the DCI of uplink transmission resource allocation, which can be encrypted based on the RNTI of the terminal device (in order to distinguish the DCI response of the network side to other UE uplink transmission scheduling requests, the RNTI of the terminal device can be a newly defined dedicated RNTI). If the terminal device receives the same RNTI and can descramble the DCI, then the terminal device can determine that the network device has received the performance monitoring request sent by the terminal device.

[0178] In some embodiments, when the terminal device sends a performance monitoring request for the AI ​​model based on MAC-CE, the response information of the network device is a DCI format for scheduling PUSCH transmission. The DCI format may include the same Hybrid Automatic Repeat reQuest (HARQ) process number (process number) of the PUSCH of the MAC-CE to which the terminal device sends the performance monitoring request, and a flipped Network Device Interface (NDI) field. When the terminal device detects the DCI, it determines that the network device has received the monitoring request. For example, the NDI field can be a 1-bit indication field. If the NDI field is reversed (from 0 to 1, or from 1 to 0), it indicates that the data transmission is a new transmission rather than a retransmission. For example, the DCI responded by the base station can be the DCI format for scheduling PUSCH transmission, wherein the HARQ process ID of the newly scheduled PUSCH is different from the HARQ process ID of the PUSCH to which the terminal device previously sent MAC-CE (the HARQ process ID can be accumulated). Therefore, if the terminal device detects that the DCI has the same HARQ process ID as the PUSCH to which the MAC-CE was previously sent, it means that the DIC responded by the base station corresponds to the MAC-CE sent by the terminal device.

[0179] S203. The terminal device performs performance monitoring on the AI ​​model based on the response to the performance monitoring request.

[0180] Among them, the terminal device can receive the response to the performance monitoring request sent by the network device, and perform performance monitoring on the AI ​​model based on the response to the performance monitoring request. For example, if the response to the performance monitoring request is to agree to enable performance monitoring, the terminal device can receive the reference signal of the AI ​​model sent by the network device, and then perform performance monitoring on the AI ​​model. If the response to the monitoring request is to refuse to enable performance monitoring, the terminal device can stop enabling performance monitoring or continue to send performance monitoring requests to the network device. This embodiment of the present disclosure is not limited to this.

[0181] In some embodiments, after a terminal device sends a performance monitoring request for an AI model to a network device, if the terminal device does not receive a response to the performance monitoring request within a certain period of time, the terminal device may resend the performance monitoring request to the network device. The performance monitoring request may be a regenerated performance monitoring request or an already generated performance monitoring request, which is not limited in the embodiments of the present disclosure. For example, if a terminal device sends a performance monitoring request to a network device and does not receive a response to the performance monitoring request within 10 seconds, the terminal device may resend the performance monitoring request to the network device.

[0182] In some embodiments, after the terminal device sends a performance monitoring request to the network device multiple times, if the terminal device does not receive a response to the performance monitoring request, the terminal device can send the performance monitoring of the AI ​​model to the network device according to the triggering event. For example, after the terminal device sends a performance monitoring request to the network device three times and has not received a response to the performance monitoring request, the terminal device can regenerate the performance monitoring request (the monitoring request can include more target information, etc.) according to the triggering event and send the performance monitoring request to the network device. In this way, the accuracy and timeliness of the performance monitoring of the AI ​​model can be improved.

[0183] Below, in conjunction with Figures 3-5, the process of terminal equipment monitoring the performance of the AI ​​model is described, where the AI ​​model is a model for processing CSI.

[0184] Figure 3 is a schematic diagram of a method for performance monitoring of an AI model provided by an embodiment of the present disclosure. In the embodiment shown in Figure 3, the part of the model that compresses CSI is located in the terminal device, and the part of the model that decompresses CSI is located in the network device. The network device performs performance monitoring of the AI ​​model, please refer to Figure 3, including the terminal device and the network device. When the terminal device turns on the performance monitoring of the AI ​​model, the network device can send a reference signal related to the channel state information to the terminal device. The terminal device can obtain the measured channel state information based on the reference signal, and the terminal device can compress the measured channel state information based on the compressed part of the model.

[0185] As shown in Figure 3, the terminal device can send compressed channel state information to the network device. The network device can then decompress the compressed channel state information based on the decompressed portion of the model to obtain decompressed channel state information. The terminal device can also send measured channel state information to the network device. The network device can then determine the performance of the model based on the measured and decompressed channel state information. This allows the network device to calculate intermediate KPIs based on the measured and decompressed CSI, and then determine the performance of the AI ​​model based on the intermediate KPIs, thereby improving the accuracy of the model's performance monitoring.

[0186] Figure 4 is a schematic diagram of another method for performance monitoring of an AI model provided by an embodiment of the present disclosure. In the embodiment shown in Figure 4, the part of the model that compresses CSI is located in the terminal device, and the part of the model that decompresses CSI is located in the network device. The terminal device performs performance monitoring of the AI ​​model, please refer to Figure 4, including the terminal device and the network device. When the terminal device turns on the performance monitoring of the AI ​​model, the network device can send a reference signal related to the channel state information to the terminal device. The terminal device can obtain the measured channel state information based on the reference signal, and the terminal device can compress the measured channel state information based on the compressed part of the model.

[0187] As shown in Figure 4, the terminal device can send compressed channel state information to the network device. The network device can then decompress the compressed channel state information based on the decompressed portion of the model to obtain decompressed channel state information. The network device can then send the decompressed channel state information to the terminal device, which can then determine the performance of the model based on the measured and decompressed channel state information. This allows the terminal device to calculate intermediate KPIs based on the measured and decompressed CSI, and then determine the performance of the AI ​​model based on these intermediate KPIs, thereby improving the accuracy of the model's performance monitoring.

[0188] Figure 5 is a schematic diagram of another method for monitoring the performance of an AI model provided by an embodiment of the present disclosure. In the embodiment shown in Figure 5, the part of the model that compresses CSI is located in the terminal device, and the part of the model that decompresses CSI is located in the network device. The terminal device monitors the AI ​​model, and the terminal device also includes a replacement model for the part of the model that decompresses CSI. Please refer to Figure 5, including the terminal device and the network device. When the terminal device turns on the performance monitoring of the AI ​​model, the network device can send a reference signal related to the channel state information to the terminal device. The terminal device can obtain the measured channel state information based on the reference signal, and the terminal device can compress the measured channel state information based on the compressed part of the model.

[0189] As shown in Figure 5, the terminal device can send compressed channel state information to the network device. The network device can then decompress the compressed channel state information based on the decompressed portion of the model to obtain decompressed channel state information. The terminal device can then decompress the compressed channel state information based on the alternative model and determine the model's performance based on the measured and decompressed channel state information. This allows the terminal device to calculate intermediate KPIs based on the measured and decompressed CSI, and further determine the performance of the AI ​​model based on the intermediate KPIs, thereby improving the accuracy of the model's performance monitoring.

[0190] It should be noted that, in the embodiments shown in FIG. 3 to FIG. 5 , sequence numbers 1, 2, ..., 7 are only used to illustrate the steps, and do not limit the order in which the steps are executed.

[0191] The disclosed embodiment provides a performance monitoring method, in which a terminal device can send a performance monitoring request of an AI model to a network device according to a triggering event, wherein the triggering event may include a first event related to the AI ​​model and / or function, and a second event related to the performance of the terminal device. The monitoring request may include an identifier of the AI ​​model, an identifier of the function of the AI ​​model, a start time and an end time of performance monitoring, and target information related to the performance indicators and measurement values ​​of the AI ​​model. The terminal device can receive a response to the performance monitoring request sent by the network device, and perform performance monitoring on the AI ​​model according to the response to the performance monitoring request. In this way, since the terminal device can start the performance monitoring process, there is no need for the network device to frequently (periodically or semi-periodically) start performance monitoring of the AI ​​model, thereby saving communication resources.

[0192] Based on the embodiment shown in Figure 2, when the AI ​​model is not activated, selected or paired, the first event may include at least one of the following: sending the identification of the supported AI model and / or the identification of the function, receiving the identification of the AI ​​model and / or the identification of the function supported by the cell covered by the current base station. Below, in combination with Figures 6-7, the process of triggering the first event in this scenario is explained.

[0193] FIG6 is a schematic diagram of a method for triggering a first event provided by an embodiment of the present disclosure. In the embodiment shown in FIG6 , the first event is the terminal device sending an identifier of a supported AI model and / or an identifier of a function. Referring to FIG6 , the method flow includes:

[0194] S601. The terminal device sends an identifier of an AI model and / or an identifier of a function supported by the terminal device to a network device.

[0195] Among them, when the AI ​​model is not activated, selected or paired, the AI ​​model or function in the current scene has not been enabled. Therefore, the terminal device can send a performance monitoring request for the AI ​​model when turning on AI model activation, AI model selection or AI model pairing.

[0196] Among them, the first event may be an event of sending an identifier of a supported AI model and / or an identifier of a function. For example, the terminal device may send an identifier of an AI model that the terminal device can currently support (or an identifier of a function) to the network device, and the network device may determine the activated AI model based on the identifier of the AI ​​model. For example, the terminal device sends to the network device identifiers of AI models supported by the terminal device, including: an identifier of AI model 1, an identifier of AI model 2, and an identifier of AI model 3. If the network device supports AI model 1 and AI model 2, the network device may activate AI model 1 and AI model 2.

[0197] It should be noted that when a terminal device accesses a new network, the terminal device can send the identification of the supported AI model and / or the identification of the function to the network device. The terminal device can also send the identification of the supported AI model and / or the identification of the function to the network device in any feasible scenario. The embodiments of the present disclosure are not limited to this.

[0198] S602: The terminal device sends a performance monitoring request to the network device.

[0199] Among them, when the terminal device sends the identifier of the supported AI model and / or the identifier of the function to the network device, the terminal device can determine that a trigger event has occurred, and the terminal device can send a performance monitoring request for the AI ​​model to the network device. For example, the terminal device sends the identifier of the supported AI model to the network device, the network device can send the identifier of the activated AI model to the AI ​​model, and the terminal device can send a performance monitoring request to the network device. The monitoring request can include the identifier of the activated AI model. In this way, when the AI ​​model is activated, the terminal device can start performance monitoring of the AI ​​model, thereby improving the stability of communication.

[0200] In some embodiments, the performance monitoring request may include the start time of performance monitoring and / or the end time of performance monitoring. For example, when the AI ​​model is not activated, selected, or paired, and the AI ​​model and / or function is not yet enabled, after the network device activates, selects, or pairs the AI ​​model, the terminal device may instruct the network model to execute the performance monitoring process of the AI ​​model after the AI ​​model is activated, selected, or paired for a period of time, thereby improving the accuracy of the performance monitoring of the AI ​​model.

[0201] It should be noted that, in this scenario, the performance monitoring request may also carry target information, which is not limited in the embodiments of the present disclosure.

[0202] The embodiment of the present disclosure provides a method for triggering a first event, sending an identifier of an AI model and / or an identifier of a function supported by a terminal device to a network device, and sending a model monitoring request to the network device. In this way, when a terminal device accesses a new network, the terminal device can promptly send the supported AI model and / or function to the network device, thereby activating, selecting, or pairing the AI ​​model and / or function supported by both the terminal device and the network device. Moreover, when the AI ​​model is activated, selected, or paired, the terminal device can start performance monitoring of the AI ​​model to improve the stability of communication.

[0203] FIG7 is a schematic diagram of another method for triggering a first event provided by an embodiment of the present disclosure. In the embodiment shown in FIG7 , the first event is that the terminal device receives an identifier of an AI model and / or an identifier of a function supported by a cell currently covered by a base station. Referring to FIG7 , the method flow includes:

[0204] S701. The terminal device receives the identifier of the AI ​​model and / or the identifier of the function supported by the cell currently covered by the base station.

[0205] Among them, the terminal device can receive the identifier of the AI ​​model and / or the identifier of the function supported by the cell covered by the current base station. For example, when the terminal device performs cell switching, the AI ​​model has not been activated, selected or paired. Therefore, the terminal device can determine the activated, selected or paired AI model or function, and start performance monitoring of the AI ​​model. For example, the network device can send the identifier of the AI ​​model supported by the cell (or the identifier of the function) to the terminal device, and the terminal device can determine the activated, selected and paired AI model based on the identifier of the AI ​​model supported by the cell and the identifier of the AI ​​model supported by the terminal device.

[0206] For example, the network device sends to the terminal device the identifiers of the AI ​​models supported by the cell, including: the identifier of AI model 1, the identifier of AI model 2, and the identifier of AI model 3. If the terminal device supports AI model 1 and AI model 2, the terminal device can request to activate AI model 1 and AI model 2.

[0207] It should be noted that when the terminal device is located in a new cell or is switching cells, the terminal device can receive the identifier of the AI ​​model supported by the cell and / or the identifier of the function sent by the network device. The terminal device can also receive the identifier of the AI ​​model supported by the cell and / or the identifier of the function sent by the network device in any feasible scenario. The embodiments of the present disclosure are not limited to this.

[0208] S702: The terminal device sends a performance monitoring request to the network device.

[0209] Among them, when the terminal device receives the identifier of the AI ​​model and / or the identifier of the function supported by the cell covered by the current base station sent by the network device, the terminal device can determine that a trigger event has occurred, and the terminal device can send a performance monitoring request for the AI ​​model to the network device. For example, when the terminal device receives the identifier of the AI ​​model supported by the cell sent by the network device, the terminal device can determine the activated AI model and send the identifier of the activated AI model to the network device, and the terminal device can send a performance monitoring request for the AI ​​model to the network device. In this way, when the AI ​​model is activated, the terminal device can start performance monitoring of the AI ​​model, thereby improving the stability of communication.

[0210] In some embodiments, the performance monitoring request may include the identification of the AI ​​model, the identification of the function, the start time of performance monitoring, the end time of performance monitoring and target information, which is not limited in the embodiments of the present disclosure.

[0211] The disclosed embodiments provide a method for triggering a first event, wherein a terminal device receives an identifier of an AI model and / or an identifier of a function supported by a cell currently covered by a base station, and the terminal device sends a performance monitoring request to a network device. In this way, when the terminal device switches cells, the terminal device can promptly activate the AI ​​model or function supported by both the terminal device and the network device, and when the AI ​​model or function is activated, the terminal device can start performance monitoring, thereby improving communication stability.

[0212] Based on any of the above embodiments, when the AI ​​model has been activated, selected or paired, the terminal device can determine a first event based on at least one information, wherein the at least one information may include the measured final key performance indicators, statistical information and / or distribution information of the measured CSI-related information, statistical information and / or distribution information of the CSI-related information inferred by the AI ​​model, the generalization indicator of the AI ​​model, the update information of the AI ​​model and / or the transmission information of the AI ​​model. When the terminal device determines that the first event is triggered, the terminal device can send a performance monitoring request of the AI ​​model to the network device.

[0213] Below, in combination with Figures 8-12, the process of the terminal device sending a performance monitoring request in this scenario is explained. It should be noted that the threshold, duration and target value in the embodiment of the present disclosure are based on protocol pre-definition and / or network side configuration and / or a mixture of protocol pre-definition and network side configuration.

[0214] FIG8 is a schematic diagram of a method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG8 , in the embodiment shown in FIG8 , the first event is an event determined based on the final key performance indicator measured, and the method flow includes:

[0215] S801. Obtain the final key performance indicators of the measurement.

[0216] The final key performance indicator measured may be a final KPI measured by the terminal device. For example, the final KPI measured by the terminal device may include parameters such as user throughput and block error rate, which are not limited in the present embodiment.

[0217] It should be noted that the terminal device can measure the final KPI according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0218] S802: Determine triggering of a first event based on the final key performance indicator measured.

[0219] If the first event is an event determined based on the measured final key performance indicator, the first event includes at least one of the following:

[0220] The first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter;

[0221] The second parameter in the final key performance indicator is greater than the threshold corresponding to the second parameter

[0222] The number of times that the first parameter in the final key performance indicator within the first time period is less than the threshold corresponding to the first parameter is greater than the first threshold;

[0223] The number of times that the second parameter in the final key performance indicator within the first time period is greater than the threshold corresponding to the second parameter is greater than the first threshold;

[0224] The deviation between the parameter in the final key performance indicator and the first target value is greater than the second threshold.

[0225] The first parameter may be proportional to the performance of the AI ​​model. For example, a larger first parameter in the final KPI indicates higher AI model performance, and a smaller first parameter in the final KPI indicates lower AI model performance. For example, the first parameter may be user throughput. A higher user throughput indicates better communication quality, which in turn indicates higher AI model performance. A lower user throughput indicates poor communication quality, which in turn indicates lower AI model performance.

[0226] The second parameter is inversely proportional to the performance of the AI ​​model. For example, the larger the second parameter in the final KPI, the lower the performance of the AI ​​model, and the smaller the second parameter in the final KPI, the higher the performance of the AI ​​model. For example, the second parameter can be the block error rate. A large block error rate indicates poor communication quality and, in turn, low AI model performance. A small block error rate indicates good communication quality and, in turn, high AI model performance.

[0227] The first target value is the target value corresponding to the parameter in the final key performance indicator. For example, if the parameter in the final KPI is throughput, the first target value may be the target value corresponding to throughput; if the parameter in the final KPI is block error rate, the first target value may be the target value corresponding to the block error rate.

[0228] It should be noted that the first threshold, the second threshold, the first duration, the first target value, the threshold corresponding to the first parameter, and the threshold corresponding to the second parameter can be obtained by protocol pre-definition and / or network device configuration and / or a mixture of protocol pre-definition and network side configuration, or can be determined based on any other feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0229] In some embodiments, if a first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter, the terminal device may determine that a first event has been triggered. For example, the first parameter may be throughput, and the threshold corresponding to the throughput may be a preset throughput. If the throughput measured by the terminal device is less than the preset throughput, it indicates that the current communication quality is poor, and the terminal device triggers the first event, thereby sending a performance monitoring request for the AI ​​model to the network device.

[0230] In some embodiments, if a second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter, the terminal device may determine that a first event has been triggered. For example, the second parameter may be a block error rate, and the threshold corresponding to the block error rate may be a preset block error rate. If the block error rate measured by the terminal device is greater than the preset block error rate, it indicates that the current communication quality is poor, and the terminal device triggers the first event, thereby sending a performance monitoring request for the AI ​​model to the network device.

[0231] In some embodiments, if the first parameter in the final key performance indicator is less than the number of times the threshold corresponding to the first parameter is greater than the first threshold within the first time period, the terminal device can determine that the first event is triggered. For example, the first parameter can be throughput, the threshold corresponding to the throughput can be threshold 1, and the first threshold can be threshold 2. Within the first time period, if the throughput measured by the terminal device (the terminal device can measure the throughput based on a preset sampling frequency) is less than threshold 1 10 times, and 10 times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the first time period is 10 seconds, the threshold corresponding to the throughput is the preset throughput, and the first threshold is 3 times. If the throughput measured by the terminal device within 10 seconds is less than the preset throughput 10 times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the AI ​​model to the network device.

[0232] In some embodiments, if the number of times the second parameter in the final key performance indicator is greater than the threshold corresponding to the second parameter within the first time period is greater than the first threshold, the terminal device can determine that the first event is triggered. For example, the second parameter can be the block error rate, the threshold corresponding to the block error rate can be threshold 1, and the second threshold can be threshold 2. Within the first time period, if the block error rate measured by the terminal device is less than threshold 1 10 times, and 10 times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the first time period is 10 seconds, the threshold corresponding to the block error rate is the preset block error rate, and the first threshold is 3 times. If the block error rate measured by the terminal device within 10 seconds is less than the preset block error rate 4 times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the AI ​​model to the network device.

[0233] In some embodiments, if the deviation between the parameter in the final key performance indicator and the first target value is greater than the second threshold, the terminal device can determine that the first event is triggered. For example, the parameter in the final key performance indicator may include a first parameter and a second parameter, wherein each parameter has a corresponding first target value. If the deviation between the parameter in the final KPI and the first target value corresponding to the parameter is greater than the second threshold, it means that the current communication quality is poor, and the terminal device can send a performance monitoring request of the AI ​​model to the network device. For example, the parameter of the final KPI is throughput, and the first target value corresponding to the throughput is a preset throughput. If the difference between the throughput measured by the terminal device and the preset throughput is greater than the second threshold, the terminal device can determine that the first event is triggered and send a performance monitoring request to the network device.

[0234] S803: Send a performance monitoring request to the network device.

[0235] Among them, when the terminal device determines that the first event is currently triggered based on the final KPI, the terminal device can send a monitoring request of the AI ​​model to the network device.

[0236] The disclosed embodiment provides a method for sending a monitoring request, wherein a terminal device can obtain the final key performance indicator of the measurement, and based on the final key performance indicator of the measurement, determine that the terminal device triggers a first event, and send a monitoring request to a network device. In this way, the terminal device can determine the communication quality based on the final KPI, and determine whether to enable the monitoring of the AI ​​model based on the communication quality. In this way, when an emergency event occurs in which the communication quality degrades, the terminal device can promptly monitor the performance of the AI ​​model, thereby improving the performance monitoring accuracy of the AI ​​model and thereby improving the stability of the communication.

[0237] FIG9 is a schematic diagram of another method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG9 , in the embodiment shown in FIG9 , the first event is an event determined based on statistical information and / or distribution information of measured CSI-related information. The method flow includes:

[0238] S901. Obtain statistical information and / or distribution information of measured CSI-related information.

[0239] The statistical information and / or distribution information of the measured CSI-related information may include information such as average delay and delay spread corresponding to the CSI-related information measured by the terminal device. For example, the CSI-related information may be CSI information, and the statistical information and / or distribution information corresponding to the CSI information measured by the terminal device may include average delay, delay spread, Doppler shift, Doppler spread, LOS distribution, NLOS distribution, channel covariance matrix, and KL (Kullback-Leibler) divergence, etc. associated with the CSI information.

[0240] It should be noted that the terminal device can obtain statistical information and / or distribution information of the measured CSI-related information according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0241] S902: Determine triggering of a first event based on statistical information and / or distribution information of measured CSI-related information.

[0242] If the first event is an event determined based on statistical information and / or distribution information of measured CSI-related information, the first event includes at least one of the following:

[0243] A third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than a threshold corresponding to the third parameter;

[0244] A fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than a threshold corresponding to the fourth parameter;

[0245] The number of times that a third parameter in the statistical information and / or distribution information of the CSI-related information measured within the second duration is greater than a threshold corresponding to the third parameter is greater than the third threshold;

[0246] The number of times that a fourth parameter in the statistical information and / or distribution information of the CSI-related information measured within the second duration is greater than a threshold corresponding to the fourth parameter is greater than the third threshold;

[0247] A deviation between a parameter in the statistical information and / or distribution information of the measured CSI-related information and the second target value is greater than a fourth threshold.

[0248] The third parameter may be inversely proportional to the performance of the AI ​​model. For example, the larger the third parameter in the statistical information and distribution information, the lower the performance of the AI ​​model, and the smaller the third parameter in the statistical information and distribution information, the higher the performance of the AI ​​model. For example, the third parameter may be average latency. A larger average latency indicates poor communication quality, which in turn indicates low AI model performance. A smaller average latency indicates better communication quality, which in turn indicates high AI model performance.

[0249] The fourth parameter may be proportional to the performance of the AI ​​model. For example, a larger fourth parameter in the statistical information and distribution information indicates a higher performance of the AI ​​model, and a smaller fourth parameter in the statistical information and distribution information indicates a lower performance of the AI ​​model. The fourth parameter may be any parameter in the statistical information and distribution information that is proportional to the performance of the AI ​​model, and this disclosure is not limited thereto.

[0250] The second target value is a target value corresponding to a parameter in the statistical information and / or distribution information of the measured CSI-related information. For example, if the parameter in the statistical information and distribution information is average delay, the second target value may be a target value corresponding to the average delay; if the parameter in the statistical information and distribution information is delay spread, the second target value may be a target value corresponding to delay spread.

[0251] It should be noted that the third threshold, the fourth threshold, the second duration, the second target value, the threshold corresponding to the third parameter, and the threshold corresponding to the fourth parameter can be predefined by the protocol and / or configured by the network device, or can be determined based on any other feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0252] In some embodiments, if a third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than a threshold corresponding to the third parameter, the terminal device may determine that a first event has been triggered. For example, the third parameter may be an average delay, and the threshold corresponding to the average delay may be a preset delay. If the average delay calculated by the terminal device is greater than the preset delay, it indicates that the current communication quality is poor, and the terminal device triggers the first event, and may then send a performance monitoring request for the AI ​​model to the network device.

[0253] In some embodiments, if a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than a threshold corresponding to the fourth parameter, the terminal device may determine that a first event has been triggered. For example, if the fourth parameter calculated by the terminal device is less than the threshold corresponding to the fourth parameter, it indicates that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request of the AI ​​model to the network device.

[0254] In some embodiments, if the third parameter in the statistical information and / or distribution information of the CSI-related information measured within the second time length is greater than the number of times the threshold corresponding to the third parameter is greater than the third threshold, the terminal device can determine that the first event is triggered. For example, the third parameter can be the average delay, the threshold corresponding to the average delay can be threshold 1, and the third threshold can be threshold 2. Within the second time length, if the average delay calculated by the terminal device is greater than threshold 1 10 times, and 10 times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the second time length is 10 seconds, the threshold corresponding to the average delay is the preset delay, and the third threshold is 3 times. If the average delay calculated by the terminal device within 10 seconds is greater than the preset delay 4 times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the AI ​​model to the network device.

[0255] In some embodiments, if the fourth parameter in the statistical information and / or distribution information of the CSI-related information measured within the second time length is less than the number of times the fourth parameter corresponds to the threshold, and is greater than the third threshold, the terminal device can determine that the first event is triggered. For example, the threshold corresponding to the fourth parameter can be threshold 1, and the third threshold can be threshold 2. Within the second time length, if the fourth parameter calculated by the terminal device is less than threshold 1 four times, and four times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the second time length is 10 seconds, the threshold corresponding to the fourth parameter is a preset threshold, and the third threshold is 3 times. If the fourth parameter corresponding to the statistical information and / or distribution information of the CSI-related information measured by the terminal device within 10 seconds is less than the preset threshold four times, the terminal device can determine that the first event is triggered, and send a performance monitoring request for the AI ​​model to the network device.

[0256] In some embodiments, if the deviation of the parameter in the statistical information and / or distribution information of the measured CSI-related information from the second target value is greater than a fourth threshold, the terminal device can determine that the first event is triggered. For example, the parameter in the statistical information and / or distribution information of the measured CSI-related information may include a third parameter and a fourth parameter, wherein each parameter has a corresponding second target value. If the deviation of the parameter in the statistical information and / or distribution information of the measured CSI-related information from the second target value corresponding to the parameter is greater than the fourth threshold, it means that the current communication quality is poor, and the terminal device can send a performance monitoring request for the AI ​​model to the network device. For example, the parameter in the statistical information and / or distribution information of the measured CSI-related information is the average delay, and the second target value corresponding to the average delay is the preset delay. If the difference between the average delay calculated by the terminal device and the preset delay is greater than the fourth threshold, the terminal device can determine that the first event is triggered and send a performance monitoring request to the network device.

[0257] S903: Send a performance monitoring request to the network device.

[0258] Among them, when the terminal device determines that the first event is currently triggered based on the statistical information and / or distribution information of the measured CSI-related information, the terminal device can send a performance monitoring request of the AI ​​model to the network device.

[0259] The embodiments of the present disclosure provide a method for sending a performance monitoring request, obtaining statistical information and / or distribution information of measured CSI-related information, determining that a terminal device triggers a first event based on the statistical information and / or distribution information of the measured CSI-related information, and sending a performance monitoring request to a network device. In this way, the terminal device can determine the communication quality based on the statistical information and / or distribution information of the measured CSI-related information, and determine whether to enable performance monitoring of the AI ​​model based on the communication quality. In this way, when an emergency event occurs in which the communication quality degrades, the terminal device can promptly monitor the performance of the AI ​​model, thereby improving the performance monitoring accuracy of the AI ​​model and thereby improving the stability of the communication.

[0260] FIG10 is a schematic diagram of another method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG10 , in the embodiment shown in FIG10 , the first event is determined based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model. The method flow includes:

[0261] S1001. Obtain statistical information and / or distribution information of CSI-related information inferred by the AI ​​model.

[0262] The statistical information and / or distribution information of the CSI-related information inferred by the AI ​​model may include information such as average delay and delay spread corresponding to the CSI-related information inferred by the AI ​​model. For example, the CSI-related information may be beam information, and the statistical information and / or distribution information corresponding to the beam information inferred by the AI ​​model may include average delay, delay spread, Doppler shift, Doppler spread, LOS distribution, NLOS distribution, channel covariance matrix, and KL (Kullback-Leibler) divergence, etc. associated with the beam information.

[0263] It should be noted that the terminal device can obtain statistical information and / or distribution information of CSI-related information inferred by the AI ​​model according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0264] S1002. Determine triggering a first event based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model.

[0265] If the first event is an event determined based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model, the first event includes at least one of the following:

[0266] A fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than a threshold corresponding to the fifth parameter;

[0267] A sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than a threshold corresponding to the sixth parameter;

[0268] The number of times that a fifth parameter in the statistical information and / or distribution information of the CSI-related information inferred within the third duration is greater than a threshold corresponding to the fifth parameter is greater than the fifth threshold;

[0269] The number of times that a sixth parameter in the statistical information and / or distribution information of the CSI-related information inferred within the third duration is greater than a threshold corresponding to the sixth parameter is greater than the fifth threshold;

[0270] A deviation between a parameter in the statistical information and / or distribution information of the inferred CSI-related information and the third target value is greater than a sixth threshold.

[0271] The fifth parameter may be inversely proportional to the performance of the AI ​​model. For example, the larger the fifth parameter in the statistical information and distribution information, the lower the performance of the AI ​​model, and the smaller the fifth parameter in the statistical information and distribution information, the higher the performance of the AI ​​model. For example, the fifth parameter may be average latency. A larger average latency indicates poor communication quality, which in turn indicates low AI model performance. A smaller average latency indicates better communication quality, which in turn indicates high AI model performance.

[0272] The sixth parameter may be proportional to the performance of the AI ​​model. For example, a larger sixth parameter in the statistical information and distribution information indicates a higher performance of the AI ​​model, and a smaller sixth parameter in the statistical information and distribution information indicates a lower performance of the AI ​​model. The sixth parameter may be any parameter in the statistical information and distribution information that is proportional to the performance of the AI ​​model, and this disclosure is not limited thereto.

[0273] The third target value is a target value corresponding to a parameter in the statistical information and / or distribution information of the inferred CSI-related information. For example, if the parameter in the statistical information and distribution information is average delay, the third target value may be a target value corresponding to the average delay; if the parameter in the statistical information and distribution information is delay spread, the third target value may be a target value corresponding to delay spread.

[0274] It should be noted that the fifth threshold, the sixth threshold, the third time duration, the third target value, the threshold corresponding to the fifth parameter, and the threshold corresponding to the sixth parameter can be predefined by the protocol and / or configured by the network device, or can be determined based on any other feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0275] In some embodiments, if a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than a threshold corresponding to the fifth parameter, the terminal device may determine that a first event has been triggered. For example, the fifth parameter may be average latency, and the threshold corresponding to the average latency may be a preset latency. If the average latency calculated by the terminal device is greater than the preset latency, it indicates that the current communication quality is poor, and the terminal device triggers the first event, thereby sending a performance monitoring request for the AI ​​model to the network device.

[0276] In some embodiments, if a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than a threshold corresponding to the sixth parameter, the terminal device may determine that a first event has been triggered. For example, if the sixth parameter calculated by the terminal device is less than the threshold corresponding to the sixth parameter, it indicates that the current communication quality is poor, and the terminal device triggers the first event, and then may send a performance monitoring request of the AI ​​model to the network device.

[0277] In some embodiments, if the fifth parameter in the statistical information and / or distribution information of the CSI-related information inferred within the third time length is greater than the number of times the threshold corresponding to the fifth parameter is greater than the fifth threshold, the terminal device can determine that the first event is triggered. For example, the fifth parameter can be the average delay, the threshold corresponding to the average delay can be threshold 1, and the fifth threshold can be threshold 2. Within the second time length, if the average delay calculated by the terminal device is greater than threshold 1 four times, and four times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the third time length is 10 seconds, the threshold corresponding to the average delay is the preset delay, and the fifth threshold is 3 times. If the average delay calculated by the terminal device within 10 seconds is greater than the preset delay four times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the AI ​​model to the network device.

[0278] In some embodiments, if the sixth parameter in the statistical information and / or distribution information of the CSI-related information inferred within the third time length is less than the number of times the threshold corresponding to the sixth parameter is greater than the fifth threshold, the terminal device can determine that the first event is triggered. For example, the threshold corresponding to the sixth parameter can be threshold 1, and the fifth threshold can be threshold 2. Within the second time length, if the sixth parameter calculated by the terminal device is less than threshold 1 four times, and four times is greater than threshold 2, the terminal device can determine that the current communication quality is poor, the terminal device triggers the first event, and then can send a performance monitoring request for the AI ​​model to the network device. For example, the third time length is 10 seconds, the threshold corresponding to the sixth parameter is a preset threshold, and the fifth threshold is 3 times. If the sixth parameter calculated by the terminal device within 10 seconds is less than the preset threshold four times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the AI ​​model to the network device.

[0279] In some embodiments, if the deviation of the parameters in the statistical information and / or distribution information of the inferred CSI-related information from the third target value is greater than the sixth threshold, the terminal device can determine that the first event is triggered. For example, the parameters in the statistical information and / or distribution information of the inferred CSI-related information may include a fifth parameter and a sixth parameter, wherein each parameter has a corresponding third target value. If the deviation of the parameters in the statistical information and / or distribution information of the inferred CSI-related information from the third target value corresponding to the parameter is greater than the sixth threshold, it means that the current communication quality is poor, and the terminal device can send a performance monitoring request for the AI ​​model to the network device. For example, the parameter in the statistical information of the inferred CSI-related information is the average delay, and the third target value corresponding to the average delay is the preset delay. If the difference between the average delay calculated by the terminal device and the preset delay is greater than the sixth threshold, the terminal device can determine that the first event is triggered and send a performance monitoring request to the network device.

[0280] S1003. Send a performance monitoring request to the network device.

[0281] Among them, when the terminal device determines that the first event is currently triggered based on the statistical information and / or distribution information of the inferred CSI-related information, the terminal device can send a performance monitoring request of the AI ​​model to the network device.

[0282] The embodiments of the present disclosure provide a method for sending a performance monitoring request, obtaining statistical information and / or distribution information of inferred CSI-related information, determining that a terminal device triggers a first event based on the statistical information and / or distribution information of the inferred CSI-related information, and sending a performance monitoring request to a network device. In this way, the terminal device can determine the communication quality based on the statistical information and / or distribution information of the inferred CSI-related information, and determine whether to enable performance monitoring of the AI ​​model based on the communication quality. In this way, when an emergency event occurs in which the communication quality degrades, the terminal device can promptly monitor the performance of the AI ​​model, thereby improving the performance monitoring accuracy of the AI ​​model and thereby improving the stability of the communication.

[0283] FIG11 is a schematic diagram of another method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG11 , in the embodiment shown in FIG11 , the first event is an event determined based on the generalization indicator of the AI ​​model, and the method flow includes:

[0284] S1101. Obtain the generalization index of the AI ​​model.

[0285] The generalization indicators of the AI ​​model can indicate the performance of the AI ​​model. For example, the generalization indicators of the AI ​​model can include the environment, scene, speed, location, physical layer carrier resource configuration, etc. of the terminal device (where the AI ​​model is located).

[0286] It should be noted that the terminal device can obtain the generalization index of the AI ​​model according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0287] S1102. Determine triggering of a first event based on a generalization indicator of the AI ​​model.

[0288] If the first event is an event determined based on the generalization indicator of the AI ​​model, the first event includes at least one of the following:

[0289] a duration during which a parameter in a performance indicator of the received reference signal is less than a seventh threshold and greater than an eighth threshold;

[0290] the number of times that a parameter in the performance indicator of the received reference signal is less than a seventh threshold within a fourth duration and greater than a ninth threshold;

[0291] The quasi co-location information of the received reference signal changes;

[0292] The dataset label of the measured CSI-related information has changed;

[0293] The duration during which the parameter in the measured speed information is greater than the tenth threshold is greater than the eleventh threshold;

[0294] The number of times that the parameter in the measured speed information is greater than the tenth threshold within the fifth time period is greater than the twelfth threshold;

[0295] The distance difference between the two positions measured at a sixth time interval is greater than the thirteenth threshold.

[0296] The reference signal may be a signal containing information related to CSI processed by the AI ​​model. For example, if the AI ​​model processes CSI, the reference signal may be a CSI-related reference signal; if the AI ​​model processes beamforming, the reference signal may be a beam-related reference signal; and if the AI ​​model processes positioning, the reference signal may be a positioning-related reference signal.

[0297] The performance indicators of the reference signal may include SINR, L1 (L1 level filtering)-RSRP, L1-RSRQ, and L3 (L3 level filtering)-RSRP. The performance indicators of the reference signal may also include any other indicators, which are not limited in the embodiments of the present disclosure. For example, the terminal device may receive the reference signal sent by the network device.

[0298] The Quasi Co-location (QCL) information may include QCL source and QCL type.

[0299] It should be noted that the fourth time duration, the fifth time duration, the sixth time duration, the seventh threshold, the eighth threshold, the ninth threshold, the tenth threshold, the eleventh threshold, the twelfth threshold, and the thirteenth threshold can be predefined by the protocol and / or configured by the network device, or can be determined based on any other feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0300] In some embodiments, if a parameter in a performance indicator of a reference signal received by a terminal device is less than a seventh threshold for a duration and greater than an eighth threshold, the terminal device may determine that a first event has been triggered. For example, the performance indicator of the reference signal may be a SINR. If the duration of the SINR being less than the seventh threshold for a duration greater than the eighth threshold indicates poor communication quality, the terminal device may determine that the first event has been triggered and send a performance monitoring request to the network device.

[0301] In some embodiments, if the parameter in the performance indicator of the reference signal received by the terminal device is less than the seventh threshold a number of times within the fourth time length and greater than the ninth threshold, the terminal device can determine that the first event is triggered. For example, the performance indicator of the reference signal can be SINR. If, within the fourth time length, the number of times the SINR determined by the terminal device is less than the seventh threshold is greater than the ninth threshold, it means that the current communication quality is poor, and the terminal device can determine that the first event is triggered, and send a performance monitoring request to the network device. For example, the fourth time length is 10 seconds, and the ninth threshold is 3 times. Within 10 seconds, if the number of times the SINR determined by the terminal device is less than the seventh threshold is 5 times, the terminal device can determine that the first event is triggered, and send a performance monitoring request to the network device.

[0302] In some embodiments, if the quasi-co-location information of the reference signal received by the terminal device changes, the terminal device may determine that a first event has been triggered. For example, if the QCL source of the reference signal received by the terminal device changes, the terminal device may determine that a first event has been triggered and send a performance monitoring request to the network device. For example, if the QCL type of the reference signal received by the terminal device changes, the terminal device may determine that a first event has been triggered and send a performance monitoring request to the network device.

[0303] In some embodiments, if the dataset tag of the CSI-related information measured by the terminal device changes, the terminal device may determine that a first event has been triggered. For example, the dataset tag may indicate the environment and scenario of the terminal device. For example, based on the dataset tag, the terminal device may determine whether the terminal device is located indoors or outdoors. For example, if the terminal device moves from indoors to outdoors, the dataset tag changes, and the terminal device may determine that the first event has been triggered and send a performance monitoring request to the network device.

[0304] In some embodiments, if the parameter in the speed information measured by the terminal device is greater than the duration of the tenth threshold and greater than the eleventh threshold, the terminal device can determine that the first event is triggered. For example, the parameter in the speed information can be the absolute value of the line speed. If the absolute value of the line speed measured by the terminal device is greater than the tenth threshold for a duration greater than the eleventh threshold, it means that the terminal device is moving quickly. The terminal device can determine that the first event is triggered and send a performance monitoring request for the model to the network device. For example, the tenth threshold is 10 meters per second and the eleventh threshold is 60 seconds. If the absolute value of the line speed measured by the terminal device is 15 meters per second within 100 seconds, the terminal device can determine that the first event is triggered and send a performance monitoring request for the model to the network device.

[0305] In some embodiments, if the parameter in the speed information measured by the terminal device is greater than the tenth threshold number of times and greater than the twelfth threshold within the fifth time period, the terminal device can determine that the first event is triggered. For example, the parameter in the speed information can be the absolute value of the line speed. Within the fifth time period, if the absolute value of the line speed measured by the terminal device (the terminal device can measure the line speed based on the sampling frequency) is greater than the tenth threshold number of times and greater than the twelfth threshold, it means that the terminal device is moving quickly. The terminal device can determine that the first event is triggered and send a performance monitoring request for the model to the network device. For example, the fifth time period is 10 seconds, the tenth threshold is 10 meters / second, and the twelfth threshold is 5 times. If within 10 seconds, the absolute value of the line speed measured by the terminal device is greater than 10 meters / second 10 times, the terminal device can determine that the first event is triggered and send a performance monitoring request for the model to the network device.

[0306] In some embodiments, if the distance difference between two positions measured by the terminal device at an interval of the sixth time duration is greater than the thirteenth threshold, the terminal device can determine that the first event is triggered. For example, the terminal device measures the position at time 1 to obtain position 1, and the terminal device measures the position at time 2 to obtain position 2 (the time duration between time 1 and time 2 is the sixth time duration). If the distance difference between position 1 and position 2 is greater than the thirteenth threshold, the terminal device can determine that the first event is triggered and send a performance monitoring request to the network device. For example, if the thirteenth threshold is 1000 meters and the sixth time duration is 60 seconds, if the distance between the two positions measured by the terminal device at an interval of 60 seconds is 2000 meters, the terminal device can determine that the first event is triggered and send a performance monitoring request to the network device.

[0307] In some embodiments, if the operating center frequency, subcarrier, and / or bandwidth configuration of the terminal device changes, the terminal device may determine that the first event is triggered. For example, if the operating center frequency of the terminal device changes, the terminal device may determine that the first event is triggered; if the subcarrier of the terminal device changes, the terminal device may determine that the first event is triggered; if the bandwidth configuration of the terminal device changes, the terminal device may determine that the first event is triggered.

[0308] S1103. Send a performance monitoring request to the network device.

[0309] Among them, when the terminal device determines that the first event is currently triggered based on the generalization indicator of the AI ​​model, the terminal device can send a performance monitoring request of the AI ​​model to the network device.

[0310] The disclosed embodiments provide a method for sending a performance monitoring request, obtaining a generalization index of an AI model, determining, based on the generalization index of the AI ​​model, that a terminal device has triggered a first event, and sending a performance monitoring request to a network device. In this way, the terminal device can determine, based on the generalization index of the AI ​​model, that the terminal device's network status has changed, thereby enabling timely performance monitoring of the AI ​​model, improving the accuracy of AI model performance monitoring, saving communication resources, and thereby improving communication stability.

[0311] FIG12 is a schematic diagram of another method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG12 , in the embodiment shown in FIG12 , the first event is an event determined based on AI model update information and / or model transfer information. The method flow includes:

[0312] S1201: Receive model transfer information and / or model update information sent by a network device.

[0313] The AI ​​model update information may indicate an AI model update, and the AI ​​model transfer information may indicate an AI model transfer. For example, a terminal device may receive AI model update information and AI model transfer information sent by a network device or server, and the terminal device may perform lifecycle management operations on the AI ​​model based on the above information.

[0314] It should be noted that the terminal device can obtain the model transmission information or model update information of the AI ​​model according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0315] S1202: Send a performance monitoring request to the network device.

[0316] If the first event is an event determined based on AI model update information or model transfer information, the first event includes at least one of the following:

[0317] receiving model update information and / or model transfer information sent by the network device;

[0318] After receiving the model update information and / or model transfer information sent by the network device, no performance monitoring related indication is received within a seventh period of time.

[0319] It should be noted that the seventh duration may be predefined by the protocol and / or configured by the network device, or may be determined based on any other feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0320] It should be noted that the terminal device can also receive the model update information and model transfer information sent by the server, which is not limited in the embodiments of the present disclosure.

[0321] In some embodiments, if the terminal device receives model update information and / or model transfer information sent by the network device, the terminal device can determine that the first event is triggered. For example, if the terminal device receives model update information sent by the network device, it means that the terminal device can perform lifecycle management operations on the AI ​​model. Therefore, the terminal device can send a performance monitoring request for the AI ​​model to the network device, and then monitor the performance of the updated AI model. For example, if the terminal device receives model transfer information sent by the network device, it means that the terminal device can perform lifecycle management operations on the AI ​​model. Therefore, the terminal device can send a performance monitoring request for the AI ​​model to the network device, and then monitor the performance of the transferred AI model.

[0322] In some embodiments, if the terminal device does not receive an indication related to performance monitoring within the seventh time period after receiving the model update information and / or model transfer information sent by the network device, the terminal device may determine that the first event is triggered. For example, after the terminal device receives the model update information and / or model transfer information sent by the network device, the terminal device may monitor the performance of the updated AI model or the transferred AI model. If the terminal device does not receive an indication related to performance monitoring sent by the network device, the terminal device may determine that the first event is triggered and send a performance monitoring request to the network device.

[0323] The disclosed embodiments provide a method for sending a performance monitoring request, which receives model transfer information and / or model update information sent by a network device and sends a performance monitoring request to the network device. In this way, after the AI ​​model is updated or transferred, the terminal device can start monitoring the performance of the AI ​​model, thereby improving the accuracy of performance monitoring and enhancing communication quality.

[0324] Based on any of the above embodiments, the triggering event includes a second event related to the performance of the terminal device, wherein the second event can be an event determined based on the upper layer signaling of the terminal device. Below, in combination with Figure 13, the process of the terminal device sending a performance monitoring request when the terminal device determines that the second event is triggered in this scenario is explained.

[0325] FIG13 is a schematic diagram of a method for sending a performance monitoring request according to an embodiment of the present disclosure. Referring to FIG13 , the method flow includes:

[0326] S1301. Obtain upper layer signaling.

[0327] Among them, the upper-layer signaling may include any information in the terminal device that interacts with the upper-layer protocol layer, which is not limited in the embodiments of the present disclosure. In addition, the terminal device can obtain the upper-layer signaling according to any feasible implementation method, which is not limited in the embodiments of the present disclosure.

[0328] S1302: Determine, according to upper layer signaling, whether to trigger a second event.

[0329] If the second event is an event determined based on upper layer signaling, the second event includes at least one of the following:

[0330] A handover occurs in the cell where the cell is located;

[0331] The first monitoring quantity is greater than the fourteenth threshold;

[0332] The second monitoring value is less than the fifteenth threshold;

[0333] A first parameter of a final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is less than a threshold corresponding to the first parameter;

[0334] A second parameter of the final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is greater than a threshold corresponding to the second parameter.

[0335] The first monitored quantity is inversely proportional to the performance of the terminal device. For example, the first monitored quantity may include power consumption, memory usage, etc. of the terminal device, which is not limited in the present embodiment.

[0336] The second monitored quantity is proportional to the performance of the terminal device. For example, the second monitored quantity may include the remaining computing power of the terminal device, the remaining memory of the terminal device, etc., which is not limited in the present embodiment.

[0337] It should be noted that the fourteenth threshold and the fifteenth threshold may be predefined by the protocol and / or configured by the network device, or may be determined based on any other feasible implementation manner, and the embodiments of the present disclosure do not limit this.

[0338] In some embodiments, if a handover occurs in the cell where the terminal device is located, the terminal device may determine that a second event is triggered. For example, when a handover occurs in the cell where the terminal device is located, the terminal device needs to determine the currently available AI model. Therefore, the terminal device may determine that a second event is triggered and send a monitoring request to the network device. For example, the terminal device may send a monitoring request to the network device based on the cell handover trigger of the terminal device. The cell handover measurement time of the terminal device and the cell handover signaling may trigger the terminal device to send a monitoring request for the AI ​​model.

[0339] In some embodiments, if the first monitored quantity is greater than a fourteenth threshold, the terminal device may determine that a second event has been triggered. For example, the first monitored quantity may be the power consumption of the terminal device. If the power consumption of the terminal device is greater than the fourteenth threshold, it indicates that the performance of the terminal device may affect the communication quality. The terminal device may determine that a second event has been triggered and send a monitoring request to the network device. For example, the first monitored quantity may be power consumption, and the fourteenth threshold may be a preset power consumption. If the current power consumption obtained by the terminal device is greater than the preset power consumption, it indicates that the current performance of the terminal device is poor, which in turn may affect the communication quality of the terminal device. Therefore, the terminal device may determine that a second event has been triggered.

[0340] In some embodiments, if the second monitored quantity is less than the fifteenth threshold, the terminal device may determine that a second event has been triggered. For example, the second monitored quantity may be the remaining computing power of the terminal device. If the remaining computing power of the terminal device is less than the fourteenth threshold, it indicates that the performance of the terminal device will affect the communication quality. The terminal device may determine that the second event has been triggered and send a monitoring request to the network device. For example, the second monitored quantity may be the remaining computing power, and the fifteenth threshold is the preset computing power. If the current remaining computing power obtained by the terminal device is less than the preset computing power, it indicates that the current performance of the terminal device is poor, which in turn will affect the communication quality of the terminal device. Therefore, the terminal device may determine that the second event has been triggered.

[0341] In some embodiments, if a first parameter of a final KPI at a future time predicted based on the final KPI at the current time is less than a threshold corresponding to the first parameter, the terminal device may determine that a second event has been triggered. For example, the first parameter may be throughput. If the throughput of the final KPI at a future time predicted by the terminal device based on the current throughput is less than a threshold corresponding to the throughput, the terminal device may determine that a second event has been triggered.

[0342] In some embodiments, if a second parameter of a final KPI at a future time predicted based on the final KPI at the current time is greater than a threshold corresponding to the second parameter, the terminal device may determine that a second event has been triggered. For example, the second parameter may be a block error rate. If the block error rate of the final KPI at a future time predicted by the terminal device based on the current throughput is greater than a threshold corresponding to the block error rate, the terminal device may determine that the second event has been triggered.

[0343] S1303: Send a performance monitoring request to the network device.

[0344] Among them, when the terminal device determines that the second event is currently triggered based on the upper-layer signaling, the terminal device can send a performance monitoring request of the AI ​​model to the network device.

[0345] The disclosed embodiments provide a method for sending a performance monitoring request, which obtains upper-layer signaling, determines based on the upper-layer signaling that a terminal device has triggered a second event, and then sends a performance monitoring request to a network device. In this way, the terminal device can determine, based on the upper-layer signaling, that the second event is related to the terminal device's performance. Because this second event can affect the terminal device's communications, when the terminal device triggers the second event, the terminal device can promptly send a performance monitoring request for the model to the network device, thereby improving the timeliness and accuracy of performance monitoring.

[0346] On the basis of any of the above embodiments, the process of a network device sending a response to a performance monitoring request to a terminal device is described below with reference to FIG. 14 .

[0347] FIG14 is a schematic diagram of a method for sending a response to a performance monitoring request to a terminal device according to an embodiment of the present disclosure. Referring to FIG14 , the method process includes:

[0348] S1401. The network device receives a performance monitoring request for the AI ​​model sent by the terminal device.

[0349] The monitoring request may be determined by the terminal device based on a triggering event.

[0350] It should be noted that the triggering events and the information carried in the monitoring request can refer to the embodiments shown in Figures 2 to 13, and the embodiments of the present disclosure will not be described in detail here.

[0351] S1402. The network device sends a response to the performance monitoring request to the terminal device.

[0352] Among them, the response of the network device to the performance monitoring request sent to the terminal device can be: judging whether the AI ​​model needs performance monitoring based on the information carried in the performance monitoring request, obtaining a judgment result, and sending a response to the performance monitoring request to the terminal device based on the judgment result.

[0353] When a network device receives a performance monitoring request, it can determine whether to perform performance monitoring on the AI ​​model based on the target information in the performance monitoring request. For example, if the information carried in the performance monitoring request indicates a high throughput, the network device may refuse to perform performance monitoring on the AI ​​model. If the information carried in the monitoring request indicates a low throughput, the network device may agree to perform performance monitoring on the AI ​​model.

[0354] In some embodiments, if the judgment result is agreement to perform performance monitoring on the AI ​​model, the response of the performance monitoring request sent by the network device to the terminal device may be agreement; if the judgment result is refusal to perform performance monitoring on the AI ​​model, the response of the performance monitoring request sent by the network device to the terminal device may be refusal.

[0355] It should be noted that if the performance monitoring request does not include target information, the network device may send a response to the performance monitoring request to the terminal device, and the response may be an agreement to start performance monitoring or an agreement to activate performance monitoring.

[0356] The disclosed embodiments provide a method for sending a response to a performance monitoring request to a terminal device. A network device receives a performance monitoring request for an AI model sent by the terminal device, determines whether the AI ​​model requires performance monitoring based on the information contained in the performance monitoring request, obtains a determination result, and sends a response to the performance monitoring request to the terminal device based on the determination result. In this way, the network device can accurately determine whether to enable performance monitoring of the AI ​​model based on the target information reported by the terminal device, thereby improving the accuracy of the AI ​​model's performance monitoring.

[0357] FIG15 is a schematic diagram of the structure of a performance monitoring device provided by an embodiment of the present disclosure. Referring to FIG15 , the performance monitoring device 1500 includes a sending module 1501, a receiving module 1502, and a monitoring module 1503, wherein:

[0358] The sending module 1501 is used to send a performance monitoring request of the AI ​​model to the network device according to the triggering event;

[0359] The receiving module 1502 is configured to receive a response to the performance monitoring request sent by the network device;

[0360] The monitoring module 1503 is used to monitor the performance of the AI ​​model based on the response to the performance monitoring request.

[0361] In some embodiments, the performance monitoring request includes an identification of the AI ​​model and / or an identification of a function.

[0362] In some embodiments, the performance monitoring request includes an identifier of an applicable model, an identifier of an applicable function, and an identifier of an applicable scenario corresponding to the performance monitoring request.

[0363] In some embodiments, the performance monitoring request includes a start time of performance monitoring and / or an end time of performance monitoring.

[0364] In some embodiments, the performance monitoring request includes target information, which is related to the performance indicators of the AI ​​model and / or the measurement values ​​of the AI ​​model.

[0365] In some embodiments, the target information includes at least one of the following:

[0366] Intermediate key performance indicators related to the AI ​​model;

[0367] Final key performance indicators related to the AI ​​model;

[0368] Statistical information related to channel state information (CSI);

[0369] distribution information of the CSI-related information;

[0370] The reference signal received power related to the AI ​​model;

[0371] the reference signal reception quality associated with the AI ​​model;

[0372] signal-to-interference-plus-noise ratio;

[0373] Speed ​​information;

[0374] Location information.

[0375] In some embodiments, the trigger event includes a first event related to the AI ​​model and / or function and a second event related to the performance of the terminal device.

[0376] In some embodiments, when the AI ​​model is not activated, not selected, or not paired, the first event includes at least one of the following:

[0377] Send the identification of supported AI models and / or capabilities;

[0378] Receive the identifier of the AI ​​model and / or the identifier of the function supported by the cell currently covered by the base station.

[0379] In some embodiments, when the AI ​​model is activated, selected, or paired, the first event is an event determined based on at least one of the following information:

[0380] The final key performance indicators measured;

[0381] Statistical information and / or distribution information of measured CSI-related information;

[0382] Statistical information and / or distribution information of CSI-related information inferred by the AI ​​model;

[0383] The generalization metric of the AI ​​model;

[0384] The update information of the AI ​​model and / or the transfer information of the AI ​​model.

[0385] In some embodiments, the first event is an event determined based on a final key performance indicator of the measurement, and the first event includes at least one of the following:

[0386] A first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter, and the first parameter is proportional to the performance of the AI ​​model;

[0387] A second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter, and the second parameter is inversely proportional to the performance of the AI ​​model;

[0388] The number of times that the first parameter in the final key performance indicator is less than the threshold corresponding to the first parameter within the first time period is greater than the first threshold;

[0389] The number of times that the second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter within the first duration is greater than the first threshold;

[0390] A deviation between the parameter in the final key performance indicator and a first target value is greater than a second threshold, and the first target value is a target value corresponding to the parameter in the final key performance indicator.

[0391] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of measured CSI-related information, and the first event includes at least one of the following:

[0392] a third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than a threshold corresponding to the third parameter, and the third parameter is inversely proportional to the performance of the AI ​​model;

[0393] a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than a threshold corresponding to the fourth parameter, and the fourth parameter is proportional to the performance of the AI ​​model;

[0394] The number of times that a third parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is greater than a threshold corresponding to the third parameter is greater than the third threshold;

[0395] The number of times that a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is less than a threshold corresponding to the fourth parameter is greater than the third threshold;

[0396] A deviation between the parameter in the statistical information and / or distribution information of the measured CSI-related information and the second target value is greater than a fourth threshold, and the second target value is a target value corresponding to the parameter in the statistical information and / or distribution information of the measured CSI-related information.

[0397] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model, and the first event includes at least one of the following:

[0398] a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than a threshold corresponding to the fifth parameter, and the fifth parameter is inversely proportional to the performance of the AI ​​model;

[0399] a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than a threshold corresponding to the sixth parameter, and the sixth parameter is proportional to the performance of the AI ​​model;

[0400] The number of times that a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is greater than a threshold corresponding to the fifth parameter is greater than the fifth threshold;

[0401] The number of times a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is less than a threshold corresponding to the sixth parameter is greater than the fifth threshold;

[0402] A deviation between the parameters in the statistical information and / or distribution information of the inferred CSI-related information and the third target value is greater than a sixth threshold, and the third target value is a target value corresponding to the parameters in the statistical information and / or distribution information of the inferred CSI-related information.

[0403] In some embodiments, the first event is an event determined based on a generalization indicator of the AI ​​model, and the first event includes at least one of the following:

[0404] a duration during which a parameter in a performance indicator of the received reference signal is less than a seventh threshold and greater than an eighth threshold;

[0405] the number of times that the parameter in the performance indicator of the received reference signal is less than the seventh threshold within the fourth time duration is greater than the ninth threshold;

[0406] The quasi co-location information of the received reference signal changes;

[0407] The dataset label of the measured CSI-related information has changed;

[0408] The duration during which the parameter in the measured speed information is greater than the tenth threshold is greater than the eleventh threshold;

[0409] The number of times that the parameter in the measured speed information is greater than the tenth threshold within the fifth time period is greater than the twelfth threshold;

[0410] The distance difference between the two positions measured at the sixth time interval is greater than the thirteenth threshold;

[0411] The operating center frequency, subcarrier and / or bandwidth configuration changes.

[0412] In some embodiments, the first event is an event determined based on update information and / or model transfer information of the AI ​​model, and the first event includes at least one of the following:

[0413] receiving model update information and / or model transfer information sent by the network device;

[0414] After receiving the model update information and / or model transfer information sent by the network device, no performance monitoring related indication is received within a seventh time period.

[0415] In some embodiments, the second event is an event determined based on upper layer signaling, and the second event includes at least one of the following:

[0416] A handover occurs in the cell where the cell is located;

[0417] A first monitoring quantity is greater than a fourteenth threshold, and the first monitoring quantity is inversely proportional to the performance of the terminal device;

[0418] The second monitoring amount is less than a fifteenth threshold, and the first monitoring amount is proportional to the performance of the terminal device;

[0419] A first parameter of a final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is less than a threshold corresponding to the first parameter;

[0420] A second parameter of the final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is greater than a threshold corresponding to the second parameter.

[0421] In some embodiments, the threshold, duration, and target value are based on protocol pre-definition and / or network-side configuration and / or a mixture of protocol pre-definition and network-side configuration.

[0422] In some embodiments, the CSI-related information includes the CSI information, beam information and positioning information.

[0423] In some embodiments, the response to the performance monitoring request includes a reply or indication of the performance monitoring request.

[0424] In some embodiments, the sending module 1501 is used to:

[0425] Sending the performance monitoring request to the network device based on the scheduling request SR of uplink control information UCI;

[0426] or,

[0427] Sending the performance monitoring request to the network device based on media access control element MAC-CE signaling;

[0428] or,

[0429] The performance monitoring request is sent to the network device based on the physical uplink control channel PUCCH resources or the physical uplink shared channel PUSCH resources of the reserved period.

[0430] FIG16 is a schematic diagram of the structure of another performance monitoring device provided by an embodiment of the present disclosure. Referring to FIG16 , the performance monitoring device 1600 includes a receiving module 1601 and a sending module 1602, wherein:

[0431] The receiving module 1601 is configured to receive a performance monitoring request for an AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event;

[0432] The sending module 1602 is configured to send a response to the performance monitoring request to the terminal device.

[0433] In some embodiments, the sending module 1602 is configured to:

[0434] Determine whether the AI ​​model needs to be monitored based on the information carried in the monitoring request, and obtain a determination result;

[0435] Based on the determination result, a response to the monitoring request is sent to the terminal device.

[0436] In some embodiments, the sending module 1602 is configured to:

[0437] Determine, based on the information contained in the performance monitoring request, whether the AI ​​model requires performance monitoring, and obtain a determination result;

[0438] Based on the determination result, a response to the performance monitoring request is sent to the terminal device.

[0439] In some embodiments, the sending module is configured to:

[0440] Receiving a scheduling request SR sent by the terminal device;

[0441] A response to the scheduling request SR is sent to the terminal device, where the response to the scheduling request SR includes downlink control information DCI for uplink transmission resource allocation, and the downlink control information DCI is encrypted based on the radio network temporary identifier RNTI of the terminal device.

[0442] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0443] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0444] It should be noted here that the above-mentioned device provided by the present disclosure can implement all the method steps implemented by the above-mentioned method embodiment and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be repeated here.

[0445] FIG17 is a schematic diagram of the structure of a terminal device provided by an embodiment of the present disclosure. Referring to FIG17 , the terminal device includes a memory 1710, a transceiver 1720, and a processor 1730:

[0446] The memory 1710 is used to store computer programs;

[0447] The transceiver 1720 is configured to transmit and receive data under the control of the processor;

[0448] The processor 1730 is configured to read the computer program in the memory and perform the following operations:

[0449] Sending performance monitoring requests for AI models to network devices based on trigger events;

[0450] Receive a response to the performance monitoring request sent by the network device, and monitor the performance of the AI ​​model based on the response to the performance monitoring request.

[0451] In some embodiments, the performance monitoring request includes an identification of the AI ​​model and / or an identification of a function.

[0452] In some embodiments, the performance monitoring request includes an identifier of an applicable model, an identifier of an applicable function, and an identifier of an applicable scenario corresponding to the performance monitoring request.

[0453] In some embodiments, the performance monitoring request includes a start time of performance monitoring and / or an end time of performance monitoring.

[0454] In some embodiments, the performance monitoring request includes target information, which is related to the performance indicators of the AI ​​model and / or the measurement values ​​of the AI ​​model.

[0455] In some embodiments, the target information includes at least one of the following:

[0456] Intermediate key performance indicators related to the AI ​​model;

[0457] Final key performance indicators related to the AI ​​model;

[0458] Statistical information related to channel state information (CSI);

[0459] distribution information of the CSI-related information;

[0460] The reference signal received power related to the AI ​​model;

[0461] the reference signal reception quality associated with the AI ​​model;

[0462] signal-to-interference-plus-noise ratio;

[0463] Speed ​​information;

[0464] Location information.

[0465] In some embodiments, the trigger event includes a first event related to the AI ​​model and / or function and a second event related to the performance of the terminal device.

[0466] In some embodiments, when the AI ​​model is not activated, not selected, or not paired, the first event includes at least one of the following:

[0467] Send the identification of supported AI models and / or capabilities;

[0468] Receive the identifier of the AI ​​model and / or the identifier of the function supported by the cell currently covered by the base station.

[0469] In some embodiments, when the AI ​​model is activated, selected, or paired, the first event is an event determined based on at least one of the following information:

[0470] The final key performance indicators measured;

[0471] Statistical information and / or distribution information of measured CSI-related information;

[0472] Statistical information and / or distribution information of CSI-related information inferred by the AI ​​model;

[0473] The generalization metric of the AI ​​model;

[0474] The update information of the AI ​​model and / or the transfer information of the AI ​​model.

[0475] In some embodiments, the first event is an event determined based on a final key performance indicator of the measurement, and the first event includes at least one of the following:

[0476] A first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter, and the first parameter is proportional to the performance of the AI ​​model;

[0477] A second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter, and the second parameter is inversely proportional to the performance of the AI ​​model;

[0478] The number of times that the first parameter in the final key performance indicator is less than the threshold corresponding to the first parameter within the first time period is greater than the first threshold;

[0479] The number of times that the second parameter in the final key performance indicator is greater than the threshold corresponding to the second parameter within the first duration is greater than the first threshold;

[0480] A deviation between the parameter in the final key performance indicator and a first target value is greater than a second threshold, and the first target value is a target value corresponding to the parameter in the final key performance indicator.

[0481] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of measured CSI-related information, and the first event includes at least one of the following:

[0482] a third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than a threshold corresponding to the third parameter, and the third parameter is inversely proportional to the performance of the AI ​​model;

[0483] a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than a threshold corresponding to the fourth parameter, and the fourth parameter is proportional to the performance of the AI ​​model;

[0484] The number of times that a third parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is greater than a threshold corresponding to the third parameter is greater than the third threshold;

[0485] The number of times that a fourth parameter in the statistical information and / or distribution information of the measured CSI-related information within the second duration is less than a threshold corresponding to the fourth parameter and greater than the third threshold;

[0486] A deviation between the parameter in the statistical information and / or distribution information of the measured CSI-related information and the second target value is greater than a fourth threshold, and the second target value is a target value corresponding to the parameter in the statistical information and / or distribution information of the measured CSI-related information.

[0487] In some embodiments, the first event is an event determined based on statistical information and / or distribution information of CSI-related information inferred by the AI ​​model, and the first event includes at least one of the following:

[0488] a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than a threshold corresponding to the fifth parameter, and the fifth parameter is inversely proportional to the performance of the AI ​​model;

[0489] a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than a threshold corresponding to the sixth parameter, and the sixth parameter is proportional to the performance of the AI ​​model;

[0490] The number of times a fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is greater than a threshold corresponding to the fifth parameter is greater than the fifth threshold;

[0491] The number of times a sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information within the third duration is less than a threshold corresponding to the sixth parameter is greater than the fifth threshold;

[0492] A deviation between the parameters in the statistical information and / or distribution information of the inferred CSI-related information and the third target value is greater than a sixth threshold, and the third target value is a target value corresponding to the parameters in the statistical information and / or distribution information of the inferred CSI-related information.

[0493] In some embodiments, the first event is an event determined based on a generalization indicator of the AI ​​model, and the first event includes at least one of the following:

[0494] a duration during which a parameter in a performance indicator of a received reference signal is less than a seventh threshold and greater than an eighth threshold;

[0495] the number of times that the parameter in the performance indicator of the received reference signal is less than the seventh threshold within the fourth time duration is greater than the ninth threshold;

[0496] The quasi co-location information of the received reference signal changes;

[0497] The dataset label of the measured CSI-related information has changed;

[0498] The duration during which the parameter in the measured speed information is greater than the tenth threshold is greater than the eleventh threshold;

[0499] The number of times that the parameter in the measured speed information is greater than the tenth threshold within the fifth time period is greater than the twelfth threshold;

[0500] The distance difference between the two positions measured at the sixth time interval is greater than the thirteenth threshold;

[0501] The operating center frequency, subcarrier and / or bandwidth configuration changes.

[0502] In some embodiments, the first event is an event determined based on update information and / or model transfer information of the AI ​​model, and the first event includes at least one of the following:

[0503] receiving model update information and / or model transfer information sent by the network device;

[0504] After receiving the model update information and / or model transfer information sent by the network device, no performance monitoring related indication is received within a seventh time period.

[0505] In some embodiments, the second event is an event determined based on upper layer signaling, and the second event includes at least one of the following:

[0506] A handover occurs in the cell where the cell is located;

[0507] A first monitoring quantity is greater than a fourteenth threshold, and the first monitoring quantity is inversely proportional to the performance of the terminal device;

[0508] The second monitoring amount is less than a fifteenth threshold, and the first monitoring amount is proportional to the performance of the terminal device;

[0509] A first parameter of a final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is less than a threshold corresponding to the first parameter;

[0510] A second parameter of the final key performance indicator at a future moment predicted based on the final key performance indicator at the current moment is greater than a threshold corresponding to the second parameter.

[0511] In some embodiments, the threshold, duration, and target value are based on protocol pre-definition and / or network-side configuration and / or a mixture of protocol pre-definition and network-side configuration.

[0512] In some embodiments, the CSI-related information includes the CSI information, beam information and positioning information.

[0513] In some embodiments, the response to the performance monitoring request includes a reply or indication of the performance monitoring request.

[0514] In some embodiments, sending a performance monitoring request of an AI model to a network device includes:

[0515] Sending the performance monitoring request to the network device based on the scheduling request SR of uplink control information UCI;

[0516] or,

[0517] Sending the performance monitoring request to the network device based on media access control element MAC-CE signaling;

[0518] or,

[0519] The performance monitoring request is sent to the network device based on the physical uplink control channel PUCCH resources or the physical uplink shared channel PUSCH resources of the reserved period.

[0520] In some embodiments, the terminal device may further include a user interface 1740. For different terminal devices, the user interface 1740 may also be an interface capable of connecting external or internal devices as required. The connected devices include but are not limited to a keypad, display, speaker, microphone, joystick, etc.

[0521] In FIG17 , the bus architecture may include any number of interconnected buses and bridges, linking together various circuits of one or more processors represented by processor 1703 and memory represented by memory 1710. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1720 may be a plurality of components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 1730 is responsible for managing the bus architecture and general processing, and the memory 1701 may store data used by the processor 1730 when performing operations.

[0522] Optionally, processor 1730 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor can also adopt a multi-core architecture.

[0523] The processor 1730 is configured to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions by calling the computer program stored in the memory 1710. The processor 1730 and the memory 1710 may also be physically separated.

[0524] It should be noted here that the above-mentioned physical device provided by the present disclosure can implement all the method steps implemented by the physical device in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be repeated here.

[0525] FIG18 is a schematic diagram of the structure of a network device provided by an embodiment of the present disclosure. Referring to FIG18 , the network device includes a memory 1810, a transceiver 1820, and a processor 1830:

[0526] The memory 1810 is used to store computer programs;

[0527] The transceiver 1820 is configured to transmit and receive data under the control of the processor;

[0528] The processor 1830 is configured to read the computer program in the memory and perform the following operations:

[0529] Receiving a performance monitoring request for an AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event;

[0530] Sending a response to the performance monitoring request to the terminal device.

[0531] In some embodiments, the sending of the response to the performance monitoring request to the terminal device includes:

[0532] Determine, based on the information contained in the performance monitoring request, whether the AI ​​model requires performance monitoring, and obtain a determination result;

[0533] Based on the determination result, a response to the performance monitoring request is sent to the terminal device.

[0534] In some embodiments, sending a response to the performance monitoring request to the terminal device includes:

[0535] Receiving a scheduling request SR sent by the terminal device;

[0536] A response to the scheduling request SR is sent to the terminal device, where the response to the scheduling request SR includes downlink control information DCI for uplink transmission resource allocation, and the downlink control information DCI is encrypted based on the radio network temporary identifier RNTI of the terminal device.

[0537] In FIG18 , the bus architecture may include any number of interconnected buses and bridges, linking together various circuits of one or more processors represented by processor 1830 and memory represented by memory 1810. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1820 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, or the like. The processor 1830 is responsible for managing the bus architecture and general processing, and the memory 1810 may store data used by the processor 1830 when performing operations.

[0538] Optionally, the processor 1830 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0539] It should be noted here that the above-mentioned physical device provided by the present disclosure can implement all the method steps implemented by the physical device in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be repeated here.

[0540] An embodiment of the present disclosure further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method described in any one of the above method embodiments.

[0541] The processor-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0542] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the method described in any one of the above method embodiments when the computer program is executed by a processor.

[0543] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0544] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0545] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0546] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0547] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. A performance monitoring method, wherein, Applied to a terminal device, the method includes: Sending a performance monitoring request for an AI model to a network device according to a trigger event; Receiving a response to the performance monitoring request sent by the network device, and performing performance monitoring on the AI model according to the response to the performance monitoring request.

2. The method according to claim 1, wherein, The performance monitoring request includes an identifier of the AI model and / or an identifier of a function.

3. The method according to claim 1 or 2, wherein The performance monitoring request includes an identifier indicating an applicable model corresponding to the performance monitoring request, an identifier of an applicable function, and an identifier of an applicable scenario.

4. The method according to any one of claims 1-3, wherein, The performance monitoring request includes a start time of performance monitoring and / or an end time of performance monitoring.

5. The method according to any one of claims 1-4, wherein, The performance monitoring request includes target information, which is related to a performance metric of the AI model and / or a metric value of the AI model.

6. The method according to claim 5, wherein, The target information includes at least one of the following: Intermediate key performance indicators related to the AI model; Final key performance indicators related to the AI model; Statistical information of information related to channel state information (CSI); Distribution information of the information related to the CSI; Reference signal received power related to the AI model; Reference signal received quality related to the AI model; Signal-to-interference-plus-noise ratio; Speed information; Location information.

7. The method according to any one of claims 1-6, wherein The trigger event includes a first event related to the AI model and / or function and a second event related to the performance of the terminal device.

8. The method according to claim 7, wherein When the AI model is not activated, not selected, or not paired, the first event includes at least one of the following: Sending an identifier of a supported AI model and / or an identifier of a function; Receiving an identifier of an AI model and / or an identifier of a function supported by a cell covered by the current base station.

9. The method according to claim 7, wherein When the AI model is activated, selected, or paired, the first event is an event determined based on at least one of the following information: Measured final key performance indicators; Statistical information and / or distribution information of measured information related to the CSI; Statistical information and / or distribution information of information related to the CSI inferred by the AI model; Generalization metrics of the AI model; Update information of the AI model and / or transfer information of the AI model.

10. The method according to claim 9, wherein, The first event is an event determined based on measured final key performance indicators, and the first event includes at least one of the following: A first parameter in the final key performance indicator is less than a threshold corresponding to the first parameter, and the first parameter is proportional to the performance of the AI model; A second parameter in the final key performance indicator is greater than a threshold corresponding to the second parameter, and the second parameter is inversely proportional to the performance of the AI model; The number of times the first parameter in the final key performance indicator is less than the threshold corresponding to the first parameter within a first time period is greater than a first threshold; The number of times the second parameter in the final key performance indicator is greater than the threshold corresponding to the second parameter within the first time period is greater than the first threshold; The deviation of a parameter in the final key performance indicator from a first target value is greater than a second threshold, and the first target value is a target value corresponding to the parameter in the final key performance indicator.

11. The method according to claim 9, wherein, The first event is an event determined based on statistical information and / or distribution information of CSI-related information obtained by measurement, and the first event includes at least one of the following: The third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than the threshold corresponding to the third parameter, and the third parameter is inversely proportional to the performance of the AI model; The fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than the threshold corresponding to the fourth parameter, and the fourth parameter is directly proportional to the performance of the AI model; The number of times that the third parameter in the statistical information and / or distribution information of the measured CSI-related information is greater than the threshold corresponding to the third parameter within a second time period is greater than a third threshold; The number of times that the fourth parameter in the statistical information and / or distribution information of the measured CSI-related information is less than the threshold corresponding to the fourth parameter within a second time period is greater than the third threshold; The deviation of the parameter in the statistical information and / or distribution information of the measured CSI-related information from the second target value is greater than a fourth threshold, where the second target value is the target value corresponding to the parameter in the statistical information and / or distribution information of the measured CSI-related information.

12. The method according to claim 9, wherein, The first event is an event determined based on statistical information and / or distribution information of CSI-related information inferred by the AI model, and the first event includes at least one of the following: The fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than the threshold corresponding to the fifth parameter, and the fifth parameter is inversely proportional to the performance of the AI model; The sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than the threshold corresponding to the sixth parameter, and the sixth parameter is directly proportional to the performance of the AI model; The number of times that the fifth parameter in the statistical information and / or distribution information of the inferred CSI-related information is greater than the threshold corresponding to the fifth parameter within a third time period is greater than a fifth threshold; The number of times that the sixth parameter in the statistical information and / or distribution information of the inferred CSI-related information is less than the threshold corresponding to the sixth parameter within a third time period is greater than the fifth threshold; The deviation of the parameter in the statistical information and / or distribution information of the inferred CSI-related information from the third target value is greater than a sixth threshold, where the third target value is the target value corresponding to the parameter in the statistical information and / or distribution information of the inferred CSI-related information.

13. The method according to claim 9, wherein The first event is an event determined based on the generalization metric of the AI model, and the first event includes at least one of the following: The duration during which the parameter in the performance metric of the received reference signal is less than a seventh threshold is greater than an eighth threshold; The number of times that the parameter in the performance metric of the received reference signal is less than the seventh threshold within a fourth time period is greater than a ninth threshold; The quasi co-location information of the received reference signal changes; The dataset label of the measured CSI-related information changes; The duration during which the parameter in the measured speed information is greater than a tenth threshold is greater than an eleventh threshold; The number of times the parameter in the measured speed information is greater than the tenth threshold within the fifth time period is greater than the twelfth threshold; The distance difference between two positions separated by the sixth time period of measurement is greater than the thirteenth threshold; The operating center frequency, subcarriers, and / or bandwidth configuration change.

14. The method according to claim 9, wherein, The first event is an event determined based on the update information and / or model transfer information of the AI model, and the first event includes at least one of the following: Receiving the model update information and / or model transfer information sent by the network device; After receiving the model update information and / or model transfer information sent by the network device, no performance monitoring-related indication is received within the seventh time period.

15. The method according to any one of claims 7-14, wherein, The second event is an event determined based on upper-layer signaling, and the second event includes at least one of the following: The cell where the device is located undergoes a handover; The first monitored quantity is greater than the fourteenth threshold, and the first monitored quantity is inversely proportional to the performance of the terminal device; The second monitored quantity is less than the fifteenth threshold, and the first monitored quantity is directly proportional to the performance of the terminal device; The first parameter of the final key performance indicator at a future time predicted based on the final key performance indicator at the current time is less than the threshold corresponding to the first parameter; The second parameter of the final key performance indicator at a future time predicted based on the final key performance indicator at the current time is greater than the threshold corresponding to the second parameter.

16. The method according to any one of claims 10-14, wherein, The thresholds, time periods, and target values are obtained based on protocol predefinitions and / or network-side configurations and / or a combination of protocol predefinitions and network-side configurations.

17. The method according to any one of claims 1-16, wherein, The CSI-related information includes the CSI information, beam information, and positioning information.

18. The method according to any one of claims 1 to 17, wherein The response to the performance monitoring request includes a reply or indication of the performance monitoring request.

19. The method according to any one of claims 1-18, wherein, Sending a performance monitoring request for the AI model to the network device includes: Sending the performance monitoring request to the network device based on a scheduling request SR of the uplink control information UCI; Or, Sending the performance monitoring request to the network device based on a media access control cell MAC-CE signaling; Or, Sending the performance monitoring request to the network device based on a physical uplink control channel PUCCH resource or a physical uplink shared channel PUSCH resource in a reserved period.

20. A performance monitoring method, wherein, Applied to a network device, the method includes: Receiving a performance monitoring request for the AI model sent by a terminal device, where the performance monitoring request is determined by the terminal device based on a triggering event; Sending a response to the performance monitoring request to the terminal device.

21. The method according to claim 20, wherein, Sending the response to the performance monitoring request to the terminal device includes: Judging whether the AI model needs to be performance-monitored according to the information carried in the performance monitoring request to obtain a judgment result; Sending a response to the performance monitoring request to the terminal device according to the judgment result.

22. The method according to claim 20 or 21, wherein Sending the response to the performance monitoring request to the terminal device includes: Receiving a scheduling request SR sent by the terminal device; Sending a response to the scheduling request SR to the terminal device, where the response to the scheduling request SR includes downlink control information DCI for uplink transmission resource allocation, and the downlink control information DCI is scrambled based on the radio network temporary identity RNTI of the terminal device.

23. A performance monitoring device, wherein, Applied to a terminal device, the performance monitoring device includes a sending module, a receiving module, and a monitoring module, where: The sending module is configured to send a performance monitoring request of an AI model to a network device according to a triggering event; The receiving module is configured to receive a response to the performance monitoring request sent by the network device; The monitoring module is configured to monitor the performance of the AI model according to the response to the performance monitoring request.

24. A performance monitoring device, wherein, Applied to a network device, the performance monitoring device includes a receiving module and a sending module, where: The receiving module is configured to receive a performance monitoring request of an AI model sent by a terminal device, and the performance monitoring request is determined by the terminal device based on a triggering event; The sending module is configured to send a response to the performance monitoring request to the terminal device.

25. A terminal device, wherein, Including a memory, a transceiver, and a processor: The memory is used to store a computer program; The transceiver is used to send and receive data under the control of the processor; The processor is configured to read the computer program in the memory and perform the following operations: Send a performance monitoring request of an AI model to a network device according to a triggering event; Receive a response to the performance monitoring request sent by the network device, and monitor the performance of the AI model according to the response to the performance monitoring request.

26. A network device, wherein, Including a memory, a transceiver, and a processor: The memory is used to store a computer program; The transceiver is used to send and receive data under the control of the processor; The processor is configured to read the computer program in the memory and perform the following operations: Receive a performance monitoring request of an AI model sent by a terminal device, and the performance monitoring request is determined by the terminal device based on a triggering event; Send a response to the performance monitoring request to the terminal device.

27. A processor-readable storage medium, wherein, The processor-readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the method according to any one of claims 1 to 19 or execute the method according to claims 20-22.

Images