Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus. The method comprises: receiving first instruction information, wherein the first instruction information is used for instructing a terminal device to acquire first data, the first data has a correspondence to a first feature, the first feature comprises the feature of the terminal device or a first function, and the first function is used for assisting communication of the terminal device. The method further comprises: sending second instruction information, wherein the second instruction information comprises the first data and / or first information determined on the basis of the first data, and the first data and / or the first information are / is used for managing the first function. The present application aims at monitoring and managing AI / ML models or functions. By determining and setting valid monitoring indexes, monitoring and subsequent management are performed on models on the basis of data features or conditions. Therefore, the granularity of model / function management is refined, and the accuracy and efficiency of performing monitoring and management operations on the models / functions are improved.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202410598097.4, filed on May 10, 2024, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more specifically, to a communication method and a communication device. Background Technology

[0003] Current mobile networks, supporting increasingly diverse services, require support for ultra-high speeds, ultra-low latency, ultra-high reliability, and massive connectivity, making network planning, configuration, and resource scheduling increasingly complex. These new demands, scenarios, and characteristics present unprecedented challenges to mobile network planning, operation, and efficient management. Relying on manual experience or simple algorithms for network planning, configuration self-optimization, and resource scheduling suffers from drawbacks such as high time consumption, high costs, and poor adaptability of self-optimization and scheduling algorithms, making it unable to address these new challenges. Introducing artificial intelligence (AI) and machine learning (ML) into mobile networks can significantly improve the efficiency of network planning, configuration, and resource scheduling, achieving network intelligence.

[0004] However, the current discussion only reveals which metrics can be used for monitoring in different AI / ML model application scenarios, how to determine the monitoring metrics, and their application in different scenarios, without clearly defining them. Summary of the Invention

[0005] This application provides a communication method and a communication device for monitoring and managing AI / ML models or functions. By identifying and setting effective monitoring indicators, the model is monitored and subsequently managed based on data characteristics or conditions. Alternatively, multiple effective monitoring indicators can be identified and set, and the model is monitored and subsequently managed based on the correlation between these indicators.

[0006] Firstly, a communication method is provided. This method is executed by a terminal device or a chip applied to the terminal device. The method includes receiving first indication information, which instructs the terminal device to acquire first data, the first data corresponding to a first feature. The first feature includes a feature of the terminal device or a first function, the first function being used to assist the terminal device in communication. The method further includes sending second indication information, the second indication information including the first data and / or first information determined based on the first data. The first data and / or the first information are used to manage the first function.

[0007] In the above scheme, the terminal device acquires the first measured data based on the first instruction information. The first data and the first feature have a corresponding relationship. The terminal device can directly report the first measured data through the second instruction information; it can also process the first data first and report the processed information; or it can report both the measured data and the processed information simultaneously. The terminal device reports to the network device through the second instruction information. The network device manages the first function based on the first data and / or first information carried in the instruction information. This scheme specifies the specific steps and signaling details for managing the model / function, as well as how to set effective features and acquire effective measurement data based on the model / function.

[0008] In one alternative implementation, the terminal device receives first instruction information from the network device side.

[0009] In another alternative implementation, the terminal device receives the first instruction information from the training node.

[0010] In another alternative implementation, the terminal device receives the first instruction information from the network node.

[0011] It should be understood that the first characteristic includes data characteristics or conditional characteristics of the terminal device and / or function / model. Different data characteristics or conditional characteristics can be set for functions / models in different application scenarios.

[0012] It should be understood that the first function includes the AI / ML functions / models running on the terminal device, and this application does not make any special limitations on this.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the second instruction information further includes the correspondence between the first data and / or the first information and the first feature.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the first data includes the measurement result of a first indicator. The first indicator is used to measure the auxiliary effect of the first function. First information is determined based on the measurement result of the first indicator. The first information is used to indicate whether the measurement result of the first indicator meets a first preset condition.

[0015] In the above scheme, the network device monitors and / or manages the first function based on the measurement results of the first indicator, according to the received second instruction information and the correspondence between the first data and / or the first information and the first feature.

[0016] For a model / function, a primary indicator for monitoring / management can be set. Based on the dimensions of this primary indicator, the model / function is monitored and managed to determine whether it meets the requirements of the primary indicator, thereby enabling further management operations. This solution also specifies how to monitor and manage the model / function based on the primary indicator, how to set reasonable primary indicator requirements (or expected values) for the primary feature, and how to obtain the first measurement data based on the primary feature. This application details the specific aspects of model / function management, which can improve the efficiency of model / function management; by setting indicators as management dimensions for the model, the granularity of model / function management is refined, improving the accuracy and efficiency of monitoring operations on the model / function.

[0017] It should be understood that the first indicator includes the monitoring indicators set for the first function, and the first function is monitored and managed from the perspective of the first indicator.

[0018] It should be understood that the first data includes the measurement results of the first indicator when the first characteristic is satisfied.

[0019] It should be understood that multiple data features can be set for an indicator, and the measurement results of the indicator under each data feature can be obtained. There is a correlation between indicators and data features. Indicators can be monitored by setting one or several specific data features, and multiple indicators can also be monitored by setting one or several specific data features.

[0020] In conjunction with the first aspect, some implementations of the first aspect also include receiving a first preset condition, which is used to trigger the terminal device to report first information.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, the first preset condition includes the expected value of the first indicator.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the second instruction information is also used to instruct the network device to manage the first function based on the first information.

[0023] In the above scheme, the terminal device monitors the first indicator of the first function based on the measured first data, determines whether the first indicator meets the preset conditions, and thus determines whether the first function meets the requirements of the usage scenario. The second instruction information carries this judgment result, instructing the network device to manage the first function. This improves the management efficiency of the model / function and refines the granularity of model / function management.

[0024] It should be understood that managing models / functions includes management operations such as switching, updating, and deactivating models / functions.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the first instruction information is further used to instruct the terminal device to report the second instruction information based on the first cycle; and / or the first instruction information is further used to instruct the first preset condition; and / or the first instruction information is further used to instruct the correspondence between the first data and the first feature included in the reported second instruction information.

[0026] In the above scheme, the network device receives second indication information from the terminal device, judges whether the first indicator of the first function meets preset conditions, and manages the model / function based on the judgment result. The network device can also configure the reporting of the second indication information from the terminal device using the first indication information, allowing for periodic or conditional reporting. The first indication information can also be configured to specify the content to be reported in the second indication information, such as the correspondence between first data and first features, or the correspondence between first data and first indicators.

[0027] It should be understood that, in one alternative implementation, the first information includes information determined by the terminal device based on the correspondence between the first data and the first feature, and by performing specific data processing on the first data.

[0028] In conjunction with the first aspect, some implementations of the first aspect also include sending first functional information. The first functional information includes a first feature corresponding to the first function, and the first functional information is used to instruct the network device to determine the first indicator.

[0029] In conjunction with the first aspect, some implementations of the first aspect also include receiving second functional information. The second functional information includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

[0030] Secondly, a communication method is provided. This method is executed by a network device or a chip applied to a network device. The method includes sending first indication information, which is used to acquire first data, the first data corresponding to a first feature. The first feature includes a feature of a terminal device or a first function, the first function being used to assist the terminal device in communication. The method also includes receiving second indication information, the second indication information including the first data and / or first information determined based on the first data. The network device manages the first function based on the first data and / or the first information.

[0031] In conjunction with the second aspect, in some implementations of the second aspect, the second instruction information further includes the correspondence between the first data and / or the first information and the first feature.

[0032] In conjunction with the second aspect, in some implementations of the second aspect, the first data includes the measurement results of the first indicator, which is used to measure the auxiliary role of the first function.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the first indication information is further used to instruct the terminal device to determine the first information based on the first data. The first information is used to indicate whether the measurement result of the first indicator meets the first preset condition.

[0034] In conjunction with the second aspect, some implementations of the second aspect also include sending a first preset condition. The first preset condition is used to trigger the terminal device to report first information.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the first preset condition includes the expected value of the first indicator.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the first function is managed based on the first information according to the second instruction information.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the first instruction information is further used to instruct the terminal device to report the second instruction information based on the first cycle; and / or the first instruction information is further used to instruct the first preset condition; and / or the first instruction information is further used to instruct the correspondence between the first data and the first feature included in the reported second instruction information.

[0038] In conjunction with the second aspect, some implementations of the second aspect also include receiving first functional information. The first functional information includes a first feature corresponding to a first function. Based on the first functional information, a first indicator is determined.

[0039] In conjunction with the second aspect, some implementations of the second aspect also include receiving second functional information. The second functional information includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

[0040] Thirdly, a communication method is provided. This method is executed by a terminal device or a chip applied to the terminal device. The method includes receiving third indication information, which instructs the terminal device to acquire second data and third data associated with a first function, wherein the second data corresponds to a second indicator, and the third data corresponds to a third indicator. The first function is used to assist the terminal device in communication. The method further includes sending fourth indication information, which includes the second data and third data and / or second information determined based on the second data and third data, the second data and third data and / or the second information being used to manage the first function.

[0041] In conjunction with the third aspect, in some implementations of the third aspect, the second data includes the measurement results of the second indicator, and the third data includes the measurement results of the third indicator. The second and third indicators are used to measure the auxiliary role of the first function. Second information is determined based on the measurement results of the second and third indicators. The second information is used to indicate whether the measurement results of the second and third indicators meet the second preset conditions.

[0042] In conjunction with the third aspect, in some implementations of the third aspect, a second preset condition is received. The second preset condition is used to trigger the terminal device to report the second information.

[0043] In conjunction with the third aspect, in some implementations of the third aspect, the second presupposition condition includes the expected values ​​of the second and third indicators.

[0044] In conjunction with the third aspect, in some implementations of the third aspect, the fourth instruction information is also used to instruct the network device to manage the first function based on the second information.

[0045] In conjunction with the third aspect, in some implementations of the third aspect, the third instruction information is also used to instruct the terminal device to report the fourth instruction information based on the first cycle, and / or the third instruction information is also used to instruct the second preset condition, and / or the third instruction information is also used to instruct the reported fourth instruction information to include the second data and / or the relationship between the third data and the second preset condition.

[0046] In conjunction with the third aspect, some implementations of the third aspect also include sending third functional information. This third functional information includes the second and third indicators corresponding to the first function.

[0047] Fourthly, a communication method is provided. This method is executed by a network device or a chip applied to a network device. The method includes sending third indication information, which is used to acquire second data and third data associated with a first function, wherein the second data corresponds to a second indicator, and the third data corresponds to a third indicator. The first function is used to assist terminal device communication. The method also includes receiving fourth indication information, which includes the second data and third data and / or second information determined based on the second data and third data, wherein the second data and third data and / or the second information are used to manage the first function.

[0048] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the second data includes the measurement results of the second indicator, and the third data includes the measurement results of the third indicator. The second and third indicators are used to measure the auxiliary role of the first function.

[0049] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the third indication information is also used to instruct the terminal device to determine the second information based on the measurement results of the second and third indicators. The second information is used to indicate whether the measurement results of the second and third indicators meet the second preset condition.

[0050] In conjunction with the fourth aspect, in some implementations of the fourth aspect, a second preset condition is sent. The second preset condition is used to trigger the terminal device to report the second information.

[0051] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the second presupposition condition includes the expected values ​​of the second and third indicators.

[0052] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the first function is managed based on the second information according to the fourth instruction information.

[0053] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the third instruction information is also used to instruct the terminal device to report the fourth instruction information based on the first cycle, and / or the third instruction information is also used to instruct the second preset condition, and / or the third instruction information is also used to instruct the reported fourth instruction information to include the second data and / or the relationship between the third data and the second preset condition.

[0054] In conjunction with the fourth aspect, some implementations of the fourth aspect also include receiving fourth functional information. This fourth functional information includes the second and third indicators corresponding to the first function.

[0055] Fifthly, a communication method is provided. This method is executed by a terminal device or a chip applied to the terminal device. The method includes receiving first indication information, which instructs the terminal device to acquire first data, the first data corresponding to a first feature. The first feature includes features of the terminal device or a first function, the first function being used to assist the terminal device in communication. The first function is managed based on the first data.

[0056] In conjunction with the fifth aspect, in some implementations of the fifth aspect, the first data includes the measurement result of a first indicator. The first indicator is used to measure the auxiliary effect of the first function. First information is determined based on the measurement result of the first indicator. The first information is used to indicate whether the measurement result of the first indicator meets a first preset condition.

[0057] In conjunction with the fifth aspect, some implementations of the fifth aspect also include receiving a first preset condition, which is used to trigger the terminal to manage the first function based on the first data.

[0058] In conjunction with the fifth aspect, in some implementations of the fifth aspect, the first presupposition condition includes the expected value of the first indicator.

[0059] In conjunction with the fifth aspect, in some implementations of the fifth aspect, the first instruction information is also used to indicate the first preset condition.

[0060] In conjunction with the fifth aspect, some implementations of the fifth aspect also include sending first functional information. The first functional information includes a first feature corresponding to a first function, and the first functional information is used to instruct the network device to determine a first indicator.

[0061] In conjunction with the fifth aspect, some implementations of the fifth aspect also include receiving second functional information. The second functional information includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

[0062] Sixthly, a communication method is provided. This method is executed by a network device or a chip applied to a network device. The method includes sending first indication information, which is used to acquire first data, the first data corresponding to a first feature. The first feature includes a feature of a terminal device or a first function, the first function being used to assist the terminal device in communication. The first data is used to manage the first function.

[0063] In conjunction with the sixth aspect, in some implementations of the sixth aspect, the first data includes the measurement result of a first indicator. The first indicator is used to measure the auxiliary effect of the first function. First information is determined based on the measurement result of the first indicator. The first information is used to indicate whether the measurement result of the first indicator meets a first preset condition.

[0064] In conjunction with the sixth aspect, some implementations of the sixth aspect also include sending a first preset condition, which is used to trigger the terminal to manage the first function based on the first data.

[0065] In conjunction with the sixth aspect, in some implementations of the sixth aspect, the first presupposition condition includes the expected value of the first indicator.

[0066] In conjunction with the sixth aspect, in some implementations of the sixth aspect, the first instruction information is also used to indicate the first preset condition.

[0067] In conjunction with the sixth aspect, some implementations of the sixth aspect also include receiving first functional information. The first functional information includes a first feature corresponding to the first function, and a first indicator is determined based on the first functional information.

[0068] In conjunction with the sixth aspect, some implementations of the sixth aspect also include sending second functional information. The second functional information includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

[0069] A seventh aspect provides a communication method. This method is executed by a terminal device or a chip applied to the terminal device. The method includes receiving third indication information, which instructs the terminal device to acquire second data and third data associated with a first function, wherein the second data corresponds to a second indicator, and the third data corresponds to a third indicator. The first function assists the terminal device in communication. The first function is managed based on the second and third data.

[0070] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the second data includes the measurement results of the second indicator, and the third data includes the measurement results of the third indicator. The second and third indicators are used to measure the auxiliary role of the first function. Second information is determined based on the measurement results of the second and third indicators. The second information is used to indicate whether the measurement results of the second and third indicators meet the second preset conditions.

[0071] In conjunction with aspect seven, in some implementations of aspect seven, a second preset condition is received. The second preset condition is used to trigger the terminal device to report second information.

[0072] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the second presupposition condition includes the expected values ​​of the second and third indicators.

[0073] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the third instruction information is also used to indicate the second preset condition.

[0074] In conjunction with the seventh aspect, some implementations of the seventh aspect also include receiving third functional information. This third functional information includes the second and third indicators corresponding to the first function.

[0075] Eighthly, a communication method is provided. The method is executed by a network device or a chip applied to a network device. The method includes sending third indication information, which instructs a terminal device to acquire second data and third data associated with a first function, wherein the second data corresponds to a second indicator, and the third data corresponds to a third indicator. The first function is used to assist the terminal device in communication. The second and third data are used to manage the first function.

[0076] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the second data includes the measurement results of the second indicator, and the third data includes the measurement results of the third indicator, the second indicator and the third indicator being used to measure the auxiliary role of the first function.

[0077] In conjunction with aspect eight, in some implementations of aspect eight, the third indication information is also used to instruct the terminal device to determine the second information based on the measurement results of the second and third indicators. The second information is used to indicate whether the measurement results of the second and third indicators meet the second preset condition.

[0078] In conjunction with aspect eight, in some implementations of aspect eight, a second preset condition is sent. The second preset condition is used to trigger the terminal device to report second information.

[0079] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the second presupposition condition includes the expected values ​​of the second and third indicators.

[0080] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the third instruction information is also used to indicate the second preset condition.

[0081] In conjunction with aspect eight, some implementations of aspect eight also include sending third functional information. This third functional information includes the second and third indicators corresponding to the first function.

[0082] A ninth aspect provides a communication apparatus for performing the methods provided in the first to eighth aspects. Specifically, the apparatus may include units and / or modules for performing the methods provided in any of the implementations of the first to eighth aspects, such as processing units and / or communication units.

[0083] In one implementation, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0084] In another implementation, the device is a chip, chip system, or circuit in a communication device. When the device is a chip, chip system, or circuit used in a terminal device, the communication unit can be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0085] A tenth aspect provides a communication apparatus, comprising: at least one processor for executing a computer program or instructions stored in a memory to perform the communication method in any of the above-described implementations of the first to eighth aspects.

[0086] In the eleventh aspect, a processor is provided for executing the methods provided in the foregoing aspects.

[0087] In a twelfth aspect, a computer-readable storage medium is provided, the computer-readable medium storing program code for execution by a device, the program code including a method for performing any of the above-described implementations of the first to eighth aspects.

[0088] In a thirteenth aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the method provided by any of the above-described implementations of the first to eighth aspects.

[0089] In a fourteenth aspect, a chip is provided, the chip including a processor and a communication interface, wherein the processor reads instructions stored in a memory through the communication interface and executes the method provided by any of the above implementations of the first to eighth aspects.

[0090] Optionally, as one implementation, the chip also includes a memory that stores computer programs or instructions. The processor is used to execute the computer programs or instructions stored in the memory. When the computer programs or instructions are executed, the processor is used to execute the methods provided by any of the above implementation methods.

[0091] In a fifteenth aspect, a communication system is provided, the communication system comprising terminal devices for performing the first, third, fifth, and seventh aspects, and network devices for performing the second, fourth, sixth, and eighth aspects. Attached Figure Description

[0092] Figure 1 is a schematic diagram of a communication scenario applicable to an embodiment of this application.

[0093] Figure 2 is a schematic diagram of an application framework provided in an embodiment of this application.

[0094] Figure 3 is a schematic diagram of another application framework provided in the embodiments of this application.

[0095] Figure 4 is a schematic diagram of the network architecture to which a positioning method provided in this application is applicable.

[0096] Figure 5 is a schematic diagram of a process provided in an embodiment of this application.

[0097] Figure 6 is a flowchart illustrating a communication method provided in an embodiment of this application.

[0098] Figure 7 is a flowchart illustrating a communication method provided in an embodiment of this application.

[0099] Figure 8 is a flowchart illustrating another communication method provided in an embodiment of this application.

[0100] Figure 9 is a flowchart illustrating another communication method provided in an embodiment of this application.

[0101] Figure 10 is a flowchart illustrating a communication method of a training node at a base station according to an embodiment of this application.

[0102] Figure 11 is a flowchart illustrating another communication method of a training node at a base station provided in an embodiment of this application.

[0103] Figure 12 is a flowchart illustrating another communication method of a training node at a base station provided in an embodiment of this application.

[0104] Figure 13 is a schematic block diagram of a communication device provided in an embodiment of this application.

[0105] Figure 14 is a schematic block diagram of a communication device provided in an embodiment of this application. Detailed Implementation

[0106] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0107] To facilitate understanding of the embodiments of this application, the following points will be explained before introducing the embodiments of this application.

[0108] First, in the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a signal (such as the first instruction information described below) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or its index. It can also indirectly indicate the information to be indicated by indicating other information, where there is a correlation between the other information and the information to be indicated. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various information, thereby reducing the instruction overhead to some extent.

[0109] Second, in this application, "at least one" refers to one or more, and "more than one" refers to two or more. Furthermore, in the embodiments of this application, "first," "second," and various numerical designations (e.g., "1," "2," etc.) are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The sequence numbers of the processes below do not imply an order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. It should be understood that the objects described in this way can be interchanged where appropriate to describe solutions other than those in the embodiments of this application.

[0110] Third, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0111] Fourth, in the various embodiments of this application, unless otherwise specified or logically conflicting, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0112] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0113] First, the communication scenarios and systems applicable to the embodiments of this application will be described.

[0114] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) communication systems, new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, and other future communication systems.

[0115] The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), Internet of Things (IoT) communication systems, or other communication systems.

[0116] In the aforementioned communication system, one device can send signals to or receive signals from another device. These signals may include information, signaling, or data. The device can also be replaced by an entity, network entity, network element, communication device, communication module, node, user equipment, mobile device, communication node, etc. This application describes the system using a device as an example. For instance, the communication system may include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device.

[0117] In this application embodiment, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0118] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0119] In this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large size, and the ability to achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those focused on a specific application function that require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0120] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0121] The network device in this application embodiment can be a device used to communicate with terminal devices. The network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass various names as follows, or be replaced by them, such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, RAN intelligent controller (RIC), etc. A base station can be a macro base station, micro base station, relay node, donor node, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center and equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in future communication networks, or equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0122] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0123] In some deployments, network devices can be devices that include central units (CUs) or distributed units (DUs), or devices that include both CUs and DUs, or devices that consist of control plane CU nodes (central unit-control plane (CU-CP)), user plane CU nodes (central unit-user plane (CU-UP)), and DU nodes. For example, network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0124] In different communication systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open radio access network (ORAN) system, CU can also be called an open CU (open CU, O-CU), DU can also be called an open DU (open DU, O-DU), CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0125] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio units, such as RRUs, AAUs, or RRHs.

[0126] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU.

[0127] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0128] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0129] In wireless communication networks, the services supported are becoming increasingly diverse, leading to a wide range of demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This makes network planning, configuration, and / or resource scheduling increasingly complex. Furthermore, as network capabilities become more powerful, such as supporting higher spectrum levels, higher-order multiple-input multiple-output (MIMO) technologies, beamforming, and / or beam management, network energy efficiency has become a hot research topic. These new demands, scenarios, and characteristics present unprecedented challenges to network planning, operation, and efficient management. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence.

[0130] Figure 1 is a schematic diagram of a communication scenario applicable to an embodiment of this application.

[0131] This application applies to the scenario shown in Figure 1 where the UE and the network communicate. The terminal device connects to the network device, for example, by accessing the core network through an access network device. The access network device can be a 5G or future communication system access network device, and the core network can be a 5G core network or a future communication system core network; this application does not limit this. The user equipment can be a handheld terminal, a vehicle-mounted terminal, a drone, a mobile terminal, etc. The access network device can be a 4th generation (4G) base station (eNB), a 5G base station (gNB), or a possible future access network device form, such as an open RAN. The core network can be a 4G evolved packet core (EPC), a 5G core network, or a possible future core network form.

[0132] Access network equipment refers to radio access network (RAN) nodes or devices that connect terminals to a wireless network; it can also be called a base station, such as an LTE eNB, NR gNB, or ng-eNB. Access network equipment connected to the core network can also support open RAN architectures. Furthermore, access network equipment may include built-in AI module functionality for training ML models and providing radio-related data analysis and policy feedback.

[0133] A terminal is a device that provides voice and / or data connectivity to a user, also known as user equipment (UE), mobile station (MS), or mobile terminal (MT). In addition, terminal devices may include built-in AI modules for training machine learning models and providing radio-related data analysis and policy feedback to access network devices.

[0134] The core network's main functions are to provide user connectivity, manage users, and carry out service delivery. It acts as the bearer network, providing interfaces to external networks; for example, the 5G core network (5GC). Core network equipment may also include network elements with different functions, such as the LMF (Low-Level Function). Corresponding core network elements may also include built-in AI modules for training ML models; or support open RAN architectures.

[0135] This application is primarily applied to wireless communication scenarios based on artificial intelligence (AI). As an example, and not a limitation, it can involve the following application scenarios: AI / ML-based beam management, AI / ML-based positioning, AI / ML-based channel state information (CSI) feedback enhancement, and AI / ML-based UE mobility management enhancement. In different application scenarios, the UE / base station or core network element can possess AI / ML capabilities and be configured with AI / ML models or functions for inference. This AI / ML model or function can be trained internally by the node or passed to the monitoring / management node by other nodes.

[0136] Figure 2 is a schematic diagram of an application framework provided in an embodiment of this application.

[0137] Figure 2 shows an example diagram of an open RAN architecture (CU-DU separation architecture).

[0138] It should be understood that the Open RAN architecture may include components other than those shown in the diagram.

[0139] In a communication system, network elements are connected via interfaces (e.g., NG, Xn) or air interfaces (Uu). These network element nodes, such as core network equipment, access network nodes (RAN nodes), and one or more devices in the terminal, may also contain one or more AI modules (only one is shown in the figure for clarity). An access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. CU and / or DU may also contain one or more AI modules.

[0140] Optionally, the CU can be further divided into CU-CP and CU-UP. CU-CP and / or CU-UP contain one or more AI models / functions. AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. An AI module can have one or more models / functions. A model / function can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models / functions can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0141] Figure 3 is a schematic diagram of another application framework provided in the embodiments of this application.

[0142] As shown in Figure 3, this communication system includes a Resource Interchange (RIC). RICs include near-real-time (near-RT) RICs and non-real-time (non-RT) RICs. Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0143] Near-RT RICs are used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Near-RT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. Optionally, Near-RT RICs can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, Near-RT RICs deliver inference results to DUs, and DUs then forward them to RUs.

[0144] Non-RT RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-RT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, the Non-RT RIC delivers the inference results to the DU, which then forwards them to the RU.

[0145] Near-RT RIC and Non-RT RIC can also be configured as separate network elements. Alternatively, Near-RT RIC and Non-RT RIC can also be part of other devices. For example, Near-RT RIC can be set in RAN nodes (e.g., CU, DU), while Non-RT RIC can be set in OAM, cloud servers, core network devices, or other network devices.

[0146] Next, a brief description of some of the technical concepts involved in this application will be given.

[0147] Machine learning (ML): ML is an important technical approach to realizing AI.

[0148] Artificial Intelligence (AI): Current mobile networks, supporting increasingly diverse services, require support for ultra-high speeds, ultra-low latency, ultra-high reliability, and massive connectivity, making network planning, configuration, and resource scheduling increasingly complex. Furthermore, the increasing use of communication spectrum in mobile networks places higher demands on base station energy efficiency. These new requirements, scenarios, and characteristics present unprecedented challenges to mobile network planning, operation, and efficient management. Relying on human experience or simple algorithms for network planning, self-optimization of network configuration, and resource scheduling suffers from drawbacks such as high time consumption, high cost, and poor adaptability of self-optimization and scheduling algorithms, making it unable to address these new challenges. Introducing artificial intelligence and machine learning into mobile networks can significantly improve the efficiency of network planning, configuration, and resource scheduling, achieving network intelligence. Artificial intelligence can simulate arbitrary nonlinear models, effectively adapting to real-world environments and approaching performance limits. Artificial intelligence and machine learning acquire large amounts of data; machine learning algorithms train models and / or make decision inferences based on this data, outputting AI models and / or decision results (such as predicting the amount of business data over a certain future time period). To achieve RAN intelligence, it is necessary to study key technologies such as the RAN intelligent wireless network framework, the related functions of AI modules / platforms, and protocol processes.

[0149] AI Models: AI models are algorithms or computer programs that enable AI functionality. An AI model represents the mapping relationship between the model's inputs and outputs. Types of AI models can include neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, or other machine learning models.

[0150] The implementation of an AI model or AI function can be hardware circuitry, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0151] Channel State Information (CSI): In wireless communication, CSI refers to the known channel properties of a communication link. This information describes how a signal propagates from the transmitter to the receiver and represents the combined effects of scattering, fading, and power attenuation with distance. This method is called channel estimation. CSI enables transmission to adapt to current channel conditions, which is crucial for achieving reliable communication at high data rates in multi-antenna systems. In practical implementation and application, the base station sends a CSI reference signal to the UE for measurement. The UE calculates various values ​​through measurement and reports them to the base station for CSI acquisition or beam management (BM), or it may not report these values ​​but only use them to select the receiving beam.

[0152] Positioning: 5G positioning is achieved collaboratively by the UE, 5G access network, access and mobility management function (AMF) network elements, location management function (LMF) network elements, unified data management (UDM) network elements, gateway mobile location center (GMLC) network elements, and location service client (LCS Client) network elements. Specifically, the LMF receives and processes positioning requests or positioning-related data requests from the AMF, selects a positioning method based on the request, measures the positioning results, and finally sends the positioning results or related positioning data back to the AMF. The AMF can receive and manage positioning requests initiated by the UE / GMLC / AMF, and also supports positioning-related interactions with the gNB based on the new radio positioning protocol for NR (NRPPa), transparently transmitting relevant positioning messages between the LMF, gNB, UE, and other entities. An LCS Client is a logical functional entity. It may be an entity within the PLMN, such as an operations and maintenance (O&M) tool, or an entity outside the PLMN, such as a third-party location server deployed outside the carrier. An LCS Client can initiate location requests carrying parameters such as Quality of Service (QoS) and instruct the AMF via GMLC.

[0153] The following description, in conjunction with Figures 4 and 5, describes the information interaction between network elements during the positioning process.

[0154] Figure 4 is a schematic diagram of the network architecture to which a positioning method provided in this application is applicable.

[0155] Figure 5 is a schematic diagram of a process provided in an embodiment of this application.

[0156] Location service requests can be initiated through different network element modules, such as through the UE or AMF itself, or indirectly through GMLC (e.g., handling location service requests initiated by LCS Client). The specific location process is as follows.

[0157] S401: Initiate a location request.

[0158] In one specific implementation, as shown in step S401a, when the location service is initiated by the UE, the location service request is sent to the gNB through the NR-Uu interface, and the gNB sends the location service request to the AMF through the N2 interface.

[0159] In another specific implementation, as shown in step S401b, when the location service request is initiated by the LCS Client, the location service request is sent to the GMLC through the Le interface, and the GMLC sends the location service request to the AMF through the NL2 interface.

[0160] In another specific implementation, as shown in step S401c, when the location service request is initiated by the AMF, the next step is executed directly.

[0161] It should be understood that a location service request may be a decision made by the AMF itself to enable location services for certain UEs.

[0162] S402: AMF sends a location service request to LMF through the NL1 interface.

[0163] S403: After receiving the location service request, the LMF sends location assistance data to the UE through the NL1, N2 and NR-Uu interfaces. The LMF and UE exchange location information based on the LPP location protocol and query relevant measurements from the UE or gNB. After calculation, the LMF finally obtains the UE's location result.

[0164] S404: The LMF returns the location results to the AMF via the NL1 interface. If the AMF is the initiator of the location function, the process ends (as shown in step S405c); otherwise, proceed to the next step.

[0165] In one specific implementation, the AMF transmits the location result to the initiating entity, namely the UE (as shown in step S405a) or the GMLC (as shown in step S405b). When the location service request is initiated by the LCS Client, the GMLC then sends the calculated location information to the LCS Client that initiated the location request.

[0166] 3GPP Release 19 has initiated relevant research projects to study the application of AI in the wireless field, including: AI for beam management and beam selection, AI for improving positioning accuracy, and AI for CSI feedback enhancement (CSI compression and CSI prediction). The specific applications of AI in these scenarios will be introduced below.

[0167] (1) AI-based beam management (BM): Based on AI prediction, it is possible to predict the beams in set A (SetA) based on the measurement results of beams in set B (SetB). As an example and not a limitation, SetB can be a relatively sparse beam set, and SetA can be a beam set that includes SetB or a different beam set from SetB. After obtaining the measurement results of SetB, the beam set in SetA is predicted based on the measurement results of SetB. The prediction result can be the Top-K beams in the beam set of SetA. The Top-K beams are the K best beams in set A, and the specific result can be the signal quality L1-RSRP of the Top-K beams.

[0168] (2) AI-based localization: AI-based localization scenarios include the following two types and five specific implementation methods. The two types include direct AI / ML localization and AI / ML assisted localization.

[0169] There are three specific implementation methods in direct AI / ML localization.

[0170] The first specific implementation, case 1b, is applied to the UE-side model and performs positioning directly based on AI / ML. For example, the UE measures the positioning reference signal (PRS) and directly predicts the positioning result based on the measurement result. This implementation method is of the highest priority.

[0171] The second specific implementation method, case 2b, involves the UE assisting the LMF side in performing AI / ML positioning. The LMF side applies the AI / ML model for positioning based on the measurement information of the positioning reference signal provided by the UE side. This implementation method is of second priority.

[0172] The third specific implementation, case 3b, involves NG-RAN-assisted AI / ML positioning on the LMF side. The LMF side uses the measurement information of the channel sounding reference signal (SRS) provided by the NG-RAN side to apply the AI / ML model for positioning. This implementation is of the highest priority.

[0173] In AI / ML-assisted localization, there are two specific implementation methods.

[0174] The fourth specific implementation method, case 2a, involves the UE-side model assisting the LMF in localization. The UE-side performs AI / ML prediction based on PRS and sends the prediction results to the LMF to assist it in localization. This implementation method is of second priority.

[0175] In the fifth specific implementation, case 3a, the NG-RAN side uses a model to assist the LMF in localization. The NG-RAN side performs AI / ML predictions based on SRS measurement results and sends the prediction results to the LMF to assist it in localization. This implementation is of the highest priority.

[0176] (3) AI-based CSI feedback enhancement: Existing 5G NR systems use codebooks as the basic tool for CSI feedback, and define multiple schemes such as Type I / II codebooks to meet different feedback accuracy requirements. However, the above codebooks are all designed for uniformly arranged antenna arrays and are not optimized for special antennas such as 3D antennas, resulting in significant performance limitations. AI-based CSI feedback can overcome these bottlenecks and achieve better feedback performance through optimization for specific channel environments. The basic principle of AI-based CSI feedback is to treat the high-dimensional channel information feedback task as an end-to-end CSI image compression and recovery task. Its basic signal flow has a structure similar to an autoencoder: 1) The encoder (usually the terminal side) uses an encoder to compress the complete channel information into a bit stream that meets the feedback requirements after feature extraction; 2) This information is fed back to the decoder (usually the base station side) via the feedback link; 3) The decoder uses a decoder to decompress the bit stream information and reconstruct its features, ultimately recovering the complete channel information. The encoder and decoder are jointly optimized during the end-to-end training process to obtain the best CSI reconstruction performance. In practical deployment, encoders and decoders need to be paired according to the training process; that is, the compressed CSI output by a certain encoder needs to be recovered by the corresponding decoder. Furthermore, AI-based channel state information prediction can also obtain unknown time-frequency resource CSIs based on existing CSIs without adding new air interface resource overhead. Although CSIs at different times / space dimensions are not completely identical, they have a certain degree of correlation, making CSI prediction possible. Traditional CSI prediction schemes are limited by prediction accuracy when handling complex data, making them difficult to implement practically. AI-based CSI prediction is expected to significantly improve prediction accuracy, thus potentially achieving the goal of obtaining unknown CSIs with low overhead in practical systems. Based on data correlation categories, AI-based CSI prediction can be divided into four types: 1) The first type considers temporal correlation, i.e., predicting the CSI of the next time moment or the next time moment based on the CSI of the previous period, mainly applied in time-varying channels or high-speed moving scenarios. 2) The second type considers frequency-related correlation, such as predicting and reconstructing downlink CSI based on the uplink CSI of FDD. 3) The third type considers spatial-related prediction problems. 4) The fourth category considers the channel correlation between adjacent users.

[0177] (4) AI-based mobility management: During mobility management, the base station configures the UE to report measurements and makes handover decisions based on the measurement reports. After introducing AI, the base station can make predictions based on the UE's limited measurement results (e.g., configuring a small number of measurement beams, or reducing the measurement of beams and cells by the UE) and select the optimal cell for handover decisions.

[0178] In the lifecycle management (LCM) process of AI / ML models, model monitoring is necessary. Functionality monitoring is a crucial part of LCM, used to monitor the performance of AI / ML functions. This involves monitoring the performance of the AI / ML model / function based on specific metrics to inform subsequent decision-making. For example, when poor performance is detected, the function / model should be managed, such as switching or deactivating the AI / ML model / function.

[0179] Taking beam management as an example, the following metrics can be used for model / function monitoring in AI-based beam management: (1) KPIs related to beam prediction accuracy, such as Top-K / 1 beam prediction accuracy. (2) KPIs related to link quality, such as throughput and L1-RSRP. (3) Performance metrics of input / output data distribution based on AI / ML. (4) The difference between measured RSRP and predicted RSRP, i.e., the difference in L1-RSRP.

[0180] AI / ML model / function management can be performed based on model / function monitoring or changes in UE / network (NW) side conditions, including model activation, selection, switching, and rollback. Model management includes scenarios where management decisions are made by the network or the UE. For network-side decisions, this can be initiated by the network or by the UE, requesting the network. For UE-side decisions, this can be triggered by network-configured events that report the UE's decision to the network, or it can be a decision made autonomously by the UE.

[0181] In view of this, this application provides a communication method and a communication device. This application mainly addresses the model / function monitoring problem in the AI / ML model or function management process, the method for determining monitoring indicators, and how to incorporate model management processes. This application also considers methods for model / function monitoring and management when model / function monitoring is associated with model / function data characteristics or conditions, or with multiple monitoring indicators. This application further implements a specific interaction process between nodes that perform monitoring and management at different nodes.

[0182] This application provides a communication method for monitoring models / functions. In some specific implementations, this application sets a monitoring indicator for the monitored AI / ML model / function, and monitors and manages the model / function based on the characteristics of the model data associated with the monitoring indicator or conditions on the UE side / network side. In other specific implementations, this application sets multiple monitoring indicators for the monitored AI / ML model / function, and monitors and manages the model / function based on the preset correlation between the multiple monitoring indicators. The main purpose of monitoring and managing the model / function is to check whether the model works as expected. The following will describe in detail the various implementation methods for setting a single monitoring indicator and setting multiple monitoring indicators.

[0183] It should be understood that in the implementation of this application, model and functionality are interchangeable concepts. In some specific implementations, only the description of model or functionality appears. It should be understood that this implementation can also be applied to functionality or model.

[0184] It should be understood that in the implementation of this application, "functionality" can be understood as a function with predictive ability, which is similar to the concept of a model. However, it does not limit a certain function to necessarily correspond to a specific model, but rather emphasizes that the node has relevant predictive ability or predictive function.

[0185] Figure 6 is a flowchart illustrating a communication method provided in an embodiment of this application. Specifically, it includes the following steps:

[0186] S501: Terminal device receives information #1.

[0187] In one specific implementation, the terminal device receives information #1 from the network device.

[0188] In another specific implementation, the terminal device receives information #1 from other network nodes.

[0189] Information #1 is used to instruct the terminal device to obtain data #1.

[0190] In one optional implementation, information #1 is further used to instruct the terminal device to report information #2 based on a first cycle; and / or information #1 is further used to instruct a first preset condition; and / or information #1 is further used to instruct that the reported information #2 includes the correspondence between data #1 and the first feature.

[0191] It should be understood that information #1 is a specific implementation of the first instruction information in the above implementation method.

[0192] It should be understood that data #1 is a specific implementation of the first data in the above implementation method.

[0193] S502: Terminal device acquires data #1.

[0194] Data #1 corresponds to feature #1, and feature #1 includes features of the terminal device or the first function. The first function is used to assist the terminal device in communication.

[0195] It should be understood that feature #1 is a specific implementation of the first feature in the above implementation methods.

[0196] S503: Terminal device sends information #2.

[0197] Information #2 includes data #1 and / or information #3 determined based on data #1. Data #1 and / or information #3 are used to manage the first function.

[0198] In one alternative implementation, information #2 also includes the correspondence between data #1 and / or information #3 and feature #1.

[0199] In one alternative implementation, data #1 includes the measurement result of a first indicator, which is used to measure the auxiliary effect of the first function.

[0200] It should be understood that, in one optional implementation, the terminal device monitors the first function, and the terminal device determines information #3 based on the measurement result of the first indicator. Information #3 is used to indicate whether the measurement result of the first indicator meets the first preset condition, and the first preset condition corresponds to the first indicator.

[0201] It should be understood that the terminal device is also used to receive a first preset condition, which is used to trigger the terminal device to report information #3.

[0202] It should be understood that the first preset condition and information #1 can be received through the same message or through different messages, and this application does not make any special limitation in this regard.

[0203] It should be understood that if the first preset condition and information #1 are received through multiple messages, this application does not impose any special restrictions on the order in which the multiple messages are received.

[0204] It should be understood that, in another alternative implementation, the network device monitors the first function, receives information #2, and determines whether the measurement result of the first indicator meets the first preset condition based on the data #1 carried in the information #2.

[0205] It should be understood that information #2 is a specific implementation of the second instruction information in the above implementation method.

[0206] It should be understood that information #3 is a specific implementation of the first information in the above implementation method.

[0207] S504: Network devices manage the first function.

[0208] In one alternative implementation, the network device receives information #2 and manages the first function based on information #3. Information #3 includes the measurement results of the terminal device for the first indicator and the judgment results of the first preset conditions.

[0209] Optionally, the following steps may also be included (not shown in the figure):

[0210] S505: The terminal device sends the first function information.

[0211] The first functional information includes the first feature corresponding to the first function. The first functional information is used to instruct the network device to determine the first indicator.

[0212] S506: The terminal device receives second function information, which includes the first indicator.

[0213] In one alternative implementation, the terminal device receives second functional information from a network node.

[0214] In another alternative implementation, the terminal device receives second functional information from the base station.

[0215] S507: Network devices receive third-function information.

[0216] In one alternative implementation, the third function information comes from the network node and includes information about the first function. The network device determines the first indicator based on the third function information.

[0217] In another alternative implementation, the third functional information comes from network nodes and includes the first indicator.

[0218] In another alternative implementation, the third functional information comes from the terminal device, and the third functional information includes the first indicator.

[0219] First, based on the implementation method shown in Figure 6, we will introduce the relevant application scenarios for setting a monitoring indicator for the monitored AI / ML model / function.

[0220] In the BM scenario, the UE side has AI / ML models / functions to predict the SetA beam set based on the measurement results of the SetB beam set. The link throughput is used as the monitoring performance indicator.

[0221] In one specific approach, different monitoring metrics correspond to different SetB and SetA. For example, when a base station is configured with a 4-beam SetB and a 32-beam SetA, the model / function throughput must be greater than the threshold thres1; otherwise, the current model does not meet the performance requirements. When configured with an 8-beam SetB and a 32-beam SetA, the model / function throughput must be greater than the threshold thres2; otherwise, the current model does not meet the performance requirements.

[0222] In another specific approach, the AI / ML model / function on the UE side is fixed at 32 beams SetA, but SetB can be selected as 4 beams, 8 beams, or 16 beams. When the base station is configured with SetB as 4 beams, 8 beams, or 16 beams, the monitoring indicators are required to be throughput > thres1, throughput > thres2, or throughput > thres3, respectively.

[0223] In another specific approach, different performance metrics are determined based on the relationship between SetA and SetB. For example, when SetB is a subset of SetA, the requirement for the monitoring metric threshold1 will be higher, while when SetB and SetA are independent sets, the requirement for the monitoring metric threshold2 will be lower.

[0224] In another specific approach, the model's monitoring metrics are related to additional conditions on the UE side, such as the UE's antenna tilt angle. Different UE antenna tilt angles correspond to different monitoring metrics.

[0225] It should be understood that in some specific implementations, performance indicators are also referred to as performance indicators, monitoring indicators, performance monitoring indicators, etc., and this application does not make any special restrictions on them.

[0226] It should be understood that in some specific implementations, monitoring is also referred to as detection, etc., and this application does not make any special limitation on this.

[0227] In UE mobility enhancement scenarios, the UE side is configured with AI / ML functions / models for mobility measurement prediction, which are used to predict mobility measurement results.

[0228] In one specific approach, the monitoring metrics are related to the conditions on the UE side. For example, different UE mobility speeds may require different levels of model / function prediction accuracy or different system performance metrics.

[0229] It should be understood that different requirements for model / function prediction accuracy include different requirements for cell and synchronization signal block (SSB) strength prediction accuracy, and may also include different requirements for other functions or models.

[0230] It should be understood that different requirements for system performance indicators include different requirements for UE throughput or UE handover success rate, and may also include different requirements for other indicators.

[0231] The following section introduces relevant application scenarios for setting multiple monitoring indicators for AI / ML models / functions under monitoring.

[0232] In the BM scenario, the UE side has AI / ML models / functions to predict the SetA beam set based on the measurement results of the SetB beam set. Multiple monitoring indicators can include at least one of the following: key performance indicators (KPIs) related to beam prediction accuracy, link quality, AI / ML-based input / output data distribution, and the difference between the measured reference signal received power (RSRP) and the predicted RSRP.

[0233] In one specific implementation, during model / functional monitoring, both link quality and the accuracy of RSRP prediction must be monitored simultaneously. The model is usable only when both requirements are met; conversely, the model fails when either requirement is not met. For example, when the detected link quality exceeds the threshold thres 1, the accuracy of RSRP prediction needs to be above 80%; when the detected link quality exceeds the threshold thres 2, the accuracy of RSRP prediction needs to be above 90%.

[0234] In UE mobility enhancement scenarios, the UE side is configured with AI / ML functions / models for mobility measurement prediction, which are used to predict mobility measurement results.

[0235] In one specific implementation, the monitoring indicators are related to the conditions on the UE side. For example, the model / function can only be used when the UE's moving speed is less than a certain threshold and the model / function prediction accuracy (e.g., cell / SSB signal strength prediction accuracy) meets the requirements.

[0236] The AI / ML models / functions discussed in the current standard are mainly divided into two categories: UE-side models / functions or network-side models / functions. For example, in the BM scenario, the UE-side model / function performs beam prediction for SetA based on the beam measurement of SetB and reports the prediction results to the base station; the network (NW)-side model / function receives the beam measurement results of SetB from the UE and then performs beam prediction for SetA.

[0237] For the NW-side model / function, both the monitoring node and the inference node are located on the NW side. This mainly corresponds to the AI / ML model between the UE and gNB. Therefore, the gNB side will perform performance monitoring based on the function / model and associated data features or conditions. The above process is implemented internally by the base station.

[0238] For UE models / functions, depending on the training node, monitoring node, and management node, they can be divided into the following 6 cases as shown in Table 1.

[0239] Table 1 Six scenarios for UE model / function

[0240] The training nodes for Cases 1-3 in Table 1 are not on the base station side. The UE side can obtain AI / ML function models from over-the-top (OTT) network elements, operations, administration, and maintenance (OAM) network elements, or core network (CN). Typically, the UE obtains AI / ML functions / models from OTT, OAM, and CN network elements based on application layer data.

[0241] In Table 1, the training nodes for Cases 4 to 6 are located on the base station side, i.e., the gNB performs UE-side model / function training and transmits it to the UE. Therefore, the base station itself possesses model / function-related information. AI / ML functions / models are deployed on the UE side, so inference is performed by the UE. Depending on the degree of involvement of the UE or base station in monitoring and management, the monitoring node may be located on the UE side or the gNB side.

[0242] The following sections will detail the monitoring and management process for AI / ML functions / models, based on the six cases mentioned above.

[0243] Figure 7 is a flowchart illustrating a communication method provided in an embodiment of this application.

[0244] In the implementation of case 1 shown in Figure 7, both the monitoring node and the management node are on the UE side. Specifically, the following steps are included:

[0245] S701: The training node sends functional information 1 to the UE.

[0246] The training node trains the model / function and transmits the model / function to the UE through function information 1.

[0247] In one specific implementation, the training nodes include OTT / OAM / CN.

[0248] It should be understood that functional information 1 is a specific implementation of information #1 in the above implementation method, and this application does not make any special limitation on it.

[0249] S702: The UE sends functional information 2 to the base station.

[0250] The UE reports the supported models / functions to the base station.

[0251] In some specific implementations, the UE can report through UE capabilities or through user assistance information (UAI).

[0252] In some specific implementations, functional information 2 is also used to indicate the availability of a model / function. Specifically, the UE capability report indicates to the base station the models / functions supported by the UE side, and it is also necessary to report whether the corresponding model / function is available through the UAI.

[0253] It should be understood that functional information 2 is a specific implementation of the third functional information in the above implementation method, and this application does not make any special limitation on it.

[0254] S703: UE obtains indication information 1.

[0255] Instruction Message 1 indicates the UE's requirements for the monitoring performance metrics of the model / function. The UE can obtain these monitoring performance metrics through the following methods:

[0256] Option 1: Obtain by following the model's transmission process.

[0257] S703a: The training node sends instruction information 1 to the UE.

[0258] The training node instructs the UE to monitor performance metrics via instruction information 1.

[0259] In one alternative implementation, the training node indicates a monitoring performance metric to the UE via indication information 1. This monitoring performance metric is associated with the data features and / or application conditions corresponding to the model. For example, it indicates the monitoring performance requirements and the corresponding data features, data feature identifiers (corresponding to specific data features) information, and model conditions (e.g., UE speed conditions; the model may correspond to one or more UE speed level conditions, such as low, medium, and high).

[0260] In another alternative implementation, the training node indicates multiple monitoring performance indicators to the UE via indication information 1. When indication information 1 indicates multiple monitoring indicator requirements, the model performance meets the requirements only if all the set monitoring requirements are met.

[0261] The management node manages the model based on the monitoring performance requirements. For example, when the monitoring performance does not meet the requirements, it is necessary to perform operations such as model switching or deactivation.

[0262] It should be understood that functional information 1 and instruction information 1 can be sent through one message or multiple messages, and this application does not make any special limitation in this regard.

[0263] It should be understood that in this implementation, the instruction information 1 is a specific implementation of the second functional information in the above implementation, and this application does not make any special limitation on it.

[0264] Option 2: The UE reports functional information, and the base station determines the monitoring performance indicators based on the functional information.

[0265] S703b: The UE sends functional information 3 to the base station.

[0266] S703c: The base station sends indication information 1 to the UE based on function information 3.

[0267] In one optional implementation, the UE sends function information 3 to the base station. Function information 3 is used to report the functions / models supported or available to the UE. Function information 3 may also include the data characteristics and conditions corresponding to the function / model. Function information 3 is used to instruct the base station to make a decision and issue a monitoring performance indicator to the UE. The base station determines the monitoring performance indicator based on function information 3. The base station instructs the UE to use indication information 1 to indicate the monitoring performance indicator corresponding to the model / function under different data characteristics or conditions.

[0268] It should be understood that in this implementation, functional information 3 is a specific implementation of the first functional information in the above implementation, and this application does not make any special limitations on it.

[0269] It should be understood that in this implementation, instruction information 1 is a specific implementation of the first instruction information in the above implementation, and this application does not make any special limitation on it.

[0270] For example, in a BM scenario, the base station can determine the available SetA / SetB for functions / models based on the information reported by the UE, and determine different monitoring indicator requirements for different SetA / SetB. The base station can then send the monitoring indicator requirements and the correspondence between SetA / SetB to the UE for the UE to perform model monitoring and model management.

[0271] In another optional implementation, the UE sends function information 3 to the base station. Function information 3 is used to report multiple monitoring indicators associated with models / functions supported or available by the UE. The base station sends instruction information 1 to the UE to indicate the requirements of multiple monitoring indicators.

[0272] Option 3: The base station obtains functional information from the training nodes, and determines the monitoring performance indicators based on the functional information.

[0273] S703d: The training node sends functional information 3 to the base station.

[0274] S703e: The base station sends indication information 1 to the UE based on function information 3.

[0275] In one optional implementation, the training node sends functional information 3 to the base station. The base station obtains relevant information and / or features of the model / function based on functional information 3, and determines a monitoring performance indicator accordingly. The determined monitoring indicator requires a correspondence between the data features and conditions corresponding to the function / model. Then, the base station sends the determined monitoring indicator and the correspondence between it and the data features and conditions to the UE via indication information 1.

[0276] It should be understood that in this implementation, functional information 3 is a specific implementation of the third functional information in the above implementation, and this application does not make any special limitations on it.

[0277] It should be understood that in this implementation, instruction information 1 is a specific implementation of the first instruction information in the above implementation, and this application does not make any special limitation on it.

[0278] In another alternative implementation, the training node sends functional information 3 to the base station. Functional information 3 is used to report multiple monitoring indicators associated with the model / function. The base station sends instruction information 1 to the UE to indicate the requirements of multiple monitoring indicators.

[0279] In one optional implementation, after the base station receives the function information 2 reported by the UE, it sends a query message to the training node, and the training node responds to the query message by sending function information 3 to the base station.

[0280] In another alternative implementation, S703d is independent of the model transfer step between the training node and the UE. The training node sends functional information 3 to the base station in other service processes to indicate relevant information about the function / model, so that the base station can determine the monitoring performance indicators of the model / function based on the functional information 3.

[0281] S704: The UE monitors and manages the functions.

[0282] The UE monitors the model / function based on the performance requirements obtained from indication information 1. The UE then manages the model / function based on the monitoring results. For example, this includes switching, updating, and deactivating the model / function.

[0283] It should be understood that this application does not impose any special restrictions on the order in which steps S702 and S704 are performed.

[0284] It should be understood that the numbering of the steps in all implementations of this application is for convenience of description only and does not constitute any limitation on the execution order of the steps.

[0285] S705: The UE sends management information 1 to the base station.

[0286] The UE reports the management results of the model / function through management information 1. Management information 1 is used to align the understanding of the model between the base station and the UE.

[0287] In one specific implementation, under the BM scenario, the base station determines the configuration of set B based on the model currently updated by the UE. Furthermore, the UE can also report monitoring-related information through management information 1, such as performance indicator monitoring results, reasons for model updates, and corresponding data characteristics or conditions.

[0288] Taking the BM scenario as an example, the UE can report the monitoring results corresponding to the input data SetB of 4 beams through Management Message 1, as well as which performance indicators are not met. For example, the UE can report that the system throughput does not meet the requirements through Management Message 1. The UE can also report system performance indicator gaps or actual performance indicators and expected performance indicators through Management Message 1. For example, the difference between the actual value and the required value of system throughput.

[0289] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0290] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0291] Figure 8 is a flowchart illustrating another communication method provided in an embodiment of this application.

[0292] In the implementation of case 2 shown in Figure 8, the monitoring node is on the UE side, and the management node is on the base station side. Specifically, it includes the following steps:

[0293] S801: The training node sends functional information 1 to the UE.

[0294] The training node trains the model / function and transmits the model / function to the UE through function information 1.

[0295] It should be understood that the way the training node sends function information 1 to the UE can be similar to the way it sent in S701 above. For the sake of brevity, it will not be described again here.

[0296] S802: The UE sends function information 2 to the base station.

[0297] The UE reports supported or available models / functions to the base station via function information 2. Similar to S702, for the sake of brevity, it will not be described in detail here.

[0298] S803: UE obtains indication information 1.

[0299] Similar to the embodiment shown in Figure 7, the UE monitors the model / function. Therefore, the UE needs to determine the monitoring indicator requirements corresponding to the model / function for monitoring purposes.

[0300] Instruction Message 1 indicates the UE's requirements for the monitoring performance metrics of the model / function. The UE can obtain these monitoring performance metrics through the following methods:

[0301] Option 1: Obtain by following the model's transmission process.

[0302] S803a: The training node sends instruction information 1 to the UE.

[0303] The training node instructs the UE to monitor performance metrics via instruction information 1.

[0304] In one alternative implementation, the training node indicates a monitoring performance metric to the UE via indication information 1. This monitoring performance metric is associated with the data characteristics and / or application conditions corresponding to the model.

[0305] In another alternative implementation, the training node indicates multiple monitoring performance indicators to the UE via indication information 1. When indication information 1 indicates multiple monitoring indicator requirements, the model performance meets the requirements only if all the set monitoring requirements are met.

[0306] Option 2: The UE reports functional information, and the base station determines the monitoring performance indicators based on the functional information.

[0307] S803b: The UE sends functional information 3 to the base station.

[0308] S803c: The base station sends indication information 1 to the UE based on function information 3.

[0309] In one optional implementation, the UE sends function information 3 to the base station. Function information 3 is used to report the functions / models that the UE supports or has available. Function information 3 may also include data characteristics and conditions corresponding to the functions / models. Function information 3 is used to instruct the base station to make a decision and issue a monitoring performance indicator to the UE.

[0310] In another optional implementation, the UE sends function information 3 to the base station. Function information 3 is used to report multiple monitoring indicators associated with models / functions supported or available by the UE. The base station sends instruction information 1 to the UE to indicate the requirements of multiple monitoring indicators.

[0311] Option 3: The base station obtains functional information from the training nodes, and determines the monitoring performance indicators based on the functional information.

[0312] S803d: The training node sends functional information 3 to the base station.

[0313] S803e: The base station sends indication information 1 to the UE based on function information 3.

[0314] In one optional implementation, the training node sends functional information 3 to the base station. The base station obtains relevant information and / or features of the model / function based on functional information 3, and determines a monitoring performance indicator accordingly. The determined monitoring indicator requires a correspondence between the data features and conditions corresponding to the function / model. Then, the base station sends the determined monitoring indicator and the correspondence between it and the data features and conditions to the UE via indication information 1.

[0315] In another alternative implementation, the training node sends functional information 3 to the base station. Functional information 3 is used to report multiple monitoring indicators associated with the model / function. The base station sends instruction information 1 to the UE to indicate the requirements of multiple monitoring indicators.

[0316] S804: UE monitors functions.

[0317] The UE monitors the model / function based on the performance requirements obtained from indication information 1, and obtains monitoring information 1.

[0318] S805: The UE sends monitoring information 1 to the base station.

[0319] Based on the configured monitoring indicator requirements, the UE reports the model monitoring results through monitoring information 1.

[0320] It should be understood that in this implementation, monitoring information 1 is a specific implementation of information #2 in the above implementation, and this application does not make any special limitations on it.

[0321] It should be understood that in this implementation, monitoring information 1 can also be a specific implementation of information #3 in the above implementation, and this application does not make any special restrictions on it.

[0322] In one specific implementation, reporting is based on the UE. The UE makes its own decisions, or the UE reports monitoring results periodically based on instructions from the training node, or the UE reports monitoring results when it determines that performance indicators do not meet requirements.

[0323] In another specific implementation, reporting is based on base station configuration. The base station configures the reporting conditions and methods for monitoring results for the UE based on the functional information 2 reported by the UE. The reporting method can be a condition-triggered single report, a non-conditional periodic report, or a condition-triggered periodic report. Reporting conditions can include triggering monitoring result reporting when a monitoring indicator reaches a certain threshold.

[0324] It should be understood that functional information 2 may include the model / function and related data features and / or conditions. Functional information 2 may also include the model / function and the correlation between multiple monitoring indicators.

[0325] The monitoring information reported by the UE is used to enable the base station to perform model / function management.

[0326] In one specific implementation, the content reported by the UE through monitoring information 1 includes at least one of the following: inference data and measured data reported by the UE to the base station, monitoring performance indicators reported by the UE, indications of whether the monitoring performance indicators reported by the UE meet the requirements, the gap between the performance indicators reported by the UE and the requirements, and the data characteristics or conditions corresponding to the monitoring indicators reported by the UE.

[0327] In another specific implementation, the UE also reports the monitoring results of multiple indicators through monitoring information 1.

[0328] S806: The base station manages the functions.

[0329] The base station performs model / function management based on the monitoring results carried in the monitoring information 1 reported by the UE. For example, the base station performs management operations such as updating, activating / deactivating, and switching models / functions.

[0330] S807: The base station sends management information 1 to the UE.

[0331] The base station sends the management results of the function / model to the UE through management information 1. The UE updates the model / function based on the instructions in management information 1 sent by the base station.

[0332] It should be understood that the content and fields contained in the signaling with the same name in steps S801 to S807 are similar to those in steps S701 to S705, and the function of the signaling with the same name is also similar. For the sake of brevity, they will not be described again here.

[0333] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0334] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0335] Figure 9 is a flowchart illustrating another communication method provided in an embodiment of this application.

[0336] In the implementation of case 3 shown in Figure 9, both the monitoring node and the management node are located on the base station side. The specific steps include:

[0337] S901: The training node sends functional information 1 to the UE.

[0338] The training node trains the model / function and transmits the model / function to the UE through function information 1.

[0339] It should be understood that the way the training node sends function information 1 to the UE can be similar to the way it sent in S701 above. For the sake of brevity, it will not be described again here.

[0340] S902: The UE sends functional information 2 to the base station.

[0341] The UE reports supported or available models / functions to the base station via function information 2. Similar to S702, for the sake of brevity, it will not be described in detail here.

[0342] In one specific implementation, functional information 2 includes data features and conditions corresponding to the model / function, which may include UE-side conditions or network-side conditions.

[0343] S903: Base station determines monitoring indicators.

[0344] Since the monitoring nodes for the model / function are located at the base station, the base station also needs to determine the monitoring indicators and requirements for the model / function for monitoring purposes. Specific methods include the following solutions:

[0345] Option 1: Obtain by following the model's transmission process.

[0346] S903a: The UE sends indication information 1 to the base station.

[0347] The UE indicates the monitoring performance indicators to the base station through indication information 1.

[0348] In one specific implementation, the functional information 1 sent from the training node to the UE may also include the monitoring indicator requirements indicated by the training node to the UE, and the UE sends the monitoring indicator requirements to the base station in the indication information 1.

[0349] It should be understood that the training node can also send other information to the UE to indicate the monitoring indicator requirements to the UE.

[0350] It should be understood that functional information 2 and indication information 1 can be sent via a single signaling message or via multiple separate signaling messages. Similarly, steps S902 and S903a can be completed via a single signaling message or via multiple separate signaling messages. This application does not impose any special limitations on this.

[0351] In one optional implementation, the aforementioned monitoring performance indicators are associated with the data characteristics and / or application conditions corresponding to the model. The indication information 1 reported by the UE is used to indicate the supported or available model / function, and also to indicate the data characteristics or application conditions corresponding to the indicators and model.

[0352] In another optional implementation, the aforementioned monitoring performance indicators include multiple monitoring performance indicators. When the monitoring indicator requirement indicated by indication information 1 is multiple monitoring indicator requirements, the model performance meets the requirements only when all multiple monitoring requirements are met.

[0353] Option 2: The UE reports the function / model to the base station, and the base station determines the monitoring indicators based on the implementation.

[0354] S903b: The UE sends instruction information 2 to the base station.

[0355] S903c: The base station determines the monitoring indicators based on instruction information 2.

[0356] In one optional implementation, the UE sends indication information 2 to the base station. Indication information 2 includes the function / model reported by the UE to the base station, and also includes the data characteristics or application conditions corresponding to the function / model. The base station determines the monitoring indicator requirements based on indication information 2. For example, the base station determines the monitoring indicator requirements under different data characteristics or conditions based on the implementation.

[0357] It should be understood that instruction information 2 and function information 2 can be the same message or different messages. This means that function information 2 and instruction information 2 can be sent via a single signaling message or via multiple separate signaling messages. This application does not impose any special limitations on this.

[0358] In another alternative implementation, the UE sends indication information 2 to the base station, which is used to indicate multiple monitoring indicators associated with the model / function.

[0359] In another alternative implementation, the UE sends indication information 2 to the base station. Indication information 2 includes the functions / models reported by the UE to the base station. The base station determines multiple monitoring indicator requirements based on indication information 2.

[0360] Option 3: The base station obtains monitoring performance indicators from the training nodes.

[0361] S903d: The training node sends instruction information 1 to the base station.

[0362] In one alternative implementation, the training node sends indication information 1 to the base station, which then obtains relevant information about the model / function and / or features of the model / function based on indication information 1, and determines a monitoring performance index accordingly.

[0363] Optionally, the base station can also obtain monitoring indicator requirements corresponding to different data features or conditions from the training node based on the instruction information 1.

[0364] In another alternative implementation, the training node sends indication information 1 to the base station, which is used to report multiple monitoring indicators related to the model / function.

[0365] Option 4: The training nodes report functions / models to the base station, and the base station determines the monitoring indicators based on the implementation.

[0366] S903e: The training node sends instruction information 2 to the base station.

[0367] S903f: The base station determines the monitoring indicators based on instruction information 2.

[0368] In one optional implementation, the training node sends indication information 2 to the base station. Indication information 2 includes data characteristics or application conditions corresponding to the function / model. The base station determines the monitoring indicator requirements based on indication information 2. For example, the base station determines the monitoring indicator requirements under different data characteristics or conditions based on the implementation.

[0369] In another alternative implementation, the training node sends indication information 2 to the base station, which is used to indicate multiple monitoring metrics associated with the model / function.

[0370] S904: The base station sends configuration information 1 to the UE.

[0371] Based on the defined model / function monitoring indicators, the base station configures the UE to report the information required for monitoring by sending configuration information 1 to the UE.

[0372] In one specific implementation, configuration information 1 includes configurations for instructing the UE to perform monitoring-related measurement configurations, monitoring reporting content configurations, and monitoring reporting conditions configurations.

[0373] It should be understood that in this implementation, configuration information 1 is a specific implementation of information #1 in the above implementation, and this application does not make any special limitations on it.

[0374] For example, monitoring-related measurement configurations are used to instruct the UE to measure relevant quantities. For instance, in a BM scenario, the base station can configure the UE to measure specific SetA and SetB, and the corresponding predicted and actual measurement results can be used for model monitoring. Monitoring reporting content configurations may include the UE reporting performance indicator type and / or data type (predicted value or actual value). Monitoring reporting condition configurations may include periodic reporting or conditional reporting configurations. When setting periodic reporting, the reporting content (performance indicator type, data type), reporting period, etc., can be configured. When setting conditional reporting, the reporting content (performance indicator type, data type), reporting threshold conditions, etc., can be configured.

[0375] It should be understood that, corresponding to the above measurement configuration, reporting content and condition configuration, the base station also needs to indicate the corresponding data characteristics or conditions in the configuration, that is, the above configuration is the relevant configuration for the model / function under the data characteristics or conditions.

[0376] S905: The UE sends monitoring information 2 to the base station.

[0377] The UE reports the information required for monitoring based on the base station configuration. In one optional implementation, the monitoring information 2 reported by the base station includes data on model / function monitoring indicators under different data characteristics or conditions. In another optional implementation, the monitoring information 2 reported by the base station includes data or required information under multiple monitoring indicators of the model / function.

[0378] It should be understood that in this implementation, monitoring information 2 is a specific implementation of information #2 in the above implementation, and this application does not make any special limitations on it.

[0379] S906: The base station monitors and manages the functions.

[0380] The base station monitors the model / function based on defined performance requirements and the data needed to monitor the model / function obtained from monitoring information 2. The base station also manages the model / function based on the monitoring results, such as switching, updating, and deactivating the model / function.

[0381] S907: The base station sends management information 1 to the UE.

[0382] The base station sends the management results of the function / model to the UE through management information 1. The UE updates the model / function based on the instructions in management information 1 sent by the base station.

[0383] It should be understood that the content and fields contained in the signaling with the same name in steps S901 to S907 are similar to those in steps S701 to S705, and the functions of the signaling with the same name are also similar. For the sake of brevity, they will not be described again here.

[0384] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0385] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0386] Figure 10 is a flowchart illustrating a communication method of a training node at a base station according to an embodiment of this application.

[0387] In the implementation of case 4 shown in Figure 10, the training node is at the base station, while the monitoring and management nodes are both on the UE side. Specifically, it includes the following steps:

[0388] S101: The UE sends function information 2 to the base station.

[0389] The UE reports the supported models / functions to the base station.

[0390] The UE reports the supported models / functions to the base station via function information 2. The UE can also report its own conditions and supported data features via function refinement 2, which may include model input / output data features.

[0391] S102: The base station sends function information 1 to the UE.

[0392] The base station trains the function / model based on functional information 2 and transmits the function / model to the UE. The base station transmits the function / model to the UE through functional information 1, which is used by the UE to perform AI / ML inference and help improve system performance.

[0393] In one specific implementation, the base station can also indicate one or more sets of data features or application conditions corresponding to the function / model through functional information 1.

[0394] S103: The base station sends indication information 1 to the UE.

[0395] The base station instructs the UE on monitoring indicator requirements via instruction information 1.

[0396] In one specific implementation, the base station indicates the monitoring indicator requirements through indication information 1, and also indicates that the monitoring indicator requirements are associated with the data characteristics or application conditions corresponding to the model / function.

[0397] In another specific implementation, the base station indicates at least two monitoring indicator requirements through indication information 1.

[0398] It should be understood that instruction information 1 and function information 1 can be sent through the same message or through different messages, and this application does not make any special limitation on this.

[0399] S104: The UE monitors and manages the functions.

[0400] The UE monitors the model / function based on the performance requirements obtained from indication information 1. The UE manages the model / function based on the monitoring results.

[0401] S105: The UE sends management information 1 to the base station.

[0402] The UE reports the management results of the model / function to the base station through management information 1.

[0403] In an alternative implementation, the UE can also indicate the reason for model management to the base station via management information 1. The UE can report to the base station via management information 1 which monitoring indicator is used for function / model management, and the monitoring results of the corresponding monitoring indicator.

[0404] As an example rather than a limitation, in the BM scenario, the UE indicates, through management information 1, that under the current SetA / SetB configuration, the system throughput is less than the required corresponding threshold (which may include the actual value), or indicates that the accuracy of the predicted top-K beam is less than a certain threshold, or indicates the predicted L1-RSRP and the actual value.

[0405] As an example rather than a limitation, in a mobility scenario, the UE indicates the current UE speed data via management information 1 and indicates that the cell signal quality is less than the required threshold.

[0406] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0407] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0408] Figure 11 is a flowchart illustrating another communication method of a training node at a base station provided in an embodiment of this application.

[0409] In the implementation of case 5 shown in Figure 11, the training node is on the base station, the monitoring node is on the UE side, and the management node is on the base station side. Specifically, it includes the following steps:

[0410] S111: The UE sends functional information 2 to the base station.

[0411] The UE reports the supported models / functions to the base station.

[0412] The UE reports the supported models / functions to the base station via function information 2. The UE can also report its own conditions and supported data features via function information 2, which may include model input / output data features.

[0413] S112: The base station sends function information 1 to the UE.

[0414] The base station trains the function / model based on the functional information 2 and transmits the function / model to the UE.

[0415] In one specific implementation, the base station can also indicate one or more sets of data features or application conditions corresponding to the function / model through functional information 1.

[0416] S113: The base station sends indication information 1 to the UE.

[0417] The base station instructs the UE on monitoring indicator requirements via instruction information 1.

[0418] In one specific implementation, the base station indicates the monitoring indicator requirements through indication information 1, and also indicates that the monitoring indicator requirements are associated with the data characteristics or application conditions corresponding to the model / function.

[0419] In another specific implementation, the base station indicates at least two monitoring indicator requirements through indication information 1.

[0420] S114: The base station sends configuration information 2 to the UE.

[0421] The base station instructs the UE on the configuration of monitoring information reporting through configuration information 2, including instructing the UE on the reporting content and reporting conditions.

[0422] In one specific implementation, the base station configures the types of monitoring indicators to be reported to the UE through configuration information 2. For example, the information to be reported to the UE may include at least one of the following: RSRP measurement data, actual results, inference results, gap between actual and measurement results, etc.

[0423] In another specific implementation, the base station can also configure the data characteristics (or data characteristic identifiers) to be reported to the UE, or the UE-side conditions, through configuration information 2.

[0424] In another specific implementation, the base station can also configure the method of reporting monitoring information to the UE through configuration information 2. This can be either periodic reporting or conditional reporting. If periodic reporting is used, the UE needs to configure the start reporting time and the reporting period; if conditional reporting is used, the UE needs to configure the threshold conditions for triggering the reporting.

[0425] In another specific implementation, the base station can also configure the UE with the configuration information 2 required by other UEs to obtain monitoring results through measurement. As an example and not a limitation, in the BM scenario, the base station configures the UE with the required configuration for calculating SetA / SetB of the monitoring results; in the mobility scenario, the base station configures the UE with the configuration required for the measurement object used to calculate the monitoring results; and in the CSI scenario, the base station configures the UE with the configuration required for CSI measurement used to calculate the monitoring results.

[0426] In another specific implementation, the base station can also configure the UE to report multi-indicator monitoring information through configuration information 2.

[0427] It should be understood that instruction information 1, function information 1, and configuration information 2 can be sent through the same message or through different messages, and this application does not make any special restrictions on this.

[0428] S115: The UE monitors the function.

[0429] The UE monitors the model / function based on the performance requirements obtained from indication information 1, and obtains monitoring information 1.

[0430] S116: The UE sends monitoring information 1 to the base station.

[0431] Based on the configured monitoring indicator requirements, the UE reports the model monitoring results through monitoring information 1.

[0432] It should be understood that when the UE meets the reporting conditions configured in configuration information 2, the UE reports the monitoring results through monitoring information 1 for base station management.

[0433] In one optional implementation, the content reported by the UE through monitoring information 1 may include one or more of the following: data characteristics, UE-side conditions, monitoring indicator results, etc.

[0434] In another alternative implementation, the content reported by the UE through monitoring information 1 may include monitoring information of multiple indicators.

[0435] S117: The base station manages the functions.

[0436] The base station performs model / function management based on the monitoring results carried in the monitoring information 1 reported by the UE.

[0437] S118: The base station sends management information 1 to the UE.

[0438] The base station sends the management results of the function / model to the UE through management information 1. The UE updates the model / function based on the instructions in management information 1 sent by the base station.

[0439] It should be understood that the content and fields contained in the signaling with the same name in steps S111 to S118 are similar to those in steps S701 to S705, and the functions of the signaling with the same name are also similar. For the sake of brevity, they will not be described again here.

[0440] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0441] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0442] Figure 12 is a flowchart illustrating another communication method of a training node at a base station provided in an embodiment of this application.

[0443] In the implementation of case 6 shown in Figure 12, the training node, monitoring node, and management node are all located on the base station side. Specifically, the following steps are included:

[0444] S121: The UE sends functional information 2 to the base station.

[0445] The UE reports the supported models / functions to the base station.

[0446] The UE reports the supported models / functions to the base station via function information 2. The UE can also report its own conditions and supported data features via function information 2, which may include model input / output data features.

[0447] S122: The base station sends functional information 1 to the UE.

[0448] The base station trains the function / model and transmits the function / model to the UE through function information 1.

[0449] In one specific implementation, the base station can also indicate one or more sets of data features or application conditions corresponding to the function / model through functional information 1.

[0450] S123: The base station sends configuration information 1 to the UE.

[0451] The base station instructs the UE on the configuration of measurement information reporting via configuration information 1. The reported measurement information is used to monitor the function / model. Configuration information 1 is also used to configure the reporting content and reporting conditions of the UE.

[0452] In one specific implementation, the base station configures the measurement objects to the UE through configuration information 1. For example, in the BM scenario, the base station configures the relevant measurement objects of SetA / SetB used by the UE to calculate the monitoring results; in the mobility scenario, the base station configures the relevant measurement objects of the UE to calculate the monitoring results; and in the CSI scenario, the base station configures the relevant measurement objects of the CSI measurement used by the UE to calculate the monitoring results.

[0453] In another specific implementation, the base station also configures the type of reporting object to the UE through configuration information 1. For example, the type of reporting object configured for the UE includes at least one of the following: RSRP measurement data, actual results, inference results, gap between actual and measurement results, etc.

[0454] In another specific implementation, the base station also configures the data characteristics (or data characteristic identifiers) of the measurement information reported to the UE, or the UE-side conditions, through configuration information 1.

[0455] In another specific implementation, the base station also configures the measurement information to be reported to the UE through configuration information 1, including measurement information of multiple monitoring indicators.

[0456] In another specific implementation, the base station also configures the reporting method of measurement information to the UE through configuration information 1, including periodic reporting or conditional reporting. If it is periodic reporting, the start reporting time and reporting period also need to be configured; if it is conditional reporting, the threshold condition for triggering the reporting also needs to be configured.

[0457] It should be understood that functional information 1 and configuration information 1 can be sent through the same message or through different messages, and this application does not make any special restrictions on this.

[0458] S124: The UE sends monitoring information 2 to the base station.

[0459] The UE performs measurements and reports based on its configuration.

[0460] In one optional implementation, the monitoring information 2 reported by the base station includes data on model / functional monitoring indicators under different data characteristics or conditions. For example, monitoring information 2 may include one or more of the following: data characteristics, UE-side conditions, monitoring indicator results, etc.

[0461] In another alternative implementation, the monitoring information 2 reported by the base station includes data or required information under multiple monitoring indicators of the model / function.

[0462] S125: The base station monitors and manages the functions.

[0463] The base station monitors the model / function based on defined performance requirements and the measurement results obtained from monitoring information 2, which are necessary for monitoring the model / function. The base station also manages the model / function based on the monitoring results, such as switching, updating, and deactivating the model / function.

[0464] S126: The base station sends management information 1 to the UE.

[0465] The base station sends the management results of the function / model to the UE through management information 1. The UE updates the model / function based on the instructions in management information 1 sent by the base station.

[0466] It should be understood that the content and fields contained in the signaling with the same name in steps S121 to S126 are similar to those in steps S701 to S705, and the function of the signaling with the same name is also similar. For the sake of brevity, they will not be described again here.

[0467] In scenarios where AI / ML models / functionally assisted LMF positioning is used on the UE side, the aforementioned base station can be replaced with an LMF, and the above process can be applied to the positioning scenario.

[0468] In scenarios where AI / ML models / functional assistance is used for LMF positioning on the base station side, the UE can be replaced by the base station, and the base station can be replaced by the LMF. The above process can be applied to the positioning scenario.

[0469] In summary, Figures 7 to 12 describe the implementation methods for the six cases in Table 1.

[0470] The above implementation method provides a process for differentiated monitoring and management of UE-side functions / models with different monitoring performance indicators under different (input / output) data characteristics or UE conditions. This allows for meeting the different model performance requirements under varying data characteristics and conditions.

[0471] If the UE performs monitoring, it will determine different monitoring indicator requirements based on the data characteristics or conditions of the model / function. The differentiated indicators may come from training nodes or base stations. The UE performs model / function monitoring based on the differentiated indicator requirements and uses them for model / function management by the UE or base station.

[0472] If monitoring is performed at the base station, the base station acquires data / functional characteristics or conditions from the model to determine different monitoring indicator requirements. The indication information for the monitoring indicators can come from the UE or training nodes (training nodes may be base stations or non-base station sides), and the base station configures monitoring information reporting or measurement reporting to the UE according to different monitoring indicator requirements for model / functional management.

[0473] The above implementation method also provides a way for UEs or base stations to perform model / function monitoring based on multi-dimensional monitoring indicator requirements.

[0474] In some specific implementations, when there are multiple monitoring indicators, the specific monitoring process, signaling details, and signaling functions for each monitoring indicator are similar to those for a single monitoring indicator. The model / function is then managed based on the correlation between the monitoring results of each individual monitoring indicator.

[0475] In other specific implementations, when there are multiple monitoring indicators, instead of setting corresponding data features or conditions for each monitoring indicator, the function / model is monitored and managed through the correlation between multiple monitoring indicators or the satisfaction of preset relationships.

[0476] If the UE performs monitoring, the UE will determine the multi-dimensional monitoring indicator requirements, which can come from the training node or the base station.

[0477] If monitoring is performed at the base station, the base station acquires the multi-dimensional monitoring indicator requirements. The indication information of the monitoring indicators can come from the UE or training nodes (training nodes may be base stations or non-base station sides), and the base station configures the UE to report monitoring information or measurement information according to the multi-dimensional monitoring indicator requirements for model / function management.

[0478] It should be understood that in the above implementation method, multiple monitoring indicators are also referred to as multidimensional monitoring indicators, and this application does not make any special limitation on them.

[0479] In AI / ML application scenarios, AI / ML-based localization is also included. As mentioned above, there are five cases for AI / ML-based localization: case1b, case2b, case3b, case2a, and case3a. The following description will be based on these five cases, combined with the training status of the UE model / function, to illustrate AI / ML-based localization.

[0480] For case 1b, the UE model / function can be divided into the following 6 cases as shown in Table 2, depending on the different training nodes, monitoring nodes and management nodes.

[0481] Table 2 shows the UE model / function situation in scenario 1b.

[0482] It should be understood that the situations shown in Table 2 and Table 1 are consistent. In some specific implementations, the specific implementation methods based on AI / ML positioning in case 1a can be referred to the specific implementation methods in Figures 6 to 12. For the sake of brevity, this application will not elaborate further here.

[0483] It should be understood that in the implementation methods shown in Figures 6 to 12, the monitoring indicators set for the function / model should include indicators related to positioning.

[0484] As an example, and not a limitation, the monitoring metric can be set to positioning accuracy. The UE will monitor the model / function by comparing the actual measured positioning value with the positioning value inferred by AI / ML.

[0485] For case 2b, the UE model / function can be divided into the following cases as shown in Table 3, depending on the different training nodes, monitoring nodes and management nodes.

[0486] Table 3 shows the UE model / function situation in scenario 2b.

[0487] It should be understood that the entire AI / ML-based positioning process in Table 3 can be implemented within the LMF network element without the influence of signaling. This application does not impose any special limitations on this.

[0488] For case 3b, the UE model / function can be divided into the following cases as shown in Table 4, depending on the different training nodes, monitoring nodes, and management nodes.

[0489] Table 4 shows the UE model / function situation in scenario 3b.

[0490] It should be understood that the entire AI / ML-based positioning process in Table 4 can be implemented within the LMF network element without the influence of signaling. This application does not impose any special limitations on this.

[0491] For case 2a, the UE model / function can be divided into the following cases as shown in Table 5, depending on the different training nodes, monitoring nodes and management nodes.

[0492] Table 5 shows the UE model / function situation in scenario 2a.

[0493] It should be understood that the situations shown in Table 5 and Table 1 are basically the same, the difference being that the monitoring and management node on the network side can be an LMF in addition to the base station. If the monitoring and management node on the network side is an LMF, the LMF network element needs to obtain the indication information required for monitoring from the base station, or OTT / OAM / CN, or UE. The specific implementation process can be referred to in Figures 6 to 12. For the sake of simplicity, this application will not elaborate further here.

[0494] For case 3a, the UE model / function can be divided into the following cases as shown in Table 6, depending on the different training nodes, monitoring nodes and management nodes.

[0495] Table 6 shows the UE model / function situation in scenario 3a.

[0496] It should be understood that the situations shown in Table 6 and Table 1 are basically the same, the difference being that the UE in the monitoring and management node is replaced by the base station, and the base station in the monitoring and management node is replaced by the LMF network element. The specific implementation process of the interaction between the LMF network element and the base station can be found in Figures 6 to 12. For the sake of brevity, this application will not elaborate further here.

[0497] The following section details the specific implementations of cases 1 to 6 in Table 1 of this application within a concrete communication architecture, including the communication architectures shown in Figures 2 and 3.

[0498] The communication architectures shown in Figures 2 and 3 include the RIC architecture under the open RAN architecture and the architecture including CU-DU. That is, the AI ​​module is independent of the network nodes, and the independent AI module can provide the functions required for AI to each network element node.

[0499] Base station-side nodes can be divided into CU and DU. In a solution where both monitoring and management are located on the base station side, the monitoring node and the management node may both be located in the CU or both in the DU. In this case, the monitoring and management processes are implemented internally within the nodes. If the monitoring node is in the DU and the management node is in the CU, interaction between the CU and the DU may be introduced.

[0500] For network-side AI / ML functional models, if DU performs inference and monitoring, and CU performs management, the introduced process includes:

[0501] S1: The CU configures the DU to perform monitoring and reports the monitoring results to the CU.

[0502] S2: CU performs model management based on the monitoring results of DU and instructs DU on the management results.

[0503] For the AI / ML function model on the UE side, the example shown in Figure 8, case 2, is used as an example for illustration. The management node can be in DU or CU.

[0504] If the interactions between the management node and DU, CU, and DU include:

[0505] In S802, the UE can report supported or available models / functions to the DU via lower-level signaling. If the UE reports via higher-level signaling (e.g., RRC signaling), the CU also needs to forward the supported or available model / function information reported by the UE to the DU.

[0506] In S803b and S803c, the UE reports model / function related information to the DU via lower-level signaling. The DU determines the monitoring indicators and the monitoring reporting configuration, and sends it to the UE via lower-level signaling. If the UE reports model / function related information to the CU via higher-level signaling, the CU also needs to forward the reported model / function related information to the DU; the DU determines the monitoring indicators and the monitoring reporting configuration, and submits them to the CU, which then sends them to the UE.

[0507] It should be understood that the steps of S803e and S803c are similar, and for the sake of brevity, they will not be described in detail here.

[0508] In S804 to S806, the UE reports model / function monitoring results to the DU via lower-level signaling. The DU performs model / function management and instructs the UE on the model management results via lower-level signaling. If the UE reports model / function monitoring results to the CU via higher-level signaling, the CU forwards the results to the DU, which then performs model / function management.

[0509] If the management node's interactions between CU, CU, and DU include:

[0510] In S802, the UE can report supported or available models / functions to the CU through higher-layer signaling. If the UE reports to the DU through lower-layer signaling, the DU also needs to forward the supported or available model / function information reported by the UE to the CU.

[0511] In S803b and S803c, the UE reports model / function related information to the CU via higher-layer signaling. The CU determines the monitoring indicators and the monitoring reporting configuration, and then sends it to the UE. If the UE reports model / function related information to the DU via lower-layer signaling, the DU forwards the information to the CU, which then determines the monitoring indicators and the monitoring reporting configuration, and sends it to the UE.

[0512] It should be understood that the steps of S803e and S803c are similar, and for the sake of brevity, they will not be described in detail here.

[0513] In S804 to S806, the UE reports model / function monitoring results to the CU via higher-layer signaling. The CU performs model / function management and instructs the UE on the model management results. If the UE reports model / function monitoring results to the DU via lower-layer signaling, the DU forwards the results to the CU, which then performs model / function management.

[0514] It should be understood that in the schemes of cases 3 to 6 shown in Figures 9 to 12, the situation between CU and DU is similar. After receiving the message from the UE, the node needs to forward it to the required node (which can be another node or the node itself); or, after generating the message, the message is sent to the UE through the appropriate node. For the sake of brevity, this application will not elaborate further here.

[0515] It should be understood that in an open RAN architecture, for base station-side training scenarios, if the training node is a CU (or DU), necessary interaction is required between the CU (or DU) and the AI ​​module to support the CU (or DU) in completing model / function training. Those skilled in the art can extend the interaction between the CU (or DU) and the AI ​​module by combining existing technologies and the implementation methods in this application, and these extensions should not be considered to exceed the protection scope of this application.

[0516] It should be understood that the CU and DU need to exchange the information required for model / function monitoring and model / function management.

[0517] In one possible approach, the data features or conditions of the model / function may be part of the model / function, meaning there is a one-to-one correspondence between the model / function and the data features and conditions, and there is no case where one model / function corresponds to multiple sets of data features or conditions.

[0518] It is understood that the various embodiments described in this application can be independent solutions or combinations based on internal logic, and all such solutions fall within the protection scope of this application. Furthermore, the explanations or descriptions of the various terms appearing in the embodiments can be referenced or interpreted mutually in the various embodiments, and are not intended to limit the scope of protection.

[0519] Figure 13 is a schematic block diagram of a communication device provided in an embodiment of this application.

[0520] As shown in Figure 13, the communication device 1000 may include a transceiver unit 1010 and a processing unit 1020. The transceiver unit 1010 can be used to implement corresponding communication functions. The transceiver unit 1010 may also be referred to as a communication interface or communication unit. The processing unit 1020 can be used to determine resources and generate information. Optionally, the transceiver unit 1010 may include a receiving unit and a sending unit, whereby the receiving unit is used to implement the function of receiving data and the sending unit is used to implement the function of sending data.

[0521] Optionally, the communication device 1000 may further include a storage unit, which can be used to store instructions and / or data. The processing unit 1020 can read the instructions and / or data in the storage unit to enable the device to implement the aforementioned method embodiments.

[0522] The communication device 1000 may be a terminal device in the above method embodiments, or it may be a chip used to implement the functions of the terminal device in the above method embodiments. It should be understood that the communication device 1000 may correspond to the terminal device in the implementation described in Figures 6 to 12 of this application, and the communication device 1000 may execute the steps corresponding to the terminal device in the implementation described in Figures 6 to 12 of this application.

[0523] In one possible design, the processing unit 1020 is used to monitor and / or manage the first function; the processing unit 1020 is used to determine the first data and / or the first information; the transceiver unit 1010 can be used to receive the first indication information from the network device; the transceiver unit 1010 is also used to send the second indication information to the network device.

[0524] In one possible design, the processing unit 1020 is used to monitor and / or manage the first function; the processing unit 1020 is used to determine the second data and / or the third data and / or the second information; the transceiver unit 1010 can be used to receive the third indication information from the network device; the transceiver unit 1010 is also used to send the fourth indication information to the network device.

[0525] The communication device 1000 may be a network device in the above method embodiments, or it may be a chip used to implement the functions of the network device in the above method embodiments. It should be understood that the communication device 1000 may correspond to the network device in the implementation described in Figures 6 to 12 of this application, and the communication device 1000 may execute the steps corresponding to the network device in the implementation described in Figures 6 to 12 of this application.

[0526] In one possible design, the processing unit 1020 is used to monitor and / or manage the first function; the transceiver unit 1010 is used to send the first instruction information to the terminal device.

[0527] In one possible design, the processing unit 1020 is used to monitor and / or manage the first function; the transceiver unit 1010 is used to send third instruction information to the terminal device.

[0528] It should also be understood that the communication device 1000 here is embodied in the form of a functional unit. The term "unit" here may refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memories for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0529] The communication device 1000 of each of the above schemes has the function of implementing the corresponding steps performed by the terminal device or network device in the above methods. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, which respectively execute the transmission and reception operations and related processing operations in each method embodiment.

[0530] In addition, the transceiver unit 1010 may also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing unit 1020 may be a processing circuit.

[0531] Figure 14 is a schematic block diagram of a communication device provided in an embodiment of this application.

[0532] The communication device 2000 shown in Figure 14 may include a processor 2010.

[0533] Optionally, as shown in FIG14, the device 2000 further includes a transceiver 2020 for receiving and / or transmitting signals. For example, the processor 2010 is used to control the transceiver 2020 to receive and / or transmit signals. Optionally, the transceiver 2020 may include a receiver for receiving signals and a transmitter for transmitting signals.

[0534] The processor 2010 may be coupled to the memory 2030, which is used to store computer programs or instructions and / or data. The processor 2010 is used to execute the computer programs or instructions stored in the memory 2030, or to read the data stored in the memory 2030, in order to perform the methods in the above method embodiments.

[0535] Optionally, there may be one or more processors 2010.

[0536] Optionally, the memory 2030 may be one or more.

[0537] Alternatively, the memory 2030 can be integrated with the processor 2010, or it can be set up separately.

[0538] As an example, processor 2010 may have the functions of processing unit 1020 shown in FIG13, memory 2030 may have the functions of storage unit, and transceiver 2020 may have the functions of transceiver unit 1010 shown in FIG13.

[0539] For example, the communication device 2000 can be used to implement the operations performed by the terminal device in the various method embodiments described above.

[0540] In one possible design, the processor 2010 is used to monitor and / or manage the first function; the processor 2010 is used to determine the first data and / or the first information; the transceiver 2020 can be used to receive the first indication information from the network device; the transceiver 2020 is also used to send the second indication information to the network device.

[0541] In one possible design, the processor 2010 is used to monitor and / or manage the first function; the processor 2010 is used to determine second data and / or third data and / or second information; the transceiver 2020 can be used to receive third indication information from the network device; the transceiver 2020 is also used to send fourth indication information to the network device.

[0542] For example, the communication device 2000 can also be used to implement the operations performed by the network device in the various method embodiments described above.

[0543] In one possible design, the processor 2010 is used to monitor and / or manage the first function; the transceiver 2020 is used to send the first instruction information to the terminal device.

[0544] In one possible design, the processor 2010 is used to monitor and / or manage the first function; the transceiver 2020 is used to send third instruction information to the terminal device.

[0545] It should be understood that the specific process by which each transceiver and processor performs the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0546] This application also provides a processor for executing computer programs or instructions stored in a memory, or reading data / signaling stored in a memory, to perform the methods in the above-described method embodiments. Optionally, there may be one or more processors.

[0547] This application also provides a chip, including a processor and a communication interface. The processor reads instructions stored in the memory through the communication interface and executes the methods provided in the above embodiments.

[0548] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by the device in the above-described method embodiments.

[0549] For example, when the computer program is executed by a computer, it enables the computer to implement the methods executed by the terminal device or network device in the various embodiments of the above methods.

[0550] This application also provides a computer program product comprising instructions that, when executed by a computer, implement the methods performed by a terminal device or network device in the above-described method embodiments.

[0551] This application also provides a communication system, including the terminal device and network device described in any of the preceding embodiments. Further, the communication system may also include the first node described in any of the preceding embodiments.

[0552] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0553] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0554] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0555] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0556] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0557] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0558] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The method is executed by a terminal device or a chip applied to the terminal device, the method comprising: Receive first instruction information, the first instruction information is used to instruct the terminal device to acquire first data, the first data has a corresponding relationship with a first feature, the first feature includes the feature of the terminal device or a first function, the first function is used to assist the terminal device in communication; Send a second instruction message, the second instruction message including the first data and / or first information determined based on the first data, the first data and / or the first information being used to manage the first function.

2. The method according to claim 1, characterized in that, The second indication information also includes the first data and / or the correspondence between the first information and the first feature.

3. The method according to claim 1 or 2, characterized in that, The first data includes the measurement results of the first indicator, which is used to measure the auxiliary effect of the first function; The first information is determined based on the measurement result of the first indicator, and the first information is used to indicate whether the measurement result of the first indicator meets the first preset condition.

4. The method according to claim 3, characterized in that, Also includes: The first preset condition is received, which is used to trigger the terminal device to report the first information.

5. The method according to claim 3 or 4, characterized in that, The first preset condition includes the expected value of the first indicator.

6. The method according to any one of claims 3 to 5, characterized in that, The second instruction information is also used to instruct the network device to manage the first function based on the first information.

7. The method according to any one of claims 1 to 6, characterized in that, The first indication information is further used to instruct the terminal device to report the second indication information based on a first cycle; and / or The first indication information is also used to indicate a first preset condition; and / or The first indication information is also used to indicate the correspondence between the first data and the first feature included in the reported second indication information.

8. The method according to any one of claims 1 to 7, characterized in that, Also includes: Send first function information, the first function information including the first feature corresponding to the first function, the first function information being used to instruct the network device to determine the first indicator.

9. The method according to any one of claims 1 to 7, characterized in that, Also includes: Receive second functional information, which includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

10. A communication method, characterized in that, The method is performed by a network device or a chip applied to the network device, the method comprising: Send a first instruction message, the first instruction message being used to acquire first data, the first data having a corresponding relationship with a first feature, the first feature including a feature of a terminal device or a first function, the first function being used to assist the terminal device in communication; The network device receives a second instruction, which includes the first data and / or first information determined based on the first data, and manages the first function based on the first data and / or the first information.

11. The method according to claim 10, characterized in that, The second indication information also includes the first data and / or the correspondence between the first information and the first feature.

12. The method according to claim 10 or 11, characterized in that, The first data includes the measurement results of a first indicator, which is used to measure the auxiliary effect of the first function.

13. The method according to claim 12, characterized in that, The first indication information is also used to instruct the terminal device to determine the first information based on the first data. The first information is used to indicate whether the measurement result of the first indicator meets the first preset condition.

14. The method according to claim 13, characterized in that, Also includes: Send the first preset condition, which is used to trigger the terminal device to report the first information.

15. The method according to claim 13 or 14, characterized in that, The first preset condition includes the expected value of the first indicator.

16. The method according to any one of claims 13 to 15, characterized in that, Based on the second instruction information, the first function is managed according to the first information.

17. The method according to any one of claims 10 to 16, characterized in that, The first indication information is further used to instruct the terminal device to report the second indication information based on a first cycle; and / or The first indication information is also used to indicate a first preset condition; and / or The first indication information is also used to indicate the correspondence between the first data and the first feature included in the reported second indication information.

18. The method according to any one of claims 10 to 17, characterized in that, Also includes: Receive first function information, the first function information including the first feature corresponding to the first function. Based on the first functional information, determine the first indicator.

19. The method according to any one of claims 10 to 17, characterized in that, Also includes: Receive second functional information, which includes a first indicator and a first feature, as well as the relationship between the first indicator and the first feature.

20. A communication device, characterized in that, The communication device includes a processor and a memory, the memory for storing computer programs or instructions, and the processor for executing the computer programs or instructions in the memory, such that the method as described in any one of claims 1 to 9 is performed. Alternatively, the method as described in any one of claims 10 to 19 may be performed.

21. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when run on a computer, causes the method as described in any one of claims 1-19 to be performed.

22. A communication system, characterized in that, The communication system includes terminal equipment and network equipment; The terminal device is used to execute the communication method as described in any one of claims 1-9; The network device is used to perform the communication method as described in any one of claims 10-19.

23. A computer program product, characterized in that, Includes instructions that, when executed on a computer, The method of any one of claims 1 to 9 is performed; or, This causes the method of any one of claims 10 to 19 to be performed.

24. A chip system, characterized in that, The chip system includes a processor, a memory, and input / output ports. The memory stores computer programs; the processor executes the computer programs stored in the memory. So that the processor performs the method as described in any one of claims 1 to 9; or, So that the processor performs the method as described in any one of claims 10 to 19.

Images