UE capability reporting method and device, equipment and medium

Abstract

The invention discloses a UE capability reporting method and device, equipment and a medium, and relates to the field of communication. The method comprises: reporting the UE capability to a network device when a reporting condition is satisfied (310). In a cellular communication system, the network equipment is indicated in a semi-static manner by dynamically reporting the UE capability, so that the flexibility and accuracy of UE capability reporting are improved, and the resource loss in the UE capability reporting process is reduced.

Description

UE capability reporting method, device, equipment and medium Technical Field

[0001] The present application relates to the field of communications, and in particular to a method, apparatus, device, and medium for reporting user equipment (UE) capabilities. Background Art

[0002] In cellular network communications, accurate and efficient coordination and intercommunication between network devices and UEs is very important, and UE capabilities are an important part of the coordination between network devices and UEs.

[0003] In related technologies, a network device sends a UE capability query to a UE, and the UE sends UE capability information to the network device. However, this reporting method cannot meet the reporting requirements in certain scenarios.

[0004] Summary of the Invention

[0005] The present invention provides a method, apparatus, device, and medium for reporting UE capabilities. These methods can report / update dynamically changing UE capabilities to network devices in a reasonable manner when UE capabilities are dynamically changing. The technical solution includes at least one of the following solutions:

[0006] According to one aspect of the present application, a method for reporting UE capabilities is provided, the method comprising:

[0007] When the reporting conditions are met, the UE capabilities are reported to the network device.

[0008] According to one aspect of the present application, a method for reporting UE capabilities is provided, the method comprising:

[0009] Receive UE capabilities reported by a terminal, where the UE capabilities are reported by the terminal when a reporting condition is met.

[0010] According to one aspect of the present application, a device for reporting UE capabilities is provided, the device including:

[0011] The first sending module is configured to report the UE capability to the network device when a reporting condition is met.

[0012] According to one aspect of the present application, a device for reporting UE capabilities is provided, the device including:

[0013] The second receiving module is configured to receive UE capabilities reported by the terminal, where the UE capabilities are reported by the terminal when a reporting condition is met.

[0014] According to one aspect of the present application, a terminal is provided, comprising: a processor; a transceiver connected to the processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to load and execute the executable instructions to implement the UE capability reporting method as described in the above aspect.

[0015] According to one aspect of the present application, a network device is provided, comprising: a processor; a transceiver connected to the processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to load and execute the executable instructions to implement the UE capability reporting method as described in the above aspects.

[0016] According to one aspect of the present application, a computer-readable storage medium is provided, wherein the computer program product stores executable instructions, and the executable instructions are loaded and executed by a computer device to implement the UE capability reporting method as described in the above aspect.

[0017] According to one aspect of the present application, a computer program product is provided, which includes computer instructions, the computer instructions are stored in a computer-readable storage medium, the processor of a computer device reads the computer instructions from the computer-readable storage medium, and the executable instructions are loaded and executed by the computer device to implement the UE capability reporting method as described in the above aspect.

[0018] According to one aspect of the present application, a chip is provided, which includes a programmable logic circuit and / or program instructions, and is used to implement the UE capability reporting method as described in the above aspect when a terminal having the chip is running.

[0019] The technical solutions provided by the embodiments of the present application include at least the following beneficial effects:

[0020] By reporting UE capabilities to network devices based on dynamic changes in UE capabilities, network devices can be dynamically instructed to improve the autonomy, accuracy, and flexibility of UE capability reporting. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] FIG1 shows a schematic diagram of a process of UE capability reporting in the related art;

[0023] FIG2 shows a schematic diagram of the structure of a neural network in the related art;

[0024] FIG3 shows a flowchart of a method for reporting UE capabilities provided by an exemplary embodiment of the present application;

[0025] FIG4 shows a flowchart of a method for reporting UE capabilities provided by an exemplary embodiment of the present application;

[0026] FIG5 shows a flowchart of a method for reporting UE capabilities provided by an exemplary embodiment of the present application;

[0027] FIG6 shows a flowchart of a method for reporting UE capabilities provided by an exemplary embodiment of the present application;

[0028] FIG7 shows a flowchart of a method for reporting UE capabilities provided by an exemplary embodiment of the present application;

[0029] FIG8 shows a structural block diagram of a UE capability reporting device provided by an exemplary embodiment of the present application;

[0030] FIG9 shows a structural block diagram of a UE capability reporting device provided by an exemplary embodiment of the present application;

[0031] FIG10 shows a schematic structural diagram of a communication device with UE capabilities provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions, and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings. Exemplary embodiments will be described in detail herein, with examples shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of devices and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0033] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0034] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining."

[0035] First, the relevant technical background involved in the embodiments of this application is introduced:

[0036] UE capability reporting:

[0037] Cellular wireless communication systems rely on accurate and efficient coordination and intercommunication between network devices such as base stations and user equipment (UE). UE capability is a key part of the coordination between base stations and UEs.

[0038] The base station can only make correct scheduling decisions for a UE after knowing its capabilities. If the UE supports a function, the base station can configure it for the UE; if the UE does not support a function, the base station cannot configure it for the UE.

[0039] The UE capability reporting process in the related art is shown in FIG1 .

[0040] UE capability reporting triggering reason: This process is triggered when the UE enters the Radio Resource Control (RRC) connected state and the next generation Node Basestation (gNB) has not obtained the UE capability information from the Core Network (CN), or the gNB wants to obtain the latest UE capability information.

[0041] UE capability reporting process: The gNB triggers this process to request the UE to report its capability information. The UE reports its capability information to the gNB. After receiving this UE capability information, the gNB forwards it to the CN for storage.

[0042] UE Capability Information Change: When a UE changes its capability information, it triggers the Non-Access Stratum (NAS) procedure to update the UE capability information. In Long Term Evolution (LTE) systems, UE capability information changes trigger the Attach procedure or the Tracking Area Update procedure. In 5G (5th Generation Mobile Communication Technology) systems, UE capability information changes occur during the registration process.

[0043] The combination of artificial intelligence (AI) and communication networks:

[0044] In recent years, artificial intelligence research and related achievements have achieved remarkable results in many fields. Artificial intelligence has become a new path for people to try to solve and deal with problems. Among the many studies, artificial intelligence research based on neural networks is an extremely important category. As shown in Figure 2, the basic structure of a simple neural network includes: input layer (10), hidden layer (20) and output layer (30). The input layer is responsible for receiving data, the hidden layer processes the data, and the final result is generated in the output layer.

[0045] The integration of wireless communication systems and AI is also a hot research topic. AI is being used to optimize system performance. The latest 3rd Generation Partnership Project (3GPP) Release 18 project also agreed to consider using AI to optimize related use cases, including positioning, beam management, and channel state information (CSI). For different use cases, model deployment, inference, and training can be performed on the network or the device side.

[0046] AI model training and reasoning require both computing power and storage capacity. If AI model training or reasoning is deployed on the terminal side, the UE's capabilities are also required. 3GPP's existing capability reporting primarily focuses on functional capabilities, such as whether the UE supports a certain feature. However, for AI-enabled use cases, in addition to the UE's need to report whether it supports the feature, the UE's computing power and storage capabilities also need to be reported to the network.

[0047] From the terminal's perspective, the UE's current services or operations directly affect the UE's available / remaining computing power / storage capacity. For example, when a user is playing games or watching movies on their phone, their computing power and storage requirements and usage may vary. Therefore, the remaining available computing power will also change in real time with the UE's current service type. For such dynamically changing capacity reporting, how to indicate this to the network is a problem that needs to be solved.

[0048] FIG3 shows a flowchart of a UE capability reporting method provided by an exemplary embodiment of the present application. This embodiment is described as being executed by a UE, and includes at least some of the following steps:

[0049] Step 310: When the reporting conditions are met, report the UE capabilities to the network device.

[0050] In this embodiment, the "UE capabilities" include dynamically changing UE capabilities. When reporting conditions are met, the UE reports the dynamically changing UE capabilities to the network device. Optionally, the UE capabilities include UE capabilities that dynamically change based on at least one of processor load, remaining memory capacity, communication bandwidth, and battery power.

[0051] Taking the UE capability as an example, if the reporting conditions are met, the UE reports the AI-related UE capability to the network device. In some embodiments, the UE capability includes at least one of the following capabilities:

[0052] Overall capabilities, for example, whether the UE supports AI functions;

[0053] Supported use cases based on AI capabilities;

[0054] Supported AI category levels;

[0055] Computing power;

[0056] Storage capacity;

[0057] ·Communication capabilities;

[0058] Battery level;

[0059] AI Model Index

[0060] Among the above-mentioned UE capabilities, total capabilities, use cases based on AI functions, supported AI category levels, etc. can be referred to as functional capabilities; computing capabilities, storage capabilities, communication capabilities, battery power, etc. can be referred to as terminal hardware capabilities.

[0061] Among them, the use case based on AI function refers to a communication use case optimized based on the AI ​​model. Optionally, the use case based on AI function includes at least one of AI-based positioning, AI-based beam management, AI-based channel status, user plane function information reporting in air interface resources, and control plane function information reporting in air interface resources. For example, the supported use case based on AI function refers to supporting at least one of AI-based positioning, AI-based beam management, and AI-based channel state information reporting; or, the supported use case based on AI function is at least one of all functions included in the user plane and control plane in the air interface resources, such as: at least one of switching, cell selection / reselection, measurement, random access process, and resource allocation.

[0062] The supported AI category level refers to the AI ​​function category supported by the AI ​​model. Optionally, the AI ​​category level includes whether at least one of training, reasoning, and data collection on the terminal side is supported. For example, the supported AI category level includes whether the UE supports at least one of AI model training on the terminal side, whether it supports AI model reasoning on the terminal side, and whether it supports AI model data collection on the terminal side.

[0063] Computing power, also known as computing power, refers to the computing power of the UE when running program tasks. Optionally, the computing power is represented by at least one of the floating-point computing power per unit time, the number of graphics processing units (GPUs), and the GPU cache size. Optionally, the computing power can be divided into total computing power and AI computing power. Total computing power, that is, total computing power, refers to the overall computing power of the UE. AI computing power refers to the computing power used by the UE to run AI models, which can reflect the complexity of the AI ​​models supported by the UE. Optionally, the AI ​​computing power is the computing power that the UE can provide for the operation of the AI ​​model; or, the computing power that is maximally allocated or currently allowed to be allocated to the operation of the AI ​​model in the total computing power of the UE; or, the computing power remaining in the total computing power of the UE excluding the computing power used for the non-AI model calculations being run; or, the computing power remaining in the computing power that the UE can allocate to the operation of the AI ​​model, excluding the computing power currently used and / or reserved.

[0064] Storage capacity refers to the UE's ability to store data. Optionally, storage capacity is represented by at least one of available memory size, available cache size, and available storage size. Optionally, storage capacity can be divided into total storage capacity and AI storage capacity. Total storage capacity refers to the UE's storage capacity when storing all data. AI storage capacity refers to the UE's storage capacity for storing and / or running AI models. Optionally, AI storage capacity is the storage capacity that the UE can provide for AI model storage and / or running; or the maximum allocated or currently allowed storage capacity of the UE's total storage capacity for AI model storage and / or running; or the remaining storage capacity of the UE's total storage capacity excluding the storage capacity used for storage of non-AI models currently running; or the remaining storage capacity of the UE's maximum storage capacity that can be allocated for AI model storage, excluding the currently used and / or reserved storage capacity. Illustratively, AI storage capacity can also be divided into static storage capacity, such as flash memory capacity, for storing AI models and AI model-related data; and dynamic storage capacity, such as memory capacity, for storing AI model running data. Communication capability, also known as transmission capability, refers to the ability of a UE to communicate or transmit data, including at least one of bandwidth, rate, and latency. Optionally, communication capability is represented by at least one of supported transmission rate, transmission latency, communication signal strength, channel quality status information, bit error rate, block error rate, and spectral efficiency. Communication capability can optionally be divided into total communication capability and AI communication capability. Total communication capability refers to the overall communication capability of the UE. AI communication capability refers to the ability of the UE to transmit AI models and / or AI model-related data, including training samples, model architecture, model parameters, and so on. Optionally, AI communication capability refers to the communication capability that the UE can provide for transmitting AI models; or, the maximum communication capability allocated or currently allowed to be allocated for transmitting AI models within the UE's total communication capability; or, the remaining communication capability of the UE's total communication capability, excluding ongoing transmissions not used by AI models; or, the remaining communication capability of the UE's maximum communication capability that can be allocated for transmitting AI models, excluding currently used and / or reserved communication capability.

[0065] Battery power refers to the battery power of the UE. It refers to the battery power available for the operation of the AI ​​model. Optionally, the battery power is represented by the remaining power. Optionally, the battery power can be divided into total battery power and AI battery power. The total battery power refers to the total battery power of the UE. The AI ​​battery power refers to the battery power used by the UE to run the AI ​​model. Optionally, the AI ​​battery power is the battery power that the UE can provide for the storage and / or operation of the AI ​​model; or, the battery power that is maximally allocated or currently allowed to be allocated to the operation of the AI ​​model in the total battery power of the UE; or, the battery power remaining in the total battery power of the UE excluding the battery power already used or expected to be used by the running non-AI model applications; or, the battery power remaining in the maximum battery power that the UE can allocate to the operation of the AI ​​model, excluding the battery power currently used and / or reserved.

[0066] The AI ​​model index, also known as the AI ​​model identifier, is used to indicate the AI ​​model. Schematically, the AI ​​model index is used to indicate the AI ​​model selected by the UE based on the current UE capabilities or the AI ​​models supported by the UE.

[0067] In some embodiments, before the UE reports its selected AI model index to the network device, it needs to obtain information about at least one AI model, where the information about the AI ​​model includes at least one of the following information: the AI ​​model index, the use case corresponding to the AI ​​model, the AI ​​model size, the AI ​​model accuracy, the AI ​​model complexity, and the generalization capability of the AI ​​model. Optionally, the information about the at least one AI model is predefined by a communication protocol, or is sent by the network device to the UE via an RRC message, or is sent by the network device to the UE via an NAS layer message, or is sent by the network device to the UE via system broadcast, or is sent by the NAS layer in the UE to the access stratum (AS).

[0068] In some embodiments, the reporting of the UE capability may also include: the granularity supported by the UE capability, such as per frequency band (Per Band), per terminal (Per UE), frequency division duplex (FDD) / time division duplex (TDD) different situations (Differ), FR1 / FR2 different situations (Differ). AI-related capability reporting can be bound to the associated use case, for example, the information element (IE) of the beam failure recovery (BFR) capability report includes capability information for AI BFR, including 1 bit (Binary Digit, bit) indicating support or non-support of AI-enabled BFR and other information, and / or at least one of the above functional capabilities, and / or at least one of the above hardware capabilities.

[0069] In some embodiments, the UE capability report includes a change in the current UE capability relative to the UE capability at the last report. Exemplarily, the change in the UE capability includes at least one of the following:

[0070] The change in current AI computing power relative to the last reported AI computing power;

[0071] The change in the current AI storage capacity relative to the last reported AI storage capacity;

[0072] The change in the current AI communication capability relative to the last reported AI communication capability;

[0073] The change in the current AI battery level relative to the last reported AI battery level;

[0074] The time difference between the current time and the last reported time;

[0075] The distance between the current position and the last reported position;

[0076] The number of serving cell handovers between the current reporting environment and the last reporting environment.

[0077] In some embodiments, the above-mentioned change amount can be indicated by explicit indication, bitmap indication, or change amount level.

[0078] In some embodiments, the UE capability report may be reporting the capability of each supported AI function use case, or the capability of a single AI function use case, or the total capability of the supported AI function. The UE may determine the capability change as a change in the total capability of the AI ​​function, or the capability of a single AI function use case, or a change in the capability of each AI function use case. That is, the granularity of the UE capability report is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case. The granularity of the UE capability change determination is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case.

[0079] In some embodiments, at least one capability in the reported content may be explicitly indicated, and / or at least one capability may be indicated separately using a capability level, and / or at least two capabilities may be indicated together using a capability level. Optionally, the capability level and / or the range corresponding to the capability level may be predefined by the communication protocol or configured by the network device.

[0080] Exemplarily, the UE capability reporting information explicitly indicates UE capability information, including at least one of the following information: the category of the UE capability, the name of the UE capability, and the parameters of the UE capability. For example, the battery level in the UE capability is indicated in an explicit indication manner, using 8 gears and 3 bits of information to indicate the current battery level. The code point "000" represents 0-12.5% ​​of the power level, the code point "001" represents 12.5-25% of the power level, and so on. The code point "111" represents 87.5-100% of the power level.

[0081] Exemplarily, the capability level is used in the UE capability reporting information to separately indicate the capability level of the current UE capability. For example, the UE capability reporting information indicates that the computing capability level is A, the storage capability level is B, and the communication capability level is C.

[0082] Exemplarily, the UE capability reporting information uses capability levels to combine and indicate the capability level of the current UE capability. Exemplarily, the UE capability reporting information indicates that the current UE capability level is A, indicating that the current UE's computing capability, storage capability, communication capability, and battery power capability levels are all A. Alternatively, as shown in Table 1, among the current UE capabilities, the floating-point computing capability is not less than a1, the available storage size is not less than a2, the transmission rate is not less than a3, and the current battery power is not less than a4. The UE uses capability level A in the UE capability reporting information to combine and indicate the capability level of the current UE capability.

[0083] Table 1 Schematic table of UE capability level combined indication

[0084]

[0085] In some embodiments, the change in the current UE capability relative to the UE capability at the time of the last report in the reported content may be explicitly indicated, and / or the change in at least one capability may be separately indicated using a capability change level, and / or the change in at least two capabilities may be combined and indicated using a capability change level. Optionally, the capability change level and / or the range corresponding to the capability change level is predefined by the communication protocol or configured by the network device.

[0086] Exemplarily, the UE capability reporting information explicitly indicates a change in current UE capability relative to the last reported UE capability, including at least one of the following information: a UE capability category, a UE capability name, and a parameter change in the UE capability. For example, in the UE capability reporting information, the AI ​​storage capability is reduced by X to explicitly indicate a change in the current AI storage capability relative to the last reported AI storage capability.

[0087] Exemplarily, the capability change level is used in the UE capability reporting information to separately indicate the change in the current UE capability relative to the UE capability at the time of the last report. For example, the UE capability reporting information indicates that the AI ​​computing capability change level is A, the AI ​​storage capability change level is B, and the AI ​​communication capability change level is C.

[0088] Exemplarily, the UE capability reporting information uses capability change levels to combine and indicate the change in the current UE capability relative to the UE capability at the time of the last report. Exemplarily, the change in the current UE computing capability is within capability change range d1, the change in battery power is within capability change range d2, the change in communication capability is within capability change range d3, and the change in storage capability is within capability change range d4. The UE uses capability change level D in the UE capability reporting information to combine and indicate the capability change level of the current UE capability.

[0089] In some embodiments, UE capabilities are reported in a Radio Resource Control (RRC) message, a Medium Access Control Control Element (MAC CE) message, or an Uplink Control Information (UCI) message. Optionally, the RRC message, MAC CE message, or UCI message indicates a change in UE capabilities.

[0090] In some embodiments, the UE reports changes in UE capabilities via RRC messages, using UE Assistance Information (UAI) signaling for message transmission. Exemplarily, satisfying at least one of the above reporting conditions can trigger the UE to report UE capabilities using the UAI reporting process.

[0091] In some embodiments, the UE capability is reported to the network device when the UE capability satisfies a first condition and / or when a change in the current reporting environment compared to the reporting environment at the last report satisfies a second condition.

[0092] In some embodiments, the UE reports UE capabilities to the network device based on the configuration of the network device.

[0093] In some embodiments, the UE reports UE capabilities to the network device upon initial access.

[0094] In some embodiments, the UE receives configuration information sent by the network device, where the configuration information is used to configure reporting resources for UE capabilities. Optionally, the UE reports UE capabilities based on the reporting resources configured by the network device.

[0095] In some embodiments, the UE reports the supported AI model index to the network device.

[0096] In some embodiments, the UE autonomously switches to an AI model corresponding to the UE capabilities based on the current UE capabilities, or the UE switches to an AI model corresponding to the UE capabilities based on the configuration of the network device.

[0097] In some embodiments, the UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a switching rule, the UE autonomously switches to an AI model corresponding to the UE's capabilities. Optionally, the switching rule is predefined by a communication protocol, configured by a network device, or determined autonomously by the UE. Optionally, the at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models are locally stored in the UE, or configured by a network device.

[0098] In some embodiments, a UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a configuration of a network device, the UE switches to an AI model corresponding to the UE's capabilities. Optionally, the at least two AI models, or the model indexes of at least two AI models, or the model parameters of at least two AI models are locally stored on the UE or configured by the network device.

[0099] In summary, the method provided in this embodiment reports UE capabilities to a network device based on dynamic changes in UE capabilities, provides semi-static instructions to the network device, and improves the autonomy, accuracy, and flexibility of UE capability reporting.

[0100] In this application, situations that meet the reporting requirements can be divided into at least three categories:

[0101] Type 1: UE capabilities meet the first condition;

[0102] Type 2: The change in the current reporting environment compared to the last reporting environment meets the second condition;

[0103] Type 3: The reporting method is based on the configuration of network devices.

[0104] Type 1: UE capability meets the first condition

[0105] When the UE capability meets the first condition, the UE capability is reported to the network device. Optionally, the first condition is predefined, or preconfigured, or configured by the network device.

[0106] In some embodiments, when a change in UE capability satisfies a first condition, the UE capability is reported to a network device.

[0107] In some embodiments, when a change in at least one capability among the UE capabilities satisfies a first condition, the UE capabilities are reported to the network device. Optionally, the at least one capability is predefined, or preconfigured, or configured by the network device.

[0108] In some embodiments, satisfying the first condition includes at least one of the following:

[0109] UE capability is lower than a first threshold;

[0110] UE capability is higher than a second threshold;

[0111] The change in UE capability relative to the last reported UE capability exceeds a third threshold.

[0112] In some embodiments, the first threshold is the minimum UE capability to ensure the operation of the AI ​​model.

[0113] Optionally, the first threshold is the minimum computing power to ensure the operation of the AI ​​model. If the current computing power of the UE is lower than the first threshold, the UE reports the UE capability to the network device.

[0114] Optionally, the first threshold is the minimum storage capacity to ensure the operation of the AI ​​model. If the current storage capacity of the UE is lower than the first threshold, the UE reports the UE capacity to the network device.

[0115] Optionally, the first threshold is the minimum communication capability to ensure the operation of the AI ​​model. If the current communication capability of the UE is lower than the first threshold, the UE reports the UE capability to the network device.

[0116] Optionally, the first threshold is the minimum battery power required to ensure the operation of the AI ​​model. If the current battery power of the UE is lower than the first threshold, the UE reports the UE capability to the network device.

[0117] In some embodiments, the second threshold is the UE capability requirement corresponding to AI models of different performance, that is, different thresholds (ranges).

[0118] Optionally, the second threshold is the different computing power requirements corresponding to AI models with different performance. When the available computing power of the UE rises above the second threshold, or falls below the second threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model.

[0119] Optionally, the second threshold is the different storage capacity requirements corresponding to AI models with different performance. When the available storage capacity of the UE rises above the second threshold, or falls below the second threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model.

[0120] Optionally, the second threshold is the different communication capability requirements corresponding to AI models with different performance. When the UE's available communication capability rises above the second threshold, or falls below the second threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model.

[0121] Optionally, the second threshold is the different battery power requirements corresponding to AI models with different performance. When the available battery power of the UE rises above the second threshold, or falls below the second threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model.

[0122] In some embodiments, the third threshold is the difference information of the change amount of the UE capability, which can represent the change amount of a single capability or the change amount of multiple capabilities.

[0123] Optionally, the third threshold is the change between the UE's current available computing power and the last reported available computing power. When the change in the UE's current available computing power compared to the last reported available computing power exceeds the third threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model or configuration.

[0124] Optionally, the third threshold is the change between the UE's current available storage capacity and the last reported available storage capacity. When the change in the UE's current available storage capacity compared to the last reported available storage capacity exceeds the third threshold, the UE reports the UE capacity to the network device, so that the network device updates the corresponding AI model or configuration.

[0125] Optionally, the third threshold is the change between the UE's current available communication capability and the last reported available communication capability. When the change in the UE's current available communication capability compared to the last reported available communication capability exceeds the third threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model or configuration.

[0126] Optionally, the third threshold is the change between the UE's current available battery power and the last reported available battery power. When the change in the UE's current available battery power compared to the last reported available battery power exceeds the third threshold, the UE reports the UE capability to the network device, so that the network device updates the corresponding AI model or configuration.

[0127] In some embodiments, the first threshold and the second threshold are in the same range, or the first threshold and the second threshold are in overlapping ranges, or the first threshold and the second threshold are in different ranges.

[0128] Type 2: The change in the current reporting environment compared to the last reporting environment meets the second condition

[0129] If the change in the current reporting environment compared to the last reporting environment satisfies a second condition, the UE capability is reported to the network device. Optionally, the second condition is predefined, preconfigured, or configured by the network device.

[0130] In some embodiments, the change in the current reporting environment compared to the reporting environment at the time of the last reporting meeting the second condition includes at least one of the following situations:

[0131] The time between the current time and the last reported time exceeds the fourth threshold;

[0132] The distance between the current location and the last reported location exceeds a fifth threshold.

[0133] In some embodiments, the fourth threshold is a time difference threshold (range) between the current moment and the last reported UE capability. If the time between the current moment and the last UE capability report exceeds the fourth threshold, the UE reports the UE capability again. Exemplarily, the fourth threshold is 30 minutes. If the time between the current moment and the last reported moment exceeds 30 minutes, the UE reports the UE capability to the network device.

[0134] In some embodiments, the fifth threshold is a distance threshold (range) or an area threshold (range). Optionally, the fifth threshold is a distance threshold, and when the distance between the current position and the last reported position exceeds the fifth threshold, the UE reports the UE capability to the network device for the network device to update the corresponding AI model or configuration. Exemplarily, the fifth threshold is 200 meters, and when the distance between the current position and the last reported position exceeds 200 meters, the UE reports the UE capability to the network device. Optionally, the fifth threshold is an area threshold, such as at least one cell, and when the distance between the current position and the last reported position exceeds the fifth threshold, the UE reports the UE capability to the network device for the network device to update the corresponding AI model or configuration. Exemplarily, the fifth threshold is a cell, and when the current position exceeds the range of the cell where the last reported position is located, the UE reports the UE capability to the network device.

[0135] In some embodiments, the UE capabilities reported by the UE to the network device include at least one of the following capabilities:

[0136] Overall capabilities, for example, whether the UE supports AI functions;

[0137] Supported use cases based on AI capabilities;

[0138] Supported AI category levels;

[0139] Computing power;

[0140] Storage capacity;

[0141] ·Communication capabilities;

[0142] Battery level;

[0143] AI model indexing.

[0144] Among the above-mentioned UE capabilities, total capabilities, use cases based on AI functions, supported AI category levels, etc. can be referred to as functional capabilities; computing capabilities, storage capabilities, communication capabilities, battery power, etc. can be referred to as terminal hardware capabilities.

[0145] Among them, the use case based on AI function refers to a communication use case optimized based on the AI ​​model. Optionally, the use case based on AI function includes at least one of AI-based positioning, AI-based beam management, AI-based channel status, user plane function information reporting in air interface resources, and control plane function information reporting in air interface resources. For example, the supported use case based on AI function refers to supporting at least one of AI-based positioning, AI-based beam management, and AI-based channel state information reporting; or, the supported use case based on AI function is at least one of all functions included in the user plane and control plane in the air interface resources, such as: at least one of switching, cell selection / reselection, measurement, random access process, and resource allocation.

[0146] The supported AI category level refers to the AI ​​function category supported by the AI ​​model. Optionally, the AI ​​category level includes whether at least one of training, reasoning, and data collection on the terminal side is supported. For example, the supported AI category level includes whether the UE supports at least one of AI model training on the terminal side, whether it supports AI model reasoning on the terminal side, and whether it supports AI model data collection on the terminal side.

[0147] Computing capacity, also known as computing power, refers to the computing power of the UE when running program tasks. Optionally, the computing capacity is represented by at least one of the floating-point computing capacity per unit time, the number of GPUs, and the GPU cache size. Optionally, the computing capacity can be divided into total computing capacity and AI computing capacity. Total computing capacity, that is, total computing power, refers to the overall computing capacity of the UE. AI computing capacity refers to the computing capacity used by the UE to run AI models, which can reflect the complexity of the AI ​​models supported by the UE. Optionally, the AI ​​computing capacity is the computing capacity that the UE can provide for the operation of AI models; or, the computing capacity that is maximally allocated or currently allowed to be allocated to the operation of AI models in the total computing capacity of the UE; or, the computing capacity remaining in the total computing capacity of the UE excluding the computing capacity used for the non-AI model calculations being run; or, the computing capacity remaining in the computing capacity that the UE can allocate to the operation of AI models, excluding the computing capacity currently used and / or reserved.

[0148] Storage capacity refers to the UE's ability to store data. Optionally, storage capacity is represented by at least one of available memory size, available cache size, and available storage size. Optionally, storage capacity can be divided into total storage capacity and AI storage capacity. Total storage capacity refers to the UE's storage capacity when storing all data. AI storage capacity refers to the UE's storage capacity for storing and / or running AI models. Optionally, AI storage capacity is the storage capacity that the UE can provide for AI model storage and / or running; or the maximum allocated or currently allowed storage capacity of the UE's total storage capacity for AI model storage and / or running; or the remaining storage capacity of the UE's total storage capacity excluding the storage capacity used for storage of non-AI models currently running; or the remaining storage capacity of the UE's maximum storage capacity that can be allocated for AI model storage, excluding the currently used and / or reserved storage capacity. Illustratively, AI storage capacity can also be divided into static storage capacity, such as flash memory capacity, for storing AI models and AI model-related data; and dynamic storage capacity, such as memory capacity, for storing AI model running data.

[0149] Communication capability, also known as transmission capability, refers to the ability of a UE to communicate or transmit data, including at least one of bandwidth, rate, and latency. Optionally, communication capability is represented by at least one of supported transmission rate, transmission latency, communication signal strength, channel quality status information, bit error rate, block error rate, and spectral efficiency. Communication capability can optionally be divided into total communication capability and AI communication capability. Total communication capability refers to the overall communication capability of the UE. AI communication capability refers to the ability of the UE to transmit AI models and / or AI model-related data, including training samples, model architecture, model parameters, and so on. Optionally, AI communication capability refers to the communication capability that the UE can provide for transmitting AI models; or, the maximum communication capability allocated or currently allowed to be allocated for transmitting AI models within the UE's total communication capability; or, the remaining communication capability within the UE's total communication capability, excluding ongoing communication capability for non-AI model transmissions; or, the remaining communication capability within the UE's maximum communication capability that can be allocated for transmitting AI models, excluding currently used and / or reserved communication capability.

[0150] Battery power refers to the battery power of the UE. It refers to the battery power available for the operation of the AI ​​model. Optionally, the battery power is represented by the remaining power. Optionally, the battery power can be divided into total battery power and AI battery power. The total battery power refers to the total battery power of the UE. The AI ​​battery power refers to the battery power used by the UE to run the AI ​​model. Optionally, the AI ​​battery power is the battery power that the UE can provide for the operation of the AI ​​model; or, the battery power that is maximally allocated or currently allowed to be allocated to the operation of the AI ​​model in the total battery power of the UE; or, the battery power remaining in the total battery power of the UE excluding the battery power already used or expected to be used by the running non-AI model applications; or, the battery power remaining in the maximum battery power that the UE can allocate to the operation of the AI ​​model, excluding the battery power currently used and / or reserved.

[0151] The AI ​​model index, also known as the AI ​​model identifier, is used to indicate the AI ​​model. Schematically, the AI ​​model index is used to indicate the AI ​​model selected by the UE based on the current UE capabilities or the AI ​​models supported by the UE.

[0152] In some embodiments, before the UE reports its selected AI model index to the network device, it needs to obtain information about at least one AI model, where the AI ​​model information includes at least one of the following: the AI ​​model index, the use case corresponding to the AI ​​model, the AI ​​model size, the AI ​​model accuracy, the AI ​​model complexity, and the generalization capability of the AI ​​model. Optionally, the information about the at least one AI model is predefined by a communication protocol, or is sent by the network device to the UE via an RRC message, or is sent by the network device to the UE via an NAS layer message, or is sent by the network device to the UE via system broadcast, or is sent by the NAS layer in the UE to the AS layer.

[0153] In some embodiments, the UE capability report may further include: the granularity supported by the UE capability, such as Per Band, Per UE, different situations of FDD / TDD, and different situations of FR1 / FR2. AI-related capability reporting can be bound to the associated use case. For example, the IE of the BFR capability report includes capability information for AI BFR, including at least one of the following information: a 1-bit indication of support or non-support of AI-enabled BFR, and / or at least one of the above functional capabilities, and / or at least one of the above hardware capabilities.

[0154] In some embodiments, the UE reports the index of the selected or supported AI model. Optionally, the AI ​​model index refers to the index of the AI ​​model supported by the current UE capabilities, or the index of the AI ​​model selected by the UE based on the current UE capabilities. After receiving the UE capabilities reported by the UE, the network device configures the first model set for the UE. UE capabilities include static capabilities and dynamic capabilities. Static capabilities refer to capabilities that do not dynamically change in the UE, such as battery capacity, storage specifications, CPU performance, etc. Dynamic capabilities refer to capabilities that dynamically change in the UE, including UE capabilities that dynamically change with at least one of the following factors: processor load, remaining memory capacity, communication bandwidth capability, and battery power. The first model set contains N AI models, all of which match the static capabilities of the UE. The network device determines the first model set that the UE can use based on the received static capabilities. Furthermore, the network device or UE determines the AI ​​model currently to be used or supported by the UE from the N AI models based on the dynamic capabilities of the UE. Furthermore, after the UE determines the currently supported AI model from the N AI models based on the dynamic capabilities, the UE also reports the AI ​​model index supported by the current UE capabilities to the network device, so that the network device also switches to the AI ​​model corresponding to the AI ​​model index. Alternatively, after the network device determines the currently supported AI model from the N AI models based on the dynamic capabilities, the network device configures the AI ​​model index supported by the current UE capabilities to the UE, so that the UE switches to the AI ​​model corresponding to the AI ​​model index.

[0155] Exemplarily, the network device associates N AI models in the first model set configured to the UE with different levels of UE capabilities, such as different levels of computing capabilities, different levels of storage capabilities, different levels of battery power, different levels of communication capabilities, etc. The UE uses the beam management (BM) function based on the AI ​​model. After the battery power is reduced, the UE autonomously switches to the AI ​​model that matches the current battery power level and reports the currently supported AI model index to the network device. Alternatively, the UE uses the BM function based on the AI ​​model. When the above-mentioned reporting conditions are met, the UE reports the UE capabilities to the network device. The network device determines the AI ​​model currently supported by the UE based on the current UE capabilities, and configures the model index of the AI ​​model to the UE. The UE switches to the corresponding AI model based on the AI ​​model index configured by the network device.

[0156] In some embodiments, the UE capability report includes a reporting time. Optionally, the reporting time includes the current time and / or the sequence number of the frame structure in which it is located. In other embodiments, the UE capability report also includes a time difference between the current time and the last reporting time.

[0157] In some embodiments, the UE capability report includes a reported position, and optionally, the reported position includes an absolute position and / or a relative position. The absolute position refers to the longitude and latitude position of the UE's current location. The relative position refers to the offset value of the UE's current position relative to the last reported position or a reference position. Optionally, the reference position is predefined by the communication protocol, or configured by the network device, or determined autonomously by the UE. Exemplarily, the reference position is the location of the base station. In other embodiments, the UE capability report also includes the distance between the current position and the last reported position.

[0158] In some embodiments, the UE capability report includes a cell identifier of a serving cell and / or a number of serving cell handovers, wherein the cell identifier of the serving cell is used to indicate to the network device the serving cell currently used by the UE, and the number of serving cell handovers is used to indicate to the network device the number of times the UE has switched serving cells between the current reporting environment and the last reporting environment. Exemplarily, the UE capability report includes information indicating that the UE's current serving cell is cell A. Exemplarily, the UE capability report includes information indicating that the UE has switched serving cells twice between the current moment and the last reporting moment.

[0159] In some embodiments, the UE capability report includes a change in the current UE capability relative to the UE capability at the last report. Exemplarily, the change in the UE capability includes at least one of the following:

[0160] The change in current AI computing power relative to the last reported AI computing power;

[0161] The change in the current AI storage capacity relative to the last reported AI storage capacity;

[0162] The change in the current AI communication capability relative to the last reported AI communication capability;

[0163] The change in the current AI battery level relative to the last reported AI battery level;

[0164] The time difference between the current time and the last reported time;

[0165] The distance between the current position and the last reported position;

[0166] The number of serving cell handovers between the current reporting environment and the last reporting environment.

[0167] In some embodiments, the above-mentioned change amount can be indicated by explicit indication, bitmap indication, or change amount level.

[0168] In some embodiments, the UE capability report may be reporting the capability of each supported AI function use case, or the capability of a single AI function use case, or the total capability of the supported AI function. The UE may determine the capability change as a change in the total capability of the AI ​​function, or the capability of a single AI function use case, or a change in the capability of each AI function use case. That is, the granularity of the UE capability report is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case. The granularity of the UE capability change determination is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case. In some embodiments, at least one capability in the reported content may be indicated explicitly, and / or at least one capability may be indicated separately using a capability level, and / or at least two capabilities may be indicated together using a capability level. Optionally, the capability level and / or the range corresponding to the capability level is predefined by the communication protocol or configured by the network device.

[0169] In some embodiments, the change in the current UE capability relative to the UE capability at the time of the last report in the reported content may be explicitly indicated, and / or the change in at least one capability may be separately indicated using a capability change level, and / or the change in at least two capabilities may be combined and indicated using a capability change level. Optionally, the capability change level and / or the range corresponding to the capability change level is predefined by the communication protocol or configured by the network device.

[0170] In some embodiments, when at least one of the UE capabilities satisfies at least one of the above-mentioned type one and / or type two, or when multiple capabilities simultaneously satisfy at least one of type one and / or type two, the UE reports the UE capabilities to the network device, so that the network device updates the corresponding AI model or configuration.

[0171] Type 3: Reporting based on network device configuration

[0172] FIG4 shows a flowchart of a UE capability reporting method provided by an exemplary embodiment of the present application. This embodiment is described as being executed by a UE, and includes at least some of the following steps:

[0173] Step 410: Receive a reporting method for network device configuration;

[0174] The reporting method includes a dynamically changed UE capability reporting period. The reporting method configured by the network device includes at least one of the following methods:

[0175] Periodic reporting;

[0176] Semi-continuous reporting;

[0177] Non-periodic reporting.

[0178] In some embodiments, before executing step 410, the UE sends capability update reporting indication information to the network device. The capability update reporting indication information is used to notify the network device that the UE wishes to update its own capability information.

[0179] In some embodiments, the reporting method is carried in an RRC message.

[0180] Step 430: Report the UE capability to the network device based on the reporting method configured by the network device.

[0181] Based on the reporting mode configured by the network device, the UE reports the UE capabilities to the network device. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message and reported to the network device.

[0182] In some embodiments, the UE capabilities reported by the UE to the network device include at least one of the following capabilities:

[0183] Overall capabilities, for example, whether the UE supports AI functions;

[0184] Supported use cases based on AI capabilities;

[0185] Supported AI category levels;

[0186] Computing power;

[0187] Storage capacity;

[0188] ·Communication capabilities;

[0189] Battery level;

[0190] AI model indexing.

[0191] Among the above-mentioned UE capabilities, total capabilities, use cases based on AI functions, supported AI category levels, etc. can be referred to as functional capabilities; computing capabilities, storage capabilities, communication capabilities, battery power, etc. can be referred to as terminal hardware capabilities.

[0192] Among them, the use case based on AI function refers to a communication use case optimized based on the AI ​​model. Optionally, the use case based on AI function includes at least one of AI-based positioning, AI-based beam management, AI-based channel status, user plane function information reporting in air interface resources, and control plane function information reporting in air interface resources. For example, the supported use case based on AI function refers to supporting at least one of AI-based positioning, AI-based beam management, and AI-based channel state information reporting; or, the supported use case based on AI function is at least one of all functions included in the user plane and control plane in the air interface resources, such as: at least one of switching, cell selection / reselection, measurement, random access process, and resource allocation.

[0193] The supported AI category level refers to the AI ​​function category supported by the AI ​​model. Optionally, the AI ​​category level includes whether at least one of training, reasoning, and data collection on the terminal side is supported. For example, the supported AI category level includes whether the UE supports at least one of AI model training on the terminal side, whether it supports AI model reasoning on the terminal side, and whether it supports AI model data collection on the terminal side.

[0194] Computing capacity, also known as computing power, refers to the computing power of the UE when running program tasks. Optionally, the computing capacity is represented by at least one of the floating-point computing capacity per unit time, the number of GPUs, and the GPU cache size. Optionally, the computing capacity can be divided into total computing capacity and AI computing capacity. Total computing capacity, that is, total computing power, refers to the overall computing capacity of the UE. AI computing capacity refers to the computing capacity used by the UE to run AI models, which can reflect the complexity of the AI ​​models supported by the UE. Optionally, the AI ​​computing capacity is the computing capacity that the UE can provide for the operation of AI models; or, the computing capacity that is maximally allocated or currently allowed to be allocated to the operation of AI models in the total computing capacity of the UE; or, the computing capacity remaining in the total computing capacity of the UE excluding the computing capacity used for the non-AI model calculations being run; or, the computing capacity remaining in the computing capacity that the UE can allocate to the operation of AI models, excluding the computing capacity currently used and / or reserved.

[0195] Storage capacity refers to the UE's ability to store data. Optionally, storage capacity is represented by at least one of available memory size, available cache size, and available storage size. Optionally, storage capacity can be divided into total storage capacity and AI storage capacity. Total storage capacity refers to the UE's storage capacity when storing all data. AI storage capacity refers to the UE's storage capacity for storing and / or running AI models. Optionally, AI storage capacity is the storage capacity that the UE can provide for AI model storage and / or running; or the maximum allocated or currently allowed storage capacity of the UE's total storage capacity for AI model storage and / or running; or the remaining storage capacity of the UE's total storage capacity excluding the storage capacity used for storage of non-AI models currently running; or the remaining storage capacity of the UE's maximum storage capacity that can be allocated for AI model storage, excluding the currently used and / or reserved storage capacity. Illustratively, AI storage capacity can also be divided into static storage capacity, such as flash memory capacity, for storing AI models and AI model-related data; and dynamic storage capacity, such as memory capacity, for storing AI model running data.

[0196] Communication capability, also known as transmission capability, refers to the ability of a UE to communicate or transmit data, including at least one of bandwidth, rate, and latency. Optionally, communication capability is represented by at least one of supported transmission rate, transmission latency, communication signal strength, channel quality status information, bit error rate, block error rate, and spectral efficiency. Communication capability can optionally be divided into total communication capability and AI communication capability. Total communication capability refers to the overall communication capability of the UE. AI communication capability refers to the ability of the UE to transmit AI models and / or AI model-related data, including training samples, model architecture, model parameters, and so on. Optionally, AI communication capability refers to the communication capability that the UE can provide for transmitting AI models; or, the maximum communication capability allocated or currently allowed to be allocated for transmitting AI models within the UE's total communication capability; or, the remaining communication capability within the UE's total communication capability, excluding ongoing communication capability for non-AI model transmissions; or, the remaining communication capability within the UE's maximum communication capability that can be allocated for transmitting AI models, excluding currently used and / or reserved communication capability.

[0197] Battery power refers to the battery power of the UE. It refers to the battery power available for the operation of the AI ​​model. Optionally, the battery power is represented by the remaining power. Optionally, the battery power can be divided into total battery power and AI battery power. The total battery power refers to the total battery power of the UE. The AI ​​battery power refers to the battery power used by the UE to run the AI ​​model. Optionally, the AI ​​battery power is the battery power that the UE can provide for the operation of the AI ​​model; or, the battery power that is maximally allocated or currently allowed to be allocated to the operation of the AI ​​model in the total battery power of the UE; or, the battery power remaining in the total battery power of the UE excluding the battery power already used or expected to be used by the running non-AI model applications; or, the battery power remaining in the maximum battery power that the UE can allocate to the operation of the AI ​​model, excluding the battery power currently used and / or reserved.

[0198] The AI ​​model index, also known as the AI ​​model identifier, is used to indicate the AI ​​model. Schematically, the AI ​​model index is used to indicate the AI ​​model selected by the UE based on the current UE capabilities or the AI ​​models supported by the UE.

[0199] In some embodiments, before the UE reports its selected AI model index to the network device, it needs to obtain information about at least one AI model, where the AI ​​model information includes at least one of the following: the AI ​​model index, the use case corresponding to the AI ​​model, the AI ​​model size, the AI ​​model accuracy, the AI ​​model complexity, and the generalization capability of the AI ​​model. Optionally, the information about the at least one AI model is predefined by a communication protocol, or is sent by the network device to the UE via an RRC message, or is sent by the network device to the UE via an NAS layer message, or is sent by the network device to the UE via system broadcast, or is sent by the NAS layer in the UE to the AS layer.

[0200] In some embodiments, the UE capability report may further include: the granularity supported by the UE capability, such as Per Band, Per UE, different situations of FDD / TDD, and different situations of FR1 / FR2. AI-related capability reporting can be bound to the associated use case. For example, the IE of the BFR capability report includes capability information for AI BFR, including at least one of the following information: a 1-bit indication of support or non-support of AI-enabled BFR, and / or at least one of the above functional capabilities, and / or at least one of the above hardware capabilities.

[0201] In some embodiments, the UE reports the index of the selected or supported AI model. Optionally, the AI ​​model index refers to the index of the AI ​​model supported by the current UE capabilities, or the index of the AI ​​model selected by the UE based on the current UE capabilities. After receiving the UE capabilities reported by the UE, the network device configures the first model set for the UE. UE capabilities include static capabilities and dynamic capabilities. Static capabilities refer to capabilities that do not dynamically change in the UE, such as battery capacity, storage specifications, CPU performance, etc. Dynamic capabilities refer to capabilities that dynamically change in the UE, including UE capabilities that dynamically change with at least one of the following factors: processor load, remaining memory capacity, communication bandwidth capability, and battery power. The first model set contains N AI models, all of which match the static capabilities of the UE. The network device determines the first model set that the UE can use based on the received static capabilities. Furthermore, the network device or UE determines the AI ​​model currently to be used or supported by the UE from the N AI models based on the dynamic capabilities of the UE. Furthermore, after the UE determines the currently supported AI model from the N AI models based on the dynamic capabilities, the UE also reports the AI ​​model index supported by the current UE capabilities to the network device, so that the network device also switches to the AI ​​model corresponding to the AI ​​model index. Alternatively, after the network device determines the currently supported AI model from the N AI models based on the dynamic capabilities, the network device configures the AI ​​model index supported by the current UE capabilities to the UE, so that the UE switches to the AI ​​model corresponding to the AI ​​model index.

[0202] Exemplarily, the network device associates N AI models in the first model set configured for the UE with different levels of UE capabilities, such as different levels of computing capabilities, different levels of storage capabilities, different levels of battery power, different levels of communication capabilities, etc. The UE uses the BM function based on the AI ​​model. After the battery power is reduced, the UE autonomously switches to the AI ​​model that matches the current battery power level and reports the currently supported AI model index to the network device. Alternatively, the UE uses the BM function based on the AI ​​model. When the above-mentioned reporting conditions are met, the UE reports the UE capabilities to the network device. The network device determines the AI ​​model currently supported by the UE based on the current UE capabilities and configures the model index of the AI ​​model to the UE. The UE switches to the corresponding AI model based on the AI ​​model index configured by the network device.

[0203] In some embodiments, the UE capability report includes a reporting time. Optionally, the reporting time includes the current time and / or the sequence number of the frame structure in which it is located. In other embodiments, the UE capability report also includes a time difference between the current time and the last reporting time.

[0204] In some embodiments, the UE capability report includes a reported position, and optionally, the reported position includes an absolute position and / or a relative position. The absolute position refers to the longitude and latitude position of the UE's current location. The relative position refers to the offset value of the UE's current position relative to the last reported position or a reference position. Optionally, the reference position is predefined by the communication protocol, or configured by the network device, or determined autonomously by the UE. Exemplarily, the reference position is the location of the base station. In other embodiments, the UE capability report also includes the distance between the current position and the last reported position.

[0205] In some embodiments, the UE capability report includes a cell identifier of a serving cell and / or a number of serving cell handovers, wherein the cell identifier of the serving cell is used to indicate to the network device the serving cell currently used by the UE, and the number of serving cell handovers is used to indicate to the network device the number of times the UE has switched serving cells between the current reporting environment and the last reporting environment. Exemplarily, the UE capability report includes information indicating that the UE's current serving cell is cell A. Exemplarily, the UE capability report includes information indicating that the UE has switched serving cells twice between the current moment and the last reporting moment.

[0206] In some embodiments, the UE capability report includes a change in the current UE capability relative to the UE capability at the last report. Exemplarily, the change in the UE capability includes at least one of the following:

[0207] The change in current AI computing power relative to the last reported AI computing power;

[0208] The change in the current AI storage capacity relative to the last reported AI storage capacity;

[0209] The change in the current AI communication capability relative to the last reported AI communication capability;

[0210] The change in the current AI battery level relative to the last reported AI battery level;

[0211] The time difference between the current time and the last reported time;

[0212] The distance between the current position and the last reported position;

[0213] The number of serving cell handovers between the current reporting environment and the last reporting environment.

[0214] In some embodiments, the above-mentioned change amount can be indicated by explicit indication, bitmap indication, or change amount level.

[0215] In some embodiments, the UE capability report may be reporting the capability of each supported AI function use case, or the capability of a single AI function use case, or the total capability of the supported AI function. The UE may determine the capability change as a change in the total capability of the AI ​​function, or the capability of a single AI function use case, or a change in the capability of each AI function use case. That is, the granularity of the UE capability report is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case. The granularity of the UE capability change determination is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case.

[0216] In some embodiments, at least one capability in the reported content may be explicitly indicated, and / or at least one capability may be indicated separately using a capability level, and / or at least two capabilities may be indicated together using a capability level. Optionally, the capability level and / or the range corresponding to the capability level may be predefined by the communication protocol or configured by the network device.

[0217] In some embodiments, the amount of change in the current UE capability in the reported content relative to the UE capability at the time of the last report can be indicated explicitly, and / or the amount of change in at least one capability can be indicated separately using a capability change level, and / or the amount of change in at least two capabilities can be indicated together using a capability change level. Optionally, the capability change level and / or the range corresponding to the capability change level is predefined by the communication protocol or configured by the network device. In some embodiments, the UE receives configuration information sent by the network device, and the configuration information is used to configure the reporting resources of the UE capability. Optionally, when the reporting method configured by the network device is satisfied, the UE reports the UE capability based on the reporting resources configured by the network device.

[0218] In some embodiments, the UE reports the supported AI model index to the network device.

[0219] In some embodiments, the UE autonomously switches to an AI model corresponding to the UE capabilities based on the current UE capabilities, or the UE switches to an AI model corresponding to the UE capabilities based on the configuration of the network device.

[0220] In some embodiments, the UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a switching rule, the UE autonomously switches to an AI model corresponding to the UE's capabilities. Optionally, the switching rule is predefined by a communication protocol, configured by a network device, or determined autonomously by the UE. Optionally, the at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models are locally stored in the UE, or configured by a network device.

[0221] In some embodiments, a UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a configuration of a network device, the UE switches to an AI model corresponding to the UE's capabilities. Optionally, the at least two AI models, or the model indexes of at least two AI models, or the model parameters of at least two AI models are locally stored on the UE or configured by the network device.

[0222] In summary, the method provided in this embodiment reports UE capabilities to a network device based on received configuration information of the network device, thereby improving the flexibility and pertinence of UE capability reporting.

[0223] This application provides an exemplary embodiment of UE capability reporting, which is described by taking the embodiment executed by the UE as an example.

[0224] The UE receives the periodic reporting mode sent by the network device and reports the UE capabilities to the network device, wherein the periodic value is a fixed value, a default value, a network device configuration, a UE autonomous determination, or a communication protocol predefined value.

[0225] In some embodiments, the reporting method sent by the network device indicates periodic reporting. Optionally, the reporting method sent by the network device is configured or indicated to include a reporting period.

[0226] In some embodiments, the UE reports the supported AI model index to the network device.

[0227] In some embodiments, the UE autonomously switches to an AI model corresponding to the UE capabilities based on the current UE capabilities, or the UE switches to an AI model corresponding to the UE capabilities based on the configuration of the network device.

[0228] In some embodiments, the UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a switching rule, the UE autonomously switches to an AI model corresponding to the UE's capabilities. Optionally, the switching rule is predefined by a communication protocol, configured by a network device, or determined autonomously by the UE. Optionally, the at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models are locally stored in the UE, or configured by a network device.

[0229] In some embodiments, a UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a configuration of a network device, the UE switches to an AI model corresponding to the UE's capabilities. Optionally, the at least two AI models, or the model indexes of at least two AI models, or the model parameters of at least two AI models are locally stored on the UE or configured by the network device.

[0230] To sum up, the method provided in this embodiment is based on the periodic reporting method sent by the received network device, and the UE reports the UE capabilities to the network device, which improves the simplicity of UE capability reporting and reduces the signaling resource loss during the UE capability reporting process in scenarios where the UE capabilities change frequently or quickly.

[0231] FIG5 shows a flowchart of a UE capability reporting method provided by an exemplary embodiment of the present application. Taking this embodiment as an example, the method is described as being executed by a UE and includes at least some of the following steps:

[0232] Step 510: receiving a reporting method of a network device configuration;

[0233] The UE receives a semi-persistent reporting mode configured by the network device, optionally including the reporting mode in an RRC message. Optionally, the reporting mode from the network device indicates semi-persistent periodic reporting. Optionally, the reporting mode from the network device indicates semi-persistent periodicity.

[0234] In some embodiments, before executing step 510, the UE sends capability update reporting indication information to the network device. The capability update reporting indication information is used to notify the network device that the UE wishes to update its own capability information.

[0235] Step 530: Receive activation signaling sent by the network device;

[0236] The UE receives activation signaling sent by the network device, which is used to activate the UE's ability to report UE using a semi-persistent period, wherein the period value is a fixed value, a default value, a network device configuration, a UE autonomous determination, or a communication protocol predefined value.

[0237] In some embodiments, step 510 and step 530 may be combined, or the activation signaling from the network device may explicitly or implicitly indicate the semi-persistent reporting mode. Optionally, the activation signaling may be configured or indicated with a semi-persistent period.

[0238] Step 550: Start / activate a semi-persistent period to report UE capabilities to the network device;

[0239] Based on the semi-persistent reporting mode configured by the network device, upon receiving activation signaling sent by the network device, the UE starts / activates a semi-persistent period to report UE capabilities to the network device. Optionally, the UE capabilities are reported to the network device in an RRC message, a MAC CE message, or a UCI message.

[0240] In some embodiments, the UE receives configuration information sent by the network device, the configuration information being used to configure reporting resources for UE capabilities. Optionally, if the semi-persistent reporting mode configured by the network device is met, the UE performs semi-persistent reporting of UE capabilities based on the semi-persistent reporting resources configured by the network device.

[0241] Step 570: Receive the deactivation signaling sent by the network device.

[0242] In some embodiments, when the UE reports UE capabilities to the network device, the UE receives deactivation signaling sent by the network device, which is used to deactivate the UE's use of a semi-persistent period to report UE capabilities, that is, the UE stops using a semi-persistent period to report UE capabilities.

[0243] In some embodiments, step 570 is an optional step.

[0244] In some embodiments, the UE reports the supported AI model index to the network device.

[0245] In some embodiments, the UE autonomously switches to an AI model corresponding to the UE capabilities based on the current UE capabilities, or the UE switches to an AI model corresponding to the UE capabilities based on the configuration of the network device.

[0246] In some embodiments, the UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a switching rule, the UE autonomously switches to an AI model corresponding to the UE's capabilities. Optionally, the switching rule is predefined by a communication protocol, configured by a network device, or determined autonomously by the UE. Optionally, the at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models are locally stored in the UE, or configured by a network device.

[0247] In some embodiments, a UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a configuration of a network device, the UE switches to an AI model corresponding to the UE's capabilities. Optionally, the at least two AI models, or the model indexes of at least two AI models, or the model parameters of at least two AI models are locally stored on the UE or configured by the network device.

[0248] In summary, the method provided in this embodiment is based on the semi-continuous reporting mode and activation signaling and / or deactivation signaling sent by the received network device, and the UE reports or stops reporting UE capabilities to the network device, thereby improving the flexibility and pertinence of UE capability reporting.

[0249] FIG6 shows a flowchart of a UE capability reporting method provided by an exemplary embodiment of the present application. This embodiment is described as being executed by a UE, and includes at least some of the following steps:

[0250] Step 610: Receive a reporting method for network device configuration;

[0251] The UE receives the reporting mode of the aperiodic reporting configured by the network device. Optionally, the reporting mode is carried in an RRC message and sent.

[0252] In some embodiments, before executing step 610, the UE sends capability update reporting indication information to the network device. The capability update reporting indication information is used to notify the network device that the UE wishes to update its own capability information.

[0253] Step 630: Receive a trigger signaling sent by a network device;

[0254] The UE receives a trigger instruction sent by the network device, where the trigger instruction is used to trigger the UE to report UE capabilities.

[0255] In some embodiments, step 610 and step 630 may be combined, or the trigger signaling from the network device may explicitly or implicitly indicate the aperiodic reporting mode.

[0256] Step 650: Report UE capabilities to the network device.

[0257] Based on the aperiodic reporting mode configured by the network device, upon receiving the trigger signaling sent by the network device, the UE reports the UE capabilities to the network device. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message and reported to the network device.

[0258] In some embodiments, the UE receives configuration information sent by the network device, the configuration information being used to configure reporting resources for UE capabilities. Optionally, if the aperiodic reporting mode configured by the network device is satisfied, the UE performs aperiodic reporting of UE capabilities based on the aperiodic reporting resources configured by the network device.

[0259] In some embodiments, the UE reports the supported AI model index to the network device.

[0260] In some embodiments, the UE autonomously switches to an AI model corresponding to the UE capabilities based on the current UE capabilities, or the UE switches to an AI model corresponding to the UE capabilities based on the configuration of the network device.

[0261] In some embodiments, the UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a switching rule, the UE autonomously switches to an AI model corresponding to the UE's capabilities. Optionally, the switching rule is predefined by a communication protocol, configured by a network device, or determined autonomously by the UE. Optionally, the at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models are locally stored in the UE, or configured by a network device.

[0262] In some embodiments, a UE has at least two AI models, or model indexes of at least two AI models, or model parameters of at least two AI models. Based on a configuration of a network device, the UE switches to an AI model corresponding to the UE's capabilities. Optionally, the at least two AI models, or the model indexes of at least two AI models, or the model parameters of at least two AI models are locally stored on the UE or configured by the network device.

[0263] In summary, the method provided in this embodiment is based on the non-periodic reporting mode and trigger signaling sent by the received network device, and the UE reports the UE capabilities to the network device, which reduces the resource loss of UE capability reporting and improves the flexibility of UE capability reporting.

[0264] This application provides an exemplary embodiment of UE capability reporting, which is described by taking the embodiment executed by a network device as an example.

[0265] The network device sends configuration information to the UE, where the configuration information is configuration information related to UE capability reporting. Optionally, the configuration information includes at least one of a reporting condition, a reporting method, and a reporting resource.

[0266] Exemplarily, the network device configures reporting conditions, and / or reporting methods, and / or reporting resources for the UE.

[0267] In some embodiments, the network device configures a reporting condition for the UE, where the reporting condition includes at least one of the reporting conditions described above.

[0268] In some embodiments, the network device receives UE capabilities reported by the UE, where the UE capabilities are reported by the UE when a reporting condition is met. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message.

[0269] In some embodiments, the network device configures a reporting method for the UE, including at least one of the following methods:

[0270] Periodic reporting;

[0271] Semi-continuous reporting;

[0272] Non-periodic reporting.

[0273] In some embodiments, the reporting method sent by the network device to the UE indicates periodic reporting. Optionally, the reporting method is carried in an RRC message. Optionally, the reporting method sent by the network device is configured or indicated with a reporting period.

[0274] In some embodiments, the network device receives UE capabilities reported by the UE, where the UE capabilities are reported by the UE based on a reporting method configured by the network device. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message.

[0275] In some embodiments, the reporting method sent by the network device to the UE indicates that there is semi-persistent periodic reporting. Optionally, the reporting method is carried in an RRC message. Optionally, the reporting method sent by the network device is configured or indicated to have a semi-persistent period.

[0276] In some embodiments, the network device sends activation signaling to the UE, where the activation signaling is used to activate the UE to report the UE capability using a semi-persistent period.

[0277] In some embodiments, the network device combines the reporting mode and the activation signaling, or the activation signaling explicitly or implicitly indicates the semi-persistent reporting mode. Optionally, the activation signaling is configured or indicated with a semi-persistent period.

[0278] In some embodiments, the network device receives UE capabilities reported by the UE, where the UE capabilities are reported by the UE starting / activating a semi-persistent period upon receiving activation signaling based on a reporting method configured by the network device. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message.

[0279] In some embodiments, the network device sends a deactivation signaling to the UE, where the deactivation signaling is used to deactivate the UE's capability of reporting the UE using a semi-persistent period, that is, the UE stops reporting the UE's capability using a semi-persistent period.

[0280] In some embodiments, the reporting mode sent by the network device to the UE indicates that aperiodic reporting is included. Optionally, the reporting mode is carried in an RRC message and sent.

[0281] In some embodiments, the network device sends a trigger signaling to the UE, where the trigger signaling is used to trigger the UE to report UE capabilities.

[0282] In some embodiments, the network device sends the reporting mode and the trigger signaling in combination, or the trigger signaling explicitly or implicitly indicates the aperiodic reporting mode.

[0283] In some embodiments, the network device receives UE capabilities reported by the UE, where the UE capabilities are reported to the network device by the UE based on a reporting method configured by the network device upon receipt of trigger signaling. Optionally, the UE capabilities are carried in an RRC message, a MAC CE message, or a UCI message.

[0284] In some embodiments, the UE capabilities reported by the UE and received by the network device include at least one of the following capabilities:

[0285] Overall capabilities, for example, whether the UE supports AI functions;

[0286] Supported use cases based on AI capabilities;

[0287] Supported AI category levels;

[0288] Computing power;

[0289] Storage capacity;

[0290] ·Communication capabilities;

[0291] Battery level;

[0292] AI model indexing.

[0293] Among the above-mentioned UE capabilities, total capabilities, use cases based on AI functions, supported AI category levels, etc. can be referred to as functional capabilities; computing capabilities, storage capabilities, communication capabilities, battery power, etc. can be referred to as terminal hardware capabilities.

[0294] Among them, the use case based on AI function refers to a communication use case optimized based on the AI ​​model. Optionally, the use case based on AI function includes at least one of AI-based positioning, AI-based beam management, AI-based channel status, user plane function information reporting in air interface resources, and control plane function information reporting in air interface resources. For example, the supported use case based on AI function refers to supporting at least one of AI-based positioning, AI-based beam management, and AI-based channel state information reporting; or, the supported use case based on AI function is at least one of all functions included in the user plane and control plane in the air interface resources, such as: at least one of switching, cell selection / reselection, measurement, random access process, and resource allocation.

[0295] The supported AI category level refers to the AI ​​function category supported by the AI ​​model. Optionally, the AI ​​category level includes whether at least one of training, reasoning, and data collection on the terminal side is supported. For example, the supported AI category level includes whether the UE supports at least one of AI model training on the terminal side, whether it supports AI model reasoning on the terminal side, and whether it supports AI model data collection on the terminal side.

[0296] Computing capacity, also known as computing power, refers to the computing power of the UE when running program tasks. Optionally, the computing capacity is represented by at least one of the floating-point computing capacity per unit time, the number of GPUs, and the GPU cache size. Optionally, the computing capacity can be divided into total computing capacity and AI computing capacity. Total computing capacity, that is, total computing power, refers to the overall computing capacity of the UE. AI computing capacity refers to the computing capacity used by the UE to run AI models, which can reflect the complexity of the AI ​​models supported by the UE. Optionally, the AI ​​computing capacity is the computing capacity that the UE can provide for the operation of AI models; or, the computing capacity that is maximally allocated or currently allowed to be allocated to the operation of AI models in the total computing capacity of the UE; or, the computing capacity remaining in the total computing capacity of the UE excluding the computing capacity used for the non-AI model calculations being run; or, the computing capacity remaining in the computing capacity that the UE can allocate to the operation of AI models, excluding the computing capacity currently used and / or reserved.

[0297] Storage capacity refers to the UE's ability to store data. Optionally, storage capacity is represented by at least one of available memory size, available cache size, and available storage size. Optionally, storage capacity can be divided into total storage capacity and AI storage capacity. Total storage capacity refers to the UE's storage capacity when storing all data. AI storage capacity refers to the UE's storage capacity used to store / run AI models. Optionally, AI storage capacity is the storage capacity that the UE can provide for AI model storage and / or execution; or the maximum allocated or currently permitted storage capacity of the UE's total storage capacity for AI model storage and / or execution; or the remaining storage capacity of the UE's total storage capacity excluding storage capacity used for storage of non-AI models currently running; or the remaining storage capacity of the UE's maximum storage capacity that can be allocated for AI model storage, excluding currently used and / or reserved storage capacity. Illustratively, AI storage capacity can also be divided into static storage capacity, such as flash memory capacity, used to store AI models and their related data; and dynamic storage capacity, such as memory capacity, used to store AI model execution data.

[0298] Communication capability, also known as transmission capability, refers to the ability of a UE to communicate or transmit data, including at least one of bandwidth, rate, and latency. Optionally, communication capability is represented by at least one of supported transmission rate, transmission latency, communication signal strength, channel quality status information, bit error rate, block error rate, and spectral efficiency. Communication capability can optionally be divided into total communication capability and AI communication capability. Total communication capability refers to the overall communication capability of the UE. AI communication capability refers to the ability of the UE to transmit AI models and / or AI model-related data, including training samples, model architecture, model parameters, and so on. Optionally, AI communication capability refers to the communication capability that the UE can provide for transmitting AI models; or, the maximum communication capability allocated or currently allowed to be allocated for transmitting AI models within the UE's total communication capability; or, the remaining communication capability within the UE's total communication capability, excluding ongoing communication capability for non-AI model transmissions; or, the remaining communication capability within the UE's maximum communication capability that can be allocated for transmitting AI models, excluding currently used and / or reserved communication capability.

[0299] Battery power refers to the battery power of the UE. It refers to the battery power available for the operation of the AI ​​model. Optionally, the battery power is represented by the remaining power. Optionally, the battery power can be divided into total battery power and AI battery power. The total battery power refers to the total battery power of the UE. The AI ​​battery power refers to the battery power used by the UE to run the AI ​​model. Optionally, the AI ​​battery power is the battery power that the UE can provide for the operation of the AI ​​model; or, the battery power that is maximally allocated or currently allowed to be allocated to the operation of the AI ​​model in the total battery power of the UE; or, the battery power remaining in the total battery power of the UE excluding the battery power already used or expected to be used by the running non-AI model applications; or, the battery power remaining in the maximum battery power that the UE can allocate to the operation of the AI ​​model, excluding the battery power currently used and / or reserved.

[0300] The AI ​​model index, also known as the AI ​​model identifier, is used to indicate the AI ​​model. Schematically, the AI ​​model index is used to indicate the AI ​​model selected by the UE based on the current UE capabilities or the AI ​​models supported by the UE.

[0301] In some embodiments, before the UE reports its selected AI model index to the network device, it needs to obtain information about at least one AI model, where the AI ​​model information includes at least one of the following: the AI ​​model index, the use case corresponding to the AI ​​model, the AI ​​model size, the AI ​​model accuracy, the AI ​​model complexity, and the generalization capability of the AI ​​model. Optionally, the information about the at least one AI model is predefined by a communication protocol, or is sent by the network device to the UE via an RRC message, or is sent by the network device to the UE via an NAS layer message, or is sent by the network device to the UE via system broadcast, or is sent by the NAS layer in the UE to the AS layer.

[0302] In some embodiments, the UE capability report may further include: the granularity supported by the UE capability, such as Per Band, Per UE, different situations of FDD / TDD, and different situations of FR1 / FR2. AI-related capability reporting can be bound to the associated use case. For example, the IE of the BFR capability report includes capability information for AI BFR, including at least one of the following information: a 1-bit indication of support or non-support of AI-enabled BFR, and / or at least one of the above functional capabilities, and / or at least one of the above hardware capabilities.

[0303] In some embodiments, the UE reports the index of the selected or supported AI model. Optionally, the AI ​​model index refers to the index of the AI ​​model supported by the current UE capabilities, or the index of the AI ​​model selected by the UE based on the current UE capabilities. After receiving the UE capabilities reported by the UE, the network device configures the first model set for the UE. UE capabilities include static capabilities and dynamic capabilities. Static capabilities refer to capabilities that do not dynamically change in the UE, such as battery capacity, storage specifications, CPU performance, etc. Dynamic capabilities refer to capabilities that dynamically change in the UE, including UE capabilities that dynamically change with at least one of the following factors: processor load, remaining memory capacity, communication bandwidth capability, and battery power. The first model set contains N AI models, all of which match the static capabilities of the UE. The network device determines the first model set that the UE can use based on the received static capabilities. Furthermore, the network device or UE determines the AI ​​model currently to be used or supported by the UE from the N AI models based on the dynamic capabilities of the UE. Furthermore, after the UE determines the currently supported AI model from the N AI models based on the dynamic capabilities, the UE also reports the AI ​​model index supported by the current UE capabilities to the network device, so that the network device also switches to the AI ​​model corresponding to the AI ​​model index. Alternatively, after the network device determines the currently supported AI model from the N AI models based on the dynamic capabilities, the network device configures the AI ​​model index supported by the current UE capabilities to the UE, so that the UE switches to the AI ​​model corresponding to the AI ​​model index.

[0304] Exemplarily, the network device associates N AI models in the first model set configured for the UE with different levels of UE capabilities, such as different levels of computing capabilities, different levels of storage capabilities, different levels of battery power, different levels of communication capabilities, etc. The UE uses the BM function based on the AI ​​model. After the battery power is reduced, the UE autonomously switches to the AI ​​model that matches the current battery power level and reports the currently supported AI model index to the network device. Alternatively, the UE uses the BM function based on the AI ​​model. When the above-mentioned reporting conditions are met, the UE reports the UE capabilities to the network device. The network device determines the AI ​​model currently supported by the UE based on the current UE capabilities and configures the model index of the AI ​​model to the UE. The UE switches to the corresponding AI model based on the AI ​​model index configured by the network device.

[0305] In some embodiments, the UE capability report includes a reporting time. Optionally, the reporting time includes the current time and / or the sequence number of the frame structure in which it is located. In other embodiments, the UE capability report also includes a time difference between the current time and the last reporting time.

[0306] In some embodiments, the UE capability report includes a reported position, and optionally, the reported position includes an absolute position and / or a relative position. The absolute position refers to the longitude and latitude position of the UE's current location. The relative position refers to the offset value of the UE's current position relative to the last reported position or a reference position. Optionally, the reference position is predefined by the communication protocol, or configured by the network device, or determined autonomously by the UE. Exemplarily, the reference position is the location of the base station. In other embodiments, the UE capability report also includes the distance between the current position and the last reported position.

[0307] In some embodiments, the UE capability report includes a cell identifier of a serving cell and / or a number of serving cell handovers, wherein the cell identifier of the serving cell is used to indicate to the network device the serving cell currently used by the UE, and the number of serving cell handovers is used to indicate to the network device the number of times the UE has switched serving cells between the current reporting environment and the last reporting environment. Exemplarily, the UE capability report includes information indicating that the UE's current serving cell is cell A. Exemplarily, the UE capability report includes information indicating that the UE has switched serving cells twice between the current moment and the last reporting moment.

[0308] In some embodiments, the UE capability report includes a change in the current UE capability relative to the UE capability at the last report. Exemplarily, the change in the UE capability includes at least one of the following:

[0309] The change in current AI computing power relative to the last reported AI computing power;

[0310] The change in the current AI storage capacity relative to the last reported AI storage capacity;

[0311] The change in the current AI communication capability relative to the last reported AI communication capability;

[0312] The change in the current AI battery level relative to the last reported AI battery level;

[0313] The time difference between the current time and the last reported time;

[0314] The distance between the current position and the last reported position;

[0315] The number of serving cell handovers between the current reporting environment and the last reporting environment.

[0316] In some embodiments, the above-mentioned change amount can be indicated by explicit indication, bitmap indication, or change amount level.

[0317] In some embodiments, the UE capability report may be reporting the capability of each supported AI function use case, or the capability of a single AI function use case, or the total capability of the supported AI function. The UE may determine the capability change as a change in the total capability of the AI ​​function, or the capability of a single AI function use case, or a change in the capability of each AI function use case. That is, the granularity of the UE capability report is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case. The granularity of the UE capability change determination is at least one of the total capability granularity, the total AI capability granularity, and the AI ​​capability granularity of a single AI function use case.

[0318] In some embodiments, at least one capability in the reported content may be explicitly indicated, and / or at least one capability may be indicated separately using a capability level, and / or at least two capabilities may be indicated together using a capability level. Optionally, the capability level and / or the range corresponding to the capability level may be predefined by the communication protocol or configured by the network device.

[0319] In some embodiments, the change in the current UE capability relative to the UE capability at the time of the last report in the reported content may be explicitly indicated, and / or the change in at least one capability may be separately indicated using a capability change level, and / or the change in at least two capabilities may be combined and indicated using a capability change level. Optionally, the capability change level and / or the range corresponding to the capability change level is predefined by the communication protocol or configured by the network device.

[0320] In some embodiments, before configuring a reporting method or reporting condition or activating signaling or triggering signaling to the UE, the network device receives capability update reporting indication information sent by the UE, and the capability update reporting indication information is used to notify the network device that the UE wishes to update its own capability information.

[0321] In some embodiments, the network device sends configuration information to the UE, where the configuration information is used to configure reporting resources for UE capabilities.

[0322] In some embodiments, the network device stores at least two AI models or model indexes of at least two AI models or model parameters of at least two AI models.

[0323] In some embodiments, the network device switches to an AI model corresponding to the UE capabilities based on the received UE capabilities.

[0324] In summary, the method provided in this embodiment enables the UE to report UE capabilities based on the configuration of the network device, thereby improving the pertinence of UE capability reporting, reducing the requirements for the UE's autonomous reporting capabilities, and improving the stability of UE capability reporting in the communication system.

[0325] FIG7 shows an exemplary embodiment of UE capability reporting provided by the present application. This embodiment is described by taking the network device as an example. This embodiment includes at least some of the following steps:

[0326] Step 710: Configure reporting conditions for the UE;

[0327] The network device configures a reporting condition for the UE, the reporting condition including at least one of the reporting conditions described above, and / or enabling / disabling an application, and / or the UE being in / out of a charging state. Optionally, the application is predefined or configured by the network device.

[0328] Step 720: receiving the UE capability reported by the UE for the i-th time;

[0329] When the reporting conditions are met, the UE reports the UE capabilities to the network device. For example, the UE capabilities are reported to the UE when the UE capabilities meet the first condition, or when the change in the current reporting environment compared to the reporting environment at the time of the last report meets the second condition, or when the UE closes the game application, or when the UE enters the charging state.

[0330] Step 730: Switch to a first AI model corresponding to the UE capability;

[0331] The network device switches to a first AI model corresponding to the UE capabilities based on the received UE capabilities.

[0332] In some implementations, the network device stores at least two AI models or at least two AI model parameters or at least two AI model indexes. Based on the received UE capabilities, the network device switches to a first AI model corresponding to the UE capabilities among the at least two AI models or at least two AI model parameters or at least two AI model indexes.

[0333] Step 740: Use the first AI model to perform a communication process;

[0334] The network device uses the first AI model to communicate with the UE. For example, the UE uses the first AI model to report CSI to the network device.

[0335] Step 750: Configure the reporting method to the UE;

[0336] The network device configures a reporting mode for the UE. Exemplarily, the network device configures a periodic reporting mode for the UE, or configures a semi-persistent periodic reporting mode for the UE, or configures an aperiodic reporting mode for the UE.

[0337] In some embodiments, the network device configures a periodic reporting method for the UE. Optionally, the reporting method indicates that there is a configured period, and the period is 1 hour.

[0338] In some embodiments, the network device configures a semi-persistent reporting mode to the UE. Optionally, a semi-persistent period is indicated in the reporting mode, and the semi-persistent period is 20 minutes.

[0339] In some embodiments, the network device sends activation signaling to the UE to activate the UE's ability to report UE using a semi-persistent period. For example, the network device sends a semi-persistent reporting mode to the UE and sends activation signaling to the UE, where the activation signaling indicates that the semi-persistent period is 10 minutes.

[0340] In some embodiments, the network device configures an aperiodic reporting mode for the UE.

[0341] In some embodiments, the network device sends a trigger signaling to the UE to trigger the UE to report the UE capability. Exemplarily, the network device sends an aperiodic reporting mode to the UE and sends the trigger signaling to the UE.

[0342] Step 760: Receive the UE capability reported by the UE for the (i+1)th time;

[0343] The network device receives the UE capability reported by the UE for the (i+1)th time. The UE capability is reported by the UE to the network device based on the received reporting mode.

[0344] Step 770: Switch to a second AI model corresponding to the UE capability;

[0345] The network device switches to a second AI model corresponding to the UE capabilities based on the received UE capabilities.

[0346] In some implementations, the network device stores at least two AI models or at least two AI model parameters or at least two AI model indexes. Based on the received UE capabilities, the network device switches to a second AI model corresponding to the UE capabilities among the at least two AI models or at least two AI model parameters or at least two AI model indexes.

[0347] Step 780: Use the second AI model to perform the communication process.

[0348] The network device uses the second AI model to communicate with the UE. For example, the UE uses the second AI model to report CSI to the network device.

[0349] In some embodiments, when at least one UE capability satisfies at least one of the above-mentioned reporting conditions, or when multiple capabilities simultaneously satisfy multiple of the above-mentioned reporting conditions, the UE reports the UE capability to the network device.

[0350] It should be understood that the above UE capability reporting methods can be used in combination.

[0351] FIG8 shows a block diagram of a UE capability reporting device provided by an exemplary embodiment of the present application. The device includes at least some of the following modules:

[0352] The first sending module 810 is configured to report UE capabilities to the network device when a reporting condition is met.

[0353] In an optional design, the first sending module 810 is further used to report the UE capability to the network device when the UE capability meets the first condition.

[0354] In an optional design, the UE capability includes at least one capability;

[0355] The first sending module 810 is further configured to report the UE capabilities to the network device when at least one capability among the UE capabilities meets the first condition.

[0356] In an optional design, the apparatus further includes: a first receiving module 830;

[0357] The at least one capability is predefined, or preconfigured, or configured by the network device to the first receiving module 830 .

[0358] In an optional design, the UE capability satisfying the first condition includes at least one of the following:

[0359] The UE capability is lower than a first threshold;

[0360] The UE capability is higher than a second threshold;

[0361] A change in the UE capability relative to the last reported UE capability exceeds a third threshold.

[0362] In an optional design, the apparatus further includes: a first receiving module 830;

[0363] The first condition is predefined; or,

[0364] The first condition is preconfigured; or,

[0365] The first condition is configured by the network device to the first receiving module 830 .

[0366] In an optional design, the first sending module 810 is further used to report the UE capability to the network device when the change in the current reporting environment compared to the reporting environment at the last reporting meets the second condition.

[0367] In an optional design, the change in the current reporting environment compared to the reporting environment at the last reporting satisfies the second condition, including:

[0368] The duration between the current time and the last reported time exceeds a fourth threshold;

[0369] The distance between the current location and the last reported location exceeds a fifth threshold.

[0370] In an optional design, the apparatus further includes: a first receiving module 830;

[0371] The second condition is predefined; or,

[0372] The second condition is preconfigured; or,

[0373] The second condition is configured by the network device to the first receiving module 830 .

[0374] In an optional design, the device further includes:

[0375] A first receiving module 830 is configured to receive a reporting method of a network device configuration;

[0376] The first sending module 810 is further configured to report the UE capability to the network device when a reporting method configured by the network device is satisfied.

[0377] In an optional design, the reporting method includes:

[0378] Periodic reporting; or,

[0379] Semi-continuous reporting; or

[0380] Non-periodic reporting.

[0381] In an optional design, the reporting method includes the semi-continuous reporting;

[0382] The first receiving module 830 is further configured to receive an activation signaling sent by the network device;

[0383] The first sending module 810 is further configured to start / activate reporting of the UE capability in a semi-persistent period upon receiving activation signaling sent by the network device;

[0384] The first receiving module 830 is further configured to receive a deactivation signaling sent by the network device;

[0385] The first sending module 810 is further configured to stop / deactivate reporting of the UE capability using the semi-persistent period upon receiving a deactivation signaling sent by the network device.

[0386] In an optional design, the reporting method includes the aperiodic reporting;

[0387] The first receiving module 830 is further configured to receive a trigger signaling sent by the network device;

[0388] The first sending module 810 is further configured to report the UE capability upon receiving a trigger signaling sent by the network device.

[0389] In an optional design, the device further includes:

[0390] The first receiving module 830 is configured to receive configuration information sent by the network device, where the configuration information is used to configure reporting resources for the UE capability.

[0391] In an optional design, the UE capability includes at least one of the following capabilities:

[0392] Whether AI functions are supported;

[0393] Use cases based on AI capabilities;

[0394] Supported AI category levels;

[0395] Computing ability;

[0396] Storage capacity;

[0397] communication capabilities;

[0398] Battery level.

[0399] In an optional design, at least one of the UE capabilities is explicitly indicated; and / or,

[0400] At least one of the UE capabilities is indicated separately using a capability level; and / or,

[0401] At least two of the UE capabilities are combined and indicated using one capability level.

[0402] In an optional design, the device further includes:

[0403] A first receiving module 830 is configured to receive a range of capability levels configured for a network device;

[0404] The range of the capability level division is configured by the network device to the first receiving module 830, or the range of the capability level division is defined by a communication protocol.

[0405] In an optional design, the UE capabilities are carried in at least one of the following messages:

[0406] Radio Resource Control RRC message;

[0407] Media access layer control unit MAC CE message;

[0408] Uplink control information UCI.

[0409] In an optional design, the first sending module 810 is also used to report the AI ​​model index supported by the UE.

[0410] In an optional design, the device further includes:

[0411] The first processing module 850 is configured to switch to an AI model corresponding to the UE capability.

[0412] In summary, the apparatus provided in this embodiment reports UE capabilities to a network device based on dynamic changes in UE capabilities, provides semi-static instructions to the network device, and improves the autonomy, accuracy, and flexibility of UE capability reporting.

[0413] FIG9 shows a block diagram of a UE capability reporting device provided by an exemplary embodiment of the present application. The device includes at least some of the following modules:

[0414] The second receiving module 910 is configured to receive UE capabilities reported by a terminal, where the UE capabilities are reported by the terminal when a reporting condition is met.

[0415] In an optional design, the UE capability is reported by the terminal when the UE capability meets the first condition;

[0416] The device further comprises:

[0417] The second sending module 930 is configured to configure the first condition to the terminal.

[0418] In an optional design, the change in the UE capability satisfying the first condition includes at least one of the following:

[0419] The UE capability is lower than a first threshold;

[0420] The UE capability is higher than a second threshold;

[0421] A change in the UE capability relative to the last reported UE capability exceeds a third threshold.

[0422] In an optional design, the UE capability is reported by the terminal when a change in a current reporting environment compared to a last reporting environment satisfies a second condition;

[0423] The device further comprises:

[0424] The second sending module 930 is configured to configure the second condition to the terminal.

[0425] In an optional design, the change in the current reporting environment compared to the reporting environment at the last reporting satisfies the second condition, including:

[0426] The duration between the current time and the last reported time exceeds a fourth threshold;

[0427] The distance between the current location and the last reported location exceeds a fifth threshold.

[0428] In an optional design, the device further includes:

[0429] The second sending module 930 is used to configure a reporting method of the UE capability to the terminal, and the UE capability is reported by the terminal based on the reporting method configured by the second sending module 930.

[0430] In an optional design, the reporting method includes:

[0431] Periodic reporting; or,

[0432] Semi-continuous reporting; or

[0433] Non-periodic reporting.

[0434] In an optional design, the reporting method includes the semi-continuous reporting;

[0435] The second sending module 930 is further configured to send activation signaling to the terminal, where the activation signaling is used to trigger the terminal to start / activate a semi-persistent period to report the UE capability;

[0436] The second sending module 930 is further configured to send a deactivation signaling to the terminal, where the deactivation signaling is configured to trigger the terminal to stop / deactivate reporting of the UE capability using the semi-persistent period.

[0437] In an optional design, the reporting method includes the aperiodic reporting;

[0438] The second sending module 930 is further configured to send a trigger signaling to the terminal, where the trigger signaling is configured to trigger the terminal to report the UE capability.

[0439] In an optional design, the device further includes:

[0440] The second sending module 930 is configured to send configuration information to the terminal, where the configuration information is used to configure reporting resources for the UE capability.

[0441] In an optional design, the UE capability includes at least one of the following capabilities:

[0442] Whether AI functions are supported;

[0443] Use cases based on AI capabilities;

[0444] Supported AI category levels;

[0445] Computing ability;

[0446] Storage capacity;

[0447] communication capabilities;

[0448] Battery level.

[0449] In an alternative design,

[0450] At least one of the UE capabilities is explicitly indicated; and / or,

[0451] At least one of the UE capabilities is indicated separately using a capability level; and / or,

[0452] At least two of the UE capabilities are combined and indicated using one capability level.

[0453] In an optional design, the device further includes:

[0454] The second sending module 930 is configured to configure the capability level division range for the UE.

[0455] In an optional design, the UE capabilities are carried in at least one of the following messages:

[0456] Radio Resource Control RRC message;

[0457] Media access layer control unit MAC CE message;

[0458] Uplink control information UCI.

[0459] In an optional design, the second receiving module 910 is also used to receive the supported AI model index reported by the UE.

[0460] In an optional design, the device further includes:

[0461] The second processing module 950 is configured to switch to an AI model corresponding to the UE capability.

[0462] In summary, the apparatus provided in this embodiment receives dynamic reporting of UE capabilities by configuring information to the UE, thereby improving the efficiency, stability, accuracy, and flexibility of UE capability reporting.

[0463] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0464] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method and will not be elaborated here.

[0465] Figure 10 shows a schematic structural diagram of a communication device (terminal device or network device) provided by an exemplary embodiment of the present application. The communication device 1000 includes: a processor 1001, a receiver 1002, a transmitter 1003, a memory 1004 and a bus 1005.

[0466] The processor 1001 includes one or more processing cores. The processor 1001 executes various functional applications and information processing by running software programs and modules.

[0467] The receiver 1002 and the transmitter 1003 may be implemented as a communication component, which may be a communication chip.

[0468] The memory 1004 is connected to the processor 1001 via a bus 1005. The memory 1004 may be used to store at least one instruction, and the processor 1001 may be used to execute the at least one instruction to implement each step in the above method embodiment.

[0469] In addition, the memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof. Volatile or non-volatile storage devices include but are not limited to: magnetic disks or optical disks, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), static random-access memory (SRAM), read-only memory (ROM), magnetic memory, flash memory, and programmable read-only memory (PROM).

[0470] In an exemplary embodiment, a computer-readable storage medium is further provided, in which at least one program is stored. The at least one program is loaded and executed by the processor to implement the UE capability reporting method provided by each of the above method embodiments.

[0471] In an exemplary embodiment, a chip is further provided. The chip includes a programmable logic circuit and / or program instructions. When the chip runs on a communication device, it is used to implement the UE capability reporting method provided by the above-mentioned various method embodiments.

[0472] In an exemplary embodiment, a computer program product is further provided. When the computer program product is executed on a processor of a computer device, the computer device executes the above-mentioned UE capability reporting method.

[0473] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0474] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for reporting UE capabilities, characterized in that: The method comprises: When the reporting conditions are met, the UE capabilities are reported to the network device.

2. The method according to claim 1, characterized in that Reporting the UE capability to the network device when the reporting conditions are met includes: When the UE capability satisfies a first condition, the UE capability is reported to the network device.

3. The method according to claim 2, characterized in that The UE capability includes at least one capability; When the UE capability satisfies the first condition, reporting the UE capability to the network device includes: When at least one capability among the UE capabilities meets the first condition, the UE capabilities are reported to the network device.

4. The method according to claim 3, characterized in that The at least one capability is predefined, or preconfigured, or configured by the network device.

5. The method according to any one of claims 2 to 4, characterized in that: The UE capability meeting the first condition includes at least one of the following: The UE capability is lower than a first threshold; The UE capability is higher than a second threshold; A change in the UE capability relative to the last reported UE capability exceeds a third threshold.

6. The method according to any one of claims 2 to 5, characterized in that: The first condition is predefined; or, The first condition is preconfigured; or, The first condition is configured by the network device.

7. The method according to claim 1, characterized in that Reporting the UE capability to the network device when the reporting conditions are met includes: When a change in the current reporting environment compared to the reporting environment at the last reporting meets a second condition, the UE capability is reported to the network device.

8. The method according to claim 7, characterized in that The change in the current reporting environment compared to the reporting environment at the last reporting time satisfies the second condition, including: The duration between the current time and the last reported time exceeds a fourth threshold; The distance between the current location and the last reported location exceeds a fifth threshold.

9. The method according to claim 7 or 8, characterized in that The second condition is predefined; or, The second condition is preconfigured; or, The second condition is configured by the network device.

10. The method according to claim 1, characterized in that Reporting the UE capability to the network device when the reporting conditions are met includes: Based on the reporting mode configured by the network device, the UE capability is reported to the network device.

11. The method according to claim 10, characterized in that The reporting methods include: Periodic reporting; or, Semi-continuous reporting; or Non-periodic reporting.

12. The method according to claim 11, characterized in that The reporting method includes the semi-continuous reporting; Reporting the UE capability to the network device based on the reporting method configured by the network device includes: Upon receiving the activation signaling sent by the network device, start / activate reporting of the UE capability in a semi-persistent period; The method further comprises: In case of receiving the deactivation signaling sent by the network device, stopping / deactivating reporting the UE capability using the half persistent period.

13. The method according to claim 11, characterized in that The reporting method includes the non-periodic reporting; Reporting the UE capability to the network device based on the reporting method configured by the network device includes: Upon receiving the trigger signaling sent by the network device, report the UE capability to the network device.

14. The method according to any one of claims 1 to 13, characterized in that: The method further comprises: Receive configuration information sent by the network device, where the configuration information is used to configure reporting resources for the UE capability.

15. The method according to any one of claims 1 to 14, characterized in that: The UE capability includes at least one of the following capabilities: Whether AI functions are supported; Use cases based on AI capabilities; Supported AI category levels; Computing ability; Storage capacity; communication capabilities; Battery level.

16. The method according to claim 15, characterized in that At least one of the UE capabilities is explicitly indicated; and / or, At least one of the UE capabilities is indicated separately using a capability level; and / or, At least two of the UE capabilities are combined and indicated using one capability level.

17. The method according to claim 16, characterized in that The range of the capability level division is configured by the network device, or the range of the capability level division is defined by the communication protocol.

18. The method according to any one of claims 1 to 17, characterized in that: The UE capability is carried in at least one of the following messages: Radio Resource Control RRC message; Media access layer control unit MAC CE message; Uplink control information UCI.

19. The method according to any one of claims 1 to 18, characterized in that The method further comprises: Report the AI ​​model index supported by the UE.

20. The method according to any one of claims 1 to 19, characterized in that The method further comprises: Switch to the AI ​​model corresponding to the UE capabilities.

21. A method for reporting UE capabilities, characterized in that: The method comprises: Receive UE capabilities reported by a terminal, where the UE capabilities are reported by the terminal when a reporting condition is met.

22. The method according to claim 21, characterized in that The UE capability is reported by the terminal when the UE capability meets the first condition; The method further comprises: The first condition is configured for the terminal.

23. The method according to claim 22, characterized in that The UE capability meeting the first condition includes at least one of the following: The UE capability is lower than a first threshold; The UE capability is higher than a second threshold; A change in the UE capability relative to the last reported UE capability exceeds a third threshold.

24. The method according to claim 21, characterized in that The UE capability is reported by the terminal when a change in the current reporting environment compared to the reporting environment at the time of the last reporting satisfies a second condition; The method further comprises: The second condition is configured for the terminal.

25. The method according to claim 24, characterized in that The change in the current reporting environment compared to the reporting environment at the last reporting time satisfies the second condition, including: The duration between the current time and the last reported time exceeds a fourth threshold; The distance between the current location and the last reported location exceeds a fifth threshold.

26. The method according to claim 21, characterized in that The UE capability is reported by the terminal based on a reporting method configured by the network device; The method further comprises: A reporting method for the UE capability is configured for the terminal.

27. The method according to claim 26, characterized in that The reporting methods include: Periodic reporting; or, Semi-continuous reporting; or Non-periodic reporting.

28. The method according to claim 27, characterized in that The reporting method includes the semi-continuous reporting; The method further comprises: Sending activation signaling to the terminal, where the activation signaling is used to trigger the terminal to start / activate reporting the UE capability in a semi-persistent period; The method further comprises: A deactivation signaling is sent to the terminal, where the deactivation signaling is used to trigger the terminal to stop / deactivate reporting the UE capability using the half persistent period.

29. The method according to claim 27, characterized in that The reporting method includes the non-periodic reporting; The method further comprises: Sending a trigger signaling to the terminal, where the trigger signaling is used to trigger the terminal to report the UE capability.

30. The method according to any one of claims 21 to 29, characterized in that The method further comprises: Sending configuration information to the terminal, where the configuration information is used to configure reporting resources for the UE capability.

31. The method according to any one of claims 21 to 30, characterized in that The UE capability includes at least one of the following capabilities: Whether AI functions are supported; Use cases based on AI capabilities; Supported AI category levels; Computing ability; Storage capacity; communication capabilities; Battery level.

32. The method according to claim 31, characterized in that At least one of the UE capabilities is explicitly indicated; and / or, At least one of the UE capabilities is indicated separately using a capability level; and / or, At least two of the UE capabilities are combined and indicated using one capability level.

33. The method according to claim 32, characterized in that The method further comprises: The capability level division range is configured for the UE.

34. The method according to any one of claims 21 to 33, characterized in that The UE capability is carried in at least one of the following messages: Radio Resource Control RRC message; Media access layer control unit MAC CE message; Uplink control information UCI.

35. The method according to any one of claims 21 to 34, characterized in that The method further comprises: Receive the supported AI model index reported by the UE.

36. The method according to any one of claims 21 to 35, characterized in that The method further comprises: Switch to the AI ​​model corresponding to the UE capabilities.

37. A UE capability reporting device, characterized in that: The device comprises: The first sending module is configured to report the UE capability to the network device when a reporting condition is met.

38. A UE capability reporting device, characterized in that: The device comprises: The second receiving module is configured to receive UE capabilities reported by the terminal, where the UE capabilities are reported by the terminal when a reporting condition is met.

39. A terminal, characterized in that: The terminal includes: processor; a transceiver connected to the processor; a memory for storing executable instructions for the processor; The processor is configured to load and execute the executable instructions to implement the UE capability reporting method according to any one of claims 1 to 20.

40. A network device, characterized in that The network equipment includes: processor; a transceiver connected to the processor; a memory for storing executable instructions for the processor; The processor is configured to load and execute the executable instructions to implement the UE capability reporting method as described in any one of claims 21 to 36.

41. A computer-readable storage medium, characterized in that The readable storage medium stores executable instructions, which are loaded and executed by a computer device to implement the UE capability reporting method as described in any one of claims 1 to 36.

42. A chip, characterized in that: The chip includes a programmable logic circuit and / or program instructions, which, when a terminal having the chip is running, is used to implement the UE capability reporting method as described in any one of claims 1 to 36.

43. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the computer instructions are loaded by the computer device and execute the UE capability reporting method as described in any one of claims 1 to 36.

Images