Ai / ML function information interaction method, and apparatus

Abstract

Provided in the embodiments of the present application are an AI / ML function information interaction method, and an apparatus. The method comprises: a first network device sends first information to a terminal device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to an available AI / ML function screened out, and the second information indicating a network side additional condition of the terminal device and / or an available AI / ML function screened out on the basis of the network side additional condition; and the first network device receives third information sent by the terminal device, the third information comprising fourth information and / or fifth information, the fourth information indicating the available AI / ML function screened out by the terminal device, the fifth information indicating an additional condition related to an AI / ML function of the terminal device and / or the network device, and the additional condition being used for determining the availability of the AI / ML function on the terminal device side.

Description

Method and apparatus for interaction of AI / ML function information TECHNICAL FIELD

[0001] The present application relates to the field of communication technology. BACKGROUND

[0002] With the commercialization of 5G (5th Generation Mobile Communication Technology) and the large-scale development of the industrial Internet industry, the application of artificial intelligence (AI) technology in the field of wireless communication has sprung up like mushrooms, among which the AI / ML model management based on machine learning (ML), especially deep learning (DL) or reinforcement learning technology is particularly important in various wireless AI applications.

[0003] In the current 3GPP (3rd Generation Partnership Project) standardization discussion, the concept of functionality is introduced to manage the AI / ML model deployed in the terminal or network device and the AI / ML life cycle. Due to the particularity of wireless communication, even if the AI / ML model is only deployed on the terminal side, the terminal side and the network side need to jointly manage the function. For example, in the process of model training, in order to meet the performance requirements of AI / ML for each use case, both sides need to start training under certain requirements or restrictions. These requirements or restrictions are collectively referred to as additional conditions. In the process of inference, only when the network and terminal sides meet the additional conditions during model training, the accuracy of inference can be expected to be qualified.

[0004] Therefore, before the start of the inference, supervision, etc. of AI / ML, the AI / ML function needs to be screened to determine the applicability of the function, that is, to determine whether the current additional conditions of the network side and the terminal side match the additional conditions during training. If they match, the function can be activated and the inference process is started, otherwise it cannot be activated. However, neither the network side nor the terminal side can obtain all the additional conditions for applicability determination without information interaction. For example, for the AI / ML function trained and deployed on the terminal side, the network side cannot know the properties related to the training data in advance, and the terminal also cannot know the additional conditions of the current network side in advance. Therefore, additional signaling and processes need to be designed to realize the applicability determination of the terminal side AI / ML function.

[0005] It should be noted that the above introduction to the technical background is only for the convenience of clearly and completely describing the technical scheme of the present application and facilitating the understanding of those skilled in the art. The above technical scheme cannot be considered as known to those skilled in the art merely because it is described in the background section of the present application.

[0006] SUMMARY

[0007] The inventors find that the above method is applicable to all AI / ML functions in wireless communication, and in the existing 3GPP standardization discussion, other use cases (such as channel state information feedback, beam management, etc.) can realize the interaction of the above additional condition information through RRC (Radio Resource Control) signaling between gNB and UE, but for the use case of AI / ML wireless positioning, there is no related information interaction design applied in the LPP (LTE Positioning Protocol) signaling and framework between the LMF (Location Management Function) as a network side management network element and the UE.

[0008] To at least one of the above problems or other similar problems, the embodiments of the present application provide an AI / ML function information interaction method and device.

[0009] According to an aspect of the embodiments of the present application, an AI / ML function information interaction device is provided, configured in a first network device, the device comprising:

[0010] a sending unit configured to send first information to a terminal device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to the screened available AI / ML function, and the second information indicating network side additional conditions of the terminal device and / or the available AI / ML function screened according to the network side additional conditions;

[0011] a receiving unit configured to receive third information sent by the terminal device, the third information comprising fourth information and / or fifth information, the fourth information indicating the available AI / ML function screened by the terminal device, and the fifth information indicating additional conditions related to the AI / ML function of the terminal device and / or the network device, the additional conditions being used to determine the availability of the AI / ML function on the terminal device side.

[0012] According to another aspect of the embodiments of the present application, an AI / ML function information interaction device is provided, configured in a terminal device, the device comprising:

[0013] receive a first information sent by a first network device, the first information comprising a first configuration information and / or a second information, the first configuration information configuring the terminal device to report information related to the filtered available AI / ML function, the second information indicating a network-side additional condition and / or the filtered available AI / ML function according to the network-side additional condition;

[0014] send a third information to the first network device, the third information comprising a fourth information and / or a fifth information, the fourth information indicating the filtered available AI / ML function of the terminal device, the fifth information indicating an additional condition related to AI / ML function of the terminal device and / or the network device, the additional condition being used to determine the applicability of the AI / ML function on the terminal device side.

[0015] One of the beneficial effects of the embodiments of the present application is that the terminal device and the network device (e.g. LMF) can determine the applicability of the AI / ML function on the terminal side by interacting the AI / ML function related information.

[0016] Specific embodiments of the application are disclosed herein, and represented in the accompanying drawings, illustrating the principles of the application in a manner that is best suited to the understanding of its principles and its practical application. It should be understood, that the scope of the application is not to be limited in scope by the embodiments specifically disclosed herein. Embodiments of the present application include many alternatives, modifications and equivalents of processes, systems, articles, materials and manufacturing that are within the scope of claims and their equivalents.

[0017] Features described and / or illustrated with respect to one implementation can be used in one or more other implementations in the same or similar manner, in combination with or in place of features in other implementations.

[0018] It should be emphasized that the term "comprises / comprising" when used in this specification is taken to mean the presence of stated features, integers, steps or components but not the exclusion of one or more other features, integers, steps, components or groups thereof. BRIEF DESCRIPTION OF DRAWINGS

[0019] Elements and features of one or more embodiments of the application described in the present application and / or illustrated in a drawing can be combined with elements and features of one or more other embodiments in the present application and / or illustrated in another drawing. Furthermore, in the drawings, like reference numerals indicate corresponding parts throughout the several drawings, and can be used to indicate corresponding parts in more than one implementation.

[0020] The accompanying drawings, which are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. It is understood that the accompanying drawings are merely exemplary of the application and are not intended to be limiting thereof. In the drawings:

[0021] FIG. 1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0022] FIG. 2 is a schematic diagram of an AI / ML function information interaction method of an embodiment of the present application;

[0023] FIG. 3 is a schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0024] FIG. 4 is another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0025] FIG. 5 is still another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0026] FIG. 6 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0027] FIG. 7 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0028] FIG. 8 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0029] FIG. 9 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0030] FIG. 10 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0031] FIG. 11 is yet another schematic diagram of AI / ML function information interaction between a first network device and a terminal device;

[0032] FIG. 12 is another schematic diagram of an AI / ML function information interaction method of an embodiment of the present application;

[0033] FIG. 13 is a schematic diagram of an AI / ML function information interaction apparatus of an embodiment of the present application;

[0034] FIG. 14 is another schematic diagram of an AI / ML function information interaction apparatus of an embodiment of the present application;

[0035] Fig. 15 is a schematic block diagram of a system configuration of a network device according to an embodiment of the present application;

[0036] Fig. 16 is a schematic block diagram of a system configuration of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The foregoing and other features of the present application will become more apparent from the following description and accompanying drawings. In the description and drawings, particular embodiments of the application have been disclosed in detail as being illustrative. It should be understood that the application is not limited to the particular embodiments described but includes variations to the technique that would be apparent to one skilled in the art. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0038] In the embodiments of the present application, the terms "first", "second", and the like are used to distinguish different elements from each other, but do not indicate spatial arrangement or temporal order of the elements, and the elements should not be limited by these terms. The term "and / or" includes any one and all combinations of the associated listed terms. The terms "comprise", "include", "have", and the like, mean the presence of the stated feature, element, component, or assembly, but do not exclude the presence or addition of one or more other features, elements, components, or assemblies.

[0039] In the embodiments of the present application, the singular forms "a", "an", and "the" include plural forms unless the context clearly indicates otherwise. The term "said" should be understood to include both the singular and the plural form, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least partially according to", and the term "based on" should be understood as "at least partially based on", unless the context clearly indicates otherwise.

[0040] In the embodiments of the present application, the term "communication network" or "wireless communication network" can refer to a network that complies with any communication standard, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), and the like.

[0041] The communication between devices in a communication system can be in accordance with any phase of communication protocol, for example, can include but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and future 5G, new radio (NR), etc., and / or other currently known or to be developed in the future communication protocols.

[0042] In the embodiments of the present application, the term "network device" refers to, for example, a device that accesses a terminal device to a communication network and provides services for the terminal device in a communication system. The network device can include but not limited to the following devices: base station (BS), core network (CN), operation administration and maintenance device (OAM), OTT (Over The Top) server device, access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0043] The base station can include but not limited to: node B (NodeB or NB), evolved node B (eNodeB or eNB) and 5G base station (gNB), IAB donor, etc., in addition to remote radio head (RRH), remote radio unit (RRU), relay or low power node (such as femto, pico, etc.). And the term "base station" can include some or all functions of them, and each base station can provide communication coverage for a specific geographic area. The term "cell" can refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0044] The core network can include, but is not limited to, an MSC (Mobile Service Center), an SGSN (Serving GPRS Support Node), a GGSN (Gateway GPRS Support Node), an MME (Mobile Management Entity), an SGW (Serving Gateway), a PGW (PDN Gateway), a 5GC (5G Core Network). And the term "core network" can include some or all of their functions.

[0045] In the embodiments of the present application, the term "user equipment" (UE, User Equipment) refers to a device that accesses a communication network through a network device and receives network services, for example, which can also be referred to as "terminal equipment" (TE, Terminal Equipment). The terminal equipment can be fixed or mobile, and can also be referred to as a mobile station (MS, Mobile Station), a terminal, a user, a subscriber station (SS, Subscriber Station), an access terminal (AT, Access Terminal), a station (station), etc.

[0046] The terminal equipment can include, but is not limited to, the following devices: a cellular phone, a personal digital assistant (PDA, Personal Digital Assistant), a wireless modem, a wireless communication device, a handheld device, a machine type communication device, a laptop computer, a cordless phone, a smart phone, a smart watch, a digital camera, etc.

[0047] For another example, in the Internet of Things (IoT, Internet of Things) and other scenarios, the terminal equipment can also be a machine or device that monitors or measures, for example, which can include but is not limited to: a machine type communication (MTC, Machine Type Communication) terminal, a vehicle communication terminal, a device to device (D2D, Device to Device) terminal, a machine to machine (M2M, Machine to Machine) terminal, etc.

[0048] The following describes the scenarios of the embodiments of the present application by way of example, but the present application is not limited thereto.

[0049] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application, which schematically illustrates a case taking a terminal device and a network device as examples. As shown in FIG. 1, the communication system 100 can include a network device 101, terminal devices 102 and 103. For simplicity, FIG. 1 illustrates only two terminal devices and one network device as examples, but embodiments of the present application are not limited thereto.

[0050] In embodiments of the present application, the network device 101 and the terminal devices 102 and 103 can perform existing services or future implementable services transmission. For example, these services can include, but are not limited to, enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0051] It is worth noting that FIG. 1 shows that the terminal devices 102 and 103 are within the coverage of the network device 101, but the present application is not limited thereto. The terminal devices 102 and 103 can not be within the coverage of the network device 101.

[0052] In embodiments of the present application, the network device 101 can be, for example, a gNB, or an entity of a core network (such as a location management function (LMF) or an access and mobility management function (AMF), or an entity of a higher layer network (such as an operation administration and maintenance (OAM), or an over the top server (OTT-server), or can also be a partial function or entity of any of the above devices.

[0053] In embodiments of the present application, for the convenience of description, in the process of AI / ML function information interaction and judgment, the current additional condition on the network side is referred to as the first condition, the current additional condition on the terminal side is referred to as the third condition, the network side additional condition in the function or model training process of the AI / ML function to be screened is referred to as the second condition, the terminal side additional condition in the function or model training process of the AI / ML function to be screened is referred to as the fourth condition, and the terminal side additional condition in the above training process preferred by the network side is referred to as the fifth condition.

[0054] The present application is applicable to the application scenarios of deploying AI / ML functions / models on the terminal side, including but not limited to the terminal-side direct-type model (Case 1) and the terminal-side auxiliary-type model (Case 2a) of wireless positioning. The embodiments of the present application will be described below in conjunction with the drawings, taking the terminal-side direct-type AI / ML function / model (Case 1) and the terminal-side auxiliary-type AI / ML function / model (Case 2a) of wireless positioning as examples. In the following description, unless otherwise specified, the meanings of "when", "if" and "in the case of" are the same and can be interchanged.

[0055] Embodiments of the first aspect

[0056] The embodiments of the present application provide an AI / ML function information interaction method, which is described from the side of a first network device. The first network device may, for example, be an LMF as a network-side management network element, but the present application is not limited thereto. The first device may also be other network elements, depending on the implemented scenario.

[0057] FIG. 2 is a schematic diagram of the AI / ML function information interaction method according to an embodiment of the present application. As shown in FIG. 2, the method comprises:

[0058] 210. The first network device sends first information to the terminal device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to the screened available AI / ML functions, and the second information indicating network-side additional conditions and / or available AI / ML functions screened according to the network-side additional conditions;

[0059] 220. The first network device receives third information sent by the terminal device, the third information comprising fourth information and / or fifth information, the fourth information indicating the available AI / ML functions screened by the terminal device, and the fifth information indicating additional conditions related to the AI / ML functions of the terminal device and / or the network device, the additional conditions being used to determine the availability of the AI / ML functions on the terminal device side.

[0060] It is worth noting that the above FIG. 2 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the various operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the description of the above FIG. 2.

[0061] According to the above embodiments, the first network device can determine the applicability of the AI / ML function at the terminal side by interacting with the terminal device for the above AI / ML function information.

[0062] FIG. 3 is a schematic diagram of the interaction of the AI / ML function information between the first network device and the terminal device, showing the case where the LMF is the first network device and the UE is the terminal device.

[0063] In some embodiments, as shown in FIG. 3, the first network device sends the terminal device the first configuration information (operation 310) by which the terminal device reports information related to the screened AI / ML function. Thus, the terminal device can send the first network device the above third information (operation 320) according to the first configuration information, for example, report the screened AI / ML function (indicated by the fourth information) and / or additional conditions (indicated by the fifth information) related to the AI / ML function of the terminal device and / or the network device.

[0064] In the above embodiments, the additional conditions (additional condition) for determining the applicability of the AI / ML function at the terminal device include but are not limited to: the current additional conditions at the terminal side (the third condition described above), the additional conditions at the terminal side during the training process (the fourth condition described above), the additional conditions at the network side during the training process (the second condition described above), and the like.

[0065] In the above embodiments, there is no limitation on how the terminal device screens the available AI / ML function.

[0066] In the above embodiments, optionally, in the case where the terminal device reports the screened AI / ML function, that is, in the case where the terminal device sends the above fourth information, the terminal device can also report the configuration information (indicated by the sixth information) corresponding to the screened AI / ML function. The configuration information is used to implement the screened AI / ML function, for example, the configuration information is used to implement at least one of the following operations of the AI / ML function: Activation, Deactivation, Inference, Monitoring, Switching, Selection, Fallback. For the above operations of the AI / ML function, please refer to the related technology, which will not be described here.

[0067] In some embodiments, the first network device sends the first configuration information to the terminal device (operation 310), and the first configuration information is used by the terminal device to determine the available AI / ML function. In some embodiments, the first network device sends the second information to the terminal device (operation 310), and the second information is used by the terminal device to determine the available AI / ML function. In some embodiments, the first network device sends the first configuration information to the terminal device (operation 310), and the terminal device determines the available AI / ML function according to the first configuration information and the second information.

[0068] In some embodiments, the sixth information used to indicate the configuration information corresponding to the available AI / ML function determined by the terminal device can be sent together with the fourth information.

[0069] In some embodiments, the first configuration information, the second information, the fourth information, the fifth information, and the sixth information can be sent through at least one of the following signaling defined by the LPP (LTE Positioning Protocol) protocol:

[0070] LPP capability exchange signaling (LPP Capability Exchange);

[0071] LPP assistance data signaling (LPP Assistance Data);

[0072] LPP location information signaling (LPP Location Information);

[0073] Other LPP signaling.

[0074] In some embodiments, the first configuration information and the second information can be sent through the same signaling, or can be sent through different signaling. Similarly, the fourth information and the fifth information can be sent through the same signaling, or can be sent through different signaling. In addition, the sixth information can be sent together with the fourth information, and the sixth information and the fourth information can share the same signaling, or can use different signaling respectively.

[0075] In some embodiments, the first network device sends the first configuration information to the terminal device, and the first configuration information does not explicitly configure the available AI / ML function filtering information, for example, the first configuration information is empty, i.e., does not contain specific content. The terminal device can filter and report the available AI / ML function according to a predetermined strategy, and the first network device can make a decision on the available AI / ML function according to the content reported by the terminal device. Thus, the terminal device has greater flexibility to select the content reported by the terminal device to the network side.

[0076] FIG. 4 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above embodiment. As shown in FIG. 4, the method comprises:

[0077] 410: The LMF sends the first configuration information to the UE, configuring the UE to report;

[0078] 420: The UE flexibly selects available AI / ML functions;

[0079] 430: The UE sends the fourth information and / or the fifth information to the LMF, to report the available AI / ML functions and / or related additional conditions selected by the UE, and optionally, the UE sends the sixth information to the LMF, to report the configuration information corresponding to the available AI / ML functions selected by the UE;

[0080] 440: The LMF makes a decision on the available AI / ML functions.

[0081] The above embodiment is applicable to the case where the network side does not have additional condition information corresponding to AI / ML training data, that is, the first network device only has network side additional condition information, but the present application is not limited thereto.

[0082] In the above embodiment, the network side can send a more flexible information collection configuration to the UE, and the UE has greater flexibility to select the content reported to the network side. Thus, AI / ML function information interaction is realized, which helps the network side to determine the availability of terminal side AI / ML functions.

[0083] In other embodiments, the first network device sends the above-mentioned first configuration information to the terminal device, which includes the available AI / ML functions selected by the first network device and / or the additional conditions corresponding to the available AI / ML functions selected by the first network device.

[0084] In the above embodiment, the first network device first selects the available AI / ML functions according to the current additional conditions of the network side, selects the AI / ML functions and / or the additional conditions corresponding to the AI / ML functions as the selection information, and configures the terminal device, for example, to further select the available AI / ML functions in the above-mentioned additional conditions. After receiving the first configuration information, the terminal device can further select and report the available AI / ML functions, and the first network device makes a decision on the available AI / ML functions according to the content reported by the terminal device.

[0085] In the above embodiment, the terminal device can further select the available AI / ML functions within the range of the available AI / ML functions selected by the first network device according to the configuration of the first network device, but the present application is not limited thereto, and the terminal device can also further select the available AI / ML functions according to the configuration of the first network device in combination with local information.

[0086] FIG. 5 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above-mentioned embodiments. As shown in FIG. 5, the method comprises:

[0087] 510: The LMF sends the first configuration information to the UE, and configures the filtering information to the UE;

[0088] 520: The UE further filters the available AI / ML functions according to the filtering information;

[0089] 530: The UE sends the fourth information and / or the fifth information to the LMF, to report the filtered available AI / ML functions and / or related additional conditions, and optionally, the UE sends the sixth information to the LMF, to report the configuration information corresponding to the filtered available AI / ML functions;

[0090] 540: The LMF makes a decision on the available AI / ML functions.

[0091] The above-mentioned embodiments are applicable to the case where the network side has no additional condition information corresponding to the AI / ML training data, that is, the first network device only has the current additional condition (the first condition) of the network side, but the present application is not limited thereto.

[0092] In the above-mentioned embodiments, the network side sends the current additional condition of the network side to the UE after initiating the AI / ML function availability decision process, and configures the filtering of the reporting content of the UE. Thus, the AI / ML function information interaction is realized, which is helpful for the network side to determine the availability of the AI / ML function of the terminal side.

[0093] In some other embodiments, the first network device sends the second information to the terminal device, the second information comprising the current additional condition of the network side of the first network device, and the terminal device can make a decision on the available AI / ML functions according to the current additional condition of the network side and the local information.

[0094] In the above-mentioned embodiments, the first network device only sends the current additional condition of the network side to the terminal device, and does not filter the available AI / ML functions, and the terminal device makes a decision on the availability in combination with the received information and the local information.

[0095] In the above-mentioned embodiments, optionally, the terminal device can further report the available AI / ML function selected through the decision to the first network device through the fourth information, or report the available AI / ML function and the configuration information corresponding thereto to the first network device through the fourth information and the sixth information, or report the configuration information corresponding to the available AI / ML function to the first network device through the sixth information.

[0096] FIG. 6 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above embodiment. As shown in FIG. 6, the method comprises:

[0097] 610: The LMF sends second information to the UE, the second information comprising the current additional condition on the network side;

[0098] 620: The UE makes a decision on available AI / ML functions based on the received information and local information;

[0099] 630: The UE sends the fourth information to the LMF to report the available AI / ML function selected by the decision, and optionally, the UE sends the sixth information to the LMF to report the configuration information corresponding to the available AI / ML function selected by the decision.

[0100] The above embodiment is applicable to the case where the network side has no additional condition information corresponding to the AI / ML training data, that is, the first network device only has the current additional condition (first condition) on the network side, but the present application is not limited thereto.

[0101] In the above embodiment, the network side sends the current additional condition on the network side to the UE after initiating the AI / ML function availability decision process, and the UE makes a decision on the availability of the AI / ML function. Thus, the AI / ML function information interaction is realized, which helps the network side to determine the availability of the AI / ML function on the terminal side.

[0102] In some other embodiments, before the first network device and the terminal device interact with the above AI / ML function information, the first network device sends the current additional condition on the network side (i.e., the network side) to at least one (one or more) terminal device including the above terminal device. At this time, the terminal device has all the judgment elements of the AI / ML function availability, and can make a preliminary decision on the AI / ML function availability on the network side, for example, make a preliminary decision on the AI / ML function availability according to the current additional condition on the network side and the local information (e.g., the additional condition on the terminal side), and request the network side to allow it to report the available AI / ML function selected by the decision.

[0103] For example, the terminal device sends a request information to the first network device, the request information requesting the first network device to allow the terminal device to report the available AI / ML function selected by the decision.

[0104] In the above embodiment, the first network device can accept the request of the terminal device and configure the terminal device to make the related report.

[0105] For example, the first network device sends second configuration information to the terminal device, the second configuration information configures the terminal device to report the available AI / ML function screened out by the terminal device (selected by the preliminary decision) or report the available AI / ML function screened out by the terminal device (selected by the preliminary decision) and the configuration information thereof.

[0106] According to the above-mentioned embodiments, the terminal device can send the fourth information mentioned above to the first network device, so as to report the available AI / ML function screened out by the terminal device (selected by the preliminary decision), and optionally, the terminal device can also send the sixth information mentioned above to the first network device, so as to report the configuration information corresponding to the available AI / ML function screened out by the terminal device (selected by the preliminary decision).

[0107] The present application is not limited thereto, and the first network device can also reject the request of the terminal device, and perform the information of the AI / ML function information with the terminal device according to the method of the above-mentioned embodiments.

[0108] In the above-mentioned embodiments, the current additional condition of the network side can be sent through the positioning related system broadcast information, for example, sent through the positioning system information block (pos-SIB), the present application is not limited thereto, and the current additional condition of the network side can also be sent through other system information, for example, sent through the master information block / system information block (MIB / SIB), etc.

[0109] In the above-mentioned embodiments, the second configuration information can be sent through at least one of the above-mentioned LPP capability interaction signaling, LPP assistance data signaling, and LPP position information signaling defined by the LPP protocol, the present application is not limited thereto, and the second configuration can also be sent through other LPP signaling, which will not be described here.

[0110] FIG. 7 is a schematic diagram of the AI / ML function information interaction between the first network device and the terminal device according to the above-mentioned embodiments. As shown in FIG. 7, the method comprises:

[0111] 710: The LMF sends broadcast information to the UE, the broadcast information comprising the current additional condition of the network side;

[0112] 720: The UE makes an availability decision of the AI / ML function according to the above-mentioned broadcast information and local information;

[0113] 730: The UE sends request information to the LMF, requesting the LMF to allow it to report the available AI / ML function selected by the decision;

[0114] 740: The LMF accepts the request of the UE or rejects the request of the UE;

[0115] 750: The LMF sends second configuration information to the UE, configuring the UE to report the AI / ML function selected by the decision or the AI / ML function and the configuration information of the AI / ML function;

[0116] 760: The UE sends the fourth information to the LMF to report the AI / ML function selected by the decision, and optionally, the sixth information to the LMF to report the configuration information corresponding to the AI / ML function selected by the decision.

[0117] The above embodiments are applicable to the case where the network side does not have additional condition information corresponding to the AI / ML training data, that is, the first network device only has the current additional condition (first condition) of the network side, but the present application is not limited thereto.

[0118] In the above embodiments, the network side gives the current additional condition of the network side to the UE through broadcast information before the AI / ML function related availability information (referred to as AI / ML available function information) interaction, and the UE can make a preliminary decision on the availability of the AI / ML function according to the current additional condition of the network side, and request the LMF to allow it to report. The LMF can accept the request of the UE and configure the UE to make corresponding report, or the LMF can also refuse the UE, and interact with the UE according to the method of the above embodiments to interact the AI / ML function information. Thus, the interaction of the AI / ML function information is realized, which helps the network side to determine the availability of the AI / ML function on the terminal side.

[0119] In some other embodiments, the first network device sends second information to the terminal device, the second information including the available AI / ML function selected by the first network device, the first network device can select the AI / ML function to be selected according to the current additional condition (first condition) of the network side and the network side additional condition (second condition) of the AI / ML function in the function or model training process, the terminal device makes a decision on the available AI / ML function according to the current additional condition (third condition) of the terminal side and the terminal side additional condition (fourth condition) in the training process, and sends the third information to the first network device.

[0120] In the above embodiments, the network side selects the available AI / ML function according to the first condition and the second condition, and provides it to the terminal device, and the terminal device makes a final decision on the available AI / ML function selected by the network side according to the third condition and the fourth condition, and reports it to the network side.

[0121] In the above embodiment, after the terminal device makes a final decision, the decision result can also be fed back to the first network device, that is, the third information described above is sent to the first network device, which can include the fourth information, and the fourth information reports the available AI / ML function selected by the decision. Optionally, the third information can also include the sixth information, and the sixth information reports the configuration information corresponding to the available AI / ML function selected by the decision.

[0122] FIG. 8 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above embodiment. As shown in FIG. 8, the method includes:

[0123] 810: The LMF sends the second information to the UE, which includes the available AI / ML function filtered by the network side according to the first condition and the second condition described above;

[0124] 820: The UE makes a decision on the available AI / ML function filtered by the network side according to the third condition and the fourth condition described above;

[0125] 830: The UE sends the fourth information to the LMF to report the available AI / ML function selected by the decision. Optionally, the UE also sends the sixth information to the LMF to report the configuration information corresponding to the available AI / ML function selected by the decision.

[0126] The above embodiment is applicable to the case where the network side has additional condition information corresponding to the AI / ML training data. The additional conditions here include both the network side and the terminal side. That is, in addition to the current additional condition (the first condition), the network side also has the network side additional condition (the second condition) and the terminal side additional condition (the fourth condition) of the AI / ML function to be filtered in the function or model training process.

[0127] In the above embodiment, the LMF first makes a decision on the network side according to the first condition and the second condition described above, and sends the available AI / ML function filtered to the UE side for further filtering and decision. In this way, the AI / ML function information interaction is realized, which helps the network side to determine the availability of the terminal side AI / ML function.

[0128] In some embodiments, the first network device sends second information to the terminal device, the second information comprising the available AI / ML functions screened by the first network device and the terminal-side additional conditions in the training process preferred by the first network device, wherein the first network device screens the AI / ML functions to be screened according to the current network-side additional conditions (first conditions) and the network-side additional conditions (second conditions) in the function or model training process of the AI / ML functions to be screened, the terminal device makes a decision on the available AI / ML functions according to the current terminal-side additional conditions (third conditions) and the terminal-side additional conditions (fourth conditions) in the training process, or according to the current terminal-side additional conditions (third conditions) and the terminal-side additional conditions (fifth conditions) in the training process preferred by the first network device, and sends the third information to the first network device.

[0129] In the above embodiments, the network side screens the available AI / ML functions according to the first conditions and the second conditions, not only provides the available AI / ML functions screened by the network side to the terminal device, but also provides the terminal-side additional conditions (fifth conditions) in the training process preferred by the network side to the terminal device, so that the terminal device can further screen the available AI / ML functions screened by the network side according to the third conditions and the fourth conditions, or the terminal device can further screen the available AI / ML functions screened by the network side according to the third conditions and the fifth conditions and report the screening results.

[0130] In the above embodiments, the terminal device can feed back the screening results to the first network device, i.e., send the third information to the first network device, the third information can comprise the fourth information and / or the fifth information, the fourth information is used to report the available AI / ML functions screened, the fifth information is used to report the additional conditions (e.g., at least one of the second conditions, the third conditions, the fourth conditions), and optionally, the third information can further comprise the sixth information, the sixth information is used to report the configuration information corresponding to the available AI / ML functions screened.

[0131] In the above embodiments, the fifth conditions and the fourth conditions can be the same or different, for example, the fifth conditions can be a subset of the fourth conditions, which is not limited in the present application. For example, there are four terminal-side additional conditions (fourth conditions) in the training process, which are A, B, C and D, and the network side preferred terminal-side additional conditions (fifth conditions) in the training process are A and C.

[0132] FIG. 9 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above embodiments. As shown in FIG. 9, the method comprises:

[0133] 910: The LMF screens the available AI / ML functions according to the first condition and the second condition;

[0134] 920: The LMF sends the second information to the UE, the second information including the available AI / ML functions screened by the LMF and the terminal-side additional condition in the training process preferred by the LMF;

[0135] 930: The UE further screens the available AI / ML functions screened by the LMF according to the third condition and the fourth condition or according to the third condition and the fifth condition, and sends the fourth information and / or the fifth information to the LMF, reporting the available AI / ML functions screened by the UE and / or the additional condition, and optionally, sends the sixth information to the LMF, reporting the configuration information corresponding to the available AI / ML functions screened by the UE;

[0136] 940: The LMF makes a final decision on the available AI / ML functions according to the content reported by the UE.

[0137] The above embodiments are applicable to the case where the network side has additional condition information corresponding to the AI / ML training data, and the additional conditions include both network-side and terminal-side conditions. That is, in addition to the current additional condition (the first condition), the network side also has the network-side additional condition (the second condition) and the terminal-side additional condition (the fourth condition) of the AI / ML function to be screened in the function or model training process.

[0138] In the above embodiments, the LMF first makes a local decision according to the first condition and the second condition, sends the available AI / ML functions screened and the terminal-side additional condition (the fifth condition) in the training process preferred by the LMF to the UE side for further screening, and makes a final decision according to the content reported by the UE. In this way, the interaction of AI / ML function information is realized, which helps the network side to determine the availability of the terminal-side AI / ML function.

[0139] In some other embodiments, the first network device sends second information to the terminal device, the second information including the available AI / ML functions screened by the first network device, wherein the first network device screens the AI / ML functions to be screened according to the current additional condition (the first condition) of the network side and the network-side additional condition (the second condition) and the terminal-side additional condition (the fourth condition) of the AI / ML functions to be screened in the function or model training process, the terminal device makes a decision on the available AI / ML functions according to the current additional condition (the third condition) of the terminal side and the terminal-side additional condition (the fourth condition) in the training process, and sends the third information to the first network device.

[0140] In the above embodiments, the network side screens the available AI / ML functions according to the first condition, the second condition, and the fourth condition, and provides the screened available AI / ML functions to the terminal device, so that the terminal device can further screen the available AI / ML functions screened by the network side according to the third condition and the fourth condition, and report the screening result.

[0141] In the above embodiments, the terminal device can feed back the screening result to the first network device, i.e., send the third information to the first network device, which can include the fourth information and / or the fifth information, report the further screened available AI / ML functions through the fourth information, and report the additional conditions (e.g., at least one of the second condition, the third condition, and the fourth condition) through the fifth information. Optionally, the third information can also include the sixth information, through which the configuration information corresponding to the further screened available AI / ML functions is reported.

[0142] FIG. 10 is a schematic diagram of AI / ML function information interaction between the first network device and the terminal device according to the above embodiments. As shown in FIG. 10, the method includes:

[0143] 1010: The LMF screens the available AI / ML functions according to the first condition, the second condition, and the fourth condition;

[0144] 1020: The LMF sends the second information to the UE, which includes the available AI / ML functions screened by the LMF;

[0145] 1030: The UE further screens the available AI / ML functions screened by the LMF according to the third condition and the fourth condition, and sends the fourth information and / or the fifth information to the LMF, which reports the screened available AI / ML functions and / or the additional conditions. Optionally, the sixth information is also sent to the LMF, which reports the configuration information corresponding to the screened available AI / ML functions;

[0146] 1040: The LMF makes a final decision on the available AI / ML functions according to the content reported by the UE.

[0147] The above embodiments are applicable to the case where the network side has additional condition information corresponding to the AI / ML training data, which includes both the network side and the terminal side. That is, in addition to the current additional condition (the first condition), the network side also has the network side additional condition (the second condition) and the terminal side additional condition (the fourth condition) of the AI / ML function to be screened in the function or model training process.

[0148] In the above embodiments, the LMF first makes a local-side judgment according to the first condition, the second condition, and the fourth condition, sends the screened available AI / ML functions to the UE side for further screening, and makes a final decision according to the content reported by the UE. In this way, the interaction of AI / ML function information is realized, which helps the network side to determine the availability of the terminal-side AI / ML function.

[0149] In yet some embodiments, the first network device sends the first configuration information to the terminal device, the first configuration information configuring the terminal device to report the terminal-side AI / ML available function information. In this way, the terminal device can report the corresponding information according to the first configuration information.

[0150] In the above embodiments, the terminal-side AI / ML available function information is, for example, the available AI / ML function screened by the terminal device according to the local information (for example, the third condition and the fourth condition). The terminal device can report the screened available AI / ML function to the first network device through the fourth information. Optionally, the terminal device can also report the configuration information corresponding to the screened available AI / ML function to the first network device through the sixth information.

[0151] In the above embodiments, the first network device can make a final decision on the available AI / ML function according to the content reported by the terminal device and the additional conditions (the first condition) of the network side at present and the additional conditions (the second condition and the fourth condition) of the network side and the terminal side in the training process.

[0152] FIG. 11 is a schematic diagram of the interaction of AI / ML function information between the first network device and the terminal device according to the above embodiments. As shown in FIG. 11, the method includes:

[0153] 1110: The LMF sends the first configuration information to the UE, the first configuration information configuring the UE to report the terminal-side AI / ML available function information;

[0154] 1120: The UE sends the fourth information to the LMF to report the screened available AI / ML function. Optionally, the UE can also send the sixth information to the LMF to report the configuration information corresponding to the screened available AI / ML function;

[0155] 1130: The LMF makes a final decision on the available AI / ML function according to the content reported by the UE.

[0156] The above embodiments are applicable to the case where the network side has additional condition information corresponding to the AI / ML training data, where the additional conditions include both network-side and terminal-side conditions. That is, in addition to the current additional condition (first condition), the network side also has network-side additional conditions (second condition) and terminal-side additional conditions (fourth condition) in the process of function or model training of the AI / ML function to be screened.

[0157] In the above embodiments, the LMF configures the UE to report terminal-side AI / ML available function information, such as the available AI / ML function screened by the UE or the available AI / ML function screened by the UE and its corresponding configuration information, and the LMF can make a final decision based on the content reported by the UE. Thus, the AI / ML function information is exchanged, which helps the network side to determine the applicability of the terminal-side AI / ML function.

[0158] The above embodiments only exemplarily illustrate the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, the above embodiments can be used alone or one or more of the above embodiments can be combined.

[0159] According to the embodiments of the present application, the terminal device and the network device (such as LMF) can determine the applicability of the terminal-side AI / ML function by exchanging AI / ML function related information.

[0160] Embodiments of the second aspect

[0161] The embodiments of the present application provide an AI / ML function information exchange method, which is described from the side of the terminal device, and the same content as the embodiments of the first aspect is not repeated.

[0162] FIG. 12 is a schematic diagram of an AI / ML function information exchange method according to an embodiment of the present application. As shown in FIG. 12, the method includes:

[0163] 1210: The terminal device receives first information sent by the first network device, where the first information includes first configuration information and / or second information, the first configuration information configures the terminal device to report information related to the screened available AI / ML function, and the second information indicates the network-side additional conditions of the terminal device and / or the available AI / ML function screened according to the network-side additional conditions;

[0164] 1220: The terminal device sends third information to the first network device, the third information comprising fourth information and / or fifth information, the fourth information indicating the AI / ML function screened out by the terminal device, and the fifth information indicating an additional condition related to the AI / ML function of the terminal device and / or the network device, the additional condition being used to determine the availability of the AI / ML function on the terminal device side.

[0165] It is worth noting that the above Figure 12 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can make appropriate modifications based on the above description, and the present application is not limited to the above Figure 12.

[0166] According to the above embodiments, the first network device can determine the applicability of the AI / ML function on the terminal side by interacting with the terminal device for the above AI / ML function information.

[0167] In some embodiments, the above additional condition comprises at least one of:

[0168] a current additional condition on the terminal side (the third condition described above);

[0169] an additional condition on the terminal side during the training process (the fourth condition described above);

[0170] an additional condition on the network side during the training process (the second condition described above).

[0171] In some embodiments, the third information further comprises sixth information, the sixth information indicating configuration information corresponding to the AI / ML function screened out by the terminal device, the configuration information being used for at least one of the following operations of the AI / ML function: activation, deactivation, inference, detection, switching, selection, fallback.

[0172] In some embodiments, the above sixth information is sent along with the above fourth information.

[0173] In some embodiments, the above first configuration information, second information, fourth information, fifth information, and sixth information are sent through at least one of the following signaling defined by the LPP protocol:

[0174] LPP capability exchange signaling (LPP Capability Exchange);

[0175] LPP assistance data signaling (LPP Assistance Data);

[0176] LPP location information signaling (LPP Location Information);

[0177] Other LPP signaling.

[0178] In some embodiments, the terminal device receives the first configuration information sent by the first network device, the first configuration information does not explicitly configure the available AI / ML function filtering information, the terminal device filters and reports the available AI / ML function according to a predetermined strategy, and the first network device makes a decision on the available AI / ML function according to the content reported by the terminal device.

[0179] In some embodiments, the terminal device receives the first configuration information sent by the first network device, the first configuration information includes the available AI / ML function filtered by the first network device according to the current additional condition on the network side and / or the additional condition corresponding to the available AI / ML function filtered by the first network device, the terminal device further filters the available AI / ML function filtered by the first network device according to the additional condition and reports, and the first network device makes a decision on the available AI / ML function according to the content reported by the terminal device.

[0180] In some embodiments, the terminal device receives the second information sent by the first network device, the second information includes the current additional condition (the first condition described above) on the network side of the first network device, and the terminal device makes a decision on the available AI / ML function according to the current additional condition (the first condition described above) on the network side and the local information (for example, the third condition described above and the fourth condition described above).

[0181] In the above embodiments, the terminal device can also report the available AI / ML function selected by the terminal device for the above decision to the first network device or the available AI / ML function and the configuration information corresponding to the available AI / ML function. That is, the terminal device can also send the fourth information described above or the fourth information and the sixth information described above to the first network device.

[0182] In some embodiments, the terminal device receives the current additional condition (the first condition described above) on the network side of the first network device sent by the first network device to at least one terminal device including the terminal device, makes a decision on the available AI / ML function according to the current additional condition (the first condition described above) on the network side of the first network device and the local information (for example, the third condition described above and the fourth condition described above), and sends request information to the first network device to request the first network device to allow the terminal device to report the available AI / ML function filtered by the terminal device.

[0183] In the above embodiments, the current additional conditions on the network side (the aforementioned first condition) can be sent via location-related system broadcast information. This location-related broadcast information may include, for example, a Position System Information Block (pos-SIB) or other system information, such as a Master Information Block / System Information Block (MIB / SIB).

[0184] In the above embodiments, the terminal device may also receive second configuration information sent by the first network device. The second configuration information configures the terminal device to report the available AI / ML functions selected by the terminal device or to report the available AI / ML functions selected by the terminal device and their corresponding configuration information.

[0185] In the above embodiments, the terminal device can send the fourth information to the first network device according to the second configuration information to report the available AI / ML functions it has selected, or send the fourth information and the sixth information to report the available AI / ML functions it has selected and their corresponding configuration information.

[0186] In the above embodiments, the second configuration information can also be sent via at least one of the following signaling methods defined by the aforementioned LPP protocol:

[0187] LPP Capability Exchange;

[0188] LPP Assistance Data;

[0189] LPP Location Information signaling;

[0190] Other LPP signaling.

[0191] In some embodiments, the terminal device receives second information sent by the first network device, the second information including available AI / ML functions filtered by the first network device, wherein the first network device can filter available AI / ML functions according to the current additional conditions on the network side (the first conditions mentioned above) and the additional conditions on the network side of the AI / ML functions to be filtered during the function or model training process (the second conditions mentioned above).

[0192] In the above embodiments, the terminal device makes decisions on the available AI / ML functions based on the current additional conditions on the terminal side (the third condition mentioned above) and the additional conditions on the terminal side during the training process (the fourth condition mentioned above).

[0193] In some embodiments, the terminal device receives second information sent by the first network device, the second information comprising the AI / ML functions filtered by the first network device and the terminal-side additional conditions (the fifth condition described above) in the training process preferred by the first network device, wherein the first network device can filter the AI / ML functions according to the current network-side additional conditions (the first condition described above) and the network-side additional conditions (the second condition described above) in the function or model training process of the AI / ML functions to be filtered.

[0194] In the above embodiments, the terminal device can make a decision on the AI / ML functions according to the current terminal-side additional conditions (the third condition described above) and the terminal-side additional conditions (the fourth condition described above) in the training process, or according to the current terminal-side additional conditions (the third condition described above) and the terminal-side additional conditions (the fifth condition described above) in the training process preferred by the first network device, and send third information to the first network device to report the decision result or the filtering result.

[0195] In the above embodiments, the first network device can make a final decision on the AI / ML functions according to the third information sent by the terminal device (i.e., the filtering result reported by the terminal device).

[0196] In some embodiments, the terminal device receives second information sent by the first network device, the second information comprising the AI / ML functions filtered by the first network device, wherein the first network device can filter the AI / ML functions according to the current network-side additional conditions (the first condition described above) and the network-side and terminal-side additional conditions (the second condition described above and the fourth condition described above) in the function or model training process of the AI / ML functions to be filtered.

[0197] In the above embodiments, the terminal device can make a decision on the AI / ML functions according to the current terminal-side additional conditions (the third condition described above) and the terminal-side additional conditions (the fourth condition described above) in the training process, and send third information to the first network device to report the decision result or the filtering result.

[0198] In the above embodiments, the first network device can make a final decision on the AI / ML functions according to the third information sent by the terminal device (i.e., the filtering result reported by the terminal device).

[0199] In some embodiments, the terminal device receives first configuration information sent by the first network device, the first configuration information configuring the terminal device to report terminal-side AI / ML available function information, and the terminal device performs corresponding reporting according to the first configuration information.

[0200] In the above embodiments, the first network device can make a decision on the available AI / ML function according to the third information sent by the terminal device and the additional conditions (the first condition) on the network side at present and the additional conditions (the second condition and the fourth condition) on the network side and the terminal side in the training process.

[0201] The above embodiments only exemplarily illustrate the embodiments of the present application, but the present application is not limited thereto, and can be appropriately modified on the basis of the above embodiments. For example, the above embodiments can be used alone or one or more of the above embodiments can be combined.

[0202] According to the embodiments of the present application, the terminal device and the network device (for example, LMF) can determine the applicability of the AI / ML function on the terminal side by interacting with the AI / ML function related information.

[0203] Embodiments of the third aspect

[0204] The embodiments of the present application provide an AI / ML function information interaction apparatus, which can be a network device or one or more components or assemblies configured in the network device. Since the apparatus has the same problem solving function as the method of the embodiments of the first aspect, the specific implementation can refer to the embodiments of the first aspect, and the same content will not be described repeatedly.

[0205] FIG. 13 is a schematic diagram of an AI / ML function information interaction apparatus according to an embodiment of the present application. As shown in FIG. 13, the apparatus 1300 includes:

[0206] The sending unit 1310 sends first information to the terminal device, the first information including first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to the screened available AI / ML function, and the second information indicating the additional conditions on the network side of the terminal device and / or the available AI / ML function screened according to the additional conditions on the network side;

[0207] The receiving unit 1320 receives third information sent by the terminal device, the third information including fourth information and / or fifth information, the fourth information indicating the available AI / ML function screened by the terminal device, and the fifth information indicating the additional conditions related to the AI / ML function of the terminal device and / or the network device, the additional conditions being used to determine the applicability of the AI / ML function on the terminal device side.

[0208] In some embodiments, the additional conditions include at least one of the following: the additional conditions on the terminal side at present, the additional conditions on the terminal side in the training process, and the additional conditions on the network side in the training process.

[0209] In some embodiments, in a case that the third information comprises the fourth information, the third information further comprises sixth information, the sixth information indicating configuration information corresponding to the available AI / ML function screened by the terminal device; the configuration information is used for at least one of the following operations of the AI / ML function: activation, deactivation, inference, detection, switching, selection, fallback.

[0210] In the above embodiments, the first configuration information, the second information, the fourth information, the fifth information, and the sixth information can be sent through at least one of the following signaling:

[0211] LPP Capability Exchange;

[0212] LPP Assistance Data;

[0213] LPP Location Information;

[0214] Other LPP signaling.

[0215] In some embodiments, as shown in FIG. 13, the apparatus 1300 further comprises:

[0216] The processing unit 1330.

[0217] In some embodiments, the sending unit 1310 sends the first configuration information to the terminal device, the first configuration information does not explicitly configure available AI / ML function screening information, the terminal device screens and reports the available AI / ML function according to a predetermined strategy; the processing unit 1330 makes a decision on the available AI / ML function according to the content reported by the terminal device.

[0218] In some embodiments, the processing unit 1330 screens the available AI / ML function according to the additional condition of the network side at present; the sending unit 1310 sends the first configuration information to the terminal device, the first configuration information comprising the available AI / ML function screened by the first network device and / or the additional condition corresponding to the available AI / ML function screened, the terminal device further screens and reports the available AI / ML function according to the additional condition; the processing unit 1330 makes a decision on the available AI / ML function according to the content reported by the terminal device.

[0219] In some embodiments, the sending unit 1310 sends the second information to the terminal device, the second information comprising the additional condition of the network side at present of the first network device, the terminal device makes a decision on the available AI / ML function according to the additional condition of the network side at present and the local information.

[0220] In the above embodiments, the receiving unit 1320 further receives the available AI / ML function or the available AI / ML function and its corresponding configuration information for the terminal device to make the above decision selection.

[0221] In some embodiments, the sending unit 1310 sends, to at least one terminal device including the above terminal device, a network-side current additional condition of the first network device, and the terminal device makes a decision on the available AI / ML function according to the network-side current additional condition and the local information.

[0222] In the above embodiments, the receiving unit 1320 further receives the request information sent by the terminal device, the request information requesting the first network device to allow the terminal device to report the available AI / ML function screened by the terminal device.

[0223] In the above embodiments, the network-side current additional condition can be sent through positioning-related system broadcast information. The positioning-related broadcast information may, for example, include a positioning system information block (pos-SIB) and / or a master information block / system information block (MIB / SIB).

[0224] In the above embodiments, the sending unit 1310 can further send, to the terminal device, second configuration information configuring the terminal device to report the available AI / ML function screened by the terminal device or to report the available AI / ML function screened by the terminal device and its configuration information.

[0225] In the above embodiments, the second configuration information can also be sent through at least one of the following signaling defined by the LPP (LTE Positioning Protocol) protocol:

[0226] LPP capability exchange signaling (LPP Capability Exchange);

[0227] LPP assistance data signaling (LPP Assistance Data);

[0228] LPP location information signaling (LPP Location Information);

[0229] Other LPP signaling.

[0230] In some embodiments, the processing unit 1330 screens the available AI / ML functions according to the network-side current additional conditions and the network-side additional conditions of the AI / ML functions to be screened in the function or model training process; and the sending unit 1310 sends second information to the terminal device, the second information including the available AI / ML functions screened by the first network device, and the terminal device makes a decision on the available AI / ML functions according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process, and sends third information to the first network device.

[0231] In some embodiments, the processing unit 1330 screens the available AI / ML functions according to the network-side current additional conditions and the network-side additional conditions of the AI / ML functions to be screened in the function or model training process; and the sending unit 1310 sends second information to the terminal device, the second information including the available AI / ML functions screened by the first network device and the terminal-side additional conditions in the training process preferred by the first network device, and the terminal device makes a decision on the available AI / ML functions according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process, or according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process preferred by the first network device, and sends third information to the first network device.

[0232] In the above embodiments, the processing unit 1330 makes a decision on the available AI / ML functions according to the third information sent by the terminal device.

[0233] In some embodiments, the processing unit 1330 screens the available AI / ML functions according to the network-side current additional conditions and the network-side and terminal-side additional conditions of the AI / ML functions to be screened in the function or model training process; and the sending unit 1310 sends second information to the terminal device, the second information including the available AI / ML functions screened by the first network device, and the terminal device makes a decision on the available AI / ML functions according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process, and sends third information to the first network device.

[0234] In the above embodiments, the processing unit 1330 makes a decision on the available AI / ML functions according to the third information sent by the terminal device.

[0235] In some embodiments, the sending unit 1310 sends first configuration information to the terminal device, the first configuration information configuring the terminal device to report terminal-side AI / ML available function information, and the terminal device reports according to the first configuration information.

[0236] In the above embodiments, the processing unit 1330 makes a decision on the available AI / ML function according to the third information sent by the terminal device and the current additional condition of the network side and the additional condition of the network side and the terminal side in the training process.

[0237] Embodiments of the present application also provide an AI / ML function information interaction device. The device may, for example, be a terminal device, or one or more components or assemblies configured in the terminal device. Since the device solves the same problem as the method of the embodiments of the second aspect, the specific implementation can refer to the embodiments of the second aspect, and the same content will not be repeated.

[0238] FIG. 14 is a schematic diagram of an AI / ML function information interaction device according to an embodiment of the present application. As shown in FIG. 14, the device 1400 includes:

[0239] The receiving unit 1410 receives first information sent by a first network device, wherein the first information includes first configuration information and / or second information, the first configuration information configures the terminal device to report information related to the screened available AI / ML function, and the second information indicates the additional condition of the terminal device network side and / or the available AI / ML function screened according to the additional condition of the network side.

[0240] The sending unit 1420 sends third information to the first network device, wherein the third information includes fourth information and / or fifth information, the fourth information indicates the available AI / ML function screened by the terminal device, and the fifth information indicates the additional condition of the AI / ML function related to the terminal device and / or the network device, which is used to determine the availability of the AI / ML function on the terminal device side.

[0241] In some embodiments, the additional condition includes at least one of the following: the current additional condition of the terminal side, the additional condition of the terminal side in the training process, and the additional condition of the network side in the training process.

[0242] In some embodiments, when the third information includes the fourth information, the third information further includes sixth information, the sixth information indicates the configuration information corresponding to the available AI / ML function screened by the terminal device; and the configuration information is used for at least one of the following operations of the AI / ML function: activation, deactivation, inference, detection, switching, selection, and fallback.

[0243] In some embodiments, the first configuration information, the second information, the fourth information, the fifth information, and the sixth information are sent through at least one of the following signaling defined by the LPP protocol:

[0244] LPP capability exchange signaling (LPP Capability Exchange);

[0245] LPP assistance data signaling (LPP Assistance Data);

[0246] LPP location information signaling (LPP Location Information);

[0247] Other LPP signaling.

[0248] In some embodiments, as shown in FIG. 14, the apparatus 1400 further includes:

[0249] The processing unit 1430.

[0250] In some embodiments, the receiving unit 1410 receives first configuration information sent by the first network device, the first configuration information not explicitly configuring available AI / ML function screening information, the processing unit 1430 and the sending unit 1420 respectively screening and reporting the available AI / ML function according to a predetermined policy, and the first network device making a decision on the available AI / ML function according to the content reported by the terminal device.

[0251] In some embodiments, the receiving unit 1410 receives first configuration information sent by the first network device, the first configuration information including available AI / ML functions screened by the first network device according to current additional conditions on the network side and / or additional conditions corresponding to the screened available AI / ML functions, the processing unit 1430 and the sending unit 1420 respectively further screening and reporting the available AI / ML functions screened by the first network device according to the above additional conditions, and the first network device making a decision on the available AI / ML function according to the content reported by the terminal device.

[0252] In some embodiments, the receiving unit 1410 receives second information sent by the first network device, the second information including current additional conditions on the network side of the first network device, and the processing unit 1430 making a decision on the available AI / ML function according to the current additional conditions on the network side and local information.

[0253] In the above embodiments, the sending unit 1420 can further report, to the first network device, available AI / ML functions on which the processing unit 1430 makes the above decision selection or the available AI / ML functions and configuration information corresponding thereto.

[0254] In some embodiments, the receiving unit 1410 receives current additional conditions on the network side sent by the first network device to at least one terminal device including the above terminal device, the processing unit 1430 makes a decision on the available AI / ML function according to the current additional conditions on the network side and local information, and the sending unit 1420 sends request information to the first network device, requesting the first network device to allow the above terminal device to report the available AI / ML functions screened by the terminal device.

[0255] In the above embodiments, the above network side current additional condition can be sent through positioning related system broadcast information. The positioning related broadcast information can include, for example, a positioning system information block (pos-SIB) and / or a master information block / system information block (MIB / SIB) transmission.

[0256] In the above embodiments, the receiving unit 1410 can also receive second configuration information sent by the first network device, the second configuration information configuring the terminal device to report the terminal device screened available AI / ML function or to report the terminal device screened available AI / ML function and its configuration information.

[0257] In the above embodiments, the second configuration information can be sent through at least one of the following signaling defined by the LPP (LTE Positioning Protocol) protocol:

[0258] LPP capability interaction signaling (LPP Capability Exchange);

[0259] LPP assistance data signaling (LPP Assistance Data);

[0260] LPP location information signaling (LPP Location Information);

[0261] Other LPP signaling.

[0262] In some embodiments, the receiving unit 1410 receives second information sent by the first network device, the second information including the available AI / ML function screened by the first network device, the processing unit 1430 makes a decision on the available AI / ML function according to the terminal side current additional condition and the terminal side additional condition in the training process, and the sending unit 1420 sends third information to the first network device; wherein the first network device screens the available AI / ML function according to the network side current additional condition and the network side additional condition of the AI / ML function to be screened in the function or model training process.

[0263] In some embodiments, the receiving unit 1410 receives second information sent by the first network device, the second information including available AI / ML functions screened by the first network device and terminal-side additional conditions in the training process preferred by the first network device, the processing unit 1430 makes a decision on the available AI / ML functions according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process, or according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process preferred by the first network device, and the sending unit 1420 sends the above-mentioned third information to the first network device; wherein the first network device screens the available AI / ML functions according to the network-side current additional conditions and the network-side additional conditions in the function or model training process of the AI / ML functions to be screened; and wherein the first network device makes a decision on the available AI / ML functions according to the above-mentioned third information sent by the terminal device.

[0264] In some embodiments, the receiving unit 1410 receives second information sent by the first network device, the second information including available AI / ML functions screened by the first network device, the processing unit 1430 makes a decision on the available AI / ML functions according to the terminal-side current additional conditions and the terminal-side additional conditions in the training process, and the sending unit 1420 sends the above-mentioned third information to the first network device; wherein the first network device screens the available AI / ML functions according to the network-side current additional conditions and the network-side and terminal-side additional conditions in the function or model training process of the AI / ML functions to be screened; and wherein the first network device makes a decision on the available AI / ML functions according to the above-mentioned third information sent by the terminal device.

[0265] In some embodiments, the receiving unit 1410 receives first configuration information sent by the first network device, the first configuration information configuring the terminal device to report terminal-side AI / ML available function information, and the sending unit 1420 reports according to the first configuration information; wherein the first network device makes a decision on the available AI / ML functions according to the above-mentioned third information sent by the terminal device and the network-side current additional conditions and the network-side and terminal-side additional conditions in the training process.

[0266] It is worth noting that the above Figs. 13 and 14 only schematically illustrate the embodiments of the present application, but the present application is not limited thereto. For example, some other modules or components can be appropriately added or some of them can be appropriately reduced. Those skilled in the art can make appropriate modifications according to the above content, and it is not limited to the description of the above Figs. 13 and 14.

[0267] In addition, for the sake of simplicity, only the connection relationship or signal direction between each component or module is exemplarily shown in FIGS. 13 and 14, but it should be clear to those skilled in the art that various related technologies such as bus connection can be adopted. Each component or module described above can be implemented by hardware facilities such as a processor, a memory, a transmitter, a receiver, etc.; the implementation of the present application is not limited thereto.

[0268] The above embodiments are only exemplarily described for the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, each of the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0269] According to the embodiments of the present application, the terminal device and the network device can determine the applicability of the AI / ML function on the terminal side by interacting with the AI / ML function related information.

[0270] Embodiments of the fourth aspect

[0271] The embodiments of the present application provide a communication system, which can be referred to FIG. 1, and the same content as the embodiments of the first aspect will not be described herein.

[0272] In some embodiments, the communication system 100 can at least include a network device 101 and terminal devices 102 and 103, in some embodiments, the network device 101 performs the functions of the first network device in the embodiments of the first aspect and the second aspect, and correspondingly, the terminal devices 102 and 103 perform the functions of the terminal device in the embodiments of the first aspect and the second aspect. Since the first network device and the terminal device have been described in the embodiments of the first aspect and the second aspect, the content is incorporated herein, and will not be described herein.

[0273] The embodiments of the present application further provide a network device.

[0274] FIG. 15 is a schematic block diagram of the system structure of the network device according to the embodiments of the present application. As shown in FIG. 15, the network device 1500 can include a processor 1510 and a memory 1520; the memory 1520 is coupled to the processor 1510. The memory 1520 can store various data; in addition, it also stores a program 1530 for information processing, and executes the program 1530 under the control of the processor 1510.

[0275] In an embodiment, the network device 1500 as the first network device in the embodiments of the first aspect and the second aspect comprises the functions of the apparatus 1300 in the embodiments of the third aspect, which can be integrated into the processor 1510 or configured separately from the processor 1510, for example, the apparatus 1300 can be configured as a chip connected with the processor 1510 to realize the functions of the apparatus by the control of the processor 1510.

[0276] In addition, as shown in FIG. 15, the network device 1500 can further include a transceiver 1540, an antenna 1550, etc.; wherein the functions of the above components are similar to the prior art, which will not be repeated here. It is worth noting that the network device 1500 does not necessarily include all the components shown in FIG. 15; in addition, the network device 1500 can also include components not shown in FIG. 15, which can be referred to the prior art.

[0277] The embodiments of the present application also provide a terminal device.

[0278] FIG. 16 is a schematic block diagram of the system structure of the terminal device according to the embodiments of the present application. As shown in FIG. 16, the terminal device 1600 can include a processor 1610 and a memory 1620; the memory 1620 is coupled to the processor 1610. It is worth noting that this figure is exemplary; other types of structures can also be used to supplement or replace this structure to realize telecommunication functions or other functions.

[0279] In an embodiment, the terminal device 1600 as the terminal device in the embodiments of the first aspect and the second aspect comprises the functions of the apparatus 1400 in the embodiments of the third aspect, which can be integrated into the processor 1610 or configured separately from the processor 1610, for example, the apparatus 1400 can be configured as a chip connected with the processor 1610 to realize the functions of the apparatus by the control of the processor 1610.

[0280] As shown in FIG. 16, the terminal device 1600 can further include a communication module 1630, an input unit 1640, a display 1650, and a power supply 1660. It is worth noting that the terminal device 1600 does not necessarily include all the components shown in FIG. 16; in addition, the terminal device 1600 can also include components not shown in FIG. 16, which can be referred to the related art.

[0281] As shown in FIG. 16, the processor 1610, also known as a controller or operation control, can include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of each component of the terminal device 1600.

[0282] The memory 1620, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. Various data can be stored, and further programs for performing related information can be stored. The processor 1610 can execute the programs stored in the memory 1620 to achieve information storage or processing, and the like. The functions of other components are similar to the existing, and will not be described here. The components of the terminal device 1600 can be implemented by dedicated hardware, firmware, software, or a combination thereof, without departing from the scope of the present application.

[0283] The embodiments of the present application further provide a computer readable program, which, when executed in a network device, causes a computer to execute the method of the embodiments of the first aspect in the network device.

[0284] The embodiments of the present application further provide a storage medium storing a computer readable program, which causes a computer to execute the method of the embodiments of the first aspect in a network device.

[0285] The embodiments of the present application further provide a computer readable program, which, when executed in a terminal device, causes a computer to execute the method of the embodiments of the second aspect in the terminal device.

[0286] The embodiments of the present application further provide a storage medium storing a computer readable program, which causes a computer to execute the method of the embodiments of the second aspect in a terminal device.

[0287] The embodiments of the present application further provide a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the method of the embodiments of the first aspect or the second aspect.

[0288] The above apparatus and method of the present application can be implemented by hardware, or by hardware in combination with software. The present application relates to a computer readable program, which, when executed by a logic component, can cause the logic component to implement the above-described apparatus or constituent components, or to implement the above-described various methods or steps. The logic component is, for example, a field programmable logic component, a microprocessor, a processor used in a computer, and the like. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, and the like.

[0289] The method / apparatus described in conjunction with the embodiments of the present application can be directly embodied as hardware, software modules executed by a processor or a combination thereof. For example, one or more of the functional blocks shown in the figures and / or one or more combinations of the functional blocks can correspond to individual software modules of a computer program flow, and can also correspond to individual hardware modules. The software modules can correspond to individual steps shown in the figures, respectively. The hardware modules can be implemented by, for example, fixing the software modules with a field programmable gate array (FPGA).

[0290] The software modules can be located in the RAM memory, the flash memory, the ROM memory, the EPROM memory, the EEPROM memory, the register, the hard disk, the mobile disk, the CD-ROM, or any other form of storage medium known in the art. One storage medium can be coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium can be an integral part of the processor. The processor and the storage medium can be located in an ASIC. The software modules can be stored in the memory of the mobile terminal, or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a MEGA-SIM card or a large-capacity flash memory device, the software modules can be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0291] One or more of the functional blocks described in conjunction with the figures and / or one or more combinations of the functional blocks can be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof, for performing the functions described in the present application. One or more of the functional blocks described in conjunction with the figures and / or one or more combinations of the functional blocks can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0292] The present application has been described above with reference to specific embodiments. However, it should be understood by those skilled in the art that the descriptions are exemplary and are not intended to limit the scope of the present application. Those skilled in the art can make various modifications and changes to the present application based on the spirit and principles of the present application, and such modifications and changes are within the scope of the present application.

[0293] In addition to the above embodiments disclosed in the present embodiment, the following notes are also disclosed:

[0294] 1.A network device comprising a memory and a processor, the memory storing a computer program, and the processor configured to execute the computer program to implement the following method:

[0295] sending, to a terminal device, first information, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to a filtered available AI / ML function, and the second information indicating a network-side additional condition and / or a filtered available AI / ML function according to the network-side additional condition;

[0296] receiving third information sent by the terminal device, the third information comprising fourth information and / or fifth information, the fourth information indicating a filtered available AI / ML function of the terminal device, and the fifth information indicating an additional condition related to an AI / ML function of the terminal device and / or the network device, the additional condition being used to determine availability of the AI / ML function on the terminal device side.

[0297] 2.A terminal device comprising a memory and a processor, the memory storing a computer program, and the processor configured to execute the computer program to implement the following method:

[0298] receiving first information sent by a first network device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to a filtered available AI / ML function, and the second information indicating a network-side additional condition and / or a filtered available AI / ML function according to the network-side additional condition;

[0299] sending, to the first network device, third information, the third information comprising fourth information and / or fifth information, the fourth information indicating a filtered available AI / ML function of the terminal device, and the fifth information indicating an additional condition related to an AI / ML function of the terminal device and / or the network device, the additional condition being used to determine availability of the AI / ML function on the terminal device side.

[0300] 3.A communication system comprising the network device of clause 1 and the terminal device of clause 2.

Claims

1. An apparatus for interaction of AI / ML function information, configured in a first network device, wherein, The apparatus comprises: a sending unit configured to send first information to a terminal device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to screened available AI / ML functions, and the second information indicating network-side additional conditions and / or available AI / ML functions screened according to the network-side additional conditions; a receiving unit configured to receive third information sent by the terminal device, the third information comprising fourth information and / or fifth information, the fourth information indicating available AI / ML functions screened by the terminal device, and the fifth information indicating additional conditions related to AI / ML functions of the terminal device and / or a network device, the additional conditions being used to determine the availability of AI / ML functions on the terminal device side.

2. The apparatus of claim 1, wherein, The additional conditions comprise at least one of: current additional conditions on the terminal side; additional conditions on the terminal side during a training process; additional conditions on the network side during a training process.

3. The apparatus according to claim 1, wherein the third information further comprises sixth information, the sixth information indicating configuration information corresponding to the available AI / ML functions screened by the terminal device; the configuration information is used for at least one of the following operations of the AI / ML functions: activation, deactivation, inference, detection, switching, selection, and fallback.

4. The apparatus according to claim 1, wherein the apparatus further comprises a processing unit; the first configuration information does not explicitly configure available AI / ML function screening information, and the terminal device screens and reports available AI / ML functions according to a predetermined strategy; the processing unit makes a decision on available AI / ML functions according to the content reported by the terminal device.

5. The apparatus according to claim 1, wherein the apparatus further comprises a processing unit configured to screen available AI / ML functions according to current additional conditions on the network side; the first configuration information comprises available AI / ML functions screened by the first network device and / or additional conditions corresponding to the screened available AI / ML functions, and the terminal device further screens and reports available AI / ML functions according to the first configuration information; the processing unit makes a decision on available AI / ML functions according to the content reported by the terminal device.

6. The apparatus according to claim 1, wherein the second information comprises current additional conditions on the network side of the first network device, and the terminal device makes a decision on available AI / ML functions according to the current additional conditions on the network side and local information.

7. The apparatus according to claim 6, wherein the receiving unit further receives available AI / ML functions selected by the terminal device for the decision or the available AI / ML functions and configuration information corresponding to the available AI / ML functions.

8. The apparatus according to claim 1, wherein The sending unit sends the current network side additional condition of the first network device to at least one terminal device including the terminal device, and the terminal device makes a decision on the available AI / ML function according to the current network side additional condition and local information; The receiving unit also receives request information sent by the terminal device, and the request information requests the first network device to allow the terminal device to report the available AI / ML function screened by the terminal device.

9. The apparatus of claim 8, wherein, The sending unit further sends second configuration information to the terminal device, and the second configuration information configures the terminal device to report the available AI / ML function screened by the terminal device or to report the available AI / ML function screened by the terminal device and configuration information thereof.

10. The apparatus of claim 1, wherein, The apparatus further comprises a processing unit; The processing unit screens the available AI / ML function according to the current network side additional condition and the network side additional condition of the AI / ML function to be screened in a function or model training process; The second information comprises the available AI / ML function screened by the first network device, and the terminal device makes a decision on the available AI / ML function according to the current terminal side additional condition and the terminal side additional condition in the training process, and sends the third information to the first network device.

11. The apparatus of claim 1, wherein, The apparatus further comprises a processing unit; The processing unit screens the available AI / ML function according to the current network side additional condition and the network side additional condition of the AI / ML function to be screened in a function or model training process; The second information comprises the available AI / ML function screened by the first network device and the terminal side additional condition in the training process preferred by the first network device, and the terminal device makes a decision on the available AI / ML function according to the current terminal side additional condition and the terminal side additional condition in the training process, or according to the current terminal side additional condition and the terminal side additional condition in the training process preferred by the first network device, and sends the third information to the first network device; The processing unit makes a decision on the available AI / ML function according to the third information sent by the terminal device.

12. The apparatus of claim 1, wherein, The apparatus further comprises a processing unit; The processing unit screens the available AI / ML function according to the current network side additional condition and the network side and terminal side additional conditions of the AI / ML function to be screened in a function or model training process; The second information comprises the available AI / ML function screened by the first network device, and the terminal device makes a decision on the available AI / ML function according to the current terminal side additional condition and the terminal side additional condition in the training process, and sends the third information to the first network device; The processing unit makes a decision on the available AI / ML function according to the third information sent by the terminal device.

13. The apparatus of claim 1, wherein, the apparatus further comprises a processing unit; the first configuration information configures the terminal device to report terminal-side AI / ML available function information, and the terminal device reports according to the first configuration information; the processing unit decides available AI / ML function according to the third information sent by the terminal device and network-side current additional conditions and network-side and terminal-side additional conditions in training process. 14.An apparatus for interaction of AI / ML function information, configured in a terminal device, wherein, the apparatus comprises: a receiving unit that receives first information sent by a first network device, the first information comprising first configuration information and / or second information, the first configuration information configuring the terminal device to report information related to screened available AI / ML function, and the second information indicating network-side additional conditions of the terminal device and / or available AI / ML function screened according to the network-side additional conditions; a sending unit that sends third information to the first network device, the third information comprising fourth information and / or fifth information, the fourth information indicating available AI / ML function screened by the terminal device, and the fifth information indicating additional conditions related to AI / ML function of the terminal device and / or network device, the additional conditions being used to determine availability of terminal device-side AI / ML function.

15. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the first configuration information does not explicitly configure available AI / ML function screening information, the processing unit and the sending unit respectively screen and report available AI / ML function according to a predetermined strategy, and the first network device decides available AI / ML function according to the content reported by the terminal device.

16. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the first configuration information comprises available AI / ML function screened by the first network device according to network-side current additional conditions and / or additional conditions corresponding to the screened available AI / ML function, the processing unit and the sending unit further screen and report the available AI / ML function screened by the first network device according to the additional conditions, and the first network device decides available AI / ML function according to the content reported by the terminal device.

17. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the second information comprises network-side current additional conditions of the first network device, the processing unit decides available AI / ML function according to the network-side current additional conditions and local information.

18. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the receiving unit receives network-side current additional conditions sent by the first network device to at least one terminal device including the terminal device; the processing unit decides available AI / ML function according to the network-side current additional conditions and local information. The sending unit sends request information to the first network device, the request information requesting the first network device to allow the terminal device to report the available AI / ML function screened by the terminal device.

19. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the second information comprises the available AI / ML function screened by the first network device; the processing unit makes a decision on the available AI / ML function according to the additional condition on the terminal side at present and the additional condition on the terminal side in the training process, and sends the third information to the first network device; wherein the first network device screens the available AI / ML function according to the additional condition on the network side at present and the additional condition on the network side in the function or model training process of the AI / ML function to be screened; or, the second information comprises the available AI / ML function screened by the first network device and the additional condition on the terminal side in the training process preferred by the first network device; the processing unit makes a decision on the available AI / ML function according to the additional condition on the terminal side at present and the additional condition on the terminal side in the training process, or according to the additional condition on the terminal side at present and the additional condition on the terminal side in the training process preferred by the first network device, and sends the third information to the first network device; wherein the first network device screens the available AI / ML function according to the additional condition on the network side at present and the additional condition on the network side in the function or model training process of the AI / ML function to be screened; and wherein the first network device makes a decision on the available AI / ML function according to the third information sent by the terminal device; or, the second information comprises the available AI / ML function screened by the first network device; the processing unit makes a decision on the available AI / ML function according to the additional condition on the terminal side at present and the additional condition on the terminal side in the training process, and sends the third information to the first network device; wherein the first network device screens the available AI / ML function according to the additional condition on the network side at present and the additional condition on the network side and the additional condition on the terminal side in the function or model training process of the AI / ML function to be screened; and wherein the first network device makes a decision on the available AI / ML function according to the third information sent by the terminal device.

20. The apparatus of claim 14, wherein, the apparatus further comprises a processing unit; the first configuration information configures the terminal device to report the AI / ML available function information on the terminal side; the sending unit reports according to the first configuration information; wherein the first network device makes a decision on the available AI / ML function according to the third information sent by the terminal device and the additional condition on the network side at present and the additional condition on the network side and the additional condition on the terminal side in the training process.

Images