Devices and methods for communication
By aligning associated identities through negotiation between network devices, the solution addresses inconsistencies in ML model life cycles, improving performance and robustness in diverse network scenarios.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2026-04-02
AI Technical Summary
Existing communication systems face challenges in ensuring consistency between different phases of an ML model's life cycle, particularly in maintaining robust performance across diverse network scenarios due to inconsistent network conditions, leading to issues with associated identity alignment.
A solution is proposed to align associated identities by receiving and determining relations between identities configured by different network devices, allowing for the transmission of information to handle these identities effectively, thereby resolving collisions through negotiation between devices.
This approach ensures consistent model training and inference by aligning associated identities, enhancing the robustness and performance of ML models across varying network conditions.
Smart Images

Figure CN2024122581_02042026_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS FOR COMMUNICATION
[0001] FIELDS
[0002] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices and methods for associated identity alignment.BACKGROUND
[0003] With developments in the integration of artificial intelligence (AI) / machine learning (ML) within the fifth generation (5G) and emerging sixth generation (6G) new radio (NR) air interface, a new frontier in network adaptability and efficiency is being explored. The 3rd generation partner project (3GPP) Release-18 study item and 3GPP Release-19 work item emphasize the importance of model generalization across various network scenarios, addressing the need for AI / ML models to maintain robust performance under diverse conditions. This includes the strategic incorporation of additional conditions to refine model training, ensuring models are well-suited to both network-side and user equipment-side requirements. There may be a plurality of phases during a life cycle of an ML model. It is important to ensure the consistency between different phases such as training and inference.SUMMARY
[0004] In general, embodiments of the present disclosure provide a solution for associated identity alignment.
[0005] In a first aspect, there is provided a first network device. The first network device comprises: a processor configured to cause the first network device to: receive, from a communication device, first information related to a first associated identity corresponding to a first additional network condition; determine, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; and transmit, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.
[0006] In a second aspect, there is provided a communication device. The communication device comprises: a processor configured to cause the communication device to: transmit, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; and receive, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.
[0007] In a third aspect, there is provided a terminal device. The terminal device comprises: a processor configured to cause the terminal device to: receive, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; and train the ML model entity based on mapping between the set of associated identities and the set of training configurations.
[0008] In a fourth aspect, there is provided a network device. The network device comprises: a processor configured to cause the network device to: transmit, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations.
[0009] In a fifth aspect, there is provided a communication method performed by a first network device. The method comprises: receiving, from a communication device, first information related to a first associated identity corresponding to a first additional network condition; determining, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; and transmitting, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.
[0010] In a sixth aspect, there is provided a communication method performed by a communication device. The method comprises: transmitting, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; and receiving, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.
[0011] In a seventh aspect, there is provided a communication method performed by a terminal device. The method comprises: receiving, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; and training the ML model entity based on mapping between the set of associated identities and the set of training configurations.
[0012] In an eighth aspect, there is provided a communication method performed by a network device. The method comprises: transmitting, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations.
[0013] In a ninth aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to the fifth, sixth, seventh, or eighth aspect.
[0014] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Through the more detailed description of some example embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:
[0016] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;
[0017] FIG. 2 illustrates an example diagram of different options of relationship between model IDs and associated IDs;
[0018] FIG. 3 illustrates a signaling flows of communication in accordance with some example embodiments of the present disclosure;
[0019] FIG. 4 illustrates a signaling flows of communication in accordance with some example embodiments of the present disclosure;
[0020] FIG. 5 illustrates a signaling flows of communication in accordance with some example embodiments of the present disclosure;
[0021] FIG. 6 illustrates a signaling flows of communication in accordance with some example embodiments of the present disclosure;
[0022] FIG. 7 illustrates a signaling flows of communication in accordance with some example embodiments of the present disclosure;
[0023] FIG. 8 illustrates a flowchart of a communication method implemented at a first network device according to some example embodiments of the present disclosure;
[0024] FIG. 9 illustrates a flowchart of a communication method implemented at a communication device according to some example embodiments of the present disclosure;
[0025] FIG. 10 illustrates a flowchart of a communication method implemented at a terminal device according to some example embodiments of the present disclosure;
[0026] FIG. 11 illustrates a flowchart of a communication method implemented at a network device according to some example embodiments of the present disclosure; and
[0027] FIG. 12 illustrates a simplified block diagram of an apparatus that is suitable for implementing example embodiments of the present disclosure.
[0028] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0029] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.
[0030] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
[0031] As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, devices on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure / network, devices for Integrated Access and Backhaul (IAB) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further have ‘multicast / broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.
[0032] The term “network device” refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , and the like.
[0033] The terminal device or the network device may have Artificial intelligence (AI) or Machine learning capability. It generally includes a model which has been trained from numerous collected data for a specific function and can be used to predict some information.
[0034] The terminal or the network device may work on several frequency ranges, e.g., FR1 (e.g., 450 MHz to 6000 MHz) , FR2 (e.g., 24.25GHz to 52.6GHz) , frequency band larger than 100 GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0035] The embodiments of the present disclosure may be performed in test equipment, e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator. In some embodiments, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In some embodiments, the first network device may be a first RAT device, and the second network device may be a second RAT device. In some embodiments, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device or the second network device. In some embodiments, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In some embodiments, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
[0036] As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term “includes” and its variants are to be read as open terms that mean “includes, but is not limited to” . The term “based on” is to be read as “at least in part based on” . The term “one embodiment” and “an embodiment” are to be read as “at least one embodiment” . The term “another embodiment” is to be read as “at least one other embodiment” . The terms “first” , “second” and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.
[0037] In some examples, values, procedures, or apparatus are referred to as “best” , “lowest” , “highest” , “minimum” , “maximum” or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.
[0038] As used herein, the term “resource” , “transmission resource” , “uplink resource” , or “downlink resource” may refer to any resource for performing a communication, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.
[0039] As used herein, the term “AI / ML model” may refer to a data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. In the context of the present disclosure, the term “AI / ML model” may be interchangeably with the terms “model” , “AI model” and “ML model” .
[0040] As used herein, the term “AI / ML model entity” may refer to an AI / ML model or a functionality enabled with an AI / ML model.
[0041] The term “UE-side (AI / ML) model” used herein may refer to an AI / ML Model of which inference is performed entirely at the UE. The term “network-side (AI / ML) model” used herein may refer to an AI / ML Model of which inference is performed entirely at the network. The term “one-sided (AI / ML) model” used herein may refer to a UE-side (AI / ML) model or a network-side (AI / ML) model. The term “two-sided (AI / ML) model” used herein may refer to a paired AI / ML Model (s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e., the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.
[0042] As discussed above, there may be a plurality of phases during a life cycle of an ML model. It is important to ensure the consistency between different phases such as training and inference, for example, ensuring the consistency at least between model training and model inference to address the impact of the changes of NW-side additional conditions.
[0043] In addition, a working assumption regarding “associated identity, ID” has been agreed to indicate NW-side additional condition used for consistency indication between model training and model inference. Thus, it is necessary to ensure UE performs correct model inference and model monitoring procedure under the basis of multiple associated ID conditions.
[0044] Regarding the associated ID, the UE may assume that NW-side additional conditions with the same associated ID are consistent at least within a cell. For UE part of two-sided model, the following example for model identification may be studied: A) a dataset is transferred from the NW / NW-side to UE / UE-side via standardized signaling; B) UE part of two-sided model (s) is (are) developed based on at least the above dataset; C) UE reports information of its UE part of two-sided model (s) corresponding to the above dataset to the NW.
[0045] From radio access network1 (RAN1) perspective, for UE-sided model (s) developed (e.g., trained, updated) at UE side, following procedure is an example (noted as AI-Example1) of MI-Option1 for further study (including the feasibility / necessity) :
[0046] A: For data collection, NW signals the data collection related configuration (s) and it / their associated ID (s) ; Associated IDs for each sub use case in relation with NW-sided additional conditions.
[0047] B: UE (s) collects the data corresponding to the associated ID (s) .
[0048] C: AI / ML models are developed (e.g., trained, updated) at UE side based on the collected data corresponding to the associated ID (s) .
[0049] D: UE reports information of its AI / ML models corresponding to associated IDs to the NW. Model ID is determined / assigned for each AI / ML model. The information may comprise relationship between model ID (s) and the associated ID (s) . Below alternatives may be used for determining / assigning the model ID (s) : Alt. 1: NW assigns Model ID; Alt. 2: UE assigns / reports Model ID; Alt. 3: Associated ID (s) is assumed as model ID (s) , where “Model ID is determined / assigned for each AI / ML model” is not needed; Alt. 4: Model ID is determined by pre-defined rule (s) in the specification
[0050] The above Step A / B / C and additional interaction of associated IDs between UE and NW may be considered as a different solution for resolving the consistency without model identification.
[0051] For the consistency of NW-side additional condition across training and inference for UE-sided model for BM Case 1 and BM Case 2, where the NW-side additional condition may at least impact UE assumption on beams of Set A / Set B, further study associated ID based option and performance monitoring-based option.
[0052] It is expected to support functionality activation / deactivation after inference configuration. The UE will indicate the gNB / location management function (LMF) whether the AI / ML functionality is available / applicable. For a functionality to be applicable at least there should at least one model available within it. For NW-side additional conditions, RRC signaling from gNB to UE can be designed for consistency between inference and training. RAN2 will wait for RAN1 input for further details. For BM use case, as a baseline the UE determines whether a functionality is applicable. Existing UE Assistance Information (UAI) framework is used at least for proactive reporting of applicable functionality.
[0053] Current 3GPP meeting discusses how to provide NW-side additional conditions by the network to a UE. The procedure may include the following steps.
[0054] At step 1, the network sends UECapabilityEnqiry message to initiate the procedure to the UE reporting its AI / ML supported functionalities.
[0055] At step 2, the UE sends UECapablityInformation message to the network, containing supported functionalities at the UE side.
[0056] At step 3, following configurations are provided from the network to the UE:
[0057] 1) the UE is allowed to do UAI reporting via OtherConfig; and
[0058] 2) the Network may provide NW-side additional condition.
[0059] The UE decides the applicable functionalities based on NW-side additional conditions (if provided) , UE-side additional conditions (internally known by UE) and model availability in device.
[0060] At step 4, the UE reports applicable functionality in the following scenarios:
[0061] 1) upon being configured to provide applicable functionality and upon change of applicable functionality via UAI; and
[0062] 2) in response to NW-side additional condition requesting applicable functionality reporting in step 3.
[0063] At step 5, the network configures inference configuration to the UE after applicable functionality reporting, if inference configuration based on supported functionality is not provided in Step 3 (i.e. inference configuration is provided in Step 5) . If inference configuration based on supported functionality is provided in Step 3, it is up to network implementation whether to provide an updated configuration or not. The applicable functionality may be activated by receiving its inference configuration when it is provided in Step 5.
[0064] Currently RAN1 / 2 is discussing how to ensure the consistency between model training and model inference. Also, RAN2 has discussed how the network would configure the NW-side additional conditions towards the UE during the model inference configuration procedure. However, it is still unclear how UE would acquire NW-side additional conditions during model training configuration procedure so that the consistency handling is not completed.
[0065] According to the embodiments of the present disclosure, a solution for associated identity alignment is proposed. In a solution, first information is received from a communication device. The first information is related to a first associated identity corresponding to a first additional network condition. a relation between the first associated identity and a second associated identity corresponding to a second additional network condition is determined based on the first information. The first associated identity and the second associated identity are configured by different network devices. Second information is transmitted to the communication device based on the relation. The second information is configured for handling at least one of the first associated identity or the second associated identity. In this way, the collision issue of associated IDs can be resolved through negotiation between devices.
[0066] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0067] FIG. 1 shows an example communication environment 100 in which example embodiments of the present disclosure can be implemented. The communication environment 100 comprises a terminal device 110, a network device 120 and a network device 130. Additionally, the network device 120 and network device 130 may provide a plurality of coverage areas, called as cells. In the example of FIG. 1, the network device 120 may provide a cell 122, and the network device 130 may provide a cell 132.
[0068] Further, in the actual communication scenario, the terminal device 110 may move over, which cause a cell switch. In the example of FIG. 1, as moving, the terminal device 110 may switch from the cell 122 provided by the network device 120 to the cell 132 provided by the network device 130.
[0069] In the environment 100, a link from the network device 120 to the terminal device 110 is referred to as a downlink, while a link from the terminal device 110 to the network device 120 is referred to as an uplink. In downlink, the network device is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or a receiver) . In uplink, the terminal device 110 is a transmitting TX device (or a transmitter) and the network device is a RX device (or a receiver) .
[0070] It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing example embodiments of the present disclosure.
[0071] In some embodiments, the terminal device 110 and the network device 120 may communicate with each other via a channel such as a wireless communication channel on an air interface (e.g., Uu interface) . The wireless communication channel may comprise a physical uplink control channel (PUCCH) , a physical uplink shared channel (PUSCH) , a physical random-access channel (PRACH) , a physical downlink control channel (PDCCH) , a physical downlink shared channel (PDSCH) and a physical broadcast channel (PBCH) . Of course, any other suitable channels are also feasible.
[0072] The communications in the communication environment 100 may conform to any suitable standards including, but not limited to, Global System for Mobile Communications (GSM) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , New Radio (NR) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , GSM EDGE Radio Access Network (GERAN) , Machine Type Communication (MTC) and the like. The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or the sixth generation (6G) networks.
[0073] As discussed above, associated ID has been agreed to indicate NW-side additional condition. The associated ID at least may be local ID, and global cell identity (GCI) may be used together with the associated ID.
[0074] Regarding the relationship between model ID (s) and the associated ID (s) , there may be below options:
[0075] Option1: One model ID is linked to one associated ID by one-to-one mapping.
[0076] Option2: One model ID may be linked to multiple associated IDs and each associated ID is only be linked to one model ID.
[0077] Option3: One associated ID (s) may be linked to multiple model IDs and each model ID is only linked to one associated ID.
[0078] Option4: Model ID (s) may be linked to associated ID (s) by many-to-many mapping.
[0079] Reference is now made to FIG. 2, which illustrates an example diagram 200 of different options of relationship between model IDs and associated IDs. In real communication scenarios, it is possible that one model is associated with multiple associated IDs for one dataset used for model training, since one model is expected to be applicable for different network additional conditions. According to the embodiments of the present disclosure, a solution for ensuring consistency for life cycle management (LCM) procedures is proposed, especially for Option 2.
[0080] Reference is now made to FIG. 3, which illustrates a signaling flow 300 of communication in accordance with some example embodiments of the present disclosure. The signaling flow 300 involves a source network device 320 (also referred to as a second network device) and a target network device 330 (also referred to as a first network device or a serving network device) .
[0081] For ease of discussion, FIG. 3 which will be described with reference to FIG. 1, for example, by taking the source network device 320 as an example of the network device 120, taking the target network device 330 as an example of the network device 130 and using optionally the terminal device 110. As the terminal device 110 moves, it may perform a handover procedure from the cell 122 provided by the source network device 320 to the cell 132 provided by the target network device 330.
[0082] In the following descriptions, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0083] It is to be understood that the operations at the terminal device 110 and the network device 120 should be coordinated. In other words, the network device 120 and the terminal device 110 should have common understanding about configurations, parameters and so on. Such common understanding may be implemented by any suitable interactions between the network device 120 and the terminal device 110 or both the network device 120 and the terminal device 110 applying the same rule / policy. In the following, although some operations are described from a perspective of the terminal device 110, it is to be understood that the corresponding operations should be performed by the network device 120. Similarly, although some operations are described from a perspective of the network device 120, it is to be understood that the corresponding operations should be performed by the terminal device 110. Merely for brevity, some of the same or similar contents are omitted here.
[0084] In addition, in the following description, some interactions are performed among the terminal device 110 and the network device 120 (such as, exchanging configuration (s) and so on) . It is to be understood that the interactions may be implemented either in one single signaling / message / configuration or multiple signaling / messages / configurations, including system information, radio resource control (RRC) message, downlink control information (DCI) message, uplink control information (UCI) message, media access control (MAC) control element (CE) and so on. The present disclosure is not limited in this regard.
[0085] It is noted that configuration information discussed below may be transmitted in a single message or more than one message. The present disclosure is not limited in this regard.
[0086] As mentioned above, the terminal device 110 may perform the handover procedure. Before performing the handover procedure, a first associated ID is configured by the source network device 320 to the terminal device 110.
[0087] As shown in FIG. 3, during the handover procedure of the terminal device 110, the source network device 320 transmits 302 the first associated ID to the target network device 330. The first associated ID may be included in first information and correspond to a first additional network condition.
[0088] In some embodiments, the first information may include the first associated ID. For example, the first associated ID may indicate an associated ID of which the corresponding network additional condition is adopted by the terminal device 110 for its applicable functionalities / supported functionalities / activated functionalities.
[0089] Alternatively, or additionally, the first information may include at least one of: a cell identity associated with the first associated ID, a functionality identity associated with the first associated ID, a machine learning model identity associated with the first associated ID, a Public Land Mobile Network identity associated with the first associated ID, or an inference configuration associated with the first associated ID.
[0090] Optionally, the first information may be forwarded by LMF / OAM from the source network device 320 towards the target network device 330.
[0091] The target network device 330 receives 304 the first associated ID. Then the target network device 330 may detect 306 whether the associated ID collision happens. For example, the target network device 330 determines a relation between the first associated ID and its own associated ID (also referred to as a second associated ID) . Then the associated ID collision may be determined based on the relation. The second associated ID may correspond to a second additional network condition.
[0092] In some embodiments, if the first associated ID is the same as the second associated ID but the corresponding first additional condition is not the same as the corresponding second additional condition, the target network device 330 may determine a collision between the first associated ID and the second associated ID. In such case, the first associated ID and the second associated ID may be referred to as a collided associated ID.
[0093] It should be noted that the source network device 320 may transmit a plurality of first associated IDs, the target network device 330 may have a plurality of second associated IDs and one or more collisions may be determined. For ease of discussion, one collision is taken as an example herein, but the present disclosure is not limited thereof.
[0094] After detecting the collision, the target network device 330 may transmit 308 a collision resolving request for the first associated ID and the second associated ID. The collision resolving request may be included in second information. For example, after determining the collision, the target network device 330 will trigger the associated ID collision resolving procedure. In details, the target network device 330 sends a collision resolving request message towards the source network device 320. The collision resolving request message may carry related information.
[0095] In some embodiments, the collision resolving request may include the first associated ID and the second associated ID. For example, the collision is detected between the first associated ID and the second associated ID. The associated IDs may be correlated with related information, such as cell IDs, model IDs, etc.
[0096] Alternatively, or additionally, the collision resolving request may include at least one of: respective cell identities associated with the first associated ID and the second associated ID, respective functionality identities associated with the first associated ID and the second associated ID, respective machine learning model identities associated with the first associated ID and the second associated ID, respective Public Land Mobile Network (PLMN) IDs associated with the first associated ID and the second associated ID, or respective inference configurations associated with the first associated ID and the second associated ID, or an applicable range for the second associated ID, the applicable range indicating an area in which the second associated ID is aligned among different network devices.
[0097] Continue with reference to FIG. 3, the source network device 320 may receive 310 the collision resolving request and transmit 312 a collision resolving response to the collision resolving request.
[0098] In some embodiments, the collision resolving response may include a feedback indication of whether to resolve the collision, for example, a collision resolving ACK / NAK indication for the corresponding collided associated IDs.
[0099] Alternatively, or additionally, the collision resolving response may include an updated value for the first associated ID, for example, a suggested updated associated ID(s) .
[0100] After receiving 314 the collision resolving response, the target network device 330 may replace 316 the first associated ID. For example, the target network device 330 may use the associated IDs suggested by the source network device 320 to replace those collided associated IDs.
[0101] After the first associated ID is updated, the target network device 330 may transmit 318 an identity updating message to the source network device 320.
[0102] In some embodiments, the identity updating message may include one or more associated IDs which are updated. For example, the identity updating message includes an updated associated ID list, of which the order of the associated ID list is according to the received ACK order of the associated ID list via associated ID collision resolving response message.
[0103] Alternatively, or additionally, the identity updating message may include one or more entries each comprising an associated ID and a corresponding updated associated ID.For example, the identity updating message includes an associated ID updated entry, of which each entry will carry the original associated ID and updated associated ID.
[0104] Alternatively, or additionally, the identity updating message may include a confirmation indication to update collided associated IDs.
[0105] In view of the above, the collision may be detected by the target network device 330. Afterwards, the collision issue of associated IDs can be resolved through negotiation between the source network device 320 and the target network device 330. The present disclosure further provides other solutions, which will be described with reference to FIGS. 4-7.
[0106] FIG. 4 illustrates a signaling flow 400 of communication in accordance with some example embodiments of the present disclosure. The signaling flow 400 involves the terminal device 110 and the target network device 330. For ease of discussion, the signaling flow 400 will be described with reference to FIG. 1.
[0107] As the example in FIG. 3, the first associated ID is configured by the source network device320 to the terminal device 110, and the second associated ID is configured by the target network device 330 to the terminal device 110.
[0108] As an example, the terminal device 110 performs model training according to the first associated ID configured by the source network device320. After the terminal device 110 hands over to the target network device 330, the terminal device 110 may receive the second associated ID from the target network device 330 and maintain previous LCM procedure with the first associated ID.
[0109] Without negotiation between the source network device 320 and the target network device 330, the associated IDs provided respectively by the source network device 320 and the target network device 330 may be collided. In such a case, the terminal device 110 may determine whether there is a collision based on a relation between the first associated ID and the second associated ID.
[0110] As shown in FIG. 4, the terminal device 110 may detect 402 a collision. For example, if the terminal device 110 detects the first associated ID is the same as the second associated ID, it will trigger the associated ID collision resolving procedure.
[0111] The terminal device 110 may perform 404 associated ID collision reporting towards the target network device 330. The target network device 330 may receive 406 a reporting message.
[0112] In some embodiments, at least one of the following information may be included within the reporting message: the first associated ID, a cell identity corresponding to the first associated ID, a network device identity corresponding to the first associated ID, a PLMN identity corresponding to the first associated ID, a functionality identity corresponding to the first associated ID, a machine learning model identity corresponding to the first associated ID, an inference configuration corresponding to the first associated ID, a data set identity corresponding to the first associated ID, or a machine learning model identity corresponding to the first associated ID.
[0113] After reporting towards the target network device 330 and before receiving any related instruction, the terminal device 110 may suspend 408 the LCM procedure of the corresponding collided associated ID and wait for associated ID collision resolving method performed at the target network device 330.
[0114] It should be noted that there may be a plurality of terminal devices using the same first associated ID configured by the same source network device 320. If the terminal device 110 detects the collision associated with the first associated ID, the plurality of terminal devices should suspend the LCM procedure of the corresponding collided associated ID and wait for the associated ID collision resolving method.
[0115] The target network device 330 may transmit 410 collision resolving information to the terminal device 110. In some embodiments, the collision resolving information may include at least one of: the collided associated ID, or an updated value for the collided associated ID.
[0116] Alternatively, or additionally, the collision resolving information may include an updating validation timer indicating a time duration after which the updated value is to be applied to the collided associated ID. For example, the updating validation timer is used to indicate that the terminal device 110 may apply the updated associated ID after a certain duration. It is because the target network device 330 also needs to update other terminal device’s associated ID, who has been configured previously. (Since those terminal devices may also encounter ID collision issues within the neighbor cells coverage) .
[0117] In some embodiments, a configuration of the updating validation timer may include related information. For example, if the terminal device 110 receives the associated ID collision resolving information from the target network device 330, it may start the timer. If the updating validation timer expired, the terminal device 110 may apply the updated associated ID and perform LCM activation for the previous collided associated ID (if it was suspended) . If the terminal device 110 receives de-configuration for the collided associated ID within the timer duration, the terminal device 110 may stop the timer.
[0118] Alternatively, or additionally, the collision resolving information may include an indication of whether to terminate an LCM procedure for the first associated ID.
[0119] If the target network device 330 indicates to stop the LCM procedure related to the previous collided associated ID, which means the associated ID configured by the source network device 320 is de-configured, and the target network device 330 would not like to update its own associated ID, yet the ID collision issue is solved.
[0120] In view of the above, the collision may be detected by the terminal device 110. Afterwards, the collision issue of associated IDs can be resolved through negotiation between the terminal device 110 and the target network device 330.
[0121] In some embodiments, the terminal device 110 capable of AI function may be pre-configured with a set of associated ID, where each associated ID represents a set of network additional conditions.
[0122] During the mobility of the terminal device 110, it may receive an LCM configuration from each network device. Different network device may configure a model training configuration and model inference configuration related to a specific associated ID, yet the terminal device may receive the same associated ID from different network device, which implies that different network device may apply the same NW-side additional condition. In such a case, the terminal device 110 should perform reporting to check whether to apply the same inference configuration. The following will describe in detail with reference to FIG. 5.
[0123] FIG. 5 illustrates a signaling flow 500 of communication in accordance with some example embodiments of the present disclosure. The signaling flow 500 involves the terminal device 110 and the target network device 330. For ease of discussion, the signaling flow 500 will be described with reference to FIG. 1.
[0124] If the terminal device 110 receives a configuration including a NW-side additional condition from the target network device 330, it may firstly perform a check on related information.
[0125] For example, the terminal device 110 may check 502 whether the associated ID related to the configured NW-side additional condition is the same as the one previously applied for specific activated / applicable / supported functionality. The terminal device 110 may further check 502 whether the repetitive associated IDs provided from the same network device, if there is the same associated ID has been found.
[0126] If the repetitive associated ID is provided from different network devices, the terminal device 110 may perform a repetitive associated ID checking procedure towards the current serving network device (i.e., the target network device 330) .
[0127] In other words, if the first associated ID is the same as the second associated ID, and the corresponding first additional NW-side condition is the same as the corresponding second additional NW-side condition, associated ID repetition may be determined. In such a case, the first associated ID and the second associated ID may be referred to as a repetitive associated ID.
[0128] As shown in FIG. 4, the terminal device 110 may transmit 504 a report message to the target network device 330. In some embodiments, the report message may include at least one of: the repetitive associated ID, a network device identity corresponding to the repetitive associated ID, a cell identity corresponding to the repetitive associated ID, an inference configuration for the repetitive associated ID, a training configuration for the repetitive associated ID, performance monitoring configuration for the repetitive associated ID, or a performance monitoring result for the repetitive associated ID.
[0129] The target network device 330 may receive 506 the report message and transmit 508 a related configuration. In some embodiments, the configuration received 510 may include at least one of: an indication of whether the repetitive associated ID is applicable, an updated inference configuration for the repetitive associated ID, an updated training configuration for the repetitive associated ID, or an updated performance monitoring configuration for the repetitive associated ID.
[0130] Alternatively, or additionally, the above configuration may include an indication to handle an LCM procedure associated with the repetitive associated ID. For example, the terminal device 110 may receive a configuration including an LCM procedure indication for current functionality, and the LCM procedure indication may include functionality activation, functionality deactivation or functionality fallback.
[0131] Alternatively, or additionally, the above configuration may include a timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated ID. For example, the terminal device 110 may receive a timer configuration, which may indicate after a certain timer duration, to apply the updated configuration for model inference configuration, model training configuration and / or model monitoring configuration. The timer may be set per configuration granularity.
[0132] In some embodiments, the timer configuration may include a timer length. For example, if the terminal device 110 receives at least one of the following updated configurations, it may start the timer: an updated model / functionality inference configuration, an updated model / functionality training configuration, or an updated model / functionality monitoring configuration. If the timer expired, the terminal device 110 may apply the corresponding updated configuration. During the timer duration, if the corresponding repetitive associated ID is de-configured, the terminal device 110 may stop the timer.
[0133] In some embodiments, the terminal device 110 may be configured to apply a global associated ID. In such embodiments, the terminal device 110 may generate a global associated ID based on the associated ID configured by a network device. The terminal device 110 may perform the following operation regarding to the configured associated ID.For example, the terminal device 110 may link the configured associated ID with a cell ID or a network device ID to generate a global associated ID. For another example, the terminal device 110 may link the cell ID or network device ID with the associated ID to generate the global associated ID. The terminal device 110 may generate a global associated ID in any suitable manner, which is not limited by the present disclosure.
[0134] Afterwards, the terminal device 110 may report the generated global associated ID towards the network devices.
[0135] In view of the above, the collision issue of associated IDs can be resolved based on pre-determined global associated IDs.
[0136] During the handover procedure, the terminal device 110 may receive an updated associated ID list from the target network device 330. To avoid the terminal device performing model training repetitively for the updated associated ID, the target network device 330 may determine whether the updated associated ID may reuse the well-trained model maintained at UE-side. The following will describe the detail with reference to FIG. 6.
[0137] FIG. 6 illustrates a signaling flow 600 of communication in accordance with some example embodiments of the present disclosure. The signaling flow 600 involves the terminal device 110 and the target network device 330. For ease of discussion, the signaling flow 600 will be described with reference to FIG. 1.
[0138] During the handover procedure or after the handover procedure, the target network device 330 may request the terminal device 110 to report related information. As shown in FIG. 6, the terminal device 110 may transmit 602 a report message to the target network device 330.
[0139] In some embodiments, the report message may include at least one of: the first associated ID, an identification of an activated ML model entity corresponding to the first associated ID, an inference configuration for the activated ML model entity, a data set configuration for the activated ML model entity, a cell identity corresponding to the activated ML model entity, or an identity of a network device corresponding to the activated ML model entity.
[0140] Afterwards, the target network device 330 may determine whether the second additional network condition is applicable to the activated ML model entity corresponding to the first associated ID. If the target network device 330 determines that the second additional network condition is applicable, it may transmit 606 the second information including merging strategy, for example, to instruct the terminal device 110 to merge the first associated ID and the second associated ID.
[0141] Then the terminal device 110 receives 608 the merging strategy. In some embodiments, the merging strategy may include at least one of: an identity of the activated ML model entity corresponding to the first associated ID, the second associated ID, or a data set for fine tuning the activated ML model entity.
[0142] As mentioned above, the target network device 330 need to determine whether the second additional network condition is applicable. In some embodiments, the target network device 330 may determine a similarity between the first additional network condition and the second additional network condition. If the target network device 330 determines that the similarity is below a threshold, it may determine that the second additional network condition is applicable the activated ML model entity.
[0143] In view of the above, the target network device 330 may determine whether the updated associated ID can be reused to avoid performing model training repetitively at the terminal device 110.
[0144] According to current RAN1 / 2 discussion, the network device may provide NW-side additional condition alone with model inference configuration (associated ID configuration is put inside BM configuration framework) . However, during model training procedure, how does the associated ID is provided for each functionality / model is not clear, so the correlation between associated ID and model / functionality may be handled by the following two ways: correlation between associated ID and model / functionality for model / functionality training at UE side, or correlation between associated ID and model / functionality for model / functionality training at network side.
[0145] FIG. 7 illustrates a signaling flow 700 of communication in accordance with some example embodiments of the present disclosure. The signaling flow 700 involves the terminal device 110 and the target network device 330. For ease of discussion, the signaling flow 700 will be described with reference to FIG. 1.
[0146] The target network device 330 transmits 702 a set of associated IDs for a ML model entity and a set of training configurations for the ML model entity. a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated IDs.
[0147] After receiving 704 the set of associated IDs and the set of training configurations, the terminal device 110 may train 706 the ML model entity based on mapping between the set of associated identities and the set of training configurations.
[0148] For example, if the terminal device 110 is enabled with AI / ML features, it may be configured with a set of associated IDs to represent NW-side additional condition. For example, the configuration may be provided as a per functionality granularity, an example may be shown as:
[0149] functionality ID-A: an associated ID list A including associated IDs 1, 2, 3, 4, and 5, and
[0150] functionality ID-B: an associated ID list B including associated IDs 6, 7, 8, 9, and 10.
[0151] Alone with each functionality ID, the target network device 330 may also provide the corresponding model / functionality training configuration. For example, such model / functionality training configuration may be mapped to one or more associated IDs, which is shown in below as an example:
[0152] functionality ID-A:
[0153] associated ID 1 model / functionality training configuration 1, and
[0154] associated ID 2 / 3 model / functionality training configuration 2.
[0155] The terminal device 110 may rely on the mapping between model / functionality training configuration and associated ID to perform model / functionality training to acquire the corresponding model which may fulfill the NW-side additional condition.
[0156] Optionally, the terminal device 110 also needs to rely on the UE-side additional condition to determine whether it has the capability to perform the model training for every configuration set.
[0157] In some embodiments, the terminal device 110 may determine whether an additional condition at the terminal device 110 is fulfilled to perform training based on a first training configuration in the set of training configurations. If the terminal device 110 determines that the additional condition is not fulfilled, it may terminate the training based on the first training configuration.
[0158] In some embodiments, the additional condition at the terminal device 110 may include at least one of: an available size of memory at the terminal device 110, a battery level at the terminal device 110, a temperature of the terminal device 110, or a mobility speed of the terminal device 110.
[0159] The terminal device 110 may stop performing model training due to its UE-side additional condition cannot be fulfilled. Afterwards, the terminal device 110 may report related information towards the target network device 330 if it stops performing model / functionality training.
[0160] In some embodiments, the terminal device 110 may transmit 708 a training report and the target network device 330 may receive 710 the training report. The training report may include at least one of: an ID of an ML model entity that has been trained, an associated ID corresponding to the trained ML model entity, an ID of an ML model entity that is untrained, or an associated ID corresponding to the untrained ML model entity.
[0161] Alternatively, or additionally, the training report may include an indication of an additional condition at the terminal device 110 that is not fulfilled. For example, such indication may include information that the available size of memory at the terminal device 110 reaches a minimum threshold of available memory. Optionally, the indication may include information that the battery level at the terminal device 110 reaches a minimum threshold of battery level. Optionally, the indication may include information that the temperature of the terminal device 110 reaches a minimum threshold of heat boundary. Optionally, the indication may include information that the mobility speed of the terminal device 110 reaches a maximum threshold of speed.
[0162] In view of the above, regarding the initial configuration of associated IDs for the terminal device 110, the terminal device 110 may determine which associated ID is used for model training, or the target network device 330 may determine which associated ID is used for model training.
[0163] FIG. 8 illustrates a flowchart of a communication method 800 implemented at a first network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 800 will be described from the perspective of the network device 130 in FIG. 1.
[0164] At block 810, the network device 130 receives, from a communication device, first information related to a first associated identity corresponding to a first additional network condition.
[0165] At block 820, the network device 130 determines, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices.
[0166] At block 830, the network device 130 transmits, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.
[0167] In some example embodiments, the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, and the first network device is caused to: in response to that the first associated identity is the same as the second associated identity, determine a collision between the first associated identity and the second associated identity; and transmit, to the second network device, the second information comprising a collision resolving request for the first associated identity and the second associated identity.
[0168] In some example embodiments, the first information comprises at least one of: the first associated identity, a cell identity associated with the first associated identity, a functionality identity associated with the first associated identity, a machine learning model identity associated with the first associated identity, a PLMN identity associated with the first associated identity, or an inference configuration associated with the first associated identity.
[0169] In some example embodiments, the collision resolving request comprises at least one of: the first associated identity and the second associated identity, respective cell identities associated with the first associated identity and the second associated identity, respective functionality identities associated with the first associated identity and the second associated identity, respective machine learning model identities associated with the first associated identity and the second associated identity, respective PLMN identities associated with the first associated identity and the second associated identity, or respective inference configurations associated with the first associated identity and the second associated identity, or an applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.
[0170] In some example embodiments, the network device 130 receives, from the second network device, a collision resolving response to the collision resolving request; and in response to the first associated identity being updated, transmits an identity updating message to the second network device.
[0171] In some example embodiments, the collision resolving response comprises at least one of: a feedback indication of whether to resolve the collision, or an updated value for the first associated identity.
[0172] In some example embodiments, the identity updating message comprises at least one of: one or more associated identities which are updated, one or more entries each comprising an associated identity and a corresponding updated associated identity, or a confirmation indication to update collided associated identities.
[0173] In some example embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, the second associated identity is configured by the first network device to the terminal device, and the first information indicates that the first associated identity and the second associated identity are a collided associated identity, and the second information comprises collision resolving information.
[0174] In some example embodiments, the first information comprises at least one of: the first associated identity, a cell identity corresponding to the first associated identity, a network device identity corresponding to the first associated identity, a Public Land Mobile Network identity corresponding to the first associated identity, a functionality identity corresponding to the first associated identity, a machine learning model identity corresponding to the first associated identity, an inference configuration corresponding to the first associated identity, a data set identity corresponding to the first associated identity, or a machine learning model identity corresponding to the first associated identity.
[0175] In some example embodiments, the collision resolving information comprises at least one of: the collided associated identity, an updated value for the collided associated identity, an updating validation timer indicating a time duration after which the updated value is to be applied to the collided associated identity, or an indication of whether to terminate a LCM procedure for the first associated identity.
[0176] In some example embodiments, the communication device comprises a terminal device, the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, and the first information indicates that the first associated identity and the second associated identity are a repetitive associated identity.
[0177] In some example embodiments, the first information comprises at least one of: the repetitive associated identity, a network device identity corresponding to the repetitive associated identity, a cell identity corresponding to the repetitive associated identity, an inference configuration for the repetitive associated identity, a training configuration for the repetitive associated identity, performance monitoring configuration for the repetitive associated identity, or a performance monitoring result for the repetitive associated identity.
[0178] In some example embodiments, the second information comprises at least one of: an indication of whether the repetitive associated identity is applicable, an updated inference configuration for the repetitive associated identity, an updated training configuration for the repetitive associated identity, an updated performance monitoring configuration for the repetitive associated identity, an indication to handle a LCM procedure associated with the repetitive associated identity, or a timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.
[0179] In some example embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information comprises at least one of: the first associated identity, an identification of an activated ML model entity corresponding to the first associated identity, an inference configuration for the activated ML model entity, a data set configuration for the activated ML model entity, a cell identity corresponding to the activated ML model entity, or an identity of a network device corresponding to the activated ML model entity.
[0180] In some example embodiments, the network device 130 determines whether the second additional network condition is applicable to the activated ML model entity corresponding to the first associated identity; and in accordance with a determination that the second additional network condition is applicable, transmits, to the terminal device, the second information indicating the terminal device to merge the first associated identity and the second associated identity.
[0181] In some example embodiments, the network device 130 determines a similarity between the first additional network condition and the second additional network condition; and in accordance with a determination that the similarity is below a threshold, determines that the second additional network condition is applicable the activated ML model entity.
[0182] In some example embodiments, the second information comprises at least one of: an identity of the activated ML model entity corresponding to the first associated identity, the second associated identity, or a data set for fine tuning the activated ML model entity.
[0183] FIG. 9 illustrates a flowchart of a communication method 900 implemented at a communication device (e.g., the terminal device 110 or the network device 120 in FIG. 1) in accordance with some embodiments of the present disclosure.
[0184] At block 910, the communication device transmits, to a first network device, first information related to a first associated identity corresponding to a first additional network condition.
[0185] At block 920, the communication device receives, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.
[0186] In some example embodiments, the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, and wherein the first associated identity is the same as the second associated identity, and the second information comprises a collision resolving request for the first associated identity and the second associated identity.
[0187] In some example embodiments, the first information comprises at least one of: the first associated identity, a cell identity associated with the first associated identity, a functionality identity associated with the first associated identity, a machine learning model identity associated with the first associated identity, a PLMN identity associated with the first associated identity, or an inference configuration associated with the first associated identity.
[0188] In some example embodiments, the collision resolving request comprises at least one of: the first associated identity and the second associated identity, respective cell identities associated with the first associated identity and the second associated identity, respective functionality identities associated with the first associated identity and the second associated identity, respective machine learning model identities associated with the first associated identity and the second associated identity, respective PLMN identities associated with the first associated identity and the second associated identity, or respective inference configurations associated with the first associated identity and the second associated identity, or an applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.
[0189] In some example embodiments, the communication device transmits, to the first network device, a collision resolving response to the collision resolving request; and receives, from the first network device, an identity updating message indicating that the first associated identity is updated.
[0190] In some example embodiments, the collision resolving response comprises at least one of: a feedback indication of whether to resolve the collision, or an updated value for the first associated identity.
[0191] In some example embodiments, the identity updating message comprises at least one of: one or more associated identities which are updated, one or more entries each comprising an associated identity and a corresponding updated associated identity, or a confirmation indication to update collided associated identities.
[0192] In some example embodiments, the communication device comprises a terminal device, and the communication device, in accordance with a determination that the first associated identity configured by a second network device to the terminal device is the same as the second associated identity configured by the first network device to the terminal device, transmits, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a collided associated identity, wherein the second information comprises collision resolving information.
[0193] In some example embodiments, the first information comprises at least one of: the first associated identity, a cell identity corresponding to the first associated identity, a network device identity corresponding to the first associated identity, a PLMN identity corresponding to the first associated identity, a functionality identity corresponding to the first associated identity, a machine learning model identity corresponding to the first associated identity, an inference configuration corresponding to the first associated identity, a data set identity corresponding to the first associated identity, or a machine learning model identity corresponding to the first associated identity.
[0194] In some example embodiments, the collision resolving information comprises at least one of: the collided associated identity, an updated value for the collided associated identity, an updating validation timer indicating a time duration after which the updated value is to be applied to the collided associated identity, or an indication of whether to terminate a LCM procedure for the first associated identity.
[0195] In some example embodiments, the communication device comprises a terminal device, and the communication device, in accordance with a determination that the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, transmits, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a repetitive associated identity.
[0196] In some example embodiments, the first information comprises at least one of: the repetitive associated identity, a network device identity corresponding to the repetitive associated identity, a cell identity corresponding to the repetitive associated identity, an inference configuration for the repetitive associated identity, a training configuration for the repetitive associated identity, performance monitoring configuration for the repetitive associated identity, or a performance monitoring result for the repetitive associated identity.
[0197] In some example embodiments, the second information comprises at least one of: an indication of whether the repetitive associated identity is applicable, an updated inference configuration for the repetitive associated identity, an updated training configuration for the repetitive associated identity, an updated performance monitoring configuration for the repetitive associated identity, an indication to handle a LCM procedure associated with the repetitive associated identity, or a timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.
[0198] In some example embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information is transmitted in response to a handover from the second network device to the first network device, and the first information comprises at least one of: the first associated identity, an identification of an activated ML model entity corresponding to the first associated identity, an inference configuration for the activated ML model entity, a data set configuration for the activated ML model entity, a cell identity corresponding to the activated ML model entity, or an identity of a network device corresponding to the activated ML model entity.
[0199] In some example embodiments, the communication device receives, from the first network device, the second information indicating the terminal device to merge the first associated identity and the second associated identity.
[0200] In some example embodiments, the second information comprises at least one of: an identity of the activated ML model entity corresponding to the first associated identity, the second associated identity, or a data set for fine tuning the activated ML model entity.
[0201] FIG. 10 illustrates a flowchart of a communication method 1000 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the terminal device 110 in FIG. 1.
[0202] At block 1010, the terminal device 110 receives, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities.
[0203] At block 1020, the terminal device 110 trains the ML model entity based on mapping between the set of associated identities and the set of training configurations.
[0204] In some example embodiments, the terminal device 110 determines whether an additional condition at the terminal device is fulfilled to perform training based on a first training configuration in the set of training configurations; and in accordance with a determination that the additional condition is not fulfilled, terminates the training based on the first training configuration.
[0205] In some example embodiments, the additional condition at the terminal device comprises at least one of: an available size of memory at the terminal device, a battery level at the terminal device, a temperature of the terminal device, or a mobility speed of the terminal device.
[0206] In some example embodiments, the terminal device 110 transmits, to the network device, a training report comprising at least one of: an identity of an ML model entity that has been trained, an associated identity corresponding to the trained ML model entity, an identity of an ML model entity that is untrained, an associated identity corresponding to the untrained ML model entity, or an indication of an additional condition at the terminal device that is not fulfilled.
[0207] FIG. 11 illustrates a flowchart of a communication method 1100 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the network device 130 in FIG. 1.
[0208] At block 1110, the network device 130 transmits, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations.
[0209] In some example embodiments, the network device 130 receives, from the terminal device, a training report comprising at least one of: an identity of an ML model entity that has been trained, an associated identity corresponding to the trained ML model entity, an identity of an ML model entity that is untrained, an associated identity corresponding to the untrained ML model entity, or an indication of an additional condition at the terminal device that is not fulfilled.
[0210] FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing embodiments of the present disclosure. The device 1200 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 1200 can be implemented at or as at least a part of the terminal device 110, the network device 120 or the network device 130.
[0211] As shown, the device 1200 includes a processor 1210, a memory 1220 coupled to the processor 1210, a suitable transceiver 1240 coupled to the processor 1210, and a communication interface coupled to the transceiver 1240. The memory 1220 stores at least a part of a program 1230. The transceiver 1240 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1240 may include at least one of a transmitter 1242 and a receiver 1244. The transmitter 1242 and the receiver 1244 may be functional modules or physical entities. The transceiver 1240 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2 / Xn interface for bidirectional communications between eNBs / gNBs, S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and the eNB / gNB, Un interface for communication between the eNB / gNB and a relay node (RN) , or Uu interface for communication between the eNB / gNB and a terminal device.
[0212] The program 1230 is assumed to include program instructions that, when executed by the associated processor 1210, enable the device 1200 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1, 3 to 11. The embodiments herein may be implemented by computer software executable by the processor 1210 of the device 1200, or by hardware, or by a combination of software and hardware. The processor 1210 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1210 and memory 1220 may form processing means 1250 adapted to implement various embodiments of the present disclosure.
[0213] The memory 1220 may be of any type suitable to the local technical network and may be implemented using any suitable data storage technology, such as a non-transitory computer readable storage medium, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. While only one memory 1220 is shown in the device 1200, there may be several physically distinct memory modules in the device 1200. The processor 1210 may be of any type suitable to the local technical network, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1200 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.
[0214] According to embodiments of the present disclosure, a first network device comprising a circuitry is provided. The circuitry is configured to: receive, from a communication device, first information related to a first associated identity corresponding to a first additional network condition; determine, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; and transmit, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the first network device as discussed above.
[0215] According to embodiments of the present disclosure, a communication device comprising a circuitry is provided. The circuitry is configured to: transmit, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; and receive, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the communication device as discussed above.
[0216] According to embodiments of the present disclosure, a terminal device comprising a circuitry is provided. The circuitry is configured to: receive, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; and train the ML model entity based on mapping between the set of associated identities and the set of training configurations. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the terminal device as discussed above.
[0217] According to embodiments of the present disclosure, a network device comprising a circuitry is provided. The circuitry is configured to: transmit, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the network device as discussed above.
[0218] The term “circuitry” used herein may refer to hardware circuits and / or combinations of hardware circuits and software. For example, the circuitry may be a combination of analog and / or digital hardware circuits with software / firmware. As a further example, the circuitry may be any portions of hardware processors with software including digital signal processor (s) , software, and memory (ies) that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In a still further example, the circuitry may be hardware circuits and or processors, such as a microprocessor or a portion of a microprocessor, that requires software / firmware for operation, but the software may not be present when it is not needed for operation. As used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (s) or a portion of a hardware circuit or processor (s) and its (or their) accompanying software and / or firmware.
[0219] According to embodiments of the present disclosure, a first network apparatus is provided. The first network apparatus comprises means for receiving, from a communication device, first information related to a first associated identity corresponding to a first additional network condition; means for determining, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; and means for transmitting, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity. In some embodiments, the first apparatus may comprise means for performing the respective operations of the method 800. In some example embodiments, the first network apparatus may further comprise means for performing other operations in some example embodiments of the method 800. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0220] According to embodiments of the present disclosure, a communication apparatus is provided. The communication apparatus comprises means for transmitting, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; and means for receiving, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity. In some embodiments, the second apparatus may comprise means for performing the respective operations of the method 900. In some example embodiments, the communication apparatus may further comprise means for performing other operations in some example embodiments of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0221] According to embodiments of the present disclosure, a terminal apparatus is provided. The terminal apparatus comprises means for receiving, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; and means for training the ML model entity based on mapping between the set of associated identities and the set of training configurations. In some embodiments, the third apparatus may comprise means for performing the respective operations of the method 1000. In some example embodiments, the terminal apparatus may further comprise means for performing other operations in some example embodiments of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0222] According to embodiments of the present disclosure, a network apparatus is provided. The network apparatus comprises means for transmitting, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations. In some embodiments, the fourth apparatus may comprise means for performing the respective operations of the method 1100. In some example embodiments, the network apparatus may further comprise means for performing other operations in some example embodiments of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0223] In summary, embodiments of the present disclosure provide the following aspects.
[0224] In an aspect, it is proposed a first network device comprising: a processor configured to cause the first network device to: receive, from a communication device, first information related to a first associated identity corresponding to a first additional network condition; determine, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; and transmit, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.
[0225] In some embodiments, the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, and the first network device is caused to: in response to that the first associated identity is the same as the second associated identity, determine a collision between the first associated identity and the second associated identity; and transmit, to the second network device, the second information comprising a collision resolving request for the first associated identity and the second associated identity.
[0226] In some embodiments, the first information comprises at least one of: the first associated identity, a cell identity associated with the first associated identity, a functionality identity associated with the first associated identity, a machine learning model identity associated with the first associated identity, a PLMN identity associated with the first associated identity, or an inference configuration associated with the first associated identity.
[0227] In some embodiments, the collision resolving request comprises at least one of: the first associated identity and the second associated identity, respective cell identities associated with the first associated identity and the second associated identity, respective functionality identities associated with the first associated identity and the second associated identity, respective machine learning model identities associated with the first associated identity and the second associated identity, respective PLMN identities associated with the first associated identity and the second associated identity, or respective inference configurations associated with the first associated identity and the second associated identity, or an applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.
[0228] In some embodiments, the first network device is further caused to: receive, from the second network device, a collision resolving response to the collision resolving request; and in response to the first associated identity being updated, transmit an identity updating message to the second network device.
[0229] In some embodiments, the collision resolving response comprises at least one of: a feedback indication of whether to resolve the collision, or an updated value for the first associated identity.
[0230] In some embodiments, the identity updating message comprises at least one of: one or more associated identities which are updated, one or more entries each comprising an associated identity and a corresponding updated associated identity, or a confirmation indication to update collided associated identities.
[0231] In some embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, the second associated identity is configured by the first network device to the terminal device, and the first information indicates that the first associated identity and the second associated identity are a collided associated identity, and the second information comprises collision resolving information.
[0232] In some embodiments, the first information comprises at least one of: the first associated identity, a cell identity corresponding to the first associated identity, a network device identity corresponding to the first associated identity, a PLMN identity corresponding to the first associated identity, a functionality identity corresponding to the first associated identity, a machine learning model identity corresponding to the first associated identity, an inference configuration corresponding to the first associated identity, a data set identity corresponding to the first associated identity, or a machine learning model identity corresponding to the first associated identity.
[0233] In some embodiments, the collision resolving information comprises at least one of: the collided associated identity, an updated value for the collided associated identity, an updating validation timer indicating a time duration after which the updated value is to be applied to the collided associated identity, or an indication of whether to terminate a LCM procedure for the first associated identity.
[0234] In some embodiments, the communication device comprises a terminal device, the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, and the first information indicates that the first associated identity and the second associated identity are a repetitive associated identity.
[0235] In some embodiments, the first information comprises at least one of: the repetitive associated identity, a network device identity corresponding to the repetitive associated identity, a cell identity corresponding to the repetitive associated identity, an inference configuration for the repetitive associated identity, a training configuration for the repetitive associated identity, performance monitoring configuration for the repetitive associated identity, or a performance monitoring result for the repetitive associated identity.
[0236] In some embodiments, the second information comprises at least one of: an indication of whether the repetitive associated identity is applicable, an updated inference configuration for the repetitive associated identity, an updated training configuration for the repetitive associated identity, an updated performance monitoring configuration for the repetitive associated identity, an indication to handle a LCM procedure associated with the repetitive associated identity, or a timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.
[0237] In some embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information comprises at least one of: the first associated identity, an identification of an activated ML model entity corresponding to the first associated identity, an inference configuration for the activated ML model entity, a data set configuration for the activated ML model entity, a cell identity corresponding to the activated ML model entity, or an identity of a network device corresponding to the activated ML model entity.
[0238] In some embodiments, the first network device is caused to: determine whether the second additional network condition is applicable to the activated ML model entity corresponding to the first associated identity; and in accordance with a determination that the second additional network condition is applicable, transmit, to the terminal device, the second information indicating the terminal device to merge the first associated identity and the second associated identity.
[0239] In some embodiments, the first network device is caused to: determine a similarity between the first additional network condition and the second additional network condition; and in accordance with a determination that the similarity is below a threshold, determine that the second additional network condition is applicable the activated ML model entity.
[0240] In some embodiments, the second information comprises at least one of: an identity of the activated ML model entity corresponding to the first associated identity, the second associated identity, or a data set for fine tuning the activated ML model entity.
[0241] In an aspect, it is proposed a communication device comprising: a processor configured to cause the communication device to: transmit, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; and receive, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.
[0242] In some embodiments, the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, and wherein the first associated identity is the same as the second associated identity, and the second information comprises a collision resolving request for the first associated identity and the second associated identity.
[0243] In some embodiments, the first information comprises at least one of: the first associated identity, a cell identity associated with the first associated identity, a functionality identity associated with the first associated identity, a machine learning model identity associated with the first associated identity, a PLMN identity associated with the first associated identity, or an inference configuration associated with the first associated identity.
[0244] In some embodiments, the collision resolving request comprises at least one of: the first associated identity and the second associated identity, respective cell identities associated with the first associated identity and the second associated identity, respective functionality identities associated with the first associated identity and the second associated identity, respective machine learning model identities associated with the first associated identity and the second associated identity, respective PLMN identities associated with the first associated identity and the second associated identity, or respective inference configurations associated with the first associated identity and the second associated identity, or an applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.
[0245] In some embodiments, the communication device is further caused to: transmit, to the first network device, a collision resolving response to the collision resolving request; and receive, from the first network device, an identity updating message indicating that the first associated identity is updated.
[0246] In some embodiments, the collision resolving response comprises at least one of: a feedback indication of whether to resolve the collision, or an updated value for the first associated identity.
[0247] In some embodiments, the identity updating message comprises at least one of: one or more associated identities which are updated, one or more entries each comprising an associated identity and a corresponding updated associated identity, or a confirmation indication to update collided associated identities.
[0248] In some embodiments, the communication device comprises a terminal device, and the communication device is caused to: in accordance with a determination that the first associated identity configured by a second network device to the terminal device is the same as the second associated identity configured by the first network device to the terminal device, transmit, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a collided associated identity, wherein the second information comprises collision resolving information.
[0249] In some embodiments, the first information comprises at least one of: the first associated identity, a cell identity corresponding to the first associated identity, a network device identity corresponding to the first associated identity, a PLMN identity corresponding to the first associated identity, a functionality identity corresponding to the first associated identity, a machine learning model identity corresponding to the first associated identity, an inference configuration corresponding to the first associated identity, a data set identity corresponding to the first associated identity, or a machine learning model identity corresponding to the first associated identity.
[0250] In some embodiments, the collision resolving information comprises at least one of: the collided associated identity, an updated value for the collided associated identity, an updating validation timer indicating a time duration after which the updated value is to be applied to the collided associated identity, or an indication of whether to terminate a LCM procedure for the first associated identity.
[0251] In some embodiments, the communication device comprises a terminal device, and the communication device is caused to: in accordance with a determination that the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, transmit, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a repetitive associated identity.
[0252] In some embodiments, the first information comprises at least one of: the repetitive associated identity, a network device identity corresponding to the repetitive associated identity, a cell identity corresponding to the repetitive associated identity, an inference configuration for the repetitive associated identity, a training configuration for the repetitive associated identity, performance monitoring configuration for the repetitive associated identity, or a performance monitoring result for the repetitive associated identity.
[0253] In some embodiments, the second information comprises at least one of: an indication of whether the repetitive associated identity is applicable, an updated inference configuration for the repetitive associated identity, an updated training configuration for the repetitive associated identity, an updated performance monitoring configuration for the repetitive associated identity, an indication to handle a LCM procedure associated with the repetitive associated identity, or a timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.
[0254] In some embodiments, the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information is transmitted in response to a handover from the second network device to the first network device, and the first information comprises at least one of: the first associated identity, an identification of an activated ML model entity corresponding to the first associated identity, an inference configuration for the activated ML model entity, a data set configuration for the activated ML model entity, a cell identity corresponding to the activated ML model entity, or an identity of a network device corresponding to the activated ML model entity.
[0255] In some embodiments, the communication device is caused to: receive, from the first network device, the second information indicating the terminal device to merge the first associated identity and the second associated identity.
[0256] In some embodiments, the second information comprises at least one of: an identity of the activated ML model entity corresponding to the first associated identity, the second associated identity, or a data set for fine tuning the activated ML model entity.
[0257] In an aspect, it is proposed a terminal device comprising: a processor configured to cause the terminal device to: receive, from a network device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; and train the ML model entity based on mapping between the set of associated identities and the set of training configurations.
[0258] In some embodiments, the terminal device is further caused to: determine whether an additional condition at the terminal device is fulfilled to perform training based on a first training configuration in the set of training configurations; and in accordance with a determination that the additional condition is not fulfilled, terminate the training based on the first training configuration.
[0259] In some embodiments, the additional condition at the terminal device comprises at least one of: an available size of memory at the terminal device, a battery level at the terminal device, a temperature of the terminal device, or a mobility speed of the terminal device.
[0260] In some embodiments, the terminal device is further caused to: transmit, to the network device, a training report comprising at least one of: an identity of an ML model entity that has been trained, an associated identity corresponding to the trained ML model entity, an identity of an ML model entity that is untrained, an associated identity corresponding to the untrained ML model entity, or an indication of an additional condition at the terminal device that is not fulfilled.
[0261] In an aspect, it is proposed a network device comprising: a processor configured to cause the network device to: transmit, to a terminal device, a set of associated identities for a ML model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations.
[0262] In some embodiments, the network device is further caused to: receive, from the terminal device, a training report comprising at least one of: an identity of an ML model entity that has been trained, an associated identity corresponding to the trained ML model entity, an identity of an ML model entity that is untrained, an associated identity corresponding to the untrained ML model entity, or an indication of an additional condition at the terminal device that is not fulfilled.
[0263] In an aspect, a first network device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the first network device discussed above.
[0264] In an aspect, a communication device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the communication device discussed above.
[0265] In an aspect, a terminal device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the terminal device discussed above.
[0266] In an aspect, a network device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the network device discussed above.
[0267] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the first network device discussed above.
[0268] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the communication device discussed above.
[0269] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.
[0270] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the network device discussed above.
[0271] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the first network device discussed above.
[0272] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the communication device discussed above.
[0273] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.
[0274] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the network device discussed above.
[0275] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representation, it will be appreciated that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
[0276] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGS. 1 to 12. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.
[0277] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0278] The above program code may be embodied on a machine readable medium, which may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0279] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0280] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1.A first network device comprising:a processor configured to cause the first network device to:receive, from a communication device, first information related to a first associated identity corresponding to a first additional network condition;determine, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; andtransmit, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.2.The first network device of claim 1, wherein the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, and the first network device is caused to:in response to that the first associated identity is the same as the second associated identity, determine a collision between the first associated identity and the second associated identity; andtransmit, to the second network device, the second information comprising a collision resolving request for the first associated identity and the second associated identity.3.The first network device of claim 2, wherein the first information comprises at least one of:the first associated identity,a cell identity associated with the first associated identity,a functionality identity associated with the first associated identity,a machine learning model identity associated with the first associated identity,a Public Land Mobile Network identity associated with the first associated identity, oran inference configuration associated with the first associated identity.4.The first network device of claim 2, wherein the collision resolving request comprises at least one of:the first associated identity and the second associated identity,respective cell identities associated with the first associated identity and the second associated identity,respective functionality identities associated with the first associated identity and the second associated identity,respective machine learning model identities associated with the first associated identity and the second associated identity,respective Public Land Mobile Network identities associated with the first associated identity and the second associated identity, orrespective inference configurations associated with the first associated identity and the second associated identity, oran applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.5.The first network device of claim 1, wherein the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, the second associated identity is configured by the first network device to the terminal device, andthe first information indicates that the first associated identity and the second associated identity are a collided associated identity, andthe second information comprises collision resolving information.6.The first network device of claim 1, wherein the communication device comprises a terminal device, the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, andthe first information indicates that the first associated identity and the second associated identity are a repetitive associated identity and the first information comprises at least one of:the repetitive associated identity,a network device identity corresponding to the repetitive associated identity,a cell identity corresponding to the repetitive associated identity,an inference configuration for the repetitive associated identity,a training configuration for the repetitive associated identity,performance monitoring configuration for the repetitive associated identity, ora performance monitoring result for the repetitive associated identity.7.The first network device of claim 6, wherein the second information comprises at least one of:an indication of whether the repetitive associated identity is applicable,an updated inference configuration for the repetitive associated identity,an updated training configuration for the repetitive associated identity,an updated performance monitoring configuration for the repetitive associated identity,an indication to handle a life cycle management procedure associated with the repetitive associated identity, ora timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.8.The first network device of claim 1, wherein the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information comprises at least one of:the first associated identity,an identification of an activated machine learning (ML) model entity corresponding to the first associated identity,an inference configuration for the activated ML model entity,a data set configuration for the activated ML model entity,a cell identity corresponding to the activated ML model entity, oran identity of a network device corresponding to the activated ML model entity.9.A communication device comprising:a processor configured to cause the communication device to:transmit, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; andreceive, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.10.The communication device of claim 9, wherein the communication device comprises a second network device, the first associated identity is configured by the second network device to a terminal device, andwherein the first associated identity is the same as the second associated identity, and the second information comprises a collision resolving request for the first associated identity and the second associated identity.11.The communication device of claim 10, wherein the collision resolving request comprises at least one of:the first associated identity and the second associated identity,respective cell identities associated with the first associated identity and the second associated identity,respective functionality identities associated with the first associated identity and the second associated identity,respective machine learning model identities associated with the first associated identity and the second associated identity,respective Public Land Mobile Network identities associated with the first associated identity and the second associated identity, orrespective inference configurations associated with the first associated identity and the second associated identity, oran applicable range for the second associated identity, the applicable range indicating an area in which the second associated identity is aligned among different network devices.12.The communication device of claim 10, wherein the communication device is further caused to:transmit, to the first network device, a collision resolving response to the collision resolving request; andreceive, from the first network device, an identity updating message indicating that the first associated identity is updated, andwherein the collision resolving response comprises at least one of:a feedback indication of whether to resolve the collision, oran updated value for the first associated identity.13.The communication device of claim 9, wherein the communication device comprises a terminal device, and the communication device is caused to:in accordance with a determination that the first associated identity configured by a second network device to the terminal device is the same as the second associated identity configured by the first network device to the terminal device, transmit, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a collided associated identity, wherein the second information comprises collision resolving information.14.The communication device of claim 9, wherein the communication device comprises a terminal device, and the communication device is caused to:in accordance with a determination that the first associated identity and the second associated identity are the same and are configured by the different network devices to the terminal device, transmit, to the first network device, the first information to indicate that the first associated identity and the second associated identity are a repetitive associated identity, andwherein the second information comprises at least one of:an indication of whether the repetitive associated identity is applicable,an updated inference configuration for the repetitive associated identity,an updated training configuration for the repetitive associated identity,an updated performance monitoring configuration for the repetitive associated identity,an indication to handle a life cycle management procedure associated with the repetitive associated identity, ora timer configuration indicating a time duration after which an updated configuration is to be applied to the repetitive associated identity.15.The communication device of claim 9, wherein the communication device comprises a terminal device, the first associated identity is configured by a second network device to the terminal device, and the first information is transmitted in response to a handover from the second network device to the first network device, and the first information comprises at least one of:the first associated identity,an identification of an activated machine learning (ML) model entity corresponding to the first associated identity,an inference configuration for the activated ML model entity,a data set configuration for the activated ML model entity,a cell identity corresponding to the activated ML model entity, oran identity of a network device corresponding to the activated ML model entity.16.A terminal device comprising:a processor configured to cause the terminal device to:receive, from a network device, a set of associated identities for a machine learning (ML) model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; andtrain the ML model entity based on mapping between the set of associated identities and the set of training configurations.17.A network device comprising:a processor configured to cause the network device to:transmit, to a terminal device, a set of associated identities for a machine learning (ML) model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities, and the ML model entity is trained based on mapping between the set of associated identities and the set of training configurations.18.A communication method implemented at a first network device, comprising:receiving, from a communication device, first information related to a first associated identity corresponding to a first additional network condition;determining, based on the first information, a relation between the first associated identity and a second associated identity corresponding to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices; andtransmitting, to the communication device based on the relation, second information for handling at least one of the first associated identity or the second associated identity.19.A communication method implemented at a communication device, comprising:transmitting, to a first network device, first information related to a first associated identity corresponding to a first additional network condition; andreceiving, from the first network device, second information for handling at least one of the first associated identity or a second associated identity to a second additional network condition, wherein the first associated identity and the second associated identity are configured by different network devices, and the second information is based on a relation between the first associated identity and the second associated identity.20.A communication method implemented at a terminal device, comprising:receiving, from a network device, a set of associated identities for a machine learning (ML) model entity, and a set of training configurations for the ML model entity, wherein a training configuration in the set of training configurations is mapped to one or more associated identities in the set of associated identities; andtraining the ML model entity based on mapping between the set of associated identities and the set of training configurations.
Citation Information
Patent Citations
Method and apparatus for base station identification discovery in wireless communications
US20130225168A1
User equipment and method for multi-SIM operation
US20230189212A1
Group-based management of artificial intelligence and machine learning models
WO2024092722A1
Methods to for reporting feedback related to ai / ML events
WO2024094868A1
User equipment, access network node, and methods thereof for implementing ai / ML models
WO2024171940A1