Response to management schemes having different communication control models

Abstract

A communication control device according to the present invention is provided with at least one processor that executes: when communication control models relating to communication control between user equipment (UE) and a network (NW) that provides a communication service to the UE can be managed by different management schemes by the UE and the NW, associating UE-side IDs of communication control models managed by the UE and NW-side IDs of communication control models managed by the NW by an ID association unit; and providing specification information for specifying correct communication control models conforming to a correspondence relationship between the UE-side IDs and the NW-side IDs from at least one of the UE and the NW to the other of the UE and the NW by a specification information provision unit.

Description

Support for different management schemes for communication control models

[0001] The present disclosure relates to accommodating different management schemes for communication control models.

[0002] The number, types, and uses of wireless communication devices (hereinafter referred to as communication devices), such as smartphones and Internet of Things (IoT) devices, are steadily increasing, and wireless communication standards are continually being expanded and improved. For example, commercial service for the fifth-generation mobile communication system, known as "5G," began in 2018, and standardization is still underway at the Third Generation Partnership Project (3GPP). Efforts are also underway to develop standards for the sixth-generation mobile communication system, or "6G," as the next-generation wireless communication standard following 5G.

[0003] With the advancement of artificial intelligence (AI) and machine learning (ML) technologies (hereinafter collectively referred to as AI / ML or AIML), studies are underway to utilize these AI / ML technologies for communication control in mobile communication networks. Mobile communication networks are divided into two parts: the communication device side, also referred to as UE (User Equipment) (hereinafter also referred to as UE side), and the network side, including base stations that provide communication services to UE (hereinafter also referred to as NW side or base station side).

[0004] US Patent Application Publication No. 2021 / 0168643

[0005] Various management schemes have been proposed to appropriately manage the AI / ML model (hereinafter also referred to as the communication control model) for communication control between communication devices and networks on both the communication device side and the network side. Since each management scheme has its advantages and disadvantages, it is possible that multiple different management schemes will ultimately be adopted in wireless communication standards such as 5G. In such cases, it is expected that different management schemes will be used on the communication device side and the network side.

[0006] The present disclosure has been made in view of the above circumstances, and provides a communication control device and the like that can appropriately handle different management schemes for communication control models on the communication device side and the network side.

[0007] A communication control device of one aspect of the present disclosure includes at least one processor that, when the communication device and the network that provides communication services to the communication device can manage a communication control model related to communication control between the communication device and the network that provides communication services to the communication device using different management schemes, performs the following operations: an ID matching unit matches the communication device side ID of the communication control model managed by the communication device with the network side ID of the communication control model managed by the network; and a specific information providing unit provides specific information from at least one of the communication device and the network to the other of the communication device and the network that allows the other of the communication device and the network to identify the correct communication control model in accordance with the correspondence between the communication device side ID and the network side ID.

[0008] In this aspect, specific information conforming to a correspondence relationship between a communication device side ID of a communication control model managed by the communication device and a network side ID of a communication control model managed by the network is provided from at least one of the communication device and the network to the other. The other of the communication device and the network that receives the specific information can identify the correct communication control model conforming to the correspondence relationship between the communication device side ID and the network side ID. Therefore, even if a management scheme different from that of the communication device or the network that transmitted the specific information is used, appropriate communication control can be achieved between the communication device and the network based on the communication control model.

[0009] Another aspect of the present disclosure is a communication control method, which, when the communication device and the network can manage a communication control model relating to communication control between the communication device and the network that provides communication services to the communication device using different management schemes, performs the following steps: associates a communication device ID of a communication control model managed by the communication device with a network ID of a communication control model managed by the network; and provides, from at least one of the communication device and the network, identification information that allows the other of the communication device and the network to identify a correct communication control model in accordance with the correspondence between the communication device ID and the network ID.

[0010] Yet another aspect of the present disclosure is a storage medium storing a communication control program that causes a computer to execute the following steps: when the communication device and the network that provides communication services to the communication device can manage a communication control model related to communication control between the communication device and the network using different management schemes, associate a communication device ID of a communication control model managed by the communication device with a network ID of a communication control model managed by the network; and provide, from at least one of the communication device and the network, identification information that causes the other of the communication device and the network to identify a correct communication control model in accordance with the correspondence between the communication device ID and the network ID.

[0011] Any combination of the above components, or any conversion of these expressions into methods, devices, systems, recording media, computer programs, etc., are also encompassed within the present disclosure.

[0012] According to the present disclosure, it is possible to appropriately deal with different management schemes for communication control models on the communication device side and the network side.

[0013] 1 is a functional block diagram of a communication control device; FIG. 2 is a diagram of a first embodiment of associating a UE ID with a NW ID by an ID associating unit; FIG. 3 is a diagram of a fourth embodiment of associating a UE ID with a NW ID by an ID associating unit; FIG. 4 is a diagram of an example in which an ID associating unit includes information on a model ID as a UE ID in information on a function ID as a NW ID; FIG. 5 is a diagram of an example in which an ID associating unit includes information on a function ID as a NW ID in information on a model ID as a UE ID; FIG. 6 is a diagram of a proposal document; FIG. 7 is a diagram of a proposal document; FIG. 8 is a diagram of a proposal document;

[0014] Hereinafter, with reference to the drawings, a detailed description will be given of a form for carrying out the present disclosure (hereinafter also referred to as an embodiment). In the description and / or drawings, the same or equivalent components, members, processes, etc. are designated by the same reference numerals, and redundant description will be omitted. The scale and shape of each part shown in the drawings are set for convenience to simplify the description, and should not be interpreted as limiting unless otherwise specified. The embodiment is an example and does not limit the scope of the present disclosure in any way. All features and combinations thereof presented in the embodiments are not necessarily essential to the present disclosure.

[0015] For convenience, the embodiments are presented by breaking down the embodiments into components for each function and / or each group of functions that realize the functions. However, one component in the embodiments may actually be realized by a combination of multiple separate components, or multiple components in the embodiments may actually be realized by a single integrated component. Furthermore, in describing the wireless communication system in the present embodiments, terminology in existing wireless communication standards such as 5G is used for convenience. This is not intended to limit the present disclosure to 5G or the like, and does not prevent the present disclosure from being applied when a technology similar to the present disclosure is provided under a different name in future wireless communication systems such as 6G.

[0016] FIG. 1 schematically illustrates an overview of a wireless communication system 1 to which a communication control device according to an embodiment of the present disclosure is applied. The wireless communication system 1 includes a 5G wireless communication system 11, a 4G wireless communication system 12, and a satellite communication system 13. The 5G wireless communication system 11 conforms to a fifth-generation mobile communication system (5G) that uses NR (New Radio) or 5G NR (Fifth Generation New Radio) as a radio access technology (RAT) and 5GC (Fifth Generation Core) as a core network (CN). The 4G wireless communication system 12 conforms to a fourth-generation mobile communication system (4G) that uses LTE (Long Term Evolution) or LTE-Advanced as a radio access technology and EPC (Evolved Packet Core) as a core network. The satellite communication system 13 is responsible for satellite communication via a communication satellite 131. Although not shown, the wireless communication system 1 may include a wireless communication system of a generation earlier than 4G, a wireless communication system of a generation later than 5G (such as 6G), or any wireless communication system that cannot be associated with a generation such as Wi-Fi (registered trademark). Furthermore, the wireless communication system 1 may not include some or all of the 5G wireless communication system 11, the 4G wireless communication system 12, and the satellite communication system 13.

[0017] The 5G wireless communication system 11 includes communication devices 2A, 2B, 2C, and 2D (hereinafter collectively referred to as communication devices 2) such as smartphones that are installed on the ground and are also referred to as UE (User Equipment) or UT (User Terminal), and multiple 5G base stations 111A, 111B, and 111C (hereinafter collectively referred to as 5G base stations 111) that can communicate via 5G NR. The base station 111 in 5G is also called a gNodeB (gNB). The communication range or support range of each of the 5G base stations 111A, 111B, and 111C is called a cell, and is illustrated as 112A, 112B, and 112C, respectively (hereinafter collectively referred to as 5G cells 112).

[0018] The size of the 5G cell 112 of each 5G base station 111 is arbitrary, but typically has a radius of several meters to several tens of kilometers. Although there is no established definition, a cell with a radius of several meters to several tens of meters is called a femtocell, a cell with a radius of tens to several tens of meters is called a picocell, a cell with a radius of several tens to several hundred meters is called a microcell, and a cell with a radius of more than several hundred meters is called a macrocell. 5G often uses high-frequency radio waves such as millimeter waves, and because of their high line-propagation ability, the radio waves are blocked by obstacles, shortening the communication distance. For this reason, 5G tends to use smaller cells than 4G and earlier generations.

[0019] A communication device 2 can perform 5G communication if it is located within at least one of multiple 5G cells 112A, 112B, and 112C. In the illustrated example, a communication device 2B located within 5G cells 112A and 112B can communicate with both 5G base stations 111A and 111B via 5G NR. Furthermore, a communication device 2C located within 5G cell 112C can communicate with 5G base station 111C via 5G NR. Communication devices 2A and 2D are located outside all of the 5G cells 112A, 112B, and 112C and are therefore unable to communicate via 5G NR. 5G communication via 5G NR between each communication device 2 and each 5G base station 111 is managed by the 5GC, which is a core network. For example, the 5GC handles data exchange with each 5G base station 111, data exchange with external networks such as EPC, satellite communication system 13, and the Internet, and mobility management of the communication device 2.

[0020] The 4G wireless communication system 12 includes multiple 4G base stations 121 (only one is shown in FIG. 1 ). The multiple 4G base stations 121 are installed on the ground and are capable of communicating with the communication device 2 via LTE or LTE-Advanced. In 4G, the base station 121 is also called an eNodeB (eNB). Like each 5G base station 111, the communication range or support area of ​​each 4G base station 121 is also called a cell and is illustrated as 122.

[0021] If the communication device 2 is located inside the 4G cell 122, it can perform 4G communication. In the illustrated example, communication devices 2A and 2B located inside the 4G cell 122 can communicate with the 4G base station 121 via LTE or LTE-Advanced. Communication devices 2C and 2D are located outside the 4G cell 122 and therefore cannot communicate via LTE or LTE-Advanced. 4G communication by LTE or LTE-Advanced between each communication device 2 and each 4G base station 121 is managed by the EPC, which is a core network. For example, the EPC handles the exchange of data with each 4G base station 121, the exchange of data with external networks such as 5GC, the satellite communication system 13, and the Internet, and the mobility management of the communication device 2.

[0022] Focusing on each of the communication devices 2A, 2B, 2C, and 2D, in the illustrated example, communication device 2A is capable of 4G communication with 4G base station 121, communication device 2B is capable of 5G communication with 5G base stations 111A and 111B and 4G communication with 4G base station 121, and communication device 2C is capable of 5G communication with 5G base station 111C. When there are multiple base stations (111A, 111B, 121) with which communication is possible, as with communication device 2B, one base station determined to be optimal in terms of communication quality, etc. is selected under the management of the core network 5GC and / or EPC, and communication with communication device 2B is performed. Furthermore, communication device 2D is not capable of communication with any of the 5G base stations 111 and 4G base station 121, and therefore performs communication via satellite communication system 13, which will be described next.

[0023] The satellite communication system 13 is a wireless communication system that uses a communication satellite 131, a low-orbit satellite that flies in space at an altitude of approximately 500 km to 700 km above the Earth's surface, as a non-terrestrial base station. Similar to the 5G base station 111 and the 4G base station 121, the communication coverage or support area of ​​the communication satellite 131 is also called a cell and is illustrated as 132. In this way, the communication satellite 131, as a non-terrestrial base station, provides the satellite communication cell 132, as a non-terrestrial communication cell, to the ground. A terrestrial communication device 2 can perform satellite communication if it is located within the satellite communication cell 132. Similar to the 5G base station 111 in the 5G wireless communication system 11 and the 4G base station 121 in the 4G wireless communication system 12, the communication satellite 131, as a base station in the satellite communication system 13, can wirelessly communicate with the communication device 2 within the satellite communication cell 132 directly or indirectly via an aircraft or the like. The radio access technology that the communication satellite 131 uses for radio communication with the communication device 2 in the satellite communication cell 132 may be 5G NR, the same as the 5G base station 111, or LTE or LTE-Advanced, the same as the 4G base station 121, or any other radio access technology that can be used by the communication device 2. Therefore, the communication device 2 does not need to be provided with special functions or components for satellite communication.

[0024] The satellite communication system 13 includes a gateway 133 as a ground station installed on the ground and capable of communicating with a communication satellite 131. The gateway 133 includes a satellite antenna for communicating with the communication satellite 131, and is connected to a 5G base station 111 and a 4G base station 121 as terrestrial base stations constituting a terrestrial network (TN) via their respective wireless access technologies, such as 5G NR or LTE, or other wired or wireless access technologies or interfaces. In this way, the gateway 133 connects the non-terrestrial network (NTN) constituted by the communication satellite 131 as a non-terrestrial base station or satellite base station and the TN constituted by the terrestrial base stations 111 and 121 so that they can communicate with each other. When the communication satellite 131 performs 5G communication with the communication device 2 in the satellite communication cell 132 using 5G NR, the 5GC connected via the gateway 133 and the 5G base station 111 (or a 5G radio access network) in the TN is used as the core network, and when the communication satellite 131 performs 4G communication with the communication device 2 in the satellite communication cell 132 using LTE or LTE-Advanced, the EPC connected via the gateway 133 and the 4G base station 121 (or a 4G radio access network) in the TN is used as the core network. In this way, appropriate cooperation is achieved between different wireless communication systems such as 5G communication, 4G communication, and satellite communication via the gateway 133.

[0025] Satellite communication using a communication satellite 131 is primarily used to cover areas where terrestrial base stations such as the 5G base station 111 and the 4G base station 121 are not installed or are few in number. In the illustrated example, a communication device 2D located outside the communication cells of all terrestrial base stations communicates with the communication satellite 131. Meanwhile, communication devices 2A, 2B, and 2C that can communicate satisfactorily with any terrestrial base station are also within the satellite communication cell 132 and can therefore communicate with the communication satellite 131. However, by communicating with the terrestrial base station rather than the communication satellite 131 as a satellite base station, the limited communication resources (including power) of the communication satellite 131 are conserved for the communication device 2D and the like. The communication satellite 131 improves the quality of communication with the communication device 2D by directing communication radio waves toward the communication device 2D within the satellite communication cell 132 using beamforming.

[0026] The size of the satellite communication cell 132 of the communication satellite 131 serving as a satellite base station can be set arbitrarily depending on the number of beams emitted by the communication satellite 131. For example, a maximum of 2,800 beams can be combined to form a satellite communication cell 132 with a diameter of approximately 24 km. As shown in the figure, the satellite communication cell 132 is typically larger than terrestrial communication cells such as the 5G cell 112 and the 4G cell 122, and may include one or more 5G cells 112 and / or 4G cells 122 therein. Note that, although the above example illustrates a communication satellite 131 flying in low orbit at an altitude of approximately 500 km to 700 km above the Earth's surface as a flying non-terrestrial base station, a communication satellite flying in high orbit such as a geostationary orbit, or an unmanned or manned aircraft or drone flying in the atmosphere at a lower altitude (e.g., approximately 20 km above the Earth's surface) such as the stratosphere, may also be used as a non-terrestrial base station in addition to or instead of the communication satellite 131.

[0027] 2 is a functional block diagram of the communication control device 3 according to this embodiment. The communication control device 3 includes an ID associating unit 31, a specific information providing unit 32, and a confirmation unit 33. As long as the communication control device 3 can achieve at least some of the functions and / or effects described below, some of these functional blocks may be omitted. These functional blocks are realized by the cooperation of hardware resources, such as a computer's central processing unit, memory, input devices, output devices, and peripheral devices connected to the computer, and software executed using these resources. Regardless of the type of computer or its location, each of the above functional blocks may be realized by the hardware resources of a single computer or by combining hardware resources distributed across multiple computers.

[0028] In particular, in this embodiment, some or all of the functional blocks of the communication control device 3 may be realized in a centralized or distributed manner by computers or processors provided in at least one of a communication device UE similar to the above-mentioned communication device 2, a network NW including a radio access network (RAN) and / or a core network configured by base stations similar to at least one of the above-mentioned base stations 111, 121, and 131, and various communication stations (relay stations (repeaters), IAB (Integrated Access and Backhaul) nodes, gateway 133, etc.) not shown that configure the RAN together with the base stations.

[0029] As will be described later, in this embodiment, at least one of the communication device UE and the network NW performs main processing by the ID associating unit 31. Furthermore, the one performs main processing by the specific information providing unit 32 and the confirmation unit 33 for the other. For simplicity of explanation, the following describes an example in which the network NW functions as the one device and the communication device UE functions as the other device. Therefore, in FIG. 2 corresponding to this example, the ID associating unit 31, the specific information providing unit 32, and the confirmation unit 33 are shown on the network NW side. However, the present disclosure can also be applied to a case in which the communication device UE functions as the one device and the network NW functions as the other device (simply swap the communication device UE and the network NW in the following explanation). In this case, the main parts of the ID associating unit 31, the specific information providing unit 32, and the confirmation unit 33 are provided on the communication device UE side (not shown).

[0030] In this embodiment, communication control between a communication device UE and a network NW that provides communication services to the communication device UE is performed using an AI / ML model (communication control model) based on AI / ML technology. In communication control, cooperative operation of the network NW and the communication device UE as communication subjects is required, and corresponding (or cooperative) AI / ML models are provided on both the network NW side and the communication device UE side.

[0031] As shown in the schematic diagram, one or more m (m is any natural number) network-side (NW-side) AI / ML models M1-1 to M1-m are provided on the network NW side so as to be usable by the network NW (e.g., a core network). The NW-side AI / ML models M1-1 to M1-m are hereinafter collectively referred to as the NW-side AI / ML model M1. The NW-side AI / ML model is also simply referred to as the NW-side model (M1). The NW-side model M1 available to the network NW is stored in storage inside or outside the network NW that is accessible by the network NW. Preferably, at least a portion of the NW-side models M1 available to the network NW (e.g., those that are frequently used) are stored in storage within the network NW.

[0032] Similarly, one or more n (n is any natural number) communication device side (UE side) AI / ML models M2-1 to M2-n are provided on the communication device UE side so as to be usable by the communication device UE. The UE side AI / ML models M2-1 to M2-n are hereinafter collectively referred to as the UE side AI / ML model M2. The UE side AI / ML model is also simply referred to as the UE side model (M2). The UE side model M2 usable by the communication device UE is stored in storage inside or outside the communication device UE that is accessible by the communication device UE. Preferably, at least a portion of the UE side models M2 usable by the communication device UE (e.g., those that are frequently used) are stored in storage within the communication device UE.

[0033] One or more NW-side models M1 and / or one or more UE-side models M2 may be provided corresponding to various use cases in communication control between the network NW and the communication device UE. Examples of the use cases include: improving channel state information (CSI) feedback for reduced overhead, improved accuracy, and appropriate prediction; beam management for improved beam selection accuracy and beam prediction in the time domain and / or the spatial domain for reduced overhead and delay; and improving positioning accuracy for different scenarios (e.g., including severe non-line-of-site (NLOS) environments). For example, when the network NW and the communication device UE cooperate to support a certain use case, the network NW selects, deploys, or executes one or more NW-side models M1 corresponding to the use case, and the communication device UE selects, deploys, or executes one or more UE-side models M2 corresponding to the use case.

[0034] In this way, in order for the network NW and the communication device UE to select and cooperate with each other through the AI / ML models M1 and M2, the NW-side model M1 used on the network NW side and the UE-side model M2 used on the communication device UE side must be consistent with each other. If the AI / ML models M1 and M2 are managed by the same management scheme on the network NW side and the communication device UE side, consistency can be easily ensured when the network NW side and the communication device UE side select the AI / ML models M1 and M2 based on a common ID or the like set under the management scheme.

[0035] However, as shown in the following specific example, the management schemes of the AI / ML models M1 and M2 (communication control models) related to communication control between the network NW and the communication device UE are not unified, and various management schemes have been proposed. Because each management scheme has its own advantages and disadvantages, it is possible that multiple different management schemes will ultimately be adopted in wireless communication standards such as 5G. In such a case, it is expected that different management schemes will be used on the network NW side and the communication device UE side. Therefore, this embodiment provides a communication control device 3 that can appropriately handle the different management schemes of the AI / ML models M1 and M2 on the network NW side and the communication device UE side.

[0036] The management scheme may also be referred to as a life cycle management (LCM) scheme for AI / ML models (communication control models). A life cycle management scheme is a scheme, system, or framework for managing each AI / ML model in each phase of its life cycle or service life. For example, to consistently manage each AI / ML model throughout each phase of its life cycle, such as generation, training, testing, deployment, monitoring, optimization, and retirement, an appropriate life cycle management scheme may be individually configured on the network NW side and the communication device UE side.

[0037] As described below, the management scheme or LCM scheme manages each AI / ML model based on an ID that uniquely identifies the entire AI / ML model or its components, and configuration data that configures or defines the entire AI / ML model or its components. The configuration data may be updated or changed as needed throughout the lifecycle of each AI / ML model. Meanwhile, the ID, in principle, remains unchanged throughout the lifecycle of each AI / ML model (from creation to retirement).

[0038] Hereinafter, the management scheme used by the network NW to manage its own NW-side model M1 will be referred to as the "NW-side AI / ML model management scheme" and denoted by SC1. The NW-side AI / ML model management scheme (SC1) will also be simply referred to as the NW-side management scheme (SC1) or the first scheme (SC1). Similarly, the management scheme used by the communication device UE to manage its own UE-side model M2 will be referred to as the "UE-side AI / ML model management scheme" and denoted by SC2. The UE-side AI / ML model management scheme (SC2) will also be simply referred to as the UE-side management scheme (SC2) or the second scheme (SC2).

[0039] Under the first scheme SC1 on the network NW side, one or more NW-side AI / ML models M1-1 to M1-m are managed. Each NW-side AI / ML model M1 includes a network-side ID (NW-side ID) for uniquely identifying it and network-side configuration data (NW-side configuration data) that configures or defines it. Note that the term "NW-side AI / ML model" here refers to the entire NW-side AI / ML model or its components. In the former case, the NW-side ID uniquely identifies the entire NW-side AI / ML model, and the NW-side configuration data configures or defines the entire NW-side AI / ML model. In the latter case, the NW-side ID uniquely identifies the components (e.g., functions and procedures described below) of the NW-side AI / ML model, and the NW-side configuration data configures or defines the components of the NW-side AI / ML model. In this latter case, a single NW-side AI / ML model or its entire lifecycle can typically be realized by combining multiple components.

[0040] Under the second scheme SC2 on the communication device UE side, one or more UE-side AI / ML models M2-1 to M2-n are managed. Each UE-side AI / ML model M2 includes a communication device ID (UE ID) for uniquely identifying it and communication device configuration data (UE configuration data) that configures or defines it. Note that the term "UE-side AI / ML model" here refers to the entire UE-side AI / ML model or its components. In the former case, the UE ID uniquely identifies the entire UE-side AI / ML model, and the UE configuration data configures or defines the entire UE-side AI / ML model. In the latter case, the UE ID uniquely identifies the components of the UE-side AI / ML model (e.g., functions and procedures, as described below), and the UE configuration data configures or defines the components of the UE-side AI / ML model. In this latter case, a single UE-side AI / ML model or its entire lifecycle can typically be realized by combining multiple components.

[0041] Although the first scheme SC1 and the second scheme SC2 may be the same at least temporarily, in the following description of the present embodiment, the first scheme SC1 and the second scheme SC2 are assumed to be different from each other. That is, in the following description, the network NW and the communication device UE use different management schemes SC1 and SC2, respectively. Specifically, an example will be described in detail in which the NW-side management scheme SC1 used by the network NW is a so-called functionality-based management scheme, and the UE-side management scheme SC2 used by the communication device UE is a so-called model-based management scheme.

[0042] However, the present disclosure can also be applied to a case where the NW-side management scheme SC1 is any management scheme other than the function-based management scheme, and the UE-side management scheme SC2 is any management scheme other than the model-based management scheme. Furthermore, although not shown in the figures, for example, on the network NW side (or the communication device UE side), multiple different management schemes (for example, both the function-based management scheme and the model-based management scheme) may be implemented in parallel.

[0043] Note that the "function-based management scheme" and "model-based management scheme" exemplified below are provisional or fluid in the proposal or discussion stage. Therefore, when these management schemes are ultimately adopted in wireless communication standards such as 5G, their names and contents may change significantly. Furthermore, management schemes different from the function-based management scheme and the model-based management scheme may be proposed and ultimately adopted in wireless communication standards such as 5G. Regardless of the specific names and contents of these schemes, the present disclosure is broadly applicable to cases where a network NW and a communication device UE may use different management schemes SC1 and SC2.

[0044] Based on the above understanding, a function-based management scheme as an example of the NW-side management scheme SC1 and a model-based management scheme as an example of the UE-side management scheme SC2 will be specifically illustrated. First, the model-based management scheme (SC2) will be specifically explained, and then the function-based management scheme (SC1) will be specifically explained.

[0045] In the model-based management scheme SC2, a unique model ID (UE-side ID) is assigned to each UE-side AI / ML model as a whole. That is, the model ID set under the model-based management scheme SC2 uniquely identifies the entire AI / ML model. The UE-side configuration data, which may be expressed as metadata for such a model ID, may be the entire AI / ML model itself (e.g., a mathematical model based on artificial intelligence and / or machine learning that performs intelligent processing such as inference on inputs and outputs results), or a collection of all components of the AI / ML model (e.g., parameters, functions, procedures). Thus, under the model-based management scheme SC2, LCM and other processes are performed on the entire AI / ML model basis. Therefore, compared to the function-based management scheme SC1 described below, the configuration of each AI / ML model is rigid and lacks flexibility. However, the model-based management scheme SC2 has the advantage of dramatically improving processing efficiency and accuracy by, for example, optimizing the AI / ML model in advance for routine, rarely changing, and rarely exception-prone processes.

[0046] Note that even under the model-based management scheme SC2, changes within the framework of each AI / ML model, such as updating parameters as components (UE-side configuration data) of each AI / ML model, are possible. When parameters of an existing AI / ML model are updated, a new AI / ML model having the updated parameters may be generated and assigned a new model ID. This new model ID may be generated by incrementing a numeric string, such as a prefix or suffix, that is part of the model ID of the existing AI / ML model.

[0047] Under the model-based management scheme SC2 described above, one or more UE-side AI / ML models M2 to be actually used on the communication device UE side are selected based on the AI / ML capabilities of the communication device UE in which it is implemented and the use cases that the communication device UE should support using the AI / ML functions (in cooperation with the network NW). Here, the communication device UE may select an appropriate UE-side AI / ML model M2 autonomously (i.e., without instructions or signaling from the network NW), or may select an appropriate UE-side AI / ML model M2 in response to instructions or signaling from the network NW.

[0048] In the function-based management scheme SC1, a unique function ID (network-side ID) is assigned to each component of each network-side AI / ML model. That is, the function ID set under the function-based management scheme SC1 uniquely identifies the component of the AI / ML model. In contrast to the model-based management scheme SC2 described above, under the function-based management scheme SC1, the configuration of each AI / ML model is not strictly defined (it may be expressed as an open format). Typically, each AI / ML model or its entire lifecycle can be realized by a combination of individual functions and procedures identified by function IDs. In this way, the component of a network-side AI / ML model to which a function ID is assigned plays a part of the network-side AI / ML model or its entire lifecycle. For example, a function ID may be assigned to some functions of a network-side AI / ML model executed at a certain point in time, or a function ID may be assigned to a procedure related to a certain phase in the lifecycle of a network-side AI / ML model.

[0049] For example, a function to which a function ID is assigned may specify the deployment architecture of an AI / ML model. Examples of the deployment architecture include the mode and level of collaboration between the network NW and the communication device UE when deploying an AI / ML model, and the entity (network NW and / or communication device UE) that leads the collaboration. Furthermore, a procedure to which a function ID is assigned may consist of one or more steps or processes related to a phase in the lifecycle of the AI / ML model. Examples of steps include updating the AI / ML model, transferring the AI / ML model, and monitoring the AI / ML model. Note that at least some of these steps may be executed by the communication device UE as the collaboration partner. Here, each individual step merely realizes a part of the LCM throughout the lifecycle of the AI / ML model. However, by selecting appropriate steps according to the phase in the lifecycle of the AI / ML model, LCM throughout the lifecycle of the AI / ML model can be effectively realized. The specific content and related parameters of the above functions and procedures are defined by network-side configuration data, which may be represented as metadata of the function ID (network-side ID).

[0050] As described above, under the function-based management scheme SC1, LCM and other processes are performed for each AI / ML model or part of its entire lifecycle. This allows for the flexible selection of functions and procedures appropriate for each phase in the lifecycle of an AI / ML model to achieve optimal AI / ML functionality. This highly flexible function-based management scheme SC1 is well-suited for non-routine processes that are subject to frequent changes and exceptions, and processes that are sensitive to the presence or level of AI / ML capabilities of communication devices (UE) and networks (NW).

[0051] Under the above-described function-based management scheme SC1, one or more functions and procedures of the NW-side AI / ML model M1 to be actually used on the network NW side are selected based on the AI / ML capabilities of the network NW in which it is implemented or the communication device UE as a cooperative partner, and the use case that the network NW (in cooperation with the communication device UE) should support using the AI / ML functions. Here, the network NW may select appropriate functions and procedures of the NW-side AI / ML model M1 autonomously (i.e., without instructions or signaling from the communication device UE), or may select appropriate functions and procedures of the NW-side AI / ML model M1 in response to instructions or signaling from the communication device UE. The NW-side AI / ML model M1 to be actually used on the network NW side for the current use case is constructed by one or more functions and procedures selected in this way.

[0052] Next, a description will be given of the communication control device 3 that can handle a situation in which the function-based management scheme SC1 is used on the network NW side and the model-based management scheme SC2 is used on the communication device UE side as described above. As described above, the communication control device 3 includes an ID associating unit 31, a specific information providing unit 32, and a confirmation unit 33.

[0053] The ID associating unit 31 associates the UE-side ID of the UE-side AI / ML model M2 (the entire model) managed by the communication device UE under the model-based management scheme SC2 with the NW-side ID of the NW-side AI / ML model M1 (components such as functions and procedures) managed by the network NW under the function-based management scheme SC1. The specific information providing unit 32 provides specific information from at least one of the communication device UE and the network NW (the network NW in this embodiment) to the other of the communication device UE and the network NW (the communication device UE in this embodiment) that causes the other to identify a correct communication control model (the UE-side AI / ML model M2 in this embodiment) in accordance with the correspondence between the UE-side ID and the NW-side ID associated by the ID associating unit 31. For example, the specific information providing unit 32 provides specific information from the network NW to the communication device UE to enable the communication device UE to identify one or more UE side IDs (i.e., one or more UE side AI / ML models M2 corresponding thereto) that correspond to the NW side IDs of one or more NW side AI / ML models M1 used on the network NW side.

[0054] Various embodiments are possible for the manner in which the ID associating unit 31 associates the UE side ID with the NW side ID and the manner in which the corresponding specific information is provided by the specific information providing unit 32, as listed below.

[0055] 3 shows a first example of association between UE-side IDs and NW-side IDs by the ID associating unit 31. In this embodiment, the ID associating unit 31 provided on the network NW side creates an ID association table as shown in FIG. 3 , which contains information on the association between UE-side IDs and NW-side IDs. The ID association table in the illustrated example is composed of three columns. The first column is a list of model IDs (UE-side IDs / Model IDs) set under a model-based management scheme SC2 on the communication device UE side. The second column is a list of function IDs (NW-side IDs / Functionality IDs) set under a function-based management scheme SC1 on the network NW side. The third column is a list of model IDs (NW-side IDs / Model Sets) that are optionally set when the network NW can use a model-based management scheme in addition to or instead of the function-based management scheme SC1 and are set under the model-based management scheme on the network NW side.

[0056] The information in the first column about the communication device UE and the information in the third column about the network NW are both model IDs set under the model-based management scheme. However, since it is considered that one model ID (UE-side AI / ML model) set on the communication device UE side is often set to multiple model IDs (NW-side AI / ML models) in the network NW that handles various processes, the expression "Model Set" is used in the third column to mean one or multiple (especially multiple) model IDs.

[0057] The model IDs on the communication device UE side in the first column, the function IDs on the network NW side in the second column, and the model IDs (model sets) on the network NW side in the third column are associated with one another by the ID associating unit 31. For example, when the communication device UE uses a UE-side AI / ML model with model ID "1", the network NW can realize the desired AI / ML function in cooperation with the communication device UE by using a NW-side AI / ML model (a set of components such as functions and procedures) with function ID "20" or a set of NW-side AI / ML models with model ID "B".

[0058] In this embodiment, the identification information providing unit 32 provided on the network NW side provides the communication device UE with the communication device UE-side model ID (information in the first column) associated with the function ID (information in the second column) or model ID (information in the third column) used by the network NW as identification information. For example, if the network NW uses a NW-side AI / ML model (a set of components such as functions and procedures) with a function ID of "20" or a set of NW-side AI / ML models with a model ID of "B," the corresponding communication device UE-side model ID of "1" is provided from the network NW to the communication device UE as identification information. As a result, the communication device UE can identify the correct UE-side AI / ML model M2 for cooperating with the network NW based on its own model ID "1" provided by the network NW as identification information.

[0059] In the first embodiment described above, the communication device ID (e.g., model ID “1”) and the network ID (e.g., function ID “20” or model ID “B”) are different from each other. For cooperative operation between the communication device UE and the network NW, the identification information providing unit 32 provides the second ID (e.g., model ID “1”) used by the communication device UE, which is associated with the first ID (e.g., function ID “20” or model ID “B”) used by the network NW, from the network NW to the communication device UE as identification information. In this case, the network NW notifies the communication device UE of only a small number of model IDs extracted from the ID correspondence table, rather than the entire ID correspondence table of FIG. 3 . This reduces the signaling load from the network NW to the communication device UE. Furthermore, the communication device UE can stably operate under its own model-based management scheme SC2, regardless of whether the network NW uses a function-based management scheme or a model-based management scheme.

[0060] In the second embodiment, the information in the first column in Fig. 3 is used on both the communication device UE side and the network NW side. As described above, the information in the first column is originally the model ID on the communication device UE side, but in the second embodiment, it is also used as the function ID on the network NW side. For example, in the first embodiment, the model ID "1" on the communication device UE side was associated with the function ID "20" on the network side, but in the second embodiment, the model ID "1" on the communication device UE side is associated with the function ID "1" on the network side.

[0061] Although such a common ID appears to be the same on the communication device UE side and the network NW side, its actual meaning is different on the communication device UE side and the network NW side. That is, on the communication device UE side, the common ID specifies a UE-side AI / ML model under the model-based management scheme SC2, and on the network NW side, it specifies a NW-side AI / ML model (a set of components such as functions and procedures) under the function-based management scheme SC1.

[0062] As described above, in the second embodiment, the ID associating unit 31 sets the communication device side ID (e.g., model ID "1") and the network side ID (e.g., function ID "1") to the same common ID (e.g., "1"). The specific information providing unit 32 provides the common ID as specific information from the network NW to the communication device UE for cooperative operation between the communication device UE and the network NW. In this case, the network NW notifies the communication device UE of only a small number of model IDs extracted from the ID correspondence table, rather than the entire ID correspondence table of FIG. 3 . This reduces the signaling load from the network NW to the communication device UE. Furthermore, the communication device UE can stably operate under its own model-based management scheme SC2, regardless of whether the network NW uses a function-based management scheme or a model-based management scheme.

[0063] In the third embodiment, the information in the second column in Fig. 3 is used on both the communication device UE side and the network NW side. As described above, the information in the second column is originally the function ID on the network NW side, but in the third embodiment, it is also used as the model ID on the communication device UE side. For example, in the first embodiment, the function ID "20" on the network NW side was associated with the model ID "1" on the communication device UE side, but in the third embodiment, the function ID "20" on the network NW side is associated with the model ID "20" on the communication device UE side.

[0064] Although such a common ID appears to be the same on the communication device UE side and the network NW side, its actual meaning is different on the communication device UE side and the network NW side. That is, on the communication device UE side, the common ID specifies a UE-side AI / ML model under the model-based management scheme SC2, and on the network NW side, it specifies a NW-side AI / ML model (a set of components such as functions and procedures) under the function-based management scheme SC1.

[0065] As described above, in the third embodiment, the ID associating unit 31 sets the communication device side ID (e.g., model ID "20") and the network side ID (e.g., function ID "20") to the same common ID (e.g., "20"). The specific information providing unit 32 provides the common ID as specific information from the network NW to the communication device UE for cooperative operation between the communication device UE and the network NW. In this case, the network NW notifies the communication device UE of only a small number of model IDs extracted from the ID correspondence table, rather than the entire ID correspondence table of FIG. 3. This reduces the signaling load from the network NW to the communication device UE. Furthermore, the communication device UE can stably operate under its own model-based management scheme SC2, regardless of whether the network NW uses a function-based management scheme or a model-based management scheme.

[0066] FIG. 4 shows a fourth example of the association between UE-side IDs and NW-side IDs by the ID associating unit 31. In this embodiment, the ID associating unit 31 provided on the network NW side creates an ID association table as shown in FIG. 4, which contains information on the association between UE-side IDs and NW-side IDs. The ID association table in the illustrated example is composed of three columns. The second column is a list of model IDs (one or more UE-side IDs / Model Sets) set under the model-based management scheme SC2 on the communication device UE side. The third column is a list of function IDs (one or more NW-side IDs / Functionality Sets) set under the function-based management scheme SC1 on the network NW side. The first column is a set ID corresponding to the set of the communication device UE-side model ID in the second column and the network NW-side function ID in the third column.

[0067] The model ID on the communication device UE side in the second column and the function ID on the network NW side in the third column are associated with each other via the set ID in the first column by the ID associating unit 31. For example, the model ID "B" on the communication device UE side in the second column and the function ID "b" on the network NW side in the third column are associated with each other via the set ID "21" in the first column by the ID associating unit 31.

[0068] In this embodiment, the identification information providing unit 32 provided on the network NW side provides the communication device UE with the set ID (information in the first column) associated with the function ID (information in the third column) used by the network NW as identification information. For example, when the network NW uses a NW-side AI / ML model (a set of components such as functions and procedures) with function ID "b," the corresponding set ID "21" is provided from the network NW to the communication device UE as identification information. The communication device UE recognizes the model ID "B" in its own model-based management scheme SC2, which corresponds to the set ID "21" provided by the network NW. As a result, the communication device UE can identify the model ID "B" that specifies the correct UE-side AI / ML model M2 for cooperative operation with the network NW that uses the NW-side AI / ML model (a set of components such as functions and procedures) with function ID "b." The communication device UE does not need to know the entire ID correspondence table of Figure 4, but only needs to know the information on the group ID in the first column and the model ID in the second column (it does not need to know the information on the function ID in the third column).

[0069] In the fourth embodiment described above, a group ID (e.g., "21") is set to integrally manage the communication device side ID (e.g., model ID "B") and the network side ID (e.g., function ID "b"). The identification information providing unit 32 provides the group ID (e.g., "21") as identification information from the network NW to the communication device UE for cooperative operation between the communication device UE and the network NW. In this case, the network NW notifies the communication device UE of only a small number of group IDs extracted from the ID correspondence table, rather than the entire ID correspondence table of FIG. 4. This reduces the signaling load from the network NW to the communication device UE. Furthermore, the communication device UE can stably operate under its own model-based management scheme SC2, regardless of whether the network NW uses a function-based management scheme or a model-based management scheme.

[0070] In the fifth embodiment, the ID associating unit 31 generates correspondence information between UE-side IDs and NW-side IDs, and the identification information providing unit 32 provides the correspondence information as identification information to the communication device UE from the network NW. For example, the ID associating unit 31 may generate the ID correspondence table shown in Figures 3 and 4 as correspondence information, and the identification information providing unit 32 may provide the entire ID correspondence table from the network NW to the communication device UE. In this way, since the communication device UE has knowledge of the entire ID correspondence table, even if it is provided with information on a function ID under a function-based management scheme SC1 used on the network NW side, it can associate the information with a correct model ID under the model-based management scheme SC2 that it is using.

[0071] In the sixth embodiment, the ID matching unit 31 includes information on one of the corresponding UE side ID and NW side ID in the other information, and the specific information providing unit 32 provides the one information as specific information from the network NW to the communication device UE.

[0072] 5 shows an example in which the ID associating unit 31 includes model ID information (Applied model ID set) as a UE-side ID in information on a function ID (Functionality ID) as a NW-side ID. In this way, function ID information in which model ID information on the communication device UE side is integrated is provided to the communication device UE by the specification information providing unit 32, so that the communication device UE can extract model ID information (Applied model ID set) that it should use from the specification information.

[0073] 6 shows an example in which the ID associating unit 31 includes information on a function ID (functionality ID) as a NW-side ID in information on a model ID (Model ID) as a UE-side ID. In this way, the model ID information (integrated with information on the function IDs on the network NW side) is provided to the communication device UE by the specific information providing unit 32, so the communication device UE can directly select a UE-side AI / ML model to be used by itself based on the model ID. Meanwhile, the network NW can correctly select a NW-side AI / ML model (a set of components such as functions and procedures) to be used by itself based on information on the function ID (functionality ID) integrated with information on the model ID.

[0074] The first to sixth embodiments described above are suitable for a case in which the communication device UE (model-based management scheme SC2) and the network NW (function-based management scheme SC1) use different management schemes. The confirmation unit 33 shown in FIG. 2 may confirm whether the communication device UE and the network NW actually manage the AI / ML model (communication control model) using different management schemes before applying the first to sixth embodiments. Then, when the confirmation unit 33 confirms that the communication device UE and the network NW actually manage the AI / ML model using different management schemes, the specific information providing unit 32 may provide the communication device UE with specific information based on at least one of the first to sixth embodiments from the network NW.

[0075] In this embodiment, the confirmation unit 33 provided on the network NW side may confirm the management scheme of the AI / ML model that the communication device UE can support. For example, the communication device UE may notify the network NW (confirmation unit 33) of the management scheme of the AI / ML model that the communication device UE can support in response to an inquiry from the network NW (confirmation unit 33) (or voluntarily). The signaling from the communication device UE to the network NW for this purpose indicates the LCM capabilities of the AI / ML model held by the communication device UE, and may therefore be expressed as, for example, "AI / ML LCM capability information" (AI / ML life cycle management capability information).

[0076] Examples of the types of management schemes for AI / ML models that the communication device UE can support include: Model-based management scheme (updateable) / configurable model Model-based management scheme (updateable) / fixed model Function-based management scheme (updateable) / configurable LCM process (functionality) Function-based management scheme (updateable) / fixed LCM process (functionality)

[0077] For example, if the confirmation unit 33 confirms that the communication device UE is compatible only with the model-based management scheme (i.e., incompatible with the function-based management scheme), the network NW (specification information providing unit 32) that uses the function-based management scheme SC1 provides the communication device UE with specific information based on at least any one of the first to sixth embodiments. In this way, information on the NW-side ID (or NW-side AI / ML model) used on the network NW side is appropriately converted into information on the UE-side ID (or UE-side AI / ML model) used on the communication device UE side via the specific information provided by the specific information providing unit 32.

[0078] On the other hand, if the confirmation unit 33 confirms that the communication device UE is compatible with the function-based management scheme, the network NW, which also uses the function-based management scheme SC1, provides the communication device UE with information on the NW-side ID (or NW-side AI / ML model) that it uses. The communication device UE can appropriately select the UE-side ID (or UE-side AI / ML model) that it should use from the information on the NW-side ID under the function-based management scheme that it also uses.

[0079] 7 illustrates a schematic example of the process performed by the communication device UE and / or the network NW. In this diagram, time progresses from top to bottom. In addition, "S" in this diagram represents a step or process.

[0080] In S0, at least a part of the correspondence information such as the ID correspondence table shown in Fig. 3 or 4 is shared in advance between the communication device UE and the network NW. As explained in relation to the first to fourth embodiments, the network NW typically grasps the entire correspondence information, but the communication device UE does not need to grasp the entire correspondence information (it may grasp the information in part) as long as it can identify the UE side ID that it should use based on the correspondence information.

[0081] In S1, the confirmation unit 33 on the network NW side inquires of the communication device UE about the management scheme of the AI / ML model that the communication device UE can support. In S2, in response to the inquiry in S1, the communication device UE notifies the network NW (confirmation unit 33) of the management scheme of the AI / ML model that the communication device UE can support in the form of "UE AI / ML capability signaling." This signaling includes, for example, information about the AI / ML processing capability of the communication device UE and the AI / ML types that the communication device UE can support.

[0082] In S3, the network NW identifies an LCM process to be executed based on the signaling in S2. In S4, the confirmation unit 33 confirms, based on the signaling in S2, the management scheme of the AI / ML model that the communication device UE can support for the LCM process identified in S3. S4 may also be expressed as a "Transformation capability check" as shown in the figure, since it is a process of confirming whether or not transformation is necessary between different management schemes for the UE side ID and the NW side ID.

[0083] In S5, the specific information providing unit 32 notifies the communication device UE of the ID management scheme to be applied on the communication device UE side based on the confirmation result in S4. For example, as described above, if the confirmation unit 33 (S4) confirms that the communication device UE is capable of supporting only the model-based management scheme, the network NW (specific information providing unit 32) notifies the communication device UE that the model-based management scheme should be applied on the communication device UE side. Alternatively, since the communication device UE is capable of supporting only the model-based management scheme in any case, this notification may be omitted. Also, if the confirmation unit 33 (S4) confirms that the communication device UE is capable of supporting the function management scheme, the network NW, which also uses the function-based management scheme SC1, notifies the communication device UE that the function-based management scheme should be applied on the communication device UE side. Note that if the confirmation unit 33 (S4) confirms that the communication device UE is capable of supporting only the function-based management scheme (i.e., is not capable of supporting the model-based management scheme), this notification may be omitted.

[0084] In S6, the network NW notifies the communication device UE of the UE-side ID (or its specific information) according to the ID management scheme notified in S5. As a result, the communication device UE can appropriately select the correct UE-side ID (or UE-side AI / ML model) corresponding to the NW-side ID (or NW-side AI / ML model) used on the network NW side.

[0085] In this embodiment, specific information conforming to a correspondence relationship between a UE side ID of a communication control model (UE side AI / ML model) managed by the communication device UE and a NW side ID of a communication control model (NW side AI / ML model) managed by the network NW is provided from at least one of the communication device UE and the network NW to the other. The other of the communication device UE and the network NW that receives the specific information can identify a correct communication control model conforming to the correspondence relationship between the UE side ID and the NW side ID. Therefore, even if a management scheme different from that of the communication device UE or the network NW that transmitted the specific information is used, appropriate communication control can be realized between the communication device UE and the network NW based on the communication control model.

[0086] Next, a proposal document relating to this embodiment is shown. The elements disclosed in this proposal document constitute part of the present disclosure and may be arbitrarily combined with the elements disclosed in the above-described embodiment.

[0087] 3GPP TSG RAN WG1 #112bis-e R1-23xxxxx eMeeting April 17th - April 26th, 2023

[0088] Source: Rakuten Mobile, Inc. Title: Discussion on AI / ML Frameworks Agenda: 9.2.1 Document Purpose: Discussion

[0089] 1 Background

[0090] In RAN Plenary #94, 3GPP agreed to consider Artificial Intelligence (AI) / Machine Learning (ML) for the NR air interface, with the following objectives [1]:

[0091] AI / ML models, terminology and descriptions to identify common specific features for the framework study: - Characterize the definition of algorithms and associated stages of complexity for AI / ML: - Model generation, e.g., where applicable, model training (including input / output, pre / post processes, online / offline, where applicable), model validation, model testing - Inference operations, e.g., where applicable, input / output, pre / post processes - Identify different levels of collaboration between UE and gNB for selected use cases, e.g., no collaboration: AI / ML algorithms based only on implementation without information exchange (for comparison purposes) - Different levels of UE / gNB collaboration targeting individual or joint ML operations - Characterize lifecycle management of AI / ML models: e.g., model training, model deployment, model inference, model monitoring, model update - Datasets for training, validation, testing and inference - Identify common notations and terminology for AI / ML functions, procedures and interfaces - Note: Where appropriate, take into account the work done on "FS_NR_ENDC_data_collect"

[0092] Based on this objective, it is necessary to discuss a framework for AI / ML deployment. At the RAN1 #109-e meeting, the following agreement was reached on the AI / ML collaboration level:

[0093] agreement

[0094] Take the following network-UE collaboration levels as one aspect to define collaboration levels: 1. Level x: No collaboration 2. Level y: Collaboration based on signaling without model transfer 3. Level z: Collaboration based on signaling with model transfer Note: Other aspects to define collaboration levels are not excluded and will be discussed in later meetings. For example, presence or absence of model updates, support for training / inference will be discussed in later meetings to define collaboration levels. FFS: Clarification is needed on level x-y boundary.

[0095] At the RAN1 #110bis-e meeting, further clarification of the boundaries between collaboration levels was discussed regarding the above agreements.

[0096] Working Assumption: Define the Level y-z boundary based on whether model delivery is transparent to 3GPP signaling on the air interface. Note: Procedures other than model transfer / delivery are decoupled from collaboration Level y-z. Note for clarification: Level y includes cases where model delivery is not involved.

[0097] agreement

[0098] We clarify the Level x / y boundary as follows: - Level x is collaboration between the network and UE through implementation-based AI / ML operation without dedicated AI / ML specific improvements (e.g., signaling for LCM, RS) (Note: AI / ML operation may depend on future standards not related to AI / ML collaboration. The AI / ML approach may be used as a baseline for performance evaluation for future releases).

[0099] Now that the definition of level x has been clarified, RAN1 needs to continue discussing the boundary between y and z. The main difference between y and z based on the definition is the existence of model transfer. Until now, handling of such AI / ML models has been based on model ID. Regarding model ID, the following agreement was reached at the RAN1 #110bis-e meeting:

[0100] agreement

[0101] Consider the LCM procedure under the assumption that the AI / ML model has a model ID with related information and / or model functions for at least some AI / ML operations. [When the network needs to recognize the UE's AI / ML model] FFS: Detailed discussion of the model ID with related information and / or model functions FFS: Use of the model ID with related information and / or model functions based on the LCM procedure FFS: Whether the model ID needs to be supported FFS: Detailed applicable AI / ML operations

[0102] agreement

[0103] Consider the following mechanisms for model selection, activation, deactivation, switching and fallback, at least for the UE-side model and the two-sided model: - Network-determined - Network-initiated - UE-initiated request to the network - UE-determined - UE decision under network-configured event triggers reported to the network - UE autonomous decision reported to the network - UE autonomous decision not reported to the network FFS: for the network-side model FFS: other mechanisms

[0104] At the RAN1#111 meeting, there was further discussion on the AI / ML model management framework, and a new term "functionality" was introduced:

[0105] agreement

[0106] For UE part / UE side models, the following mechanisms are considered for LCM procedures: For feature-based LCM procedures, suggestion of activation / deactivation / switching / fallback based on individual AI / ML features Note: A UE may have one AI / ML model for a feature or a UE may have multiple AI / ML models for a feature FFS: whether and how to suggest a feature For model-ID based LCM procedures, suggestion of model selection / activation / deactivation / switching / fallback based on individual model-ID

[0107] Working Assumption (see Figure 8)

[0108] agreement

[0109] For ease of discussion, we consider at least the cases shown in FIG. 9 for the combinations of model delivery / transfer to the UE, training location, UE-side model, and UE portion of the two-sided model.

[0110] agreement

[0111] For the UE side model and the UE part of the two-sided model: - For AI / ML feature identification - Reuse the legacy 3GPP framework of features as a starting point for the discussion - For a given sub-use case, the UE will suggest the set of features / functionality that it supports ■Starts UE capability reporting - For AI / ML model identification - Models are identified in the network by a model ID. The UE indicates the supported AI / ML models - In capability-based LCM - The network indicates activation / deactivation / fallback / switching of AI / ML functions via 3GPP signaling (e.g., RRC, MAC-CE, DCI) - Models do not have to be specified in the network and the UE may perform model-level LCM ■ Consider whether and how much awareness / interaction the NW should have about model-level LCM - In model-ID-based LCM, models are specified in the network and the network / UE may perform activation / deactivation / selection / switching of individual AI / ML models via model ID FFS: Relationship between capability specification and model specification FFS: Performance monitoring and impact of RAN4 FFS: Detailed understanding of models

[0112] agreement

[0113] - AI / ML enabled features represent features for which AI / ML may be used

[0114] agreement

[0115] - For function specification, there may be one or more functions defined within the AI / ML enabled features

[0116] In this paper, our perspective on further clarification of collaboration level boundaries, model IDs and model function usage is presented.

[0117] 2 Discussion on the classification of collaboration levels for AI / ML use in the air interface

[0118] Table 1 (Fig. 10) describes our understanding of the features for each collaboration level.

[0119] We believe that level x is sufficiently well defined and does not require further discussion.

[0120] Level y: Collaboration based on signaling without model transfer At this collaboration level, various types of information exchange can be considered. Regarding the actual information shared between the network and the UE, several types of information can be considered:

[0121] a. AI / ML auxiliary information i. Parameters for adjusting AI / ML models / inference ii. Parameters for controlling AI / ML function applications b. Suggestion of whether the AI / ML model needs to be updated

[0122] Our understanding of the agreed classification is to classify the impact of standardization on signaling standards. To further discuss the signaling required for level y, we need to classify what kind of collaboration is included in this collaboration level. Our understanding is that level y includes the following collaborations:

[0123] Level y-1: NW-based AI / ML application. All AI / ML-related functions are located on the NW side, except for the measurement function on the UE side. The UE may report necessary measurement information to the NW.

[0124] Level y-2: Two-sided AI / ML application Both the network and the user equipment (UE) are responsible for some part of the AI / ML operations, including training, inference, model management, etc. The details and feasibility of this level should be further explored.

[0125] Level y-3: UE-based AI / ML application. All AI / ML-related functions are in the UE, except for some measurement functions on the network side. The network may suggest necessary measurement information to the UE.

[0126] The above classifications may be defined independently, in which case they may be called frameworks.

[0127] Level z: Signaling-based collaboration with model transfer. At this level, the network can manage the models used by the UE for AI / ML operations. Training is primarily performed on the network side, and the resulting updated models can be sent to the UE. The reverse operation is also possible from a technical point of view. In our opinion, the first priority at this collaboration level is to specify the interaction between the network and the UE regarding the management of aligned AI / ML models in a common data format. Based on the common data format, 3GPP can discuss how model parameters are managed, how model updates are performed, and how necessary auxiliary information is signaled.

[0128] Another possibility is to download third-party AI / ML models from the Internet to UE or network nodes. The previous meeting further clarified that at the collaboration level, model transactions are based on proprietary formats. Our understanding is that the controllability of proprietary format models is unclear at this time.

[0129] Observation 1: If proprietary format models are to be able to interact with 3GPP systems, a common interface must be specified, even for AI / ML models based on proprietary formats.

[0130] The following working assumptions about the boundary between y and z are acceptable as consensus:

[0131] Working Assumptions Define the Level y-z boundary based on whether model delivery is transparent to 3GPP signaling on the air interface. Note: Procedures other than model transfer / delivery are decoupled from collaboration Level y-z. Note for clarification: Level y includes cases where model delivery is not involved.

[0132] In our opinion, for this review item phase, any procedure except for model transfer / delivery, as described in the WA, can be discussed independently of the collaboration level discussions.

[0133] Proposal 2 The following working assumptions are confirmed: Define the Level y-z boundary based on whether model delivery is transparent to 3GPP signaling on the air interface. Note: Procedures other than model transfer / delivery are decoupled from collaboration Level y-z. Clarification note: Level y includes cases where model delivery is not involved.

[0134] Proposal 3 Further clarification of AI / ML collaboration level y includes: Level y-1: NW-based AI / ML applications Level y-2: Two-sided AI / ML applications Level y-3: UE-based AI / ML applications The above clarifications can be defined independently as frameworks instead of collaboration level clarifications.

[0135] Proposal 4: For collaboration level z, the controllable model parameters should be aligned with collaboration level y.

[0136] 3 Discussion of models and function specification

[0137] As shown in Section 1, RAN1 has agreed to use Model ID for life cycle management. However, the details of how to handle each step for LCM are still one of the FFS points. In our view, Model ID can be used in multiple areas in LCM. We will explain how Model ID can be used in the following areas:

[0138] AI / ML Model Parameter Exchange Based on the UE's AI / ML capabilities, the NW can configure the UE with necessary parameter suggestions, or the UE can notify necessary information about the UE upon request from the NW. For example, such parameter sets can be predefined and classified as indexes. The index for such model parameter exchange may be defined as a model ID.

[0139] Observation 1: Model IDs are useful for AI / ML model parameter exchange

[0140] Model Update / Upgrade Based on the UE's AI / ML model repository, the following procedures may be applied: (i) New Model Update (ii) Existing Model Upgrade (iii) Inference Update (iv) Model Training

[0141] Regarding model updates / upgrades, one of the points of discussion is how to effectively manage the history of model updates / upgrades. To achieve this management of the model history, it is useful to assign an ID to each model.

[0142] Observation 2: Model IDs are useful for model updates / upgrades

[0143] Performance Monitoring, Model Training Based on the model performance feedback and the assessed KPIs, the gNB can take one of the following actions: (i) New model update (ii) Existing model upgrade (iii) Inference update (iv) No action (v) Model training

[0144] To implement model-related procedures, KPI monitoring should be performed together with knowledge of the currently applied model in the NW and / or UE. In this sense, the model ID is necessary to realize performance monitoring and model training.

[0145] Proposal 5: Performance monitoring should be done with recognition of model ID.

[0146] Observation 3: Model ID is useful for performance monitoring and model training

[0147] As mentioned above, the Model ID can be a key player in many procedures for lifecycle management. At collaboration level z, the Model ID is useful for handling these procedures, since both the network and the UE should be aware of the models they exchange. For collaboration level y, the applicability of the Model ID depends on the type of information shared between the gNB and the UE.

[0148] Observation 4: Model IDs are useful for at least collaboration level z

[0149] Observation 5: A model ID may be defined as a set of model parameters or model data

[0150] Another point about the model ID is who manages the model ID. At least, both cases of gNB signaling and UE signaling are considered. In the example of gNB signaling, the network can suggest a model ID to suggest the model that the UE should deploy. In the case of UE signaling, the UE can suggest to the network the model that the UE deploys. At least for collaboration level z, both cases are beneficial for the network to manage the models in the system.

[0151] Proposal 6: Both gNB and UE can suggest model ID depending on the framework they are deployed in.

[0152] According to R1-2212326, one of the purposes of model functions is to manage the supported collaboration level depending on, for example, the mobility of the UE and the size of the area that one or more AI / ML models should support. Therefore, management of the relationship between function IDs and model IDs is necessary. Such configuration may be predefined in the standard or configured by signaling depending on the use case to which AI / ML is applied.

[0153] In addition to the relationship between capabilities and AI / ML models, capabilities must be defined based on the required collaboration level, since the collaboration level is strongly related to the applied AI / ML LCM framework. The possible collaboration level depends not only on the UE capabilities, but also on, for example, the UE's mobility, the number of UEs managed by the AI / ML operation, and the size of the supported area. Therefore, capabilities may change over time depending on the UE's situation.

[0154] As agreed in the previous meeting, the Model ID can be implied as part of the Feature ID. However, it is not clear whether the entire set of related parameters needs to be updated along with the Feature ID every time, for example, in response to changes in UE mobility. Therefore, in addition to the Feature ID-based management, it is necessary to ensure a way to update AI / ML-related parameters separately when necessary.

[0155] Observation 6: The exact set of parameters for a feature can be defined depending on the use case.

[0156] Proposal 7: Model IDs should be suggestable separately from feature IDs, in addition to being suggested within feature IDs.

[0157] The function is "a process / method of specifying AI / ML functions for common understanding between the NW and the UE." Therefore, it should include all necessary parameters to perform collaboration between the NW and the UE. At least the following parameters should be included: ■ Model ID ■ Collaboration level

[0158] Proposal 8: Features should be associated with model IDs and collaboration levels.

[0159] Different companies have different views on the definition of model and function terms. Figure 11 (relationship between different model definitions) shows a summary of the different terms from our point of view.

[0160] In our understanding, function specification is strongly related to model structure specification, since the model structure is determined based on the use case and the AI / ML capabilities of the UE. Therefore, if structure specification is necessary, it should be performed as function specification before model specification.

[0161] See Figure 12 (function specification and model specification).

[0162] Proposal 9: If function specification is performed within the 3GPP framework, it should be performed before model specification.

[0163] From the model specification point of view, the problem is how to specify the model structure. There are several possibilities to solve the problem:

[0164] ■Solution 1: UE-driven - The model structure is identified in the same way during function identification. ■Solution 2: Network-driven - The model structure is identified in the same way during function identification. ■Solution 3: The model structure is identified by differentiating model IDs taking into account the model structure. ■Solution 4: The UE individually suggests to the network the model structure to be deployed. ■Solution 5: Model performance requirements for each use case are specified in the standard. The UE selects an appropriate model structure that meets the specified requirements without any knowledge from the network.

[0165] In Solution 1, the UE decides which model structure to apply based on information about available AI / ML use cases, while in Solution 2, the network decides which model structure to apply based on the UE's report of its AI / ML capabilities.

[0166] There are other methods that do not involve functional specification. In solution 3, the model structure is specified by including model structure ID information in the model ID (hierarchical ID) by implying a model ID. In solution 4, the model structure is specified by an arbitrary scheme outside the 3GPP standard. In solution 5, only the model performance is specified along with the applicable model structure. The applied model structure is specified depending on the use case by referring to the standard.

[0167] Proposal 10: Further discuss the preferred solution for specifying model structure, with or without function specification.

[0168] 4 Conclusion

[0169] In this contribution, AI / ML frameworks and Model ID were discussed. The following suggestions and observations were made:

[0170] Proposal 1: For model z, the application of specific AI / ML model applications can be excluded.

[0171] Proposal 2 The following working assumptions are confirmed: Define the Level y-z boundary based on whether model delivery is transparent to 3GPP signaling on the air interface. Note: Procedures other than model transfer / delivery are decoupled from collaboration Level y-z. Clarification note: Level y includes cases where model delivery is not involved.

[0172] Proposal 3 Further clarification of AI / ML collaboration level y includes: Level y-1: NW-based AI / ML applications Level y-2: Two-sided AI / ML applications Level y-3: UE-based AI / ML applications The above clarifications can be defined independently as frameworks instead of collaboration level clarifications.

[0173] Observation 1: Model IDs are useful for AI / ML model parameter exchange

[0174] Observation 2: Model IDs are useful for model updates / upgrades

[0175] Proposal 4: For collaboration level z, the controllable model parameters should be aligned with collaboration level y.

[0176] Proposal 5: Performance monitoring should be done with recognition of model ID.

[0177] Observation 3: Model ID is useful for performance monitoring and model training

[0178] Observation 4: Model IDs are useful for at least collaboration level z

[0179] Observation 5: A model ID may be defined as a set of model parameters or model data

[0180] Proposal 6: Both gNB and UE can suggest model ID depending on the framework they are deployed in.

[0181] Observation 6: The exact set of parameters for a feature can be defined depending on the use case.

[0182] Proposal 7: Model IDs should be suggestable separately from feature IDs, in addition to being suggested within feature IDs.

[0183] Proposal 8: Features should be associated with model IDs and collaboration levels.

[0184] Proposal 9: If function specification is performed within the 3GPP framework, it should be performed before model specification.

[0185] Proposal 10 Further discuss preferred solutions for identifying model structures with or without function identification. For example: ■ Solution 1: UE-driven - identify model structures in the same way during function identification. ■ Solution 2: NW-driven - identify model structures in the same way during function identification. ■ Solution 3: identify model structures by differentiating model IDs taking into account the model structure. ■ Solution 4: UEs individually suggest to the network the model structure they will be deployed in. ■ Solution 5: Model performance requirements for each use case are specified in the standard. The UE selects the appropriate model structure that meets the specified requirements without knowledge from the network.

[0186] Reference [1] RP-213599, New SI: Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface, 3GPP TSG RAN Meeting #94e, E-meeting, Dec 6th-17th, 2021. [2] TR 37.817, “Study on enhancement for data collection for NR and ENDC”, Rel-17, Mar. 2022.

[0187] The present disclosure has been described above based on the embodiments. Various modifications are possible to the combinations of the components and processes in the exemplary embodiments, and it will be obvious to those skilled in the art that such modifications are included within the scope of the present disclosure.

[0188] The configuration, operation, and function of each device and method described in the embodiments can be realized by hardware resources, software resources, or a combination of hardware and software resources. Examples of hardware resources include processors, ROM, RAM, and various integrated circuits. Examples of software resources include operating systems, applications, and other programs.

[0189] This disclosure may be expressed in the following terms:

[0190] Item 1: A communication control device comprising at least one processor that executes the following: when a communication control model relating to communication control between a communication device and a network that provides communication services to the communication device can be managed by the communication device and the network using different management schemes, an ID associating unit associates a communication device side ID of the communication control model managed by the communication device with a network side ID of the communication control model managed by the network, and providing, by a specific information providing unit, specific information from at least one of the communication device and the network to the other of the communication device and the network that allows the other of the communication device and the network to identify the correct communication control model in accordance with the corresponding relationship between the communication device side ID and the network side ID. Item 2: The communication control device according to item 1, wherein the specific information providing unit provides the specific information that allows the communication device side ID to be identified from the network to the communication device. Item 3: The communication control device according to item 1 or 2, wherein the communication device side ID and the network side ID are different from each other, and the identification information providing unit provides a second ID used by one of the communication device and the network, which is associated with a first ID used by the other of the communication device and the network, from one of the communication device and the network to the other as the identification information. Item 4: The communication control device according to item 1 or 2, wherein the ID associating unit sets the communication device side ID and the network side ID to the same common ID, and the identification information providing unit provides the common ID as the identification information from one of the communication device and the network to the other. Item 5: The communication control device according to item 1 or 2, wherein the ID associating unit sets a pair ID corresponding to a pair of the communication device side ID and the network side ID, and the identification information providing unit provides the pair ID as the identification information from one of the communication device and the network to the other. Item 6: The communication control device according to item 5, wherein the other of the communication device and the network recognizes an ID in its own management scheme that corresponds to the pair ID provided from the one of the communication device and the network.Item 7: The communication control device according to item 1 or 2, wherein the ID associating unit generates correspondence information between the communication device side ID and the network side ID, and the identification information providing unit provides the correspondence information as the identification information from one of the communication device and the network to the other. Item 8: The communication control device according to item 1 or 2, wherein the ID associating unit includes information on one of the corresponding communication device side ID and the network side ID in information on the other, and the identification information providing unit provides the information on the one of the corresponding communication device side ID and the network to the other as the identification information. Item 9: The communication control device according to any of items 1 to 8, wherein the at least one processor executes, by a confirmation unit, confirmation as to whether the communication device and the network manage the communication control model using different management schemes, and the identification information providing unit provides the identification information from at least one of the communication device and the network to the other when it is confirmed that the communication device and the network manage the communication control model using different management schemes. Item 10: A communication control method that, when a communication control model relating to communication control between a communication device and a network that provides communication services to the communication device can be managed by the communication device and the network using different management schemes, associates a communication device side ID of the communication control model managed by the communication device with a network side ID of the communication control model managed by the network, and provides specific information from at least one of the communication device and the network to the other of the communication device and the network that allows the other of the communication device and the network to identify the correct communication control model in accordance with the correspondence between the communication device side ID and the network side ID.Item 11: A storage medium storing a communication control program that causes a computer to execute the following steps: when a communication control model relating to communication control between a communication device and a network that provides communication services to the communication device can be managed by the communication device and the network using different management schemes, associate a communication device side ID of the communication control model managed by the communication device with a network side ID of the communication control model managed by the network; and provide specific information from at least one of the communication device and the network to the other of the communication device and the network that allows the other of the communication device and the network to identify the correct communication control model in accordance with the correspondence between the communication device side ID and the network side ID.

[0191] This application claims priority based on Japanese Patent Application No. 2023-022402 filed on February 16, 2023, and Japanese Patent Application No. 2023-062135 filed on April 6, 2023, the entire contents of which are incorporated by reference.

[0192] The present disclosure relates to accommodating different management schemes for communication control models.

[0193] 1 Wireless communication system, 2 Communication device, 3 Communication control device, 11 5G wireless communication system, 12 4G wireless communication system, 13 Satellite communication system, 31 ID correspondence unit, 32 Specific information provision unit, 33 Verification unit, 111 5G base station, 112 5G cell, 121 4G base station, 122 4G cell, 131 Communication satellite, 132 Satellite communication cell, 133 Gateway, SC1 Function-based management scheme, SC2 Model-based management scheme.

Claims

1. When a communication control model relating to communication control between a communication device and a network that provides a communication service to the communication device can be managed by the communication device and the network using different management schemes, an ID matching unit associates a communication device side ID of the communication control model managed by the communication device with a network side ID of the communication control model managed by the network; providing, by a specific information providing unit, specific information from at least one of the communication device and the network to the other of the communication device and the network, for allowing the other to identify the correct communication control model in accordance with a correspondence relationship between the communication device side ID and the network side ID; A communication control device that executes the above.

2. The communication control device according to claim 1 , wherein the identification information providing unit provides the identification information for identifying the communication device side ID from the network to the communication device.

3. the communication device side ID and the network side ID are different from each other, the specific information providing unit provides, as the specific information, from one of the communication device and the network to the other of the communication device and the network, a second ID used by the other of the communication device and the network, which is associated with a first ID used by the other of the communication device and the network; The communication control device according to claim 1 .

4. the ID associating unit sets the communication device side ID and the network side ID to the same common ID; the specific information providing unit provides the common ID as the specific information from one of the communication device and the network to the other; The communication control device according to claim 1 .

5. the ID associating unit sets a pair ID corresponding to a pair of the communication device side ID and the network side ID; the specific information providing unit provides the group ID as the specific information from one of the communication device and the network to the other; The communication control device according to claim 1 .

6. The communication control device according to claim 5 , wherein the other of the communication device and the network recognizes an ID in its own management scheme that corresponds to the pair ID provided by the other.

7. the ID corresponding unit generates correspondence information between the communication device side ID and the network side ID; the specific information providing unit provides the correspondence relationship information as the specific information from one of the communication device and the network to the other; The communication control device according to claim 1 .

8. the ID associating unit includes information on one of the corresponding communication device side ID and the corresponding network side ID in information on the other; the specific information providing unit provides the one of the information as the specific information from one of the communication device and the network to the other; The communication control device according to claim 1 .

9. A confirmation unit confirms whether the communication device and the network manage the communication control model with different management schemes; the specific information providing unit provides the specific information from at least one of the communication device and the network to the other when it is confirmed that the communication device and the network manage the communication control model using different management schemes. The communication control device according to claim 1 .

10. When a communication control model relating to communication control between a communication device and a network that provides a communication service to the communication device can be managed by the communication device and the network using different management schemes, a communication device side ID of the communication control model managed by the communication device is associated with a network side ID of the communication control model managed by the network; providing, from at least one of the communication device and the network, to the other of the communication device and the network, identification information for identifying the correct communication control model in accordance with the correspondence relationship between the communication device side ID and the network side ID; A communication control method for performing the above.

11. When a communication control model relating to communication control between a communication device and a network that provides a communication service to the communication device can be managed by the communication device and the network using different management schemes, a communication device side ID of the communication control model managed by the communication device is associated with a network side ID of the communication control model managed by the network; providing, from at least one of the communication device and the network, to the other of the communication device and the network, identification information for identifying the correct communication control model in accordance with the correspondence relationship between the communication device side ID and the network side ID; A communication control program that causes a computer to execute the above.