Methods and apparatuses for supporting an artificial intelligence (AI) task in a radio resource control (RRC) inactive state of a user equipment (UE)
The RAN node supports AI tasks in the RRC inactive state by triggering paging and managing context relocation, addressing the lack of support in current systems and optimizing resource use for AI task execution.
Patent Information
- Application Number
- PCT/CN2024/109236
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2025-08-21
AI Technical Summary
Current wireless communication systems lack support for artificial intelligence (AI) tasks in the RRC inactive state of user equipment (UE), specifically in transitioning to the RRC connected state, managing AI task-related context relocation, and handling AI task-related resume procedures.
Implementing a radio access network (RAN) node that triggers paging procedures for AI tasks, transmits AI task-related causes, and receives RRC resume requests, enabling network-triggered transitions and context management for AI tasks in the RRC inactive state.
Facilitates efficient AI task execution in the RRC inactive state by defining AI task-related RAN paging triggers and managing context relocation, allowing for optimized resource allocation and reduced unnecessary resource usage.
Smart Images

Figure CN2024109236_21082025_PF_FP_ABST
Abstract
Description
METHODS AND APPARATUSES FOR SUPPORTING AN ARTIFICIAL INTELLIGENCE (AI) TASK IN A RADIO RESOURCE CONTROL (RRC) INACTIVE STATE OF A USER EQUIPMENT (UE)TECHNICAL FIELD
[0001] The present disclosure relates to wireless communications, and more specifically to methods and apparatuses for supporting an artificial intelligence (AI) task in a radio resource control (RRC) inactive state of a user equipment (UE) .BACKGROUND
[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g. time-domain resources (e.g. symbols, slots, subframes, frames, or the like) or frequency-domain resources (e.g. subcarriers, carriers, or the like) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g. sixth generation (6G) ) .SUMMARY
[0003] An article "a" before an element is unrestricted and understood to refer to "at least one" of those elements or "one or more" of those elements. The terms "a, " "at least one, " "one or more, " and "at least one of one or more" may be interchangeable. As used herein, including in the claims, "or" as used in a list of items (e.g. a list of items prefaced by a phrase such as "at least one of" or "one or more of" or "one or both of" ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase "based on" shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as "based on condition A" may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" shall be construed in the same manner as the phrase "based at least in part on. Further, as used herein, including in the claims, a "set" may include one or more elements.
[0004] Some implementations of the present disclosure provide a radio access network (RAN) node. The RAN node includes at least one memory; and at least one processor coupled to the at least one memory and configured to cause the RAN node to: trigger a paging procedure related to one or more artificial intelligence (AI) tasks; transmit a paging message including an AI task related cause to a user equipment (UE) ; and receive, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.
[0005] In some implementations of the RAN node described herein, the paging procedure is triggered in at least one of the following cases: the RAN node wants to update one or more AI or machine learning (ML) training models for the one or more AI tasks of the UE; the RAN node wants to transmit one or more new AI or ML training models for the one or more AI tasks to the UE; the RAN node wants to update one or more configuration parameters of the one or more AI tasks that are performed in an RRC inactive state of the UE; the RAN node wants to configure one or more new AI tasks to the UE; the RAN node wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE; the RAN node receives AI task related data of the UE from a core network (CN) ; the RAN node receives AI task related signalling of the UE from the CN; the RAN node decides to get data collected by the UE in the RRC inactive state; or if the RAN node is a first RAN node, the RAN node receives a RAN paging message including the AI task related cause from a second RAN node.
[0006] In some implementations of the RAN node described herein, the RAN node is one of the following: a last serving RAN node for the UE; a current serving RAN node for the UE; or an AI task originated RAN node.
[0007] In some implementations of the RAN node described herein, if the RAN node is the first RAN node, the RAN node is a current serving RAN node for the UE, the second RAN node is a last serving RAN node or the AI task originated RAN node.
[0008] In some implementations of the RAN node described herein, the AI task related cause includes at least one of the following: a cause to indicate that the paging procedure is triggered for an AI or ML purpose; a cause to indicate type information of the one or more AI tasks; a cause to indicate that the RAN node receives AI task related data of the UE from a core network (CN) ; a cause to indicate that the RAN node receives AI task related signalling of the UE from the CN; a cause to indicate that the RAN node wants to update one or more configuration parameters of the one or more AI tasks that are performed in the RRC inactive state of the UE; cause to indicate that the RAN node wants to configure one or more new AI tasks to the UE; a cause to indicate that the RAN node wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE; or a cause to indicate that the RAN node decides to get data collected by the UE in the RRC inactive state.
[0009] In some implementations of the RAN node described herein, the type information of the one or more AI tasks includes at least one of the following: data collection; sensing; positioning; or an AI or ML training model.
[0010] In some implementations of the RAN node described herein, the AI task related cause is a first AI task related cause, and the RRC resume request includes a second AI task related cause.
[0011] In some implementations of the RAN node described herein, the second AI task related cause includes at least one of the following: the one or more AI tasks become applicable; the one or more AI tasks become available; the one or more AI tasks are complete; the valid time of the one or more AI tasks has been elapsed; a timer related to the one or more AI tasks expires; or an RRC cause.
[0012] In some implementations of the RAN node described herein, the RRC cause includes at least one of the following: a cause to indicate that an RRC connection resume procedure is initiated by an AI or ML purpose; a cause to indicate that the RRC connection resume procedure is initiated by a mobile originated AI or ML purpose; or a cause to indicate that the RRC connection resume procedure is initiated by a mobile terminated AI or ML purpose.
[0013] In some implementations of the RAN node described herein, the RAN node is a current serving RAN node for the UE, and the processor of the RAN node is configured to transmit a first message including the second AI task related cause to a third node, and the third node is one of the following: a last serving RAN node for the UE; or an AI task originated RAN node.
[0014] In some implementations of the RAN node described herein, the processor of the RAN node is configured to receive, from the third node, a partial UE context including at least one of the following: an AI task related UE context; and transport information of the AI task originated RAN node.
[0015] In some implementations of the RAN node described herein, the processor of the RAN node is configured to: receive, from the third node, uplink (UL) transport network layer (TNL) address information of CRBs related to the one or more AI tasks; and transmit, to the third node, downlink (DL) TNL address information of the CRBs related to the one or more AI tasks.
[0016] In some implementations of the RAN node described herein, the processor of the RAN node is configured to transmit an RRC resume message to the UE, to resume the CRBs related to the one or more AI tasks.
[0017] In some implementations of the RAN node described herein, the processor of the RAN node is configured to: detect an end of a data transmission of the one or more AI tasks; and transmit, to the third node, first information to indicate the end of the data transmission of the one or more AI tasks.
[0018] In some implementations of the RAN node described herein, the end of the data transmission of the one or more AI tasks is detected in at least one of the following cases: o further data transmission of the one or more AI tasks is received by the RAN node for a time duration; no further data transmission of the one or more AI tasks is transmitted from the RAN node for a time duration; or the RAN node receives an end indication for the end of the data transmission of the one or more AI tasks from the UE.
[0019] In some implementations of the RAN node described herein, the processor of the RAN node is configured to receive, from the third node, a full UE context including transport information of the AI task originated RAN node.
[0020] In some implementations of the RAN node described herein, the processor of the RAN node is configured to transmit transport information of the RAN node to the third node.
[0021] In some implementations of the RAN node described herein, the transport information of the RAN node includes at least one of the following: AI task transport network layer (TNL) information allocated by the RAN node; internet protocol (IP) information allocated by the RAN node; RAN node identifier (ID) information of the RAN node; or ID information of the one or more AI tasks.
[0022] In some implementations of the RAN node described herein, the processor of the RAN node is configured to: receive data of the one or more AI tasks from the UE; and transmit the data of the one or more AI tasks to the AI task originated RAN node according to the transport information of the AI task originated RAN node.
[0023] In some implementations of the RAN node described herein, the data of the one or more AI tasks is transmitted in a general packet radio service (GPRS) tunneling protocol-user plane (GTP-U) tunnel established between the RAN node and AI task originated RAN node.
[0024] In some implementations of the RAN node described herein, the RAN node is a last serving RAN node for the UE, and the processor of the RAN node is configured to transmit a paging message including the AI task related cause to a current serving RAN node for the UE or an AI task originated RAN node.
[0025] In some implementations of the RAN node described herein, the RAN node is a last serving RAN node for the UE, and the processor of the RAN node is configured to receive a first message including the second AI task related cause from a current serving RAN node for the UE.
[0026] In some implementations of the RAN node described herein, the last serving RAN node is an AI task originated RAN node.
[0027] In some implementations of the RAN node described herein, the first message is a retrieval UE context request message.
[0028] In some implementations of the RAN node described herein, the first message includes information indicating that the RRC resume request from the UE is associated with the one or more AI tasks.
[0029] In some implementations of the RAN node described herein, the processor of the RAN node is configured to transmit, to the current serving RAN node, a partial UE context including an AI task related UE context.
[0030] In some implementations of the RAN node described herein, the partial UE context is included in a partial UE context transfer message.
[0031] In some implementations of the RAN node described herein, the AI task related UE context includes at least one of the following: AI task type information; one or more quality of service (QoS) requirements of the one or more AI tasks; one or more QoS parameters of the one or more AI tasks; protocol data unit (PDU) session information for the one or more AI tasks; RRC configuration information for the one or more AI tasks; or RRC configuration information of a computing radio bearer (CRB) associated with the one or more AI tasks.
[0032] In some implementations of the RAN node described herein, the RRC configuration information for the one or more AI tasks includes at least one of the following: packet data convergence protocol (PDCP) configuration information; medium access control (MAC) configuration information; radio link control (RLC) configuration information; or physical layer (PHY) configuration information.
[0033] In some implementations of the RAN node described herein, the processor of the RAN node is configured to: transmit, to the current serving RAN node, uplink (UL) transport network layer (TNL) address information of CRBs related to the one or more AI tasks; and receive, from the current serving RAN node, downlink (DL) TNL address information of the CRBs related to the one or more AI tasks.
[0034] In some implementations of the RAN node described herein, the processor of the RAN node is configured to receive, from the current serving RAN node, first information to indicate an end of a data transmission of the one or more AI tasks.
[0035] In some implementations of the RAN node described herein, the first information is included in a retrieve UE context confirm message.
[0036] In some implementations of the RAN node described herein, the processor of the RAN node is configured to transmit, to the current serving RAN node, a full UE context including transport information of the AI task originated RAN node.
[0037] In some implementations of the RAN node described herein, the full UE context is included in a retrieve UE context response message.
[0038] In some implementations of the RAN node described herein, the transport information of the AI task originated RAN node includes at least one of the following: AI task transport network layer (TNL) information allocated by the AI task originated RAN node; internet protocol (IP) information allocated by the AI task originated RAN node; RAN node identifier (ID) information of the AI task originated RAN node; or ID information of the one or more AI tasks.
[0039] In some implementations of the RAN node described herein, the processor of the RAN node is configured to receive transport information of the current serving RAN node from the current serving RAN node.
[0040] In some implementations of the RAN node described herein, the processor of the RAN node is configured to transmit the transport information of the current serving RAN node to the AI task originated RAN node.
[0041] In some implementations of the RAN node described herein, the transport information of the current serving RAN node includes at least one of the following: AI task transport network layer (TNL) information allocated by the current serving RAN node; internet protocol (IP) information allocated by the current serving RAN node; RAN node identifier (ID) information of the current serving RAN node; or ID information of the one or more AI tasks.
[0042] In some implementations of the RAN node described herein, the AI task TNL information includes at least one of the following: IP address information associated with the one or more AI tasks; or general packet radio service (GPRS) tunneling protocol-user plane (GTP-U) tunnel endpoint identifier (TEID) information associated with the one or more AI tasks.
[0043] In some implementations of the RAN node described herein, the AI task TNL information is per an AI task or per a CRB of the AI task.
[0044] In some implementations of the RAN node described herein, data of the one or more AI tasks is transmitted in a general packet radio service (GPRS) tunneling protocol-user plane (GTP-U) tunnel established between the current serving RAN node and AI task originated RAN node.
[0045] Some implementations of the present disclosure provide a processor for wireless communication, comprising at least one controller coupled with at least one memory and configured to cause the processor to: trigger a paging procedure related to one or more artificial intelligence (AI) tasks; transmit a paging message including an AI task related cause to a user equipment (UE) ; and receive, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.
[0046] Some implementations of the present disclosure provide a method performed by a radio access network (RAN) node. The method includes: triggering a paging procedure related to one or more artificial intelligence (AI) tasks; transmitting a paging message including an AI task related cause to a user equipment (UE) ; and receiving, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.
[0048] Figure 2 illustrates an example of a user equipment (UE) 200 in accordance with aspects of the present disclosure.
[0049] Figure 3 illustrates an example of a processor 300 in accordance with aspects of the present disclosure.
[0050] Figure 4 illustrates an example of a network equipment (NE) 400 in accordance with aspects of the present disclosure.
[0051] Figure 5 illustrates a flowchart of a method related to an AI task in accordance with aspects of the present disclosure.
[0052] Figure 6 illustrates a schematic diagram of a network triggered transition of a UE in accordance with aspects of the present disclosure.
[0053] Figure 7 illustrates a schematic diagram of an AI task related RRC resume procedure without a UE context relocation in accordance with aspects of the present disclosure.
[0054] Figure 8 illustrates a schematic diagram of AI task related RRC resume with a UE context relocation in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0055] In general, a 5G system supports a protocol data unit (PDU) connectivity service, i.e., a service that provides exchange of PDUs between a UE and a data network identified by a data network name (DNN) . The PDU connectivity service is supported via PDU sessions that are established upon a request from a UE. A PDU session is terminated or anchored at a user plane function (UPF) . In case of mobility, a UE is moved from a source network node (e.g. a source gNB) to a target network node (e.g. a target gNB) , and a path switch procedure is performed to switch the downlink (DL) data transmission path from between a UPF and the source gNB to between the UPF and the target gNB.
[0056] Currently, a concept of 6G AI-as-a-Service (AIaaS) is discussed to support 6G native AI, for example, a new 6G mobile network provides ubiquitous intelligent services. 6G AIaaS is to build distributed, efficient, energy-saving and secure AI services (including AI model training, reasoning, deployment, and etc. ) and open ecology through the connection, computing, data, model and other resources and functions of the network (including 6G core network, 6G wireless access network and 6G terminal) . AIaaS may also be called as "a network AI service. " An AI service refers to the provision of AI technology, AI traffic or AI resource to the served party. Typical 6G AIaaS services include that a 6G network provides users with large-scale distributed model training, inference, generation, optimization and other AI services. The service objects can be end users, third-party users, and network operation and maintenance (O&M) .
[0057] An AI task is to enable a network AI service that will involve the coordination and deployment of computing power, connections, AI algorithms, and data among multiple devices. To support and achieve an AI task, a new bearer type to carry data or signalling transmission for an AI task may be introduced, that can be called as a computing radio bearer (CRB) . A CRB can be used for data management (e.g., data collection) , computing power offload, AI lifecycle management for the AI task. A CRB is carried by a user plane protocol such as a PDU session, a data radio bearer (DRB) or a quality of service (QoS) flow. Another possible protocol stack is carried by a control plane protocol such as a new protocol other than RRC, a new signaling radio bearer (SRB) in RRC, or an upper layer signalling encapsulated in existing RRC.
[0058] For instance, serval types of AI tasks can be performed in an RRC_INACTIVE state of a UE:
[0059] (1) Data collection in RRC_INACTIVE: the UE performs data collection in an RRC_INACTIVE e.g. for an AI functionality or for training or inference for an AI task. One example, the UE collects one or more layer-1 (L1) or layer-3 (L3) measurement results in the RRC_INACTIVE state.
[0060] (2) Training in RRC_INACTIVE: the UE may perform AI / ML training in the RRC_INACTIVE state for an AI task or an AI functionality since AI / ML training does not need a data transmission between the UE and a network node.
[0061] (3) Positioning: the UE may perform AI / ML positioning in the RRC_INACTIVE state. For example, the UE in the RRC_INACTVE state collects fingerprint information and uses the fingerprint information to predict accurate positioning information.
[0062] (4) Sensing: the UE may perform a sensing function in the RRC_INACTIVE state. For example, the UE in the RRC_INACTVE state senses a surrounding object and uses AI / ML to predict the object.
[0063] Currently, details of supporting AI tasks in an RRC inactive state (i.e. RRC_INACTIVE state) of a UE have not been discussed. For instance, to support AI tasks in the RRC_INACTIVE state, the following issues need to be solved:
[0064] (1) How to support a network triggered transition from the RRC_INACTIVE state to the RRC_CONNECTED state (i.e. an RRC connected state) due to an AI / ML task. Currently, RAN paging trigger events only include DL user data or DL signalling. Some embodiments of the present disclosure define an AI task related RAN paging trigger event, and a new AI task related RAN paging cause is included in a paging message, e.g. a RAN paging message.
[0065] (2) How to support an AI task related RRC resume procedure without a UE context relocation. For example, some embodiments of the present disclosure define that a serving RAN node (i.e. a current serving RAN node or a receiving RAN node) of a UE may provide one or more AI task related causes, which are received from the UE, to a last serving RAN node of the UE. The last serving RAN node may transfer a partial UE context including the AI task related context (e.g. one or more CRB related configurations) to the serving RAN node.
[0066] (3) How to support an AI task related RRC resume procedure with a UE context relocation. For example, some embodiments of the present disclosure enable a data transmission between a serving RAN node of a UE and an AI task originated RAN node.
[0067] The present disclosure aims to solve the above issues and provides methods and apparatuses for an AI task related state transition from RRC_INACTIVE to RRC_CONNECTED of a UE. In particular, some embodiments of the present disclosure provide a solution to enable a network triggered transition from RRC_INACTIVE to RRC_CONNECTED due to an AI / ML task. For instance, an AI task triggered RAN paging may be triggered. In some embodiments, an AI task related RAN paging trigger event are defined, and a new AI task related RAN paging cause is included in a RAN paging message. According to an AI task related RAN paging cause, a UE may set one or more appropriate causes for an RRC resume procedure, and the UE may only resume one or more CRBs that are related to an AI task. Some embodiments of the present disclosure assume that DRBs for user data are not necessarily resumed if the RRC resume procedure is triggered by one or more AI task related causes (i.e. AI task related reasons) .
[0068] Some embodiments of the present disclosure provide a solution to enable an AI task related RRC resume procedure without a UE context relocation. For example, a UE may provide one or more AI task related causes in an RRC resume request message. A serving RAN node of a UE may send a retrieval UE context request message including one or more AI task related causes to a last serving RAN node of the UE. The last serving RAN node may transfer a partial UE context including an AI task related UE context to the serving RAN node. The serving RAN node may send, to the UE, an RRC resume message including information (e.g. an indication) to indicate that the UE resumes CRBs only for one or more AI tasks, so as to resume one or more AI task related CRBs.
[0069] Some other embodiments of the present disclosure provide a solution to enable an AI task related RRC resume procedure with a UE context relocation. For example, a last serving RAN node of a UE may decide to relocate a UE context and may provide transport information of an AI task originated RAN node to a serving RAN node of the UE. The serving RAN node may send transport information of the serving RAN node to the last serving RAN node. Transport information of a RAN node may be used for a data transmission for the AI task between two RAN nodes.
[0070] In the embodiments of the present disclosure, an AI task may also be named as an AI / ML task or the like. An AI training model may also be named as an AI or ML training model or the like. An RRC resume may also be named as an RRC connection resume procedure or the like. More details of the embodiments of the present disclosure will be illustrated in the following text in combination with the appended drawings.
[0071] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.
[0072] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN) , a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g. receive signaling, transmit signaling) over a Uu interface.
[0073] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g. voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN) . In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.
[0074] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.
[0075] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.
[0076] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g. S1, N2, or network interface) . In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g. via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .
[0077] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g. a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g. a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g. data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.
[0078] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g. via an S1, N2, or another network interface) . The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g. a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g. control information, data, and the like) between the UE 104 and the application server using the established session (e.g. the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g. one or more network functions of the CN 106) .
[0079] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g. time resources (e.g. symbols, slots, subframes, frames, or the like) or frequency resources (e.g. subcarriers, carriers) ) to perform various operations (e.g. wireless communications) . In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.
[0080] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g. μ=0) may be associated with a first subcarrier spacing (e.g. 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g. μ=0) associated with the first subcarrier spacing (e.g. 15 kHz) may utilize one slot per subframe. A second numerology (e.g. μ=1) may be associated with a second subcarrier spacing (e.g. 30 kHz) and a normal cyclic prefix. A third numerology (e.g. μ=2) may be associated with a third subcarrier spacing (e.g. 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g. μ=3) may be associated with a fourth subcarrier spacing (e.g. 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g. μ=4) may be associated with a fifth subcarrier spacing (e.g. 240 kHz) and a normal cyclic prefix.
[0081] A time interval of a resource (e.g. a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.
[0082] Additionally or alternatively, a time interval of a resource (e.g. a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g. quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g. quantity) of symbols (e.g. OFDM symbols) . In some implementations, the number (e.g. quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g. applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g. μ=0) associated with a first subcarrier spacing (e.g. 15 kHz) may be used interchangeably between subframes and slots.
[0083] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) . In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g. control information, data) . In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.
[0084] FR1 may be associated with one or multiple numerologies (e.g. at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g. μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g. μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g. μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g. at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g. μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g. μ=3) , which includes 120 kHz subcarrier spacing.
[0085] Figure 2 illustrates an example of a UE 200 in accordance with aspects of the present disclosure. The UE 200 may include a processor 202, a memory 204, a controller 206, and a transceiver 208. The processor 202, the memory 204, the controller 206, or the transceiver 208, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0086] The processor 202, the memory 204, the controller 206, or the transceiver 208, or various combinations or components thereof may be implemented in hardware (e.g. circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0087] The processor 202 may include an intelligent hardware device (e.g. a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 202 may be configured to operate the memory 204. In some other implementations, the memory 204 may be integrated into the processor 202. The processor 202 may be configured to execute computer-readable instructions stored in the memory 204 to cause the UE 200 to perform various functions of the present disclosure.
[0088] The memory 204 may include volatile or non-volatile memory. The memory 204 may store computer-readable, computer-executable code including instructions when executed by the processor 202 cause the UE 200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 204 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0089] In some implementations, the processor 202 and the memory 204 coupled with the processor 202 may be configured to cause the UE 200 to perform one or more of the functions described herein (e.g. executing, by the processor 202, instructions stored in the memory 204) . For example, the processor 202 may support wireless communication at the UE 200 in accordance with examples as disclosed with respect to Figures 5-8.
[0090] The controller 206 may manage input and output signals for the UE 200. The controller 206 may also manage peripherals not integrated into the UE 200. In some implementations, the controller 206 may utilize an operating system such as or other operating systems. In some implementations, the controller 206 may be implemented as part of the processor 202.
[0091] In some implementations, the UE 200 may include at least one transceiver 208. In some other implementations, the UE 200 may have more than one transceiver 208. The transceiver 208 may represent a wireless transceiver. The transceiver 208 may include one or more receiver chains 210, one or more transmitter chains 212, or a combination thereof. The means for receiving abovementioned in the processor 202 or the means for transmitting in the processor 202 may be implemented via at least one transceiver 208.
[0092] A receiver chain 210 may be configured to receive signals (e.g. control information, data, packets) over a wireless medium. For example, the receiver chain 210 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 210 may include at least one amplifier (e.g. a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 210 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 210 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0093] A transmitter chain 212 may be configured to generate and transmit signals (e.g. control information, data, packets) . The transmitter chain 212 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 212 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 212 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0094] Figure 3 illustrates an example of a processor 300 in accordance with aspects of the present disclosure. The processor 300 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 300 may include a controller 302 configured to perform various operations in accordance with examples as described herein. The processor 300 may optionally include at least one memory 304, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 300 may optionally include one or more arithmetic-logic units (ALUs) 306. One or more of these components may be in electronic communication or otherwise coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g. buses) .
[0095] The processor 300 may be a processor chipset and include a protocol stack (e.g. a software stack) executed by the processor chipset to perform various operations (e.g. receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g. memory local to or included in the processor chipset (e.g. the processor 300) or other memory (e.g. random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .
[0096] The controller 302 may be configured to manage and coordinate various operations (e.g. signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 300 to cause the processor 300 to support various operations in accordance with examples as described herein. For example, the controller 302 may operate as a control unit of the processor 300, generating control signals that manage the operation of various components of the processor 300. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0097] The controller 302 may be configured to fetch (e.g. obtain, retrieve, receive) instructions from the memory 304 and determine subsequent instruction (s) to be executed to cause the processor 300 to support various operations in accordance with examples as described herein. The controller 302 may be configured to track memory address of instructions associated with the memory 304. The controller 302 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 302 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 300 to cause the processor 300 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 302 may be configured to manage flow of data within the processor 300. The controller 302 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 300.
[0098] The memory 304 may include one or more caches (e.g. memory local to or included in the processor 300 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 304 may reside within or on a processor chipset (e.g. local to the processor 300) . In some other implementations, the memory 304 may reside external to the processor chipset (e.g. remote to the processor 300) .
[0099] The memory 304 may store computer-readable, computer-executable code including instructions that, when executed by the processor 300, cause the processor 300 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 302 and / or the processor 300 may be configured to execute computer-readable instructions stored in the memory 304 to cause the processor 300 to perform various functions. For example, the processor 300 and / or the controller 302 may be coupled with or to the memory 304, the processor 300, the controller 302, and the memory 304 may be configured to perform various functions described herein. In some examples, the processor 300 may include multiple processors and the memory 304 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0100] The one or more ALUs 306 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 306 may reside within or on a processor chipset (e.g. the processor 300) . In some other implementations, the one or more ALUs 306 may reside external to the processor chipset (e.g. the processor 300) . One or more ALUs 306 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 306 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 306 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 306 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 306 to handle conditional operations, comparisons, and bitwise operations.
[0101] The processor 300 may support wireless communication in accordance with examples as described with respect to Figures 5-8 as described below. In some implementations, the processor 300 may be configured to support a means for performing operations of a RAN node as described with respect to Figure 5. The processor 300 may be configured to or operable to support: a means for triggering a paging procedure related to one or more AI tasks; a means for transmitting a paging message including an AI task related cause to a UE; and a means for receiving, from the UE, an RRC resume request related to the one or more AI tasks.
[0102] It should be appreciated by persons skilled in the art that the components in exemplary processor 300 may be changed, for example, some of the components in exemplary processor 300 may be omitted or modified or new component (s) may be added to exemplary processor 300, without departing from the spirit and scope of the disclosure. For example, in some embodiments, the processor 300 may not include the ALUs 306.
[0103] Figure 4 illustrates an example of a NE 400 in accordance with aspects of the present disclosure. The NE 400 may include a processor 402, a memory 404, a controller 406, and a transceiver 408. The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g. operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0104] The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations or components thereof may be implemented in hardware (e.g. circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0105] The processor 402 may include an intelligent hardware device (e.g. a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 402 may be configured to operate the memory 404. In some other implementations, the memory 404 may be integrated into the processor 402. The processor 402 may be configured to execute computer-readable instructions stored in the memory 404 to cause the NE 400 to perform various functions of the present disclosure.
[0106] The memory 404 may include volatile or non-volatile memory. The memory 404 may store computer-readable, computer-executable code including instructions when executed by the processor 402 cause the NE 400 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 404 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0107] In some implementations, the processor 402 and the memory 404 coupled with the processor 402 may be configured to cause the NE 400 to perform one or more of the functions described herein (e.g. executing, by the processor 402, instructions stored in the memory 404) . For example, the processor 402 may support wireless communication at the NE 400 in accordance with examples as disclosed herein. For example, the NE 400 may be configured to support a means for performing the operations as described with respect to Figures 5-8 as described below.
[0108] In some implementations, the NE 400 may be a RAN node as described with respect to Figure 5. The NE 400 may be configured to support: a means for triggering a paging procedure related to one or more AI tasks; a means for transmitting a paging message including an AI task related cause to a UE; and a means for receiving, from the UE, an RRC resume request related to the one or more AI tasks.
[0109] The controller 406 may manage input and output signals for the NE 400. The controller 406 may also manage peripherals not integrated into the NE 400. In some implementations, the controller 406 may utilize an operating system such as or other operating systems. In some implementations, the controller 406 may be implemented as part of the processor 402.
[0110] In some implementations, the NE 400 may include at least one transceiver 408. In some other implementations, the NE 400 may have more than one transceiver 408. The transceiver 408 may represent a wireless transceiver. The transceiver 408 may include one or more receiver chains 410, one or more transmitter chains 412, or a combination thereof. The means for receiving or the means for transmitting abovementioned in the processor 402 may be implemented via at least one transceiver 408.
[0111] A receiver chain 410 may be configured to receive signals (e.g. control information, data, packets) over a wireless medium. For example, the receiver chain 410 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 410 may include at least one amplifier (e.g. a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 410 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 410 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0112] A transmitter chain 412 may be configured to generate and transmit signals (e.g. control information, data, packets) . The transmitter chain 412 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 412 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 412 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0113] It should be appreciated by persons skilled in the art that the components in exemplary NE 400 may be changed, for example, some of the components in exemplary NE 400 may be omitted or modified or new component (s) may be added to exemplary NE 400, without departing from the spirit and scope of the disclosure. For example, in some embodiments, the NE 400 may not include the controller 406.
[0114] Figure 5 illustrates a flowchart of a method related to an AI task in accordance with aspects of the present disclosure. The operations of the method may be implemented by a RAN node (e.g. a last serving RAN node or a current serving RAN node of a UE) as described herein. In some implementations, the RAN node may execute a set of instructions to control the function elements of the RAN node to perform the described functions. In some implementations, aspects of operations 502, 504 and 506 may be performed by NE 400 as described with reference to Figure 4. Each of operations 502, 504 and 506 may be performed in accordance with examples as described herein. Specific examples are described in the embodiments of Figures 6-8 as follows.
[0115] At 502, the method may include triggering, by a RAN node (denoted as RAN node #1) , a paging procedure related to one or more AI tasks. In different embodiments, RAN node #1 may be a last serving RAN node for a UE, a current serving RAN node (e.g. a receiving RAN node) for the UE; or an AI task originated RAN node. The last serving RAN node is the RAN node which sent the UE into RRC_INACTIVE state.
[0116] In some implementations, the paging procedure may be triggered in at least one of the following cases for the UE in RRC_INACTIVE with AI task configuration:
[0117] (1) RAN node #1 wants to update one or more AI or ML training models for the one or more AI tasks of the UE;
[0118] (2) RAN node #1 wants to transmit one or more new AI or ML training models for the one or more AI tasks to the UE;
[0119] (3) RAN node #1 wants to update one or more configuration parameters of the one or more AI tasks that are performed in an RRC inactive state (i.e. RRC_INACTIVE) of the UE; (4) RAN node #1 wants to configure one or more new AI tasks to the UE;
[0120] (5) RAN node #1 wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE;
[0121] (6) RAN node #1 receives AI task related data of the UE from a CN;
[0122] (7) RAN node #1 receives AI task related signalling of the UE from the CN;
[0123] (8) RAN node #1 decides to get data collected by the UE in the RRC inactive state; or
[0124] (9) RAN node #1 receives a RAN paging message including an AI task related cause (denoted as AI task related cause #1) from another RAN node (denoted as RAN node #2) . For example, if RAN node #1 is a current serving RAN node for a UE, RAN node #2 is a last serving RAN node for the UE or an AI task originated RAN node.
[0125] At 504, RAN node #1 may transmit a paging message including AI task related cause #1 to a UE.
[0126] In some embodiments, AI task related cause #1 includes at least one of the following:
[0127] (1) A cause to indicate that the paging procedure is triggered for an AI or ML purpose, e.g. a general cause.
[0128] (2) A cause to indicate type information of the one or more AI tasks, e.g. a specific cause. For instance, the type information of the one or more AI tasks includes at least one of the following: data collection; sensing; positioning; or an AI or ML training model.
[0129] (3) A cause to indicate that RAN node #1 receives AI task related data of the UE from a CN.
[0130] (4) A cause to indicate that RAN node #1 receives AI task related signalling of the UE from the CN.
[0131] (5) A cause to indicate that RAN node #1 wants to update one or more configuration parameters of the one or more AI tasks that are performed in the RRC inactive state of the UE.
[0132] (6) A cause to indicate that RAN node #1 wants to configure one or more new AI tasks to the UE.
[0133] (7) A cause to indicate that RAN node #1 wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE. For example, RAN node #1 wants to terminate or release all or a subset of the one or more AI tasks.
[0134] (8) A cause to indicate that RAN node #1 decides to get data collected by the UE in the RRC inactive state.
[0135] At 506, RAN node #1 may receive, from the UE, an RRC resume request related to the one or more AI tasks. For example, the RRC resume request includes another AI task related cause (denoted as AI task related cause #2) . In some embodiments, AI task related cause #2 includes at least one of the following:
[0136] (1) the one or more AI tasks become applicable;
[0137] (2) the one or more AI tasks become available;
[0138] (3) the one or more AI tasks are complete;
[0139] (4) the valid time of the one or more AI tasks has been elapsed;
[0140] (5) a timer related to the one or more AI tasks expires; or
[0141] (6) a general RRC cause. In an example, the general RRC cause may be "AI / ML, " which means that the RRC connection resume procedure is initiated by an AI / ML purpose. In another example, the general RRC cause may be "AI / ML mobile originate (MO) , " which means that the RRC connection resume procedure is initiated by a mobile originated AI / ML purpose. In an additional example, the general RRC cause may be "AI / ML mobile terminated (MT) , " which means that the RRC connection resume procedure is initiated by a mobile terminated AI / ML purpose respectively.
[0142] In some embodiments (denoted as Embodiment #a) , RAN node #1 is the current serving RAN node for the UE. In some other embodiments (denoted as Embodiment #b) , RAN node #1 is the last serving RAN node for the UE. Specific examples are described in the embodiments of Figures 6, 7 and 8 as follows.
[0143] In Embodiment #athat RAN node #1 is the current serving RAN node for the UE, RAN node #1 may transmit a message (denoted as message #1) including AI task related cause #1 to another node (denoted as RAN node #3) . RAN node #3 may be the last serving RAN node for the UE or an AI task originated RAN node. In some cases, the last serving RAN node and the AI task originated RAN node are the same RAN node.
[0144] For example, message #1 is a retrieval UE context request message, e.g. a Retrieval UE Context Request message. In some implementations, message #1 may be for an RRC resume of the UE. For instance, message #1 includes information indicating that the RRC resume request from the UE (which is received at 506) is associated with the one or more AI tasks, e.g. an indication to indicate that the RRC resume request of the UE is for an AI task.
[0145] In some implementations of Embodiment #a, RAN node #1 may receive a partial UE context from RAN node #3. The partial UE context may be included in a partial UE context transfer message, e.g. a PARTIAL UE CONTEXT TRANSFER message. For example, the partial UE context includes at least one of the following:
[0146] (1) An AI task related UE context, e.g. which includes at least one of the following:
[0147] a) AI task type information. For example, the AI task can be (but not limited to) one of the following types:
[0148] - Data Collection in RRC_INACTIVE: the UE performs data collection in RRC_INACTIVE, e.g. for an AI functionality or for training or inference for an AI task. In one example, the UE collects L1 or L2 measurement results in RRC_INACTIVE state.
[0149] - Training in RRC_INACTIVE: the UE may perform AI / ML training in RRC_INACTIVE state for an AI task or an AI functionality since AI / ML training does not need data transmission between the UE and the network.
[0150] - Positioning: the UE may perform AI / ML positioning in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state collects more fingerprint information and use the fingerprint information to predict more accurate positioning information.
[0151] - Sensing: the UE may perform a sensing function in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state senses surrounding object and uses AI / ML to predict the object.
[0152] b) One or more QoS requirements of the one or more AI tasks.
[0153] c) One or more QoS parameters of the one or more AI tasks.
[0154] d) PDU session information for the one or more AI tasks, e.g. PDU session IDs.
[0155] e) RRC configuration information for the one or more AI tasks. For example, the RRC configuration information includes at least one of the following: PDCP configuration information; MAC configuration information; RLC configuration information; or PHY configuration information.
[0156] f) RRC configuration information of a CRB associated with the one or more AI tasks, e.g. one or more CRBs that carry a data transmission for AI tasks in air interface.
[0157] (2) Transport information of the AI task originated RAN node, e.g. which includes at least one of the following:
[0158] a) AI task TNL information allocated by the AI task originated RAN node, e.g. denoted as "AI task TNL information @AI task originated RAN node. " In some implementation, the AI task TNL information includes: IP address information associated with the one or more AI tasks; and / or GTP-U TEID information associated with the one or more AI tasks. The AI task TNL information may be per an AI task or per a CRB of the AI task.
[0159] b) IP information allocated by the AI task originated RAN node, e.g. denoted as "IP @ AI task originated RAN node. "
[0160] c) RAN node ID information of the AI task originated RAN node.
[0161] d) ID information of the one or more AI tasks.
[0162] In some implementations of Embodiment #a, RAN node #1 may receive, from RAN node #3, UL TNL address information of CRBs related to the one or more AI tasks (e.g. UL TNL address of CRBs for AI task) . In an implementation, RAN node #1 may transmit, to RAN node #3, DL TNL address information of the CRBs related to the one or more AI tasks (e.g. DL TNL address of CRBs for the one or more AI tasks) .
[0163] In some implementations of Embodiment #a, RAN node #1 may transmit an RRC resume message (e.g. an RRCResume message) to the UE, to resume the CRBs related to the one or more AI tasks (i.e. CRBs only for AI task) .
[0164] In some implementations of Embodiment #a, RAN node #1 may detect an end of a data transmission of AI task (e.g. an end AI task) , and transmit, to RAN node #3, information (denoted as information #1) to indicate the end of the data transmission of AI task. For instance, information #1 is included in a retrieve UE context confirm message, e.g. a RETRIEVE UE CONTEXT CONFIRM message.
[0165] In some implementations, the end of the data transmission of AI task is detected by RAN node #1 in at least one of the following cases:
[0166] (1) no further data transmission of AI task is received by RAN node #1 for a time duration;
[0167] (2) no further data transmission of AI task is transmitted from RAN node #1 for a time duration; or
[0168] (3) RAN node #1 receives an end indication for the end of the data transmission of AI task from the UE.
[0169] In some implementations of Embodiment #a, RAN node #1 may receive a full UE context from RAN node #3. For instance, the full UE context is included in a retrieve UE context response message, e.g. a RETRIEVE UE CONTEXT RESPONSE message. The full UE context may include transport information of the AI task originated RAN node. In some implementations, the transport information includes at least one of the following:
[0170] (1) AI task TNL information allocated by the AI task originated RAN node, e.g. denoted as "AI task TNL information @AI task originated RAN node. " In an implementation, the AI task TNL information includes: IP address information associated with the one or more AI tasks; and / or GTP-U TEID information associated with the one or more AI tasks. The AI task TNL information may be per an AI task or per a CRB of the AI task.
[0171] (2) IP information allocated by the AI task originated RAN node, e.g. denoted as "IP @AI task originated RAN node. "
[0172] (3) RAN node ID information of the AI task originated RAN node, e.g. a RAN node ID.
[0173] (4) ID information of the one or more AI tasks.
[0174] In some implementations of Embodiment #a, RAN node #1 may transmit transport information of RAN node #1 (i.e. transport information of the current serving RAN node) to RAN node #3. For example, the transport information of RAN node #1 includes at least one of the following:
[0175] (1) AI task TNL information allocated by RAN node #1, e.g. denoted as "AI task TNL information @receiving RAN node. " In some implementation, the AI task TNL information includes: IP address information associated with the one or more AI tasks; and / or GTP-U TEID information associated with the one or more AI tasks. The AI task TNL information may be per an AI task or per a CRB of the AI task.
[0176] (2) IP information allocated by RAN node #1, e.g. denoted as "IP @receiving RAN node. "
[0177] (3) RAN node ID information of RAN node #1, e.g. a RAN node ID.
[0178] (4) ID information of the one or more AI tasks.
[0179] In some implementations of Embodiment #a, RAN node #1 may receive data or signaling of the one or more AI tasks (e.g. an AI task report, an update of an AI model, and / or configuration information) from the UE, and transmit the data of the one or more AI tasks to the AI task originated RAN node according to the transport information of the AI task originated RAN node. In some implementations of Embodiment #a, RAN node #1 may receive data or signaling of the one or more AI tasks from the AI task originated RAN node according to the transport information of the RAN node #1. And RAN node #1 sends the data or signaling to the UE. In some implementations of Embodiment #a, the data or signaling of the one or more AI tasks is transmitted in a GTP-U tunnel established between RAN node #1 (the current serving RAN node) and AI task originated RAN node. Specific examples are described in the embodiments of Figures 7 and 8 as follows.
[0180] In Embodiment #b that RAN node #1 is a last serving RAN node for the UE, RAN node #1 may transmit a paging message including AI task related cause #1 to "acurrent serving RAN node for the UE" or "an AI task originated RAN node. " A specific example is described in the embodiments of Figure 6 as follows.
[0181] In Embodiment #b that RAN node #1 is a last serving RAN node for the UE, RAN node #1 may receive a message (e.g. message #1) including AI task related cause #2 from a current serving RAN node for the UE. For example, the message is a retrieval UE context request message, e.g. a Retrieval UE Context Request message. The message may be for an RRC resume of the UE. The message may include information indicating that the RRC resume request from the UE is associated with the one or more AI tasks, e.g. an indication to indicate that the RRC resume request of the UE is for an AI task.
[0182] In some implementations of Embodiment #b, RAN node #1 (i.e. the last serving RAN node) may be an AI task originated RAN node. That is, a RAN node which originated an AI task is the last serving RAN node of the UE.
[0183] In some implementations of Embodiment #b, RAN node #1 may transmit a partial UE context to the current serving RAN node. For instance, the partial UE context is included in a partial UE context transfer message, e.g. a PARTIAL UE CONTEXT TRANSFER message. The partial UE context may include an AI task related UE context, e.g. which includes at least one of the following:
[0184] (1) AI task type information;
[0185] (2) one or more QoS requirements of the one or more AI tasks;
[0186] (3) one or more QoS parameters of the one or more AI tasks;
[0187] (4) PDU session information for the one or more AI tasks, e.g. PDU session IDs;
[0188] (5) RRC configuration information for the one or more AI tasks, for example, the RRC configuration information includes: PDCP configuration information; MAC configuration information; RLC configuration information; and / or PHY configuration information; or
[0189] (6) RRC configuration information of a CRB associated with the one or more AI tasks, e.g. CRBs that carry a data transmission for AI tasks in air interface.
[0190] In some implementations of Embodiment #b, RAN node #1 may transmit, to the current serving RAN node, UL TNL address information of CRBs related to the one or more AI tasks (e.g. UL TNL address of CRBs for AI tasks) , and receive, from the current serving RAN node, DL TNL address information of the CRBs related to the one or more AI tasks (e.g. DL TNL address of CRBs for AI tasks) .
[0191] In some implementations of Embodiment #b, RAN node #1 may receive, from the current serving RAN node, information (e.g. information #1) to indicate an end of a data transmission of AI task. For instance, the information is included in a retrieve UE context confirm message, e.g. RETRIEVE UE CONTEXT CONFIRM message.
[0192] In some implementations of Embodiment #b, RAN node #1 may transmit a full UE context to the current serving RAN node. For instance, the full UE context is included in a retrieve UE context response message, e.g. a RETRIEVE UE CONTEXT RESPONSE message. The full UE context may include transport information of the AI task originated RAN node, e.g. which includes at least one of the following:
[0193] (1) AI task TNL information allocated by the AI task originated RAN node, e.g. denoted as "AI task TNL information @AI task originated RAN node. " In some implementation, the AI task TNL information includes: IP address information associated with the one or more AI tasks; and / or GTP-U TEID information associated with the one or more AI tasks. The AI task TNL information may be per an AI task or per a CRB of the AI task.
[0194] (2) IP information allocated by the AI task originated RAN node, e.g. denoted as "IP @AI task originated RAN node. "
[0195] (3) RAN node ID information of the AI task originated RAN node.
[0196] (4) ID information of the one or more AI tasks.
[0197] In some implementations of Embodiment #b, RAN node #1 may receive transport information of the current serving RAN node (i.e. transport information of a receiving RAN node) from the current serving RAN node. In some implementations, RAN node #1 may transmit the transport information to the AI task originated RAN node. For instance, the transport information includes at least one of the following:
[0198] (1) AI task TNL information allocated by the current serving RAN node, e.g. denoted as "AI task TNL information @receiving RAN node. " For example, the AI task TNL information includes at least one of the following: IP address information associated with the one or more AI tasks; or GTP-U TEID information associated with the one or more AI tasks. The AI task TNL information may be per an AI task or per a CRB of the AI task.
[0199] (2) IP information allocated by the current serving RAN node, e.g. denoted as "IP @ receiving RAN node. "
[0200] (3) RAN node ID information of the current serving RAN node.
[0201] (4) ID information of the one or more AI tasks.
[0202] In some implementations of Embodiment #b, data of the one or more AI tasks is transmitted in a GTP-U tunnel established between the current serving RAN node and AI task originated RAN node. Specific examples are described in the embodiments of Figures 7 and 8 as follows.
[0203] It should be noted that the method described in Figure 5 describes possible implementations, and that the operations and the steps may be rearranged or otherwise eliminated or modified and that other implementations are possible, without departing from the spirit and scope of the disclosure.
[0204] Figure 6 illustrates a schematic diagram of a network triggered transition of a UE in accordance with aspects of the present disclosure. Details described in all other embodiments of the present disclosure are applicable for the embodiments shown in Figure 6.
[0205] The embodiments of Figure 6 focuses on a network triggered transition of a UE from RRC_INACTIVE to RRC_CONNECTED due to an AI / ML task. When a UE in an RRC_INACTIVE state with configured one or more AI tasks, a RAN node may want to update AI task related configuration information, or update an AI / ML model of an AI task, or send more assistance data for the AI task or receiving AI task related data or signalling of the UE from a CN. For example, the RAN node needs to send a RAN paging message to the UE. The embodiments of Figure 6 provide an AI task triggered RAN paging procedure. For instance, an AI task related RAN paging trigger event are defined; a new AI task related RAN paging cause is included in RAN paging message; and according to AI task related RAN paging cause, a UE sets one or more appropriate causes for an RRC resume procedure and only resumes the CRBs that are related to AI task. Some embodiments of Figure 6 assume that data radio bearers (DRB) sfor user data are not necessarily resumed if the RRC resume procedure is triggered by the AI task related causes (i.e. AI task related reasons) .
[0206] In particular, at 601, a UE in RRC_INACTIVE state is configured with at least one AI task. For example, the AI task can be one of the following types:
[0207] - Data Collection in RRC_INACTIVE: the UE performs data collection in RRC_INACTIVE, e.g. for an AI functionality or for training or inference for an AI task. In one example, the UE collects L1 or L2 measurement results in RRC_INACTIVE state.
[0208] - Training in RRC_INACTIVE: the UE may perform AI / ML training in RRC_INACTIVE state for an AI task or an AI functionality since AI / ML training does not need a data transmission between the UE and the network.
[0209] - Positioning: the UE may perform AI / ML positioning in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state collects more fingerprint information and use the fingerprint information to predict more accurate positioning information.
[0210] - Sensing: the UE may perform a sensing function in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state senses surrounding object and uses AI / ML to predict the object.
[0211] The originated node that owns the AI task (i.e. an AI task originated RAN node which initializes the AI task) can be any of the following:
[0212] (1) A RAN node itself, and the UE is selected by the RAN node to support the AI task.
[0213] (2) A CN node (e.g. network data analytics function (NWDAF) , or a location management function (LMF) ) , and the UE is selected by the CN node or the RAN node to support the AI task.
[0214] (3) An over-the-top (OTT) server, and the UE is selected by the CN node or the RAN node to support the AI task.
[0215] At 602, an AI task related RAN paging trigger event occurs. In some implementations, when the UE is in RRC_INACTIVE state and configured one or more AI tasks, a RAN node may want to update AI task related configuration information, or update an AI / ML model of an AI task, or send more assistance data for the AI task or receiving AI task related data or signalling of the UE from a CN. The RAN node may be the last serving RAN node which sent the UE into RRC_INACTIVE state (as shown in Figure 6) . Or, the RAN node may be an AI task originated RAN node which initializes the AI task (not shown in Figure 6) , e.g. if the last serving RAN node and the AI task originated RAN node are the same node.
[0216] In such implementations of operation 602, the RAN node needs to send a RAN paging message to the UE. For example, the RAN paging may be triggered in at least one of the following cases:
[0217] (1) when the RAN node wants to update an AI / ML training model for an AI task or send a new AI / ML training model for the AI task to the UE;
[0218] (2) when the RAN node wants to update one of configuration parameters of the AI task that is performed in the RRC_INACTIVE state for the UE;
[0219] (3) when the RAN node wants to configure a new AI task to the UE;
[0220] (4) when the RAN node wants to terminate an AI task that is performed in the RRC_INACTIVE state;
[0221] (5) when the RAN node receives AI task related data or signalling from core network; or
[0222] (6) when the RAN node decides to get data collected by the UE in RRC_INACTIVE state.
[0223] At 603, an AI task related RAN paging is triggered. The RAN paging may be triggered either only in cells controlled by the last serving RAN node or may be triggered also by means of Xn RAN Paging in cells controlled by other RAN node, configured to the UE in the RAN-based Notification Area (RNA) . The last serving RAN node may decide the RAN paging area (e.g. a list of cells) . The last serving RAN node may send the RAN paging message to another RAN node (e.g. a serving RAN node of the UE) that controls the cells within the RAN paging area.
[0224] At 603, the last serving RAN node (e.g. which may also be the AI task originated RAN node) may send a RAN paging message to a serving RAN node of the UE. Taking 5G as an example, the last serving gNB sends Xn-AP RAN Paging message to a gNB.
[0225] At 603A (optional) , the last serving RAN node (e.g. which may also be the AI task originated RAN node) may also send a paging message to the UE.
[0226] At 603 or 603A, the paging message sent by the last serving RAN node may include an AI task related cause (e.g. AI task related cause #1 as described above) , to indicate that the paging message is triggered by an AI task related reason. The AI task related cause may be named as "AI task related reason, " "AI task related cause for RAN paging, " or "AI task related cause for paging" or the like. The AI task related cause can be one of:
[0227] (1) a general cause to represent that the paging is triggered for an AI / ML purposes;
[0228] (2) a specific cause to represent the type of one or more AI tasks that trigger the paging, e.g. the type may be data collection, sensing, positioning, an AI / ML training model and / or etc.
[0229] (3) a cause to indicate that the last serving RAN node receives AI task related data or signalling of the UE from a CN;
[0230] (4) a cause to indicate that the last serving RAN node wants to update a configuration parameter of the AI task that is performed in the RRC_INACTIVE state for the UE;
[0231] (5) a cause to indicate that the last serving RAN node wants to configure a new AI task to the UE;
[0232] (6) a cause to indicate that the last serving RAN node wants to terminate an AI task that is performed in the RRC_INACTIVE state; or
[0233] (7) a cause to indicate the last serving RAN node decides to get data collected by the UE in RRC_INACTIVE state.
[0234] At 604, the serving RAN node sends a paging message to the UE. The paging message may include the AI task related cause (e.g. AI task related cause #1) , which is received from the last serving RAN node at 603. At 605, the UE may handle the AI task related cause in the paging message.
[0235] In some embodiments, when the UE receives the paging message including the AI task related cause (e.g. AI task related cause #1) , e.g. at 603A and / or 604, an RRC layer of the UE may forward the AI task related cause to an upper layer of the UE. The upper layer of the UE may be an AI / ML dedicated layer or a NAS layer or a link performance prediction (LPP) layer. The UE's upper layer may decide whether to respond the paging message. If the UE's upper layer decides to respond the paging message, the UE's upper layer may provide, to the RRC layer, the AI task related cause for an RRC state transition from RRC_INACTIVE to RRC_CONNECTED. For example, the AI task related cause can be an AI / ML related terminated call, which represents that the RRC resume procedure is triggered by the AI / ML related terminated call.
[0236] In some embodiments, the UE's upper layer may also provide the access category to the RRC layer. For example, the access category can be an AI / ML terminated access category, which indicates that the access attempt's category is an AI / ML related terminated call.
[0237] In some embodiments of Figure 6, the UE may use the AI / ML terminated access category in an access barring procedure to decide whether the access attempt is allowed. The UE may provide the AI / ML related terminated call cause to the network node in an RRC resume request message, e.g. an RRC Resume Request. For instance, the UE may transmit an RRC resume request message including an AI task cause (e.g. AI task related cause #2 as described above) , e.g. at 702 of Figure 7 or at 802 of Figure 8 as described below.
[0238] Figure 7 illustrates a schematic diagram of an AI task related RRC resume procedure without a UE context relocation in accordance with aspects of the present disclosure. Details described in all other embodiments of the present disclosure are applicable for the embodiments shown in Figure 7.
[0239] Some embodiments of Figure 7 assume that AI task data is secured (e.g. encryption or decryption, integrity protection or verification) by an upper layer e.g. by an AI / ML layer, so that the UE does not need to update a security key during an RRC resume procedure.
[0240] In the embodiments of Figure 7, a serving RAN node (e.g. a current serving RAN node or a receiving RAN node) of a UE provides AI task related causes (e.g. AI task related cause #2 as described above) received from the UE to a last serving RAN node of the UE. The last serving RAN node decides to keep a UE context and not relocate the UE context to the serving RAN node. The last serving RAN node transfers a partial UE context including the AI task related context (e.g. CRB related configurations) to the serving RAN node. The embodiments of Figure 7 only resume CRB related configuration information, but do not update the security key.
[0241] In particular, at 701, the UE in RRC_INACTIVE state is configured with at least one AI task. For example, the AI task can be one of the following types:
[0242] - Data Collection in RRC_INACTIVE: the UE performs data collection in RRC_INACTIVE, e.g. for an AI functionality or for training or inference for an AI task. In one example, the UE collects L1 or L2 measurement results in RRC_INACTIVE state.
[0243] - Training in RRC_INACTIVE: the UE may perform AI / ML training in RRC_INACTIVE state for an AI task or an AI functionality since AI / ML training does not need a data transmission between the UE and the network.
[0244] - Positioning: the UE may perform AI / ML positioning in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state collects more fingerprint information and use the fingerprint information to predict more accurate positioning information.
[0245] - Sensing: the UE may perform a sensing function in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state senses a surrounding object and uses AI / ML to predict the object.
[0246] At 702, the UE may trigger an RRC resume for an AI task related reason or cause (e.g. AI task related cause #2) . For example, the UE initiates the RRC Connection Resume procedure when upper layers or an access stratum (AS) layer requests the resume of a suspended RRC connection. For the AI task triggered RRC Connection Resume procedure, the upper layers or the AS layer may request the resume of a suspended RRC connection in one of the following cases:
[0247] (1) when the AI task becomes applicable or available, which refers to that the UE is ready to apply for model inference for the AI task. For an AI task to be applicable, there should be at least one model available within the AI task;
[0248] (2) when the AI task is complete, for example, the UE has performed the AI task completely and the results of the AI task is available in the UE;
[0249] (3) when the valid time of the AI task has been elapsed since receiving an RRC Release message or since the AI task starts or when a timer (denoted as timer #1) related to the one or more AI tasks expires. If the valid time is expired, the UE shall stop performing the AI task or trigger RRC state transition procedure to RRC_CONNECTED state;
[0250] (4) when the UE moves to a cell that is not in the valid area of the AI task; or
[0251] (5) when the UE receives the paging message including an AI task related cause (e.g. AI task related cause #1 as described above) as in the embodiments of Figure 6.
[0252] At 702, the UE sends an RRC resume request message (e.g. an RRC Resume Request) to the serving RAN node. The UE may provide the AI task related causes (e.g. AI task related cause #2) in the RRC resume request message. The AI task related causes may include:
[0253] (1) the AI task becomes applicable or available;
[0254] (2) the AI task is complete;
[0255] (3) the valid time of the AI task has been elapsed;
[0256] (4) a timer (e.g. timer #1) related to the one or more AI tasks expires; or
[0257] (5) a general RRC cause. In an example, the general RRC cause may be "AI / ML, " which means that the RRC connection resume procedure is initiated by an AI / ML purpose. In another example, the general RRC cause may be "AI / ML MO, " which means that the RRC connection resume procedure is initiated by a mobile originated AI / ML purpose. In an additional example, the general RRC cause may be "AI / ML MT, " which means that the RRC connection resume procedure is initiated by a mobile terminated AI / ML purpose respectively.
[0258] At 703, the serving RAN node (e.g. a receiving gNB) sends a retrieval UE context request message (e.g. a Retrieval UE Context Request) to the last serving RAN node (e.g. last serving gNB) . For example, the serving RAN node identifies the last serving RAN node using the I-RNTI and retrieves the UE context by means of Xn-AP Retrieve UE Context procedure. The serving RAN node indicates that the UE request is for an AI task and may also provide AI task related causes (e.g. AI task related cause #2) . The AI task related causes are the same as in operation 702.
[0259] At 704, the last serving RAN node decides not to relocate the full UE context. When receiving the AI task indication and / or AI task related causes (e.g. AI task related cause #2) , the last serving RAN node may decide not to relocate all UE context to the serving RAN node. For example, the last serving RAN node may decide only relocate the AI task related UE context to the serving RAN node.
[0260] At 705, the last serving RAN node transfers a partial UE context including AI task related UE context. For example, the last serving RAN node sends a PARTIAL UE CONTEXT TRANSFER message, which includes an AI task related UE context, to the serving RAN node. The AI task related UE context may include:
[0261] (1) AI task types;
[0262] (2) QoS requirements of the AI task;
[0263] (3) QoS parameters of the AI task;
[0264] (4) PDU session information, e.g. PDU session IDs for the AI task;
[0265] (5) RRC configuration information including PDCP, MAC, RLC, PHY configuration information for the AI tasks; or
[0266] (6) RRC configuration information of CRBs that carry data transmissions for AI tasks in an air interface.
[0267] In some embodiments, the transport information of the AI task originated RAN node may be included in the partial UE context transmitted at 705. The transport information of AI task originated RAN node can be:
[0268] (1) "AI task TNL information @AI task originated RAN node. " The "AI task TNL information @AI task originated RAN node" may include an IP address and a GTP-U TEID, which is used to receive or transmit any data of the AI task by the AI task originated RAN node from or to the serving RAN node. "AI task TNL information @ AI task originated RAN node" can be per AI task or per CRB of the AI task.
[0269] (2) "IP @AI task originated RAN node. " When the serving RAN node receives the AI task report from the UE, the serving RAN node sends the AI task report directly to the AI task initiated RAN node according to the "IP @AI task originated RAN node. " The AI task ID may also be provided together with the AI task report.
[0270] (3) RAN node ID of the AI task originated RAN node" and AI task ID. When the serving RAN node receives the AI task report from the UE, the serving RAN node sends the AI task report directly to the AI task initiated RAN node with the RAN node ID.
[0271] At 705, the last serving RAN node may provide UL TNL address of CRBs for AI tasks.
[0272] At 706, the serving RAN node may acknowledge receiving the partial UE context and provide associated DL TNL address of CRBs. The full UE context is kept at the last serving RAN node, and the AI task related UE context is established at the serving RAN node. Then, UL GTP-U tunnel and / or DL GTP-U tunnel are established for CRBs for data transmission for the AI task. The TNL address comprises an IP address and a GTP-U TEID. A GTP-U tunnel can be established in operations 705 and 706.
[0273] At 707, the serving RAN node sends an RRC resume message to the UE to resume AI tasks related CRBs. The RRC resume message includes an indication to indicate that the UE resumes CRBs only for AI task. It is assumed that the UE has two types of RBs. To support and achieve an AI task, a new bearer type to carry data or signalling transmission for an AI task will be introduced, that can be called as CRB. The CRB can be used for data management, computing power offload, AI lifecycle management for the AI task. While the DRBs are used for data transmission of user data.
[0274] When receives the indication at 707, the UE resumes CRBs and continues to suspend the DRBs. After the RRC resume, the UE sends the data for the AI task to the serving RAN node by the CRBs at 708A. At 708B, the serving RAN node forwards the data to the last serving RAN node, e.g. by the GTP-U tunnel which was established in operations 705 and 706 or forwards the data to the AI task originated RAN node e.g. by the transport information of the AI task originated RAN node received at 705 .
[0275] At 709-712, the UE enters RRC_INACTIVE state.
[0276] In particular, at 709, the serving RAN node requests to release the UE into RRC_INACTIVE state. For example, when the serving RAN node detects an end of data transmission of AI task (for example, there is no further data transmission for a duration or receiving an end indication from the UE) , the serving RAN node sends a RETRIEVE UE CONTEXT CONFIRM message with an indication to indicate the end of data transmission of AI task at 709.
[0277] Upon receiving the RETRIEVE UE CONTEXT CONFIRM message and deciding to terminate the data transmission of AI tasks, the last serving RAN node responds to the serving RAN node with the RETRIEVE UE CONTEXT FAILURE message including an encapsulated RRC release message at 710.
[0278] The serving RAN node may release the established partial UE context. At 711, the serving RAN node sends an RRC release message to the UE. At 712, the UE moves to RRC_INACTIVE state if a suspend indication is included in the RRC release message.
[0279] Optionally, if the last serving RAN node is different form the AI task originated RAN node (e.g. as shown in Figure 7) , the last serving RAN node may forward the transport information of the serving RAN node (which is received at 706) to the AI task originated RAN node at 706A.
[0280] In case of the AI task TNL information is used, a GTP-U tunnel may be established between the serving RAN node and the AI task originated RAN node, for data transmission of AI task at 708C.
[0281] In some embodiments of Figure 7, the AI task originated RAN node can be a CN node, or an OTT or an operation administration and maintenance (OAM) . Transport information of a RAN node can be a node ID, or a node address (e.g., an IP address) . The serving RAN node can send AI task results directly to a RAN node according to its transport information of the RAN node.
[0282] Figure 8 illustrates a schematic diagram of AI task related RRC resume with a UE context relocation in accordance with aspects of the present disclosure. Details described in all other embodiments of the present disclosure are applicable for the embodiments shown in Figure 8.
[0283] In the embodiments of Figure 8, a serving RAN node (e.g. a current serving RAN node or a receiving RAN node) of a UE provides AI task related causes (e.g. AI task related cause #2 as described above) received from the UE to a last serving RAN node of the UE. The last serving RAN node decides to relocate the UE context to the serving RAN node. After receiving data of the AI task, the serving RAN node forwards the data to an AI task originated RAN node. Since the AI task may be initialized by a RAN node, some mechanisms for data transmission of AI task between RAN nodes are needed.
[0284] In particular, at 801, the UE in RRC_INACTIVE state is configured with at least one AI task. For example, the AI task can be one of the following types:
[0285] - Data Collection in RRC_INACTIVE: the UE performs data collection in RRC_INACTIVE, e.g. for an AI functionality or for training or inference for an AI task. In one example, the UE collects L1 or L2 measurement results in RRC_INACTIVE state.
[0286] - Training in RRC_INACTIVE: the UE may perform AI / ML training in RRC_INACTIVE state for an AI task or an AI functionality since AI / ML training does not need data transmission between the UE and the network.
[0287] - Positioning: the UE may perform AI / ML positioning in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state collects more fingerprint information and use the fingerprint information to predict more accurate positioning information.
[0288] - Sensing: the UE may perform a sensing function in RRC_INACTIVE state. For example, the UE in RRC_INACTVE state senses surrounding object and uses AI / ML to predict the object.
[0289] At 802, the UE may trigger an RRC resume for an AI task related reason or cause (e.g. AI task related cause #2) . For example, the UE initiates an RRC Connection Resume procedure when upper layers or an AS layer requests the resume of a suspended RRC connection. For the AI task triggered RRC Connection Resume procedure, the upper layers or the AS layer may request the resume of a suspended RRC connection in one of the following cases:
[0290] (1) when the AI task becomes applicable or available, which refers to that the UE is ready to apply for model inference for the AI task. For an AI task to be applicable, there should be at least one model available within the AI task;
[0291] (2) when the AI task is complete, for example, the UE has performed the AI task completely and the results of the AI task is available in the UE;
[0292] (3) when the valid time of the AI task has been elapsed since receiving an RRC Release message or since the AI task starts or when a timer (e.g. timer #1) related to the one or more AI tasks expires. If the valid time is expired, the UE shall stop performing the AI task or trigger RRC state transition procedure to RRC_CONNECTED state;
[0293] (4) when the UE moves to a cell that is not in the valid area of the AI task; or
[0294] (5) when the UE receives the paging message including an AI task related cause (e.g. AI task related cause #1 as described above) as in the embodiments of Figure 6.
[0295] At 802, the UE sends an RRC resume request message (e.g. an RRC Resume Request) to the serving RAN node. The UE may provide the AI task related causes (e.g. AI task related cause #2) in the RRC resume request message. The AI task related causes may include:
[0296] (1) the AI task becomes applicable or available;
[0297] (2) the AI task is complete;
[0298] (3) the valid time of the AI task has been elapsed;
[0299] (4) a timer (e.g. timer #1) related to the one or more AI tasks expires; or
[0300] (5) a general RRC cause. In an example, the general RRC cause may be "AI / ML, " which means that the RRC connection resume procedure is initiated by an AI / ML purpose. In another example, the general RRC cause may be "AI / ML MO, " which means that the RRC connection resume procedure is initiated by a mobile originated AI / ML purpose. In an additional example, the general RRC cause may be "AI / ML MT, " which means that the RRC connection resume procedure is initiated by a mobile terminated AI / ML purpose respectively.
[0301] At 803, the serving RAN node (e.g. a receiving gNB) sends a retrieval UE context request message (e.g. a Retrieval UE Context Request) to the last serving RAN node (e.g. last serving gNB) . For example, the serving RAN node identifies the last serving RAN node using the I-RNTI and retrieves the UE context by means of Xn-AP Retrieve UE Context procedure. The serving RAN node indicates that the UE request is for an AI task and may also provide AI task related causes (e.g. AI task related cause #2) . The AI task related causes are the same as in operation 802.
[0302] At 804, the last serving RAN node decides to relocate a UE context and responds with the RETRIEVE UE CONTEXT RESPONSE message. The transport information of an AI task originated RAN node is included in the UE context. The transport information of the AI task originated RAN node can be:
[0303] (1) "AI task TNL information @AI task originated RAN node. " The "AI task TNL information @AI task originated RAN node" may include an IP address and a GTP-U TEID, which is used to receive or transmit any data of the AI task by the AI task originated RAN node from or to the serving RAN node. "AI task TNL information @ AI task originated RAN node" can be per AI task or per CRB of the AI task.
[0304] (2) "IP @AI task originated RAN node. " When the serving RAN node receives data of AI tasks (e.g. an AI task report, an update of an AI model, and / or configuration information) from the UE, the serving RAN node may send the data of AI tasks directly to the AI task initiated RAN node according to the "IP @AI task originated RAN node. " The AI task ID may also be provided together with the data of AI tasks.
[0305] (3) "RAN node ID of the AI task originated RAN node" and an AI task ID. When the serving RAN node receives data of AI tasks (e.g. an AI task report, an update of an AI model, and / or configuration information) from the UE, the serving RAN node may send the data of AI tasks directly to the AI task initiated RAN node with the RAN node ID.
[0306] At 805, the serving RAN node sends an RRC resume message to the UE. At 806, the serving RAN node sends transport information of the serving RAN node to the last serving RAN node. At 807, the last serving RAN node forwards the transport information of the serving RAN node to the AI task originated RAN node. The transport information of the serving RAN node can be:
[0307] (1) "AI task TNL information @receiving RAN node. " "AI task TNL information @ receiving RAN node" may include an IP address and a GTP-U TEID, which is used to receive or transmit any data of the AI task by the serving RAN node. "AI task TNL information @receiving RAN node" can be per AI task or per CRB of the AI task.
[0308] (2) "IP @receiving RAN node. " For AI task reconfiguration, the AI task originated RAN node sends the updated parameters of the AI task to the serving RAN node according to the "IP @receiving RAN node. " The serving RAN node sends the updated parameter of the AI task to the UE.
[0309] (3) "RAN node ID of the receiving RAN node" and an AI task ID. For AI task reconfiguration, the AI task originated RAN node may send the updated parameters of the AI task to the serving RAN node according to the "RAN node ID of the serving RAN node" and AI task ID. The serving RAN node may send the updated parameters of the AI task to the UE.
[0310] In case of AI task TNL information is used, a GTP-U tunnel is established between the serving RAN node and the AI task originated RAN node for data transmission of AI task.
[0311] After the RRC resume, the UE sends the data for the AI task to the serving RAN node by the CRBs at 808A. At 808B, the serving RAN node forwards the data to the last serving RAN node, e.g. by the GTP-U tunnel which was established in operations 806 and 807.
[0312] In some embodiments of Figure 8, the AI task originated RAN node can be a CN node, or an OTT or an OAM. Transport information of a RAN node can be a node ID, or a node address (e.g., an IP address) . The serving RAN node can send AI task results directly to a RAN node according to its transport information of the RAN node.
[0313] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1.A radio access network (RAN) node, comprising:at least one memory; andat least one processor coupled to the at least one memory and configured to cause the RAN node to:trigger a paging procedure related to one or more artificial intelligence (AI) tasks;transmit a paging message including an AI task related cause to a user equipment (UE) ; andreceive, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.2.The RAN node of Claim 1, wherein the paging procedure is triggered in at least one of the following cases:the RAN node wants to update one or more AI or machine learning (ML) training models for the one or more AI tasks of the UE;the RAN node wants to transmit one or more new AI or ML training models for the one or more AI tasks to the UE;the RAN node wants to update one or more configuration parameters of the one or more AI tasks that are performed in a RRC inactive state of the UE;the RAN node wants to configure one or more new AI tasks to the UE;the RAN node wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE;the RAN node receives AI task related data of the UE from a core network (CN) ;the RAN node receives AI task related signalling of the UE from the CN;the RAN node decides to get data collected by the UE in the RRC inactive state; orif the RAN node is a first RAN node, the RAN node receives a RAN paging message including the AI task related cause from a second RAN node.3.The RAN node of Claim 1, wherein the RAN node is one of the following:a last serving RAN node for the UE;a current serving RAN node for the UE; oran AI task originated RAN node.4.The RAN node of Claim 1, wherein the AI task related cause includes at least one of the following:a cause to indicate that the paging procedure is triggered for an AI or ML purpose;a cause to indicate type information of the one or more AI tasks;a cause to indicate that the RAN node receives AI task related data of the UE from a core network (CN) ;a cause to indicate that the RAN node receives AI task related signalling of the UE from the CN;a cause to indicate that the RAN node wants to update one or more configuration parameters of the one or more AI tasks that are performed in the RRC inactive state of the UE;a cause to indicate that the RAN node wants to configure one or more new AI tasks to the UE;a cause to indicate that the RAN node wants to terminate or release at least one AI task of the one or more AI tasks that are performed in the RRC inactive state of the UE; ora cause to indicate that the RAN node decides to get data collected by the UE in the RRC inactive state.5.The RAN node of Claim 1, wherein the AI task related cause is a first AI task related cause, and the RRC resume request includes a second AI task related cause.6.The RAN node of Claim 5, wherein the second AI task related cause includes at least one of the following:the one or more AI tasks become applicable;the one or more AI tasks become available;the one or more AI tasks are complete;the valid time of the one or more AI tasks has been elapsed;a timer related to the one or more AI tasks expires; oran RRC cause.7.The RAN node of Claim 6, wherein the RRC cause includes at least one of the following:a cause to indicate that an RRC connection resume procedure is initiated by an AI or ML purpose;a cause to indicate that the RRC connection resume procedure is initiated by a mobile originated AI or ML purpose; ora cause to indicate that the RRC connection resume procedure is initiated by a mobile terminated AI or ML purpose.8.The RAN node of any of Claims 5, 6 and 7, wherein the RAN node is a current serving RAN node for the UE, and the processor of the RAN node is configured to transmit a first message including the second AI task related cause to a third node, and the third node is one of the following:a last serving RAN node for the UE; oran AI task originated RAN node.9.The RAN node of Claim 8, wherein the processor of the RAN node is configured to receive, from the third node, a partial UE context including at least one of the following:an AI task related UE context; andtransport information of the AI task originated RAN node.10.The RAN node of Claim 9, wherein the AI task related UE context includes at least one of the following:AI task type information;one or more quality of service (QoS) requirements of the one or more AI tasks;one or more QoS parameters of the one or more AI tasks;protocol data unit (PDU) session information for the one or more AI tasks;RRC configuration information for the one or more AI tasks; orRRC configuration information of a computing radio bearer (CRB) associated with the one or more AI tasks.11.The RAN node of Claim 8, wherein the processor of the RAN node is configured to receive, from the third node, a full UE context including transport information of the AI task originated RAN node.12.The RAN node of Claim 11, wherein the processor of the RAN node is configured to transmit transport information of the RAN node to the third node.13.The RAN node of Claim 12, wherein the transport information of the RAN node includes at least one of the following:AI task transport network layer (TNL) information allocated by the RAN node;internet protocol (IP) information allocated by the RAN node;RAN node identifier (ID) information of the RAN node; orID information of the one or more AI tasks.14.The RAN node of Claim 5, wherein the RAN node is a last serving RAN node for the UE, and the processor of the RAN node is configured to receive a first message including the second AI task related cause from a current serving RAN node for the UE.15.The RAN node of Claim 14, wherein the processor of the RAN node is configured to transmit, to the current serving RAN node, a full UE context including transport information of the AI task originated RAN node.16.The RAN node of Claim 11 or Claim 15, wherein the transport information of the AI task originated RAN node includes at least one of the following:AI task transport network layer (TNL) information allocated by the AI task originated RAN node;internet protocol (IP) information allocated by the AI task originated RAN node;RAN node identifier (ID) information of the AI task originated RAN node; orID information of the one or more AI tasks.17.The RAN node of Claim 15, wherein the processor of the RAN node is configured to receive transport information of the current serving RAN node from the current serving RAN node.18.The RAN node of Claim 1, wherein the RAN node is a last serving RAN node for the UE, and the processor of the RAN node is configured to transmit a paging message including the AI task related cause to a current serving RAN node for the UE or an AI task originated RAN node.19.A processor for wireless communication, comprising:at least one controller coupled with at least one memory and configured to cause the processor to:trigger a paging procedure related to one or more artificial intelligence (AI) tasks;transmit a paging message including an AI task related cause to a user equipment (UE) ; andreceive, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.20.A method performed by a radio access network (RAN) node, comprising:triggering a paging procedure related to one or more artificial intelligence (AI) tasks;transmitting a paging message including an AI task related cause to a user equipment (UE) ; andreceiving, from the UE, a radio resource control (RRC) resume request related to the one or more AI tasks.