Continuous transmission for artificial intelligence / machine learning

Abstract

Augmented 3GPP New Radio (NR) air interface features can support use of artificial intelligence and machine learning (AI / ML). Continued confidential delivery of AI / ML model data between user equipment

Description

[0002] Due to the great success of AI / ML technologies, transmission / delivery of AI / ML model / data has been discussed, for example, in 3rd Generation Partnership Project (3GPP) . SUMMARY

[0003] In a first aspect of the present disclosure, there is provided a UE, which comprises means for performing: collecting, from a first apparatus, first data related to at least one AI / ML process related to the UE and / or the first apparatus; encrypting the first data and / or integrity protecting the first data; after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the integrity protected and / or encrypted first data, a first indication indicating that the first data is related to the first apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0004] In a second aspect of the present disclosure, there is provided a first apparatus, which comprises means for sending, to a user equipment, a first data related to at least one AI / ML process related to the UE and / or the first apparatus; receiving, from a second apparatus to whom the UE has been handed over, an encrypted and / or integrity protected first data and a second indication indicating each identifier of the at least one AI / ML process.

[0005] In a third aspect of the present disclosure, there is provided a second apparatus, which comprises means for receiving, from a user equipment, first data related to at least one AI / ML process related to the UE and / or a first apparatus, a first indication indicating that the first data is related to a first apparatus, and a second indication indicating each identifier of the at least one AI / ML process; transmitting, to a first apparatus, the first data and the second indication.

[0006] In a fourth aspect of the present disclosure, there is provided a method for a user equipment, the method comprising: collecting, from a first apparatus, first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus; encrypting the first data and / or integrity protecting the first data; after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the integrity protected and / or encrypted first data, a first indication indicating that the first data is related to the first apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0007] In a fifth aspect of the present disclosure, there is provided a method for a first apparatus, the method comprising: sending, to a user equipment, first data related to at least one AI / ML process related to the UE and / or the first apparatus; receiving, from a second apparatus to whom the UE has been handed over, an encrypted and / or integrity protected first data and a second indication indicating each identifier of the at least one AI / ML process.

[0008] In a sixth aspect of the present disclosure, there is provided a method for a second apparatus, the method comprising: receiving, from a user equipment, first data related to at least one AI / ML process related to the UE and / or a first apparatus, a first indication indicating that the first data is related to a first apparatus, and a second indication indicating each identifier of the at least one AI / ML process; transmitting, to a first apparatus, the first data and the second indication.

[0009] In a seventh aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a user equipment, cause the computer to carry out: collecting, from a first apparatus, first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus; encrypting the first data and / or integrity protecting the first data; after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the integrity protected and / or encrypted first data, a first indication indicating that the first data is related to the first apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0010] In an eighth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a first apparatus, cause the computer to carry out: sending, to a user equipment, first data related to at least one AI / ML process related to the UE and / or the first apparatus; receiving, from a second apparatus to whom the UE has been handed over, an encrypted and / or integrity protected first data and a second indication indicating each identifier of the at least one AI / ML process.

[0011] In a ninth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a second apparatus, cause the computer to carry out: receiving, from a user equipment, first data related to at least one AI / ML process related to the UE and / or a first apparatus, a first indication indicating that the first data is related to a first apparatus, and a second indication indicating each identifier of the at least one AI / ML process; transmitting, to a first apparatus, the first data and the second indication.

[0012] In a tenth aspect of the present disclosure, there is provided a UE, which comprises means for collecting, from a first apparatus, a first data related to at least one AI / ML process related to the UE and / or the first apparatus; determining that the user equipment has been handed-over to a second apparatus; transmitting, to the second apparatus, the first data.

[0013] In an eleventh aspect of the present disclosure, there is provided a first apparatus, which comprises means for: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0014] In a twelfth aspect of the present disclosure, there is provided a second apparatus, which comprises means for: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0015] In a thirteenth aspect of the present disclosure, there is provided a method for a user equipment, the method comprising: collecting, from a first apparatus, a first data related to at least one AI / ML process related to the UE and / or the first apparatus; determining that the user equipment has been handed-over to a second apparatus; transmitting, to the second apparatus, the first data.

[0016] In a fourteenth aspect of the present disclosure, there is provided a method for a first apparatus, the method comprising: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0017] In a fifteenth aspect of the present disclosure, there is provided a method for a second apparatus, the method comprising: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0018] In a sixteenth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a user equipment, cause the computer to carry out: collecting, from a first apparatus, a first data related to at least one AI / ML process related to the UE and / or the first apparatus; determining that the user equipment has been handed-over to a second apparatus; transmitting, to the second apparatus, the first data.

[0019] In a seventeenth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a first apparatus, cause the computer to carry out: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0020] In an eighteenth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a second apparatus, cause the computer to carry out: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.

[0021] In a nineteenth aspect of the present disclosure, there is provided a UE, which comprise means for: receiving, from a first apparatus, an indication indicating confidentiality of first data; generating a key; collecting, from the first apparatus, the first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus; encrypting the first data using the generated key; and after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the encrypted first data.

[0022] In a twentieth aspect of the present disclosure, there is provided a first apparatus, which comprises means for: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment related to the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; sending, to the user equipment, a second indication indicating confidentiality of the first data; after the handover process is completed, receiving, from the second apparatus, encrypted first data that was encrypted by the user equipment and was sent by the user equipment to the second apparatus.

[0023] In a twenty-first aspect of the present disclosure, there is provided a second apparatus, which comprises means for: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, at least encrypted first data that was encrypted by the user equipment and was sent to the second apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0024] In a twenty-second aspect of the present disclosure, there is provided a method for a user equipment, the method comprising: receiving, from a first apparatus, an indication indicating confidentiality of first data; generating a key; collecting, from the first apparatus, the first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus; encrypting the first data using the generated key; and after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the encrypted first data.

[0025] In a twenty-third aspect of the present disclosure, there is provided a method for a first apparatus, the method comprising: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment related to the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; sending, to the user equipment, a second indication indicating confidentiality of the first data; after the handover process is completed, receiving, from the second apparatus, encrypted first data that was encrypted by the user equipment and was sent by the user equipment to the second apparatus.

[0026] In a twenty-fourth aspect of the present disclosure, there is provided a method for a second apparatus, the method comprising: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, at least encrypted first data that was encrypted by the user equipment and was sent to the second apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0027] In a twenty-fifth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a user equipment, cause the computer to carry out: receiving, from a first apparatus, an indication indicating confidentiality of first data; generating a key; collecting, from the first apparatus, the first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus; encrypting the first data using the generated key; and after a process of a handover of the UE from the first apparatus to a second apparatus is completed, transmitting, to the second apparatus, the encrypted first data.

[0028] In a twenty-sixth aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a first apparatus, cause the computer to carry out: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment related to the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; sending, to the user equipment, a second indication indicating confidentiality of the first data; after the handover process is completed, receiving, from the second apparatus, encrypted first data that was encrypted by the user equipment and was sent by the user equipment to the second apparatus.

[0029] In a twenty-seventh aspect of the present disclosure, there is provided a computer program comprising instructions which, when the program is executed by a computer of a second apparatus, cause the computer to carry out: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus; in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, at least encrypted first data that was encrypted by the user equipment and was sent to the second apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0030] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0032] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0033] FIG. 2 illustrates a simplified block diagram of an apparatus that is suitable for implementing example embodiments of the present disclosure;

[0034] FIG. 3 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure;

[0035] FIG. 4 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0036] FIG. 5 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0037] FIG. 6 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0038] FIG. 7 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0039] FIG. 8 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0040] FIG. 9 illustrates a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0041] FIG. 10 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0042] FIG. 11 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0043] FIG. 12 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0044] FIG. 13 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0045] FIG. 14 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0046] FIG. 15 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0047] FIG. 16 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0048] FIG. 17 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure;

[0049] FIG. 18 illustrates a flowchart of a method implemented at an apparatus according to some example embodiments of the present disclosure

[0050] Throughout the drawings, the same or similar reference numerals represent the same or similar element. DETAILED DESCRIPTION

[0051] Principles of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein may be implemented in various manners other than the ones described below.

[0052] As used herein, the term “communication network” refers to a network in accordance with any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), the sixth generation (6G) communication protocols, and / or any other protocols either currently known or later realized. Embodiments of the present disclosure may be applied in various communication systems. Because of the rapid development in communications, it is anticipated that future communication technologies and systems may embody the present disclosure. The present disclosure should not be limited to only the systems described herein.

[0053] FIG. 1 shows a schematic representation of a 5G communication network. The 5G communication network may comprise a user equipment (UE), radio access network (RAN) nodes gNBl and gNB2. The UE may communicate with at least one of the RAN nodes. The 5G communication network may further comprise at least one Access and Mobility Management Function (AMF), which may act as a core network node for access and mobility management. An AMF is responsible for handling connection and mobility management tasks for a UE connecting to a core network. As part of this, the AMF may receive signaling over an interface (e.g., an N1 and / or N2 interface) to and / or from a UE, and act as an access point to the 5GC. After sending an initial non-access stratum (NAS) message, the AMF may send an Authentication and Key Agreement (AKA) request to the UE.

[0054] It should be understood that the number of network nodes and that of the user devices shown in FIG. 1 are given for the purpose of illustration without suggesting any limitations. The communication network 100 may also include any suitable number of network devices and terminal devices.

[0055] FIG. 2 illustrates an example of a RAN node 200 according to some examples of the disclosure. As illustrated in FIG. 2, the communication module 240 is for bidirectional communications. The communication module 240 has one or more communication interfaces which facilitate communications with one or more other modules or devices. In some example embodiments, the communication module 240 may also include at least one antenna.

[0056] A processor 210 may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The RAN node 200 may have multiple processors synchronized with the same clock.

[0057] A memory 220 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 224, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 222 and other volatile memories that will not last in a powerdown duration.

[0058] A computer program 230 includes instructions executable by the associated processor 210. These instructions may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 230 may be stored in a memory, e.g., the ROM 224. The processor 210 may perform any suitable actions and processes by loading the program 230 into the RAM 222.

[0059] The example embodiments of the present disclosure may be implemented by means of the program 230 so that the RAN node 200 may perform any process of the disclosure as discussed with reference to FIG. 11, FIG. 12, FIG. 14, FIG. 15, FIG. 17 and FIG. 18. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0060] In some example embodiments, the program 230 may be contained in a computer readable medium which may be included in the RAN node 200, such as in the memory 220 or other storage devices that are accessible by the RAN node 200. The RAN node 200 may load the program 230 from the computer readable medium to the RAM 222 for execution. The computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0061] As used herein, the term “radio access network node” or “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU).

[0062] FIG. 3 illustrates an example of a communication device 300, such as the UE illustrated in FIG. 1. The communication device 300 may be provided by any device capable of sending and receiving radio signals. The communication device 300 may comprise a transceiver for transmitting and / or receiving, for example, wireless signals carrying communications, for example, radio signals. The communications may be one or more of voice, electronic mail (email), text messages, multimedia data, machine data and so on.

[0063] The communication device 300 may receive and transmit wireless signals (e.g., radio signals) over an air or radio interface 307 via an appropriate receiver and transmitter, respectively. In FIG. 3 a transceiver is numerically designated 306. The transceiver 306 may comprise, for example, a radio part and associated antenna arrangement. The antenna arrangement may be arranged internally or externally to the mobile device and may comprise one or more antenna elements. The antenna arrangement may be a multi-input multi output (MIMO) antenna.

[0064] The communication device 300 may be provided with at least one processor 301, at least one memory ROM 302a, at least one RAM 302b and other possible components 303 for use in software and hardware aided execution of tasks it is designed to perform, including control of access to and communications with access networks (e.g., the 5G-RAN orNG-RAN illustrated in FIG. 1) and other communication devices. The at least one processor 301 is coupled to the RAM 302b and the ROM 302a. The at least one processor 301 may be configured to execute appropriate software code 308. The software code 308 may for example allow to perform one or more operations of the communication device 300. The software code 308 may be stored in the ROM 302a.

[0065] The processors, the ROM, and the RAM, the transceiver and other circuitry of the communication device 300 (e.g., a modem) can be provided on a circuit board, in chipsets, or in a system on chip. The circuit board, chipsets or system on chip is numerically denoted 304. The communication device 300 may optionally have a user interface such as a key pad 305, touch sensitive screen or pad, a combination thereof or the like. Optionally one or more of a display, a speaker and a microphone may be provided depending on the actual implementation of the communication device 300.

[0066] The term “user equipment” or “terminal device” refers to any end device that may be capable of wireless communications. By way of example, but not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0067] Further, as used herein, the term “resource,” “radio resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, communications between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling communications, and the like. However, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It should be noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0068] 3GPP TR 38.843- “Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR air interface (Release 18)” VI8.0.0 raised a topic “explores the benefits of augmenting the air-interface with features enabling improved support of AI / ML”. In that study, the 3GPP framework for AI / ML was analyzed for an air-interface corresponding to each target use case regarding different aspects of the air-interface, such as performance, complexity, and potential specification impact. The study identified what is required for an adequate AI / ML model characterization and description establishing pertinent terminologies for discussions and subsequent evaluations. Various levels of collaboration between the gNB and UE were identified and considered. Impacts of relevant 3GPP specifications were assessed in order to improve the overall understanding of what would be required to enable AI / ML techniques for the air-interface.

[0069] In the current state of art, when it comes to the continuity of transferring or delivering of data concerning AI / ML model between a UE and its serving gNB as illustrated in FIG. 4, the following problems arise:

[0070] - In the case where the UE experiences a handover from a source to a target cell, there exists no mechanism for confidentially transmitting the data (e.g. AI / ML model parameters) to the previous gNB to which the UE was attached when it participated in an AI / ML process.

[0071] - In the case where there is an ongoing Federated Learning (FL) model training process between the UE and the previous gNB, the model parameters (or subsequent updates) can be accessed by the new gNB, a situation which is not desirable depending on requirements of a device / network vendor agreement.

[0072] It is expected that the above problems will become more prominent for 5G-Advanced and 6G technologies due to an increased frequency requiring AI / ML model training at UE and gNB. Note that transferring the data back to the previous serving gNB in case of handover occurrence is particularly needed and beneficial. Usually, when the UE is at the cell border, a handover to another cell occurs. This is the kind of data from which model training (e.g., when the model is addressed to provide a recommendation on UE handover time) can benefit. Hence, transmission of data to the previous serving cell even after connection to a new serving cell, in a secure, confidential and integrity-protecting manner, is vital.

[0073] The present disclosure describes a mechanism for continuous transmission of data / model (AI / ML model) to the previous serving cell (source base station) after connected to a new service cell (target base station) in a secure, confidential and integrity-protected manner.

[0074] The present disclosure describes a Model / Data Confidentiality Indicator which is allocated to a UE, when a model training / inference / feedback process needs to be kept confidential and / or integrity-protected between the UE and a serving gNB. This indicator can be provided to the UE by either the source gNB itself via an enhanced RRC configuration message or by the AMF via an enhanced NAS message. The present disclosure further describes a Common Protection Key generated at the UE and the source gNB (with which the UE has established such an integrity / confidentiality-protected data / model relationship), thus ensuring integrity and confidentiality of the AI / ML process between the UE and the serving gNB.

[0075] The present disclosure describes a Remote Data Forwarding indicator included in a UE data / model payload when this payload needs to be (confidentially) forwarded from the UE to the previously serving (source) gNB via the currently serving (target) gNB, after a UE handover execution is complete but before the remote data / model transfer terminates. The present disclosure further describes termination events which, when encountered mark the end of the remote data / model transfer relationship between the UE and the gNB with which the UE has established such a relationship. The Remote Data Forwarding indicator enables transfer of remote data concerning the model between a UE and a source gNB after the occurrence of a UE mobility event (e.g. a handover from the source gNB to a target gNB). In the following description, the terms “source gNB” and “previously serving gNB” may be used interchangeably; and the terms “target gNB” and “currently serving gNB” may be used interchangeably .

[0076] The present disclosure describes AI / ML Process ID(s) which is allocated by the source gNB. The AI / ML Process ID(s) may be provided to the UE, together with the Model / Data Confidentiality Indicator. The AI / ML Process ID(s) identify the AI / ML training / inference / monitoring process(es) which is active when the UE is handed over to a target cell, and which requires the data collected by the UE for the identified AI / ML process to be provided to the source gNB for its remote consumption. The AI / ML Process ID(s) enables mapping between a UE dataset / model for remote reporting to a gNB (e.g. the source gNB) to the running AI / ML Processes at this (remote) gNB.

[0077] In the present disclosure, once the Model / Data Confidentiality Indicator is sent to the UE (together with the corresponding AI / ML Process ID(s) reflecting the AI / ML process(es) to be kept integrity protected and confidential (encrypted) if / when remote data / model transfer initiates), both the UE and the gNB may concurrently generate a Common Protection Key.

[0078] In the present disclosure, after a handover execution event is completed for the UE, this event may be used as a trigger to activate remote data / model transfer with the source gNB (with which the UE has previously established such an integrity / confidentiality-protected data / model relationship). The event may include, e.g. handover procedure from a source gNB to a target gNB being completed. Once this trigger event occurs, the UE applies integrity protection, encrypts the payload / data with the corresponding keys (common protection keys), and transmits the encrypted and integrity protected data to its currently serving (target) gNB with a Remote Data Forwarding indicator and the corresponding AI / ML Process ID(s).

[0079] On the other hand, the currently serving (target) gNB, once it receives the data, along with the Remote Data Forwarding indicator and the corresponding AI / ML Process ID(s), it forwards the data (along with the corresponding AI / ML Process ID(s)) to the previously serving (source) gNB.

[0080] As a result, data useful to the AI / ML Process(es) originating from a UE that has been handed over to another cell amidst the AI / ML Process can still be accessed by the source gNB hosting / participating to this AI / ML Process and till a termination criterion for remote data / model transfer is met. Such AI / ML process may include e.g., centralized model training, providing inference data or feedback data for model monitoring, etc.

[0081] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0082] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0083] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0084] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0085] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0086] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0087] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0088] FIG. 5 shows a communication flow chart according to some example embodiments of the present disclosure. Base station gNBl and gNB2 are connected via an Xn interface. The gNBl can be e.g. gNBl in FIG. 1 of the current disclosure, the gNB2 can be e.g. gNB2 in FIG. 1 of the current disclosure. A UE is connected to the gNBl and moving to the gNB2, and the service for the UE will be handed over from the gNBl to the gNB2.

[0089] In Step 1, the UE is connected to gNBl, and gNBl shares the model or model parameter or data with UE. The Model is the one used for AI / ML process carried out in source gNBl. The AI / ML process may include e.g. model training, model inference, or model monitoring, etc.

[0090] In Step 2, if it is expected that the UE should share the model or model parameters or data related to AI / ML process (e.g. model training, inference and / or feedback) with only gNBl, then the gNBl provides an indication “Model / Data Confidentiality Indicator”, wherein the value of the Model / Data Confidentiality Indicator may be set to be “True” ( Model / Data Confidentiality Indicator = True), to the UE via an RRC reconfiguration message. Alternatively, AMF may provide the indication to the UE over a new IE in the NAS message.

[0091] In Step 3, if gNBl expects the data from UE, then gNBl shall generate the keys KgNB-Mint and KgNB-Menc, wherein the key KgNB-Mint is used for integrity protection, and the key KgNB-Menc is used for encryption. The generated key shall be common between UE and gNBl, i.e., UE and gNBl both can generate the same key independently based on a root key KgNB. Whenever the root key KgNB is refreshed, further keys, including KgNB-Mint and KgNB-Menc, shall also be refreshed.

[0092] In Step 4, the UE moves and attaches to gNB2.

[0093] In Step 5, by decoding gNB2 Master Information Block (MIB) / System Information Block (SIB), the UE realizes that its serving gNB has changed and the collected data available in the UE belongs to the previous serving gNB (gNBl), then UE sends integrity protected and / or encrypted payload / data to the gNB2. The payload / data is integrity protected / encrypted with the KgNB-Mint / KgNB-Menc keys.

[0094] In Step 6, the UE sends the payload to gNB2 and along with a Remote Data Forwarding indicator indicating that data belongs to previous serving gNB. Besides, the UE sends AI / ML Process IDs which is used to indicate to the gNBl which AI / ML process the forwarded data / payload are intended for.

[0095] In Step 7, gNB2 cannot understand the data / payload because it is encrypted, and integrity protected by keys common only for gNBl and the UE. As the payload is accompanied by a Remote Data Forwarding indicator, gNb2 forwards the data to gNBl over Xn interface, together with the AI / ML Process IDs. In some embodiments of the current disclosure, in a single UE data payload, some data (e.g., the first half) are intended for e.g., AI / ML Process #1 and some other data (e.g., the second half) are intended for e.g., AI / ML Process #2 at gNBl. Accordingly, these ordered fractions can be additional information to be forwarded to gNBl via gNB2.

[0096] In Step 8, gNbl may decrypt the data and verify if it is not modified (integrity check) using the common generated key in Step 3 and then accept it.

[0097] By the method of FIG. 5, the gNBl is able to receive AI / ML process related data / model from the UE, even if the UE moves out of the service range of the gNBl (i.e. the UE is handed over to a gNB2).

[0098] Reference is now made to FIG. 6, which shows a case of remote data collection / model transfer according to some example embodiments of the present disclosure. As shown in FIG. 6, gNBl and gNB2 are of equal data / model confidentiality level for the UE (e.g., as belonging to the same mobile operator, to which the UE-owing user has already provided consent to provide data for the needs of AI / ML-based network operation, also potentially to the same network vendor, with which the UE device vendor may have an established business relationship). The gNBl can be e.g. gNBl in FIG. 1 of the current disclosure, the gNB2 can be e.g. gNB2 in FIG. 1 of the current disclosure, and the UE can be e.g. the UE in FIG. 1 of the current disclosure. The UE is first moving within the service coverage of the gNBl and moves out of the service coverage of the gNBl and attaches to the gNB2 (i.e. the UE is handed over from the gNBl to the gNB2).

[0099] In Step 0, at time to, gNB 1 sends a DATA COLLECTION REQUEST message to gNB2 via Xn Interface, requesting for start of a remote data collection mode after a handover procedure being completed for the UE. The remote data forwarding mode may be indicated by a new bit of the Reporting Characteristic IE called “Remote Data Forwarding”, which takes the value of “1” when such remote data forwarding mode needs to be activated after UE handover execution to another cell is completed. Besides, the relevant AI / ML Process IDs may be included in the same request, which indicate the relevant AI / ML Processes that are in progress and in need for remote data forwarding. In case the target gNB (gNB2) accepts the request, a Measurement ID pair is created representing the context of this remote data forwarding request.

[0100] In Step 1, at time ti, UE obtains initial access to gNBl.

[0101] In Step 2, at time t2, UE is scheduled by gNBl for data collection for AI / ML process.

[0102] In Step 3, at time t?, legacy / local data collection / training collaboration starts.

[0103] In Step 4, at time t4, HANDOVER REQUEST message is sent from source gNBl to target gNB2. This message includes the Measurement ID pair created in Step 0. As the Measurement ID pair created in Step 0 (which is mutually known by gNBl and gNB2) accompanied the HANDOVER REQUEST message, gNB2 is aware of the need for remote data / model transfer from this handed over UE to gNBl, and gNBl is aware of the AI / ML Process(es) to be impacted by this specific remote data collection process that has initiated.

[0104] In Step 5, at time t5, HANDOVER REQUEST ACKNOWLEDGE message is sent from target gNB2 to source gNB 1.

[0105] In Step 6, at time te, HO execution is completed, i.e. the procedure of the handover is completed, and remote data reporting mode starts.

[0106] In Step 7, at time t?,ii remote data reporting is terminated due to termination event Ei. The termination event Ei may include, but not limit to, the following:

[0107] - Resource (radio, storage) limitation at the target gNB (gNB2) to which the UE is handed over,

[0108] - Battery level of the UE drops below a threshold,

[0109] - gNB2 issues a handover request to a third gNB, gNB3 (where the gNB3 is out of scope of confidential remote data collection &model transfer),

[0110] - UE RRC state changes from CONNECTED to IDLE / INACTIVE,

[0111] - UE’s distance from gNBl is above a threshold.

[0112] By the method of FIG. 6, the gNBl is able to receive AI / ML process related data / model from the UE, even if the UE moves out of the service range of the gNBl (i.e. the UE is handed over to a gNB2). Besides, since gNBl and gNB2 are of equal data / model confidentiality level, thus, the data transmitted to gNBl via gNB2 from the UE does not need to be encrypted.

[0113] Reference is now made to FIG. 7, which shows a case of encrypted remote data collection / model transfer according to some example embodiments of the present disclosure. As shown in FIG. 7, gNBl and gNB2 are of different data / model confidentiality level to the UE (e.g., gNB2 belongs to a different mobile operator or network vendor, as compared to gNBl). The gNBl can be e.g. gNBl in FIG. I of the current disclosure, the gNB2 can be e.g. gNB2 in FIG. 1 of the current disclosure, and the UE can be e.g. the UE in FIG. 1 of the current disclosure. The UE is first moving within the service coverage of the gNBl and moves out of the service coverage of the gNBl and attaches to the gNB2 (i.e. the UE is handed over from the gNBl to the gNB2).

[0114] In StepO, at time to, gNBl sends a DATA COLLECTION REQUEST message to gNB2 via Xn Interface, requesting for start of a remote data collection mode after a handover procedure being completed for the UE. The remote data forwarding mode may be indicated by a new bit of the Reporting Characteristic IE called “Remote Data Forwarding”, which takes the value of “1” when such remote data forwarding needs to be activated after UE handover execution to another cell is completed. Besides, the relevant AI / ML Process IDs may be included in the same request, which represent the relevant AI / ML Processes that are in progress and in need for remote data forwarding. In case the target gNB (gNB2) accepts the request, a Measurement ID pair is created representing the context of this remote data forwarding request.

[0115] In Step 1, at time ti, UE obtains initial access to gNBl.

[0116] In Step 2, at time t2, UE is scheduled by gNBl for data collection for the AI / ML process. Model / Data Confidentiality Indicator is sent to UE, and encryption / decryption keys are commonly generated at gNBl and UE.

[0117] In Step 3, at time t3, unencrypted data collection / training collaboration starts.

[0118] In Step 4, at time t4. HANDOVER REQUEST message is sent from source gNBl to target gNB2. This message includes the Measurement ID pair created in Step 0.

[0119] In Step 5, at time t5, HANDOVER REQUEST ACKNOWLEDGE message is sent from target gNB 2 to source gNB 1.

[0120] In Step 6, at time t6, gNBl requests UE to switch to encrypted remote data collection.

[0121] In Step 7, at time t?, HO execution is completed, i.e. the procedure of the HO is completed, remote data reporting mode starts, with encrypted data / model transfer.

[0122] In Step 8, at time ts,i, encrypted remote data collection / training collaboration is terminated due to termination event Ei. The termination event Ei may include, but not limit to, the following:

[0123] - Resource (radio, storage) limitation at the target gNB (gNB2) to which the UE is handed over,

[0124] - Battery level of the UE drops below a threshold,

[0125] - gNB2 issues a handover request to a third cell (where the gNB3 is out of scope of confidential remote data collection &model transfer),

[0126] - UE RRC state changes from CONNECTED to IDLE / INACTIVE,

[0127] - UE’s distance from gNB 1 is above a threshold.

[0128] By the method of FIG. 7, the gNBl is able to receive AI / ML process related data / model from the UE, even if the UE moves out of the service range of the gNBl (i.e. the UE is handed over to a gNB2), so as to make sure a continuous transmission of the model / data for a AI / ML process. Besides, since gNBl and gNB2 are of different data / model confidentiality levels, thus, the data forwarded to gNBl via gNB2 is security protected from mis-access by the gNB2.

[0129] Further, a key generation scheme is disclosed according to one or more embodiments of the current description.

[0130] Referring now to FIG. 8 which shows generating of a security key based on a RAND value. In an embodiment the UE / gNB may comprise at least one processor 301 / 210 configured to generate the KgNB-Mint / KgNB-Menc key 816 by executing electronic instructions stored in, and accessed and retrieved from, at least one memory (e.g., see FIG. 3, memory 302 or GIG. 2 memory 220) to complete a cryptographic Key Derivation Function (KDF) process that generates the KgNB-Mint / KgNB-Menc key 816. For example, as shown in FIG. 8, the KDF may receive a RAND value 13, a fixed constant (FC) value 15 and then execute the KDF process according to an integrity protection algorithm / confidentiality protection algorithm to generate the KgNB-Mint / KgNB-Menc key. In an embodiment, FC values may be values determined by a telecommunications standard or adopted by a telecommunications vendor. In a further embodiment, the RAND value is provided to UE from the gNB.

[0131] Alternatively, the KgNB-Mint / KgNB-Menc key may be generated based on a count value shared and separately maintained between the UE and gNB. Referring now to FIG. 9, the KDF may receive a COUNT value 913, a fixed constant (FC) value 915 and then execute the KDF process according to an integrity protection algorithm / confidentiality protection algorithm to generate the KgNB-Mint / KgNB-Menc key. In an embodiment, FC values may be values determined by a telecommunications standard or adopted by a telecommunications vendor. In a further embodiment, the COUNT value 913 may be maintained by UE and gNB independently. gNB may ask UE to increment the COUNT value on each refresh.

[0132] Further, FIG. 10- FIG. 18 illustrate several methods for forwarding AI / ML related data / model from gNB2 to gNBl according to embodiments of the current disclosure.

[0133] FIG. 10- FIG. 12 illustrate a method of forwarding AI / ML related data / model in a security manner.

[0134] FIG. 10 shows a flowchart of an example method 1000 implemented at a UE in accordance with some example embodiments of the present disclosure.

[0135] At block 1010, the UE collects first data from a first apparatus, wherein the first data is related to at least one AI / ML process related to the UE and / or the first apparatus. The first apparatus can be e.g. the gNBl of FIG. 1 of the current disclosure, the UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE is attached to the first apparatus and the first apparatus serves as a serving base station for the UE.

[0136] At block 1020, the UE may encrypt the first data, and may integrity protect the first data.

[0137] At block 1030, after a process of a handover of the UE from the first apparatus to a second apparatus is completed, the UE transmits, to the second apparatus, the integrity protected and / or encrypted first data, a first indication indicating that the first data is related to the first apparatus, and a second indication indicating each identifier of the at least one AI / ML process. The second apparatus can be e.g. the gNB2 of FIG. 1 of the current disclosure. After the handover procedure, the second apparatus serves as a serving base station for the UE. The UE, however, is able to send the first data to the first apparatus via the second apparatus, because of the first indication received by the second apparatus. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0138] In some example embodiments, the method 1000 may further comprise receiving, from the first apparatus, a third indication indicating confidentiality of the first data. The third indication is received via an RRC reconfiguration message.

[0139] Alternatively, in some example embodiments, the method 1000 may further comprise receiving, from a first network function, the third indication indicating confidentiality of the first data. The third indication is received via a NAS message, and the first network function comprises an AMF. The third indication can be. E.g. the Model / Data Confidentiality Indicator as disclosed in previous embodiments of the current disclosure.

[0140] In some example embodiments, the method 1000 may further comprise generating a first key based on a first random value provided by the first apparatus, and the first data is encrypted with the generated first key. In some example embodiments, the method 600 may further comprise generating a second key based on a second random value provided by the first apparatus, and integrity protecting the first data with the generated second key. The first key and / or the second key can be generated according to the method as illustrated in FIG. 8 of the current disclosure.

[0141] Alternatively, in some example embodiments, the method 1000 may further comprise generating a first key based on a first count value shared with the first apparatus, and encrypting the first data with the generated first key. In some example embodiments, the method 1000 may further comprise generating a second key based on a second count value shared with the first apparatus, and integrity protecting the first data with the generated second key. The first key and / or the second key can be generated according to the method as illustrated in FIG. 9 of the current disclosure.

[0142] In some example embodiments, the method 600 may further comprise receiving, from the first apparatus, each identifier of the at least one AI / ML process.

[0143] In some example embodiments, the method 600 may further comprise terminating transmitting the integrity protected and / or encrypted first data to the second apparatus in case of occurrence of any of the following events:

[0144] - radio resource related to the second apparatus drops below a first threshold;

[0145] - battery level of the user equipment drops below a second threshold;

[0146] - the second apparatus initiates a handover request to a third apparatus;

[0147] - a RRC state of the user equipment is changed to IDLE / inactive; or

[0148] - a distance between the first apparatus and the user equipment exceeds a third threshold.

[0149] In some example embodiments, the at least one AI / ML process comprises at least one of AI / ML training / inference / monitoring process.

[0150] In some example embodiments, the first data comprises at least a second data and a third data, the second data being related to a second AI / ML process of the at least one AI / ML process, the third data being related to a third AI / ML process of the at least one AI / ML process, and wherein the second indication indicates at least an identifier of the second AI / ML process and an identifier of the third AI / ML process.

[0151] FIG. 11 shows a flowchart of an example method 700 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. The first apparatus can be e.g. the gNBl in FIG. 1.

[0152] At block 1110, the first apparatus sends, to a user equipment, first data related to at least one AI / ML process related to the UE and / or the first apparatus. The UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE is attached to the first apparatus and the first apparatus serves as a serving base station for the UE.

[0153] At block 1120, the first apparatus receives, from a second apparatus to whom the UE has been handed over, an encrypted and / or integrity protected first data and a second indication indicating each identifier of the at least one AI / ML process. The second apparatus can be e.g. the gNB2 in FIG. 1. The second apparatus and the fist apparatus are connected by a Xn interface. The UE is handed over from the first apparatus to the second apparatus, and the second apparatus becomes the serving base station for the UE. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0154] In some example embodiments, the method 1100 may further comprise sending, to the user equipment, a third indication indicating confidentiality of the first data. The third indication can be, e.g. the Model / Data Confidentiality Indicator as disclosed in previous embodiments of the current disclosure.

[0155] In some example embodiments, the method 1100 may further comprise generating a first key based on a first random value provided by the first apparatus; generating a second key based on a second random value provided by the first apparatus; decrypting the received encrypted first data using the generated first key; and verifying the received integrity protected first data using the generated second key. The first key and / or the second key can be generated according to the method as illustrated in FIG. 8 of the current disclosure.

[0156] FIG. 12 shows a flowchart of an example method 1200 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. The second apparatus can be e.g. the gNB2 in FIG. 1.

[0157] At block 1210, the second apparatus receives, from a user equipment, first data related to at least one AI / ML process related to the UE and / or a first apparatus, a first indication indicating that the first data is related to a first apparatus, and a second indication indicating each identifier of the at least one AI / ML process. The UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE was originally connected to the gNBl, and collects data from the gNBl. After a handover to a gNB2, the UE is able to send the data collected form the gNBl to gNBl via gNB2. gNBl and gNB2 are connected by an Xn interface. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0158] At block 1220, the second apparatus transmits, to the first apparatus, the first data and the second indication.

[0159] FIG. 13- FIG. 15 illustrate a method of continuous transmission of AI / ML related data / model in an unencrypted manner while the UE is crossing the cells.

[0160] FIG. 13 shows a flowchart of an example method 1300 implemented at a UE in accordance with some example embodiments of the present disclosure.

[0161] At block 1310, the UE collects, from a first apparatus, a first data related to at least one AI / ML process related to the UE and / or the first apparatus. The first apparatus can be e.g. the gNBl of FIG. 1 of the current disclosure, the UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE is attached to the first apparatus and the first apparatus serves as a serving base station for the UE.

[0162] At block 1320, the UE determines that the user equipment has been handed-over to a second apparatus;

[0163] At block 1330, the UE transmits, to the second apparatus, the first data.

[0164] In some example embodiments, the method 900 may further comprise terminating transmitting the collected first data to the second apparatus in case of occurrence of any of the following events:

[0165] - radio resource related to the second apparatus drops below a first threshold;

[0166] - battery level of the user equipment drops below a second threshold;

[0167] - the second apparatus initiates a handover request to a third apparatus;

[0168] - a RRC state of the user equipment is changed to IDLE / inactive; or

[0169] - a distance between the first apparatus and the user equipment exceeds a third threshold.

[0170] FIG. 14 shows a flowchart of an example method 1400 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. The first apparatus can be e.g. the gNBl in FIG. 1.

[0171] At block 1410, the first apparatus sends, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus. The second apparatus can be e.g. the gNB2 of FIG. 1 of the current disclosure. After the handover procedure, the second apparatus serves as a serving base station for the UE. The UE, however, is able to send the first data to the first apparatus via the second apparatus, because of the first indication received by the second apparatus. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure.

[0172] At block 1420, after the handover process is completed, the first apparatus receives, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0173] In some example embodiments, the method 1400 may further comprise sending, to the second apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises each identifier of the at least one AI / ML process.

[0174] In some example embodiments, the method 1400 may further comprise creating a first measurement ID in connection with the first indication and the each identifier of the at least one AI / ML process, wherein the data collection request further comprises the first measurement ID.

[0175] In some example embodiments, the method 1400 may further comprise receiving, from the second apparatus, a data collection response, wherein the data collection response comprises a second measurement ID created by the second apparatus, the second measurement ID being in connection with the first measurement ID.

[0176] In some example embodiments, the method 1400 may further comprise sending, to the second apparatus, a handover request including a measurement ID pair comprising the second measurement ID and the first measurement ID.

[0177] In some example embodiments, the method 1400 may further comprise receiving, from the second apparatus, a handover request acknowledgement message in connection with the handover request.

[0178] FIG. 15 shows a flowchart of an example method 1500 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. The second apparatus can be e.g. the gNB2 in FIG. 1.

[0179] At block 1510, the second apparatus receives, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus. The UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE was originally connected to the gNBl, and collects data from the gNBl. After a handover to a gNB2, the UE is able to send the data collected form the gNBl to gNBl via gNB2. gNBl and gNB2 are connected by an Xn interface. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0180] At block 1520, in an instance that the received first indication indicates an activated remote data forwarding mode, the second apparatus transfers, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0181] In some example embodiments, the method 1500 may further comprise receiving, from the first apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises the identifier of the at least one AI / ML process and a first measurement ID in connection with the first indication and the each identifier of the at least one AI / ML process.

[0182] In some example embodiments, the method 1500 may further comprise creating a second measurement ID in connection with the first measurement ID, and sending, to the first apparatus, a data collection response comprising the second measurement ID.

[0183] In some example embodiments, the method 1500 may further comprise receiving, from the first apparatus, a handover request measurement ID pair comprising the first measurement ID and the second measurement ID.

[0184] In some example embodiments, the method 1500 may further comprise sending, to the first apparatus, a handover request acknowledgement message in response to the handover request.

[0185] In some example embodiments, the first data is received from the UE and then forwarded to the first apparatus.

[0186] FIG. 16- FIG. 18 illustrate a method of continuous transmission of AI / ML related data / model in an encrypted manner while the UE is crossing the cells.

[0187] FIG. 16 shows a flowchart of an example method 1600 implemented at a UE in accordance with some example embodiments of the present disclosure.

[0188] At block 1610, the UE receives, from a first apparatus, a third indication indicating confidentiality of first data. The first apparatus can be e.g. the gNBl of FIG. 1 of the current disclosure, the UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE is attached to the first apparatus and the first apparatus serves as a serving base station for the UE.

[0189] At block 1620, the UE generates a key. The key can be generated according to the method as illustrated in FIG. 8 / 9 of the current disclosure.

[0190] At block 1630, the UE collects, from the first apparatus, the first data related to at least one AI / ML process related to the UE and / or the first apparatus.

[0191] At block 1640, the UE encrypts the first data using the generated key.

[0192] At block 1650, after a process of a handover of the UE from the first apparatus to a second apparatus is completed, the UE transmits, to the second apparatus, the encrypted first data. The second apparatus can be e.g. the gNB2 of FIG. 1 of the current disclosure. After the handover procedure, the second apparatus serves as a serving base station for the UE. The UE, however, is able to send the first data to the first apparatus via the second apparatus, because of the first indication received by the second apparatus. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0193] In some example embodiments, the method 1600 may further comprise terminating transmitting the encrypted first data to the second apparatus in case of occurrence of any of the following events:

[0194] - radio resource related to the second apparatus drops below a first threshold;

[0195] - battery level of the user equipment drops below a second threshold;

[0196] - the second apparatus initiates a handover request to a third apparatus;

[0197] - a RRC state of the user equipment is changed to IDLE / inactive; or

[0198] - a distance between the first apparatus and the user equipment exceeds a third threshold.

[0199] FIG. 17 shows a flowchart of an example method 1700 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. The first apparatus can be e.g. the gNBl in FIG. 1.

[0200] At block 1710, the first apparatus sends, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment related to the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus. The second apparatus can be e.g. the gNB2 of FIG. 1 of the current disclosure. After the handover procedure, the second apparatus serves as a serving base station for the UE. The UE, however, is able to send the first data to the first apparatus via the second apparatus, because of the first indication received by the second apparatus. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure.

[0201] At block 1720, the first apparatus sends, to the user equipment, a third indication indicating confidentiality of the first data. The third indication can be. E.g. the Model / Data Confidentiality Indicator as disclosed in previous embodiments of the current disclosure.

[0202] At block 1730, after the handover process is completed, the first apparatus receives, from the second apparatus, encrypted first data that was encrypted by the user equipment and was sent to the second apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0203] In some example embodiments, the method 1700 may further comprise sending, to the second apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises each identifier of the at least one AI / ML process.

[0204] In some example embodiments, the method 1700 may further comprise creating a first measurement ID in connection with the first indication and the each identifier of the at least one AI / ML process, wherein the data collection request further comprises the first measurement ID.

[0205] In some example embodiments, the method 1700 may further comprise receiving, from the second apparatus, a data collection response, wherein the data collection response comprises a second measurement ID created by the second apparatus, the second measurement ID being in connection with the first measurement IDO

[0206] In some example embodiments, the method 1700 may further comprise sending, to the second apparatus, a handover request including a measurement ID pair comprising the second measurement ID and the first measurement ID.

[0207] In some example embodiments, the method 1700 may further comprise receiving, from the second apparatus, a handover request acknowledgement message in response to the handover request.

[0208] FIG. 18 shows a flowchart of an example method 1800 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. The second apparatus can be e.g. the gNB2 in FIG. 1.

[0209] At block 1810, the second apparatus receives, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment related to the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus. The UE can be e.g. the UE of FIG. 1 of the current disclosure. The UE was originally connected to the gNBl, and collects data from the gNBl. After a handover to a gNB2, the UE is able to send the data collected form the gNBl to gNBl via gNB2. gNBl and gNB2 are connected by an Xn interface. The first indication can be e.g. the remote data forwarding indicator as disclosed in previous embodiments of the current disclosure. The second indication can be e.g. the AI / ML process ID as disclosed in previous embodiments of the current disclosure.

[0210] At block 1820, in an instance that the received first indication indicates an activated remote data forwarding mode, the second apparatus transfers, to the first apparatus, encrypted first data that was encrypted by the user equipment and was sent to the second apparatus, and a second indication indicating each identifier of the at least one AI / ML process.

[0211] In some example embodiments, the method 1800 may further comprise receiving, from the first apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises each AI / ML process IDs related to the first data. The data collection request contains a first measurement ID in connection with the first indication and the each identifier of the at least one AI / ML process.

[0212] In some example embodiments, the method 1800 may further comprise creating, by the second apparatus, a second measurement ID in connection with the first measurement ID, and sending, to the first apparatus, a data collection response comprising the second measurement ID.

[0213] In some example embodiments, the method 1800 may further comprise receiving, from the first apparatus, a handover request including a measurement ID pair consisting of the first and second measurement IDs. The first measurement ID is created by the first apparatus, and is in connection with the first indication and the each AI / ML process IDs related to the first data. The first measurement ID and the second measurement ID corresponds to each other and form a measurement ID pair.

[0214] In some example embodiments, the method 1800 may further comprise sending, to the first apparatus, a handover request acknowledge in response to the handover request.

[0215] The first indication as introduced in the current disclosure can be added as an additional bit to the Reporting Characteristics IE (information element) of the DATA COLLECTION REQUEST message in 3GPP TS 38.423. This extra reporting characteristic can be called “Remote Data Forwarding”. When this bit takes the value of “1”, then, upon a successful handover execution completion for the UE, remote data / model transfer can resume for this UE. The (confidential) forwarding of remote data / models from UE to the gNB with this established relationship will be performed by means of DATA COLLECTION UPDATE messages (either a single one or multiple ones depending on the periodicity with which the UE will provide such data during the remote data forwarding session). Besides, the AI / ML Process ID(s) associated to this request (which are active at the time of the request and in need for remote data forwarding) can be included to the same DATA COLLECTION REQUEST message (i.e., with “Remote Data Forwarding” taking the value of “1”). This can be an additional IE of the DATA COLLECTION REQUEST (e.g, “AI / ML Process ID List”) that shall be only optionally included when “Remote Data Forwarding” Reporting Characteristic bit takes the value of “1”.

[0216] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0217] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0218] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0219] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0220] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0221] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable subcombination. 5

[0222] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. 10

Claims

1) A user equipment, UE, comprising means for performing:collecting, from a first apparatus, first data related to at least one artificial intelligence / machine learning, AI / ML, process related to the UE and / or the first apparatus;determining that the user equipment has been handed over to a second apparatus;transmitting, to the second apparatus, the first data.2) The user equipment as claimed in claim 1, further comprising means for: terminating transmitting the collected first data to the second apparatus in case of occurrence of any of the following events:when radio resource related to the second apparatus drops below a first threshold;when battery level of the user equipment drops below a second threshold;when the second apparatus initiates a handover request to a third apparatus;when a radio resource control, RRC, state of the user equipment is changed to idle / inactive; orwhen a distance between the first apparatus and the user equipment exceeds a third threshold.3) A first apparatus comprising means for performing:sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus;after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.4) The first apparatus as claimed in claim 3, further comprising means for: sending, to the second apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises the identifier of the at least one AI / ML process.5) The first apparatus as claimed in claim 4, further comprising means for: creating a first measurement identifier, ID, in connection with the first indication and the each identifier of the at least one AI / ML process, wherein the data collection request further comprises the first measurement ID.6) The first apparatus as claimed in claim 5, further comprising means for: receiving, from the second apparatus, a data collection response, wherein the data collection response comprises a second measurement ID created by the second apparatus, the second measurement ID being in connection with the first measurement ID.7) The first apparatus as claimed in claim 6, further comprising means for: sending, to the second apparatus, a handover request including a measurement ID pair comprising the first measurement ID and the second measurement ID.8) The first apparatus as claimed in claim 7, further comprising means for: receiving, from the second apparatus, a handover request acknowledgement in connection with the handover request.9) A second apparatus comprising means for performing: receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover ofa user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus;in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.10)The second apparatus as claimed in claim 9, further comprising means for: receiving, from the first apparatus, a data collection request comprising the first indication, wherein the data collection request further comprises i) the identifier of the at least one AI / ML process, and ii) a first measurement ID in connection with the first indication and the identifier of the at least one AI / ML process.11)The second apparatus as claimed in claim 10, further comprising means for: creating a second measurement ID in connection with the first measurement ID, andsending, to the first apparatus, a data collection response comprising the second measurement ID.12) The second apparatus as claimed in claim 11, further comprising means for: receiving, from the first apparatus, a handover request including a measurement ID pair comprising the first measurement ID and the second measurement ID.13)The second apparatus as claimed in claim 12, further comprising means for: sending, to the first apparatus, a handover request acknowledgement in response to the handover request.14)The second apparatus as claimed in any of claims 9-13, further comprising means for:receiving, from the user equipment, the first data.15)The first apparatus as claimed in any preceding claim comprising a first base station, and the second apparatus as claimed in any preceding claim comprising a second base station.16)A method for a user equipment, the method comprising:collecting, from a first apparatus, first data related to at least one AI / ML process related to the UE and / or the first apparatus;determining that the user equipment has been handed-over to a second apparatus;transmitting, to the second apparatus, the first data.17)A method for a first apparatus, the method comprising:sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus;after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.18)A method for a second apparatus, the method comprising:receiving, from a first apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus iscompleted, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus;in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.19)A computer program comprising instructions which, when the program is executed by a computer of a user equipment, cause the computer to carry out: collecting, from a first apparatus, first data related to at least one AI / ML process related to the UE and / or the first apparatus;determining that the user equipment has been handed-over to a second apparatus;transmitting, to the second apparatus, the first data.20)A computer program comprising instructions which, when the program is executed by a computer of a first apparatus, cause the computer to carry out: sending, to a second apparatus, a first indication indicating an activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being related to at least one AI / ML process related to the UE and / or the first apparatus;after the handover process is completed, receiving, from the second apparatus, the first data and a second indication indicating each identifier of the at least one AI / ML process.21 )A computer program comprising instructions which, when the program is executed by a computer of a second apparatus, cause the computer to carry out:receiving, from a first apparatus, a first indication indicating an5 activation status of a remote data forwarding mode, wherein an activated remote data forwarding mode indicates that after a process of a handover of a user equipment from the first apparatus to the second apparatus is completed, a first data collected by the user equipment from the first apparatus is to be transferred to the first apparatus, the first data being10 related to at least one AI / ML process related to the UE and / or the first apparatus;in an instance that the received first indication indicates an activated remote data forwarding mode, transferring, to the first apparatus, the first data and a second indication indicating each identifier15 of the at least one AI / ML process.

Images