Artificial intelligence various mode measurement process

Abstract

Processes, methods, architectures, devices, systems, apparatuses, and computer program products relating to artificial intelligence specific idle / inactive / connected mode measurement processes. In an embodiment, a method implemented by a wireless transmit receive unit (WTRU), the method comprising: receiving a first message from a network, the first message comprising a configuration regarding AI / ML model training and associated measurement and logging periodicity; performing a minimization of drive test (MDT) measurement; selecting an AI / ML model for training based on the first message; training the selected AI / ML model based on the MDT measurements; and in response to the accuracy of the trained AI / ML model being higher than a configured accuracy threshold, triggering a transition to a connected state and reporting the trained AI / ML model identification and AI / ML model parameters to the network.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims the benefit of U.S. Provisional Patent Application No. 63 / 395,994, filed on August 8, 2022, which is incorporated herein by reference. Technical Field

[0003] The present disclosure relates generally to the fields of communications, software, and coding, including, for example, methods, architectures, devices, and systems related to artificial intelligence-specific idle / inactive / connected mode measurement procedures. Background Art

[0004] For many artificial intelligence / machine learning (AI / ML) tasks, fragmented data collected by mobile devices may be necessary to train global models. For some AI / ML model training and model inference operations, the input data may need to be continuous and a time series of information at each specific granularity. In some cases, tasks and environmental changes may require different AI / ML models to perform the same feature prediction. Therefore, another training and inference cycle may be required with a different data set representing the new environmental changes. The current measurement reporting mechanism can support AI / ML at the network for training purposes. Since the provided measurement data will be non-continuous or contain past measurements, the network may need to perform AI / ML training operations first and then perform prediction / inference operations. Therefore, the traditional measurement process may not enable the network to perform predictions immediately after the wireless transmit / receive unit (WTRU) provides the measurement data. Today, the computing resources used in mobile devices can undertake the execution of AI / ML operations in a certain capacity. In order to improve AI / ML operations with these capable devices and an existing or new set of measurements, the network can distribute training operations to WTRUs capable of performing AI / ML operations. The network may then request the WTRU to provide trained model parameters which may be immediately aggregated by the network to derive a global, use case-specific, or region-specific AI / ML model that may be immediately used by the network for prediction / inference for WTRUs with the same or similar environmental variations.

[0005] Therefore, there is a need to enhance the measurement and logging procedures to enable the network to efficiently utilize the available measurements at the WTRU. Summary of the invention

[0006] In an embodiment, a method implemented by a wireless transmit receive unit (WTRU) may include transmitting AI / ML capability information, the AI / ML capability information including available AI / ML models, AI / ML model accuracy levels, computing power (e.g., FLOPs) for training and / or inference, AI-specific memory capacity (e.g., for training data and / or model storage). Possibly, the method may include receiving the AI / ML model from a network. The method may also include receiving a configuration regarding AI / ML model training and associated measurement and logging periodicity, wherein the configuration may include any of the following: report type, indication of the AI / ML model (e.g., already available or network configured), selection criteria (e.g., based on mobility scenarios such as low mobility and at the cell edge, etc.), input / output parameters, loss / reward function, accuracy threshold level, training data configuration (e.g., minimum data set size for training), conditional logging configuration (e.g., based on AI / ML model accuracy), and conditional training configuration (e.g., based on a specific location). The method may include performing MDT measurements, wherein performing MDT measurements may include logging conventional MDT measurements and / or skipping MDT measurement logging opportunities when one or more of the following conditions are met: (i) the AI / ML model is still in a training phase with existing logged MDT measurement data; (ii) the trained AI / ML model is validated using (e.g., immediate / current) measurements; or (iii) the trained AI / ML learning model reaches a configured accuracy threshold level. The method may also include selecting an AI / ML model for training based on an indication of the AI / ML model and configured selection criteria. Possibly, if the logged MDT measurement data satisfies a training data configuration (e.g., the dataset size is greater than a configured minimum dataset size, batch size, etc. for training) and if a conditional training criterion is met (e.g., the WTRU is located at a specific location), the method may perform training of the AI ​​model and / or log AI / ML model parameters. Upon completion of the training process, the method may include performing one or more of the following actions: if the model accuracy level is above a configured accuracy threshold level, triggering a transition to a connected state, reporting an AI / ML model identity and AI / ML model parameters. In addition, if the model accuracy level is above the configured accuracy threshold level, the method may also include reporting the recorded validity time of the trained AI / ML model that achieves the given accuracy threshold level (e.g., the trained AI / ML model in the low / high mobility scenario can achieve the given threshold level within a specific time window). If the model accuracy level is equal to or below the configured accuracy threshold level, the method may include reporting the recorded MDT measurement; the maximum AI / ML model accuracy level achieved during training.

[0007] In another embodiment, a method implemented by a remote wireless transmit receive unit (WTRU) may include enabling the WTRU to receive and store vendor-specific and / or network-provided AI / ML models. The method may include transmitting AI / ML capability information, the AI / ML capability information including available AI / ML models, their accuracy levels, computing power (e.g., FLOPs) for training and reasoning, AI / ML-specific memory capacity (e.g., for training data and / or model storage). Possibly, the method may include receiving the AI / ML model from the network. The method may also include receiving a configuration regarding AI / ML model validation / reasoning and associated measurement and logging periodicity, wherein the configuration may include any of the following: report type, indication of the AI / ML model (e.g., already available or network configured), selection criteria (e.g., based on mobility scenarios such as low mobility and at the cell edge, etc.), input / output parameters, loss / reward function, accuracy threshold level, conditional logging configuration (e.g., based on AI model accuracy), and conditional reasoning configuration (e.g., based on a specific location). The method may include performing MDT measurements. Performing MDT measurements may include logging traditional MDT measurements and / or skipping MDT measurement logging opportunities when one or more of the following conditions are met: (i) using (e.g., instant / current) measurements to verify the selected AI / ML model, or (ii) the selected AI / ML learning model reaches a configured accuracy threshold level. The method may also include enabling the WTRU to verify the AI / ML model using logged MDT measurements and / or (e.g., instant / current) measurements. The method may also include selecting an AI / ML model for verification based on an indication of the AI / ML model and configured selection criteria, wherein if a conditional reasoning criterion is met (e.g., the WTRU is located at a specific location), the method may include performing verification of the AI ​​model and / or logging the AI / ML model accuracy level achieved. After completing the verification process, if the model accuracy level is below the configured accuracy threshold level, the method may include performing any of the following actions: triggering a transition to a connected state, reporting an AI / ML model identity, indicating that the accuracy level is below a threshold, and triggering / requesting a training and verification process. After completing the validation process, if the model accuracy level is equal to or higher than a configured accuracy threshold level, the method may include performing the following actions: the WTRU skips logging measurements.

[0008] In an embodiment, a method implemented in a WTRU for training an AI / ML model with measurements of a related data set may include the step of receiving a first message from a network, the first message including information indicating a configuration of measurements associated with artificial intelligence / machine learning model training. The first message may also include information indicating a periodicity of recording. In an embodiment, before receiving the first message, the method may include the step of transmitting AI / ML capability information to the network. The method may include the step of performing measurements configured for AI / ML model training in an idle state or an inactive state. The method may also include the step of selecting an AI / ML model for training based on the first message; and the step of training the selected AI / ML model based on the measurements performed. The measurements configured for AI / ML model training may be of the type of minimization of drive tests (MDT) measurements. In response to the accuracy level of the trained AI / ML model being higher than a configured accuracy threshold level or in this case, the method may include the step of triggering a transition to a connected state, and the step of transmitting a second message to the network, the second message including information indicating an identification of the selected trained AI / ML model and AI / ML model parameters. The accuracy level of the AI / ML model may be determined based on the measurements performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] A more detailed understanding may be obtained from the following detailed description given by way of example in conjunction with the accompanying drawings. As with the detailed description, each of the figures in such drawings is an example. Therefore, the figures (figures) and detailed description should not be considered limiting, and other equally effective examples are possible and possible. In addition, the same reference numerals ("labels") in the various figures indicate the same elements, and wherein:

[0010] Figure 1A is a system diagram illustrating an example communication system;

[0011] Figure 1B It shows that it can be Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within the communication system is shown;

[0012] Figure 1C It shows that it can be Figure 1A A system diagram of an example radio access network (RAN) and an example core network (CN) used within the illustrated communication system;

[0013] Figure 1D It shows that it can be Figure 1A A system diagram of yet another example RAN and yet another example CN used within the communication system shown;

[0014] Figure 2is a message flow diagram illustrating an example of a unidirectional radio resource control (RRC) signaling procedure for logged measurement configuration;

[0015] Figure 3 is an example of a timeline for a conventional minimization of drive testing (MDT) process;

[0016] Figure 4 is a system diagram showing an example of neighbor cell prediction;

[0017] Figure 5 is an example of a timeline of AI / ML model training operations at a WTRU.

[0018] Figure 6 is an example of a timeline of AI / ML model validation operations at a WTRU; and

[0019] Figure 7 is a flow chart illustrating an example of a method implemented in a WTRU for training an AI / ML model with relevant data set measurements. DETAILED DESCRIPTION

[0020] In the following detailed description, many specific details are set forth to provide a thorough understanding of the embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples can be practiced without some or all of the specific details set forth herein. In other cases, well-known methods, programs, components and circuits are not described in detail to avoid blurring the following description. In addition, the embodiments and examples not specifically described herein can replace the embodiments and other examples explicitly, implicitly and / or inherently described, disclosed or otherwise provided (collectively referred to as "providing") herein to practice or practice in combination with them. Although various embodiments in which equipment, systems, devices, etc. and / or any of its elements perform operations, processes, algorithms, functions, etc. and / or any part thereof are described and / or claimed herein, it should be understood that any embodiment described and / or claimed herein assumes that any equipment, systems, devices, etc. and / or any of its elements are configured to perform any operations, processes, algorithms, functions, etc. and / or any part thereof.

[0021] Example Communication System

[0022] The methods, devices, and systems provided herein are well suited for communications involving wired and wireless networks. Figures 1A to 1D An overview of various types of wireless devices and infrastructure is provided in which various elements of the network can utilize, perform, be arranged according to, and / or be adapted and / or configured for the methods, devices, and systems provided herein.

[0023] Figure 1Ais a system diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, broadcast, etc. to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content through shared system resources including wireless broadband. For example, the communication system 100 may employ one or more channel access methods such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single carrier FDMA (SC-FDMA), zero tail (ZT) unique word (UW) discrete Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, filter bank multi-carrier (FBMC), etc.

[0024] like Figure 1A As shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110 and other networks 112, but it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d (any of which may be referred to as a “station” and / or “STA”) may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, a personal digital assistant (PDA), a smart phone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automated process chain), a consumer electronic device, a device operating on a commercial and / or industrial wireless network, etc. Any of the WTRUs 102a, 102b, 102c, 102d may be interchangeably referred to as a UE.

[0025] The communication system 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, for example, to facilitate access to one or more communication networks such as the CN 106 / 115, the Internet 110, and / or the network 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node B (NB), an eNode-B (eNB), a master Node B (HNB), a master eNode-B (HeNB), a gNode-B (gNB), a NR Node B (NR NB), a site controller, an access point (AP), a wireless router, etc. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0026] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), a relay node, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as cells (not shown). These frequencies may be in a licensed spectrum, an unlicensed spectrum, or a combination of a licensed spectrum and an unlicensed spectrum. A cell may provide coverage of wireless services to a specific geographic area that may be relatively fixed or may vary over time. The cell may also be divided into cell sectors. For example, a cell associated with the base station 114a may be divided into three sectors. Therefore, in an embodiment, the base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple-output (MIMO) technology, and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in a desired spatial direction.

[0027] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0028] More specifically, as described above, the communication system 100 may be a multiple access system and may employ one or more channel access schemes such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA) which may use Wideband CDMA (WCDMA) to establish the air interface 116. WCDMA may include communication protocols such as High Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High Speed ​​Downlink Packet Access (HSDPA) and / or High Speed ​​Uplink Packet Access (HSUPA).

[0029] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a wireless technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA) which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0030] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as New Radio (NR) to establish NR radio access over the air interface 116.

[0031] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may jointly implement LTE radio access and NR radio access, for example using dual connectivity (DC) principles. Thus, the air interface used by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0032] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement wireless technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), etc.

[0033] Figure 1A The base station 114b in the example may be, for example, a wireless router, a master Node-B, a master eNode-B, or an access point, and may utilize any suitable RAT to facilitate wireless connectivity in a local area, such as a business location, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a wireless technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a wireless technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-a, LTE-a Pro, NR, etc.) to establish any of a small cell, a pico cell, or a femto cell. As Figure 1A As shown, base station 114b may be directly connected to Internet 110. Therefore, base station 114b may not need to access Internet 110 via CN 106 / 115.

[0034] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications and / or Voice over Internet Protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calls, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although Figure 1A Not shown, but it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT or a different RAT as the RAN 104 / 113. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) that employs any of GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technologies.

[0035] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network that provides plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols such as the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), and / or the Internet Protocol (IP) in the TCP / IP Internet protocol suite. The networks 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may use the same RAT as the RAN 104 / 114 or a different RAT.

[0036] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communication system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). Figure 1A The illustrated WTRU 102c may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0037] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B As shown, the WTRU 102 may include, among other things, a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0038] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. Although Figure 1B The processor 118 and the transceiver 120 are depicted as separate components, but it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, such as in an electronic package or chip.

[0039] The transmit / receive element 122 may be configured to transmit signals to or receive signals from a base station (e.g., base station 114a) via an air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be a transmitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF signals and optical signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0040] Although the transmit / receive element 122 is Figure 1B Although depicted as a single element in the figure, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0041] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and to demodulate signals received by the transmit / receive element 122. As described above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs (e.g., such as NR and IEEE 802.11).

[0042] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from: a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an organic light emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from and store data in any type of suitable memory, such as a non-removable memory 130 and / or a removable memory 132. The non-removable memory 130 may include a random access memory (RAM), a read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, etc. In other embodiments, the processor 118 may access information from and store data in a memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0043] The processor 118 may receive power from the power source 134 and may be configured to distribute the power to and / or control power to other components in the WTRU 102. The power source 134 may be any suitable device for providing power to the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel-metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0044] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to or in lieu of the information from the GPS chipset 136, the WTRU 102 may receive location information from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of receiving signals from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by any suitable location-determination method while remaining consistent with an embodiment.

[0045] The processor 118 may also be coupled to other components / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality, and / or wired or wireless connectivity. For example, the components / peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (e.g., for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, module, a frequency modulation (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, etc. Components / peripherals 138 may include one or more sensors, which may be gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors; geolocation sensors; altimeters, light sensors, touch sensors, magnetometers, barometers, gesture sensors, biometric sensors, and / or humidity sensors.

[0046] The WTRU 102 may include a full-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) and downlink (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via hardware (e.g., choke) or signal processing via a processor (e.g., a separate processor (not shown) or via the processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) or downlink (e.g., for reception)) may be concurrent and / or simultaneous.

[0047] Figure 1C 1 is a system diagram showing the RAN 104 and the CN 106 in accordance with an embodiment. As described above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0048] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, for example, the eNode-B 160a may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0049] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in uplink (UL) and / or downlink (DL), etc. Figure 1C As shown, eNode-Bs 160a, 160b, 160c may communicate with each other via an X2 interface.

[0050] Figure 1C The illustrated CN 106 may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements is depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0051] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, etc. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other wireless technologies, such as GSM and / or WCDMA.

[0052] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to and from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing the context of the WTRUs 102a, 102b, 102c, and the like.

[0053] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0054] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0055] Although the WTRU Figures 1A to 1D Although depicted as a wireless terminal, it is contemplated that in certain representative embodiments such a terminal may (eg, temporarily or permanently) utilize a wired communication interface with a communication network.

[0056] In a representative embodiment, other network 112 may be a WLAN.

[0057] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STA) associated with the AP. The AP may access a distribution system (DS) or another type of wired / wireless network that loads traffic into and / or out of the BSS or has an interface thereto. Traffic originating from outside the BSS to the STA may be reached by the AP and may be delivered to the STA. Traffic from the STA to a destination outside the BSS may be sent to the AP to be delivered to the corresponding destination. Traffic between STAs within the BSS may be sent by the AP, for example, where the source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as point-to-point traffic. Point-to-point traffic may be sent between the source STA and the destination STA using a direct link setup (DLS) (e.g., directly sent between them). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunnel DLS (TDLS). A WLAN using an independent BSS (IBSS) mode may not have an AP, and STAs (eg, all STAs) within or using the IBSS may communicate directly with each other. The IBSS communication mode may sometimes be referred to herein as an "ad hoc" communication mode.

[0058] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, the AP can send beacons on a fixed channel, such as a primary channel. The primary channel can be a fixed width (e.g., a 20 MHz wide bandwidth) or a width dynamically set via signaling. The primary channel can be an operating channel of the BSS and can be used by STAs to establish a connection with the AP. In certain representative embodiments, carrier sense multiple access-collision avoidance (CSMA / CA) can be implemented, for example, in an 802.11 system. For CSMA / CA, STAs (e.g., each STA) including the AP can sense the primary channel. If the primary signal is sensed / detected by a particular STA and / or is determined to be busy, the particular STA can back off. One STA (e.g., only one station) can transmit in a given BSS at any given time.

[0059] A high throughput (HT) STA may communicate using a 40 MHz wide channel, for example, via a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0060] Very high throughput (VHT) STA can support 20MHz, 40MHz, 80MHz and / or 160MHz wide channels. 40MHz and / or 80MHz channels can be formed by combining continuous 20MHz channels. A 160MHz channel can be formed by combining 8 continuous 20MHz channels, or by combining two discontinuous 80MHz channels, which can be referred to as an 80+80 configuration. For the 80+80 configuration, the data can be passed through a fragment parser after channel coding, which can divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time domain processing can be performed on each stream respectively. The stream can be mapped to two 80MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above-mentioned operation of the 80+80 configuration can be reversed, and the combined data can be sent to a media access control (MAC) layer, an entity, etc.

[0061] 802.11af and 802.11ah support operating modes below 1 GHz. The channel operating bandwidth and carrier are reduced in 802.11af and 802.11ah relative to those used in 802.11n and 802.11ac. 802.11af supports 5MHz, 10MHz and 20MHz bandwidths in TV white space (TVWS) spectrum, and 802.11ah supports 1MHz, 2MHz, 4MHz, 8MHz and 16MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah can support meter type control / machine type communication (MTC), such as MTC devices in macro coverage. MTC devices may have certain capabilities, for example, limited capabilities, including support for (e.g., only support for) certain and / or limited bandwidths. MTC devices may include batteries with battery life above a threshold (e.g., to maintain very long battery life).

[0062] A WLAN system that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) includes a channel that can be designated as a primary channel. The primary channel may have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by the STA that supports the minimum bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for STAs (e.g., MTC-type devices) that support (e.g., only support) a 1MHz mode, the primary channel may be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the state of the primary channel. If the primary channel is busy, for example, due to a STA (which only supports a 1MHz operating mode) transmitting to the AP, the entire available band may be considered busy even if most of the band remains idle and may be available.

[0063] In the United States, the available frequency band that can be used by 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz, depending on the country code.

[0064] Figure 1D1 is a system diagram showing the RAN 113 and the CN 115 according to an embodiment. As described above, the RAN 113 may employ NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0065] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, for example, the gNB 180a may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be located on an unlicensed spectrum, while the remaining component carriers may be located on a licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement coordinated multi-point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNB 180a and gNB 180b (and / or gNB 180c).

[0066] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable parameter sets. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of varying or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0067] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as the eNode Bs 160a, 160b, 160c). In a standalone configuration, the WTRUs 102a, 102b, 102c may use one or more of the gNBs 180a, 180b, 180c as mobility anchors. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration, the WTRU 102a, 102b, 102c may communicate / connect with the gNB 180a, 180b, 180c while also communicating / connecting with another RAN, such as the eNode-B 160a, 160b, 160c. For example, the WTRU 102a, 102b, 102c may implement the DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNode-B 160a, 160b, 160c may serve as a mobility anchor for the WTRU 102a, 102b, 102c, and the gNB 180a, 180b, 180c may provide additional coverage and / or throughput to serve the WTRU 102a, 102b, 102c.

[0068] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, support for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards a user plane function (UPF) 184a, 184b, routing of control plane information towards an access and mobility management function (AMF) 182a, 182b, etc. Figure 1D As shown, gNBs 180a, 180b, and 180c may communicate with each other via an Xn interface.

[0069] Figure 1DThe illustrated CN 115 may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and at least one data network (DN) 185a, 185b. Although each of the foregoing elements is described as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0070] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRU 102a, 102b, 102c, supporting network slicing (e.g., handling different protocol data unit (PDU) sessions with different requirements), selecting a specific SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. The AMF 182a, 182b may use network slicing, for example, to customize CN support for the WTRU 102a, 102b, 102c based on the type of service the WTRU 102a, 102b, 102c is utilizing. For example, different network slices may be established for different use cases, such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, etc. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other wireless technologies (such as LTE, LTE-A, LTE-A Pro) and / or non-3GPP access technologies (such as Wi-Fi).

[0071] The SMF 183a, 183b may be connected to the AMF 182a, 182b in the CN 115 via the N11 interface. The SMF 183a, 183b may also be connected to the UPF 184a, 184b in the CN 115 via the N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b, and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0072] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, etc.

[0073] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local data network (DN) 185a, 185b via an N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b through the UPF 184a, 184b.

[0074] Given that Figures 1A to 1D and Figures 1A to 1D 102a to 102d, base stations 114a to 114b, eNode-Bs 160a to 160c, MMEs 162, SGWs 164, PGWs 166, gNBs 180a to 180c, AMFs 182a to 182b, UPFs 184a to 184b, SMFs 183a to 183b, DNs 185a to 185b, and / or any other elements / devices described herein. A simulation device may be one or more devices configured to simulate one or more or all of the functions described herein. For example, a simulation device may be used to test other devices and / or simulate network and / or WTRU functions.

[0075] The simulation device can be designed to implement one or more tests of other devices in a laboratory environment and / or an operator network environment. For example, one or more simulation devices can perform one or more or all functions when fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. One or more simulation devices can perform one or more or all functions when temporarily implemented / deployed as part of a wired and / or wireless communication network. The simulation device can be directly coupled to another device for testing purposes, and / or can use over-the-air wireless communication to perform testing.

[0076] One or more simulation devices can perform one or more (including all) functions when not implemented / deployed as part of a wired and / or wireless communication network. For example, the simulation device can be used for testing scenarios in a test laboratory and / or a wired and / or wireless communication network that is not deployed (e.g., testing) to implement testing of one or more components. One or more simulation devices can be test equipment. The simulation device can use direct RF coupling and / or wireless communication via RF circuits (e.g., which can include one or more antennas) to transmit and / or receive data.

[0077] Example of Idle / Inactive Measurement

[0078] For WTRUs in Radio Resource Control Idle state (RRC Idle state) and RRC Inactive state, a logged Minimization of Drive Test (MDT) procedure is used. For logged MDT measurement collection for RRC Inactive WTRUs, the actual logging procedure within the WTRU may be performed in RRC Inactive state and may continue in RRC Idle state; and vice versa. The logged measurements stored in the WTRU during RRC Inactive and RRC Idle states are retained for a given common period before being deleted.

[0079] Two types of Logged MDT procedures are defined, namely, signaling-based and management-based. In signaling-based Logged MDT, the NG-RAN stores the Logged MDT configuration in the WTRU context. However, in management-based MDT, there is no such requirement. For both procedures, the NG-RAN may configure MDT for the WTRU when the WTRU resumes the RRC connection in the last serving NG-RAN.

[0080] refer to Figure 2 The network may initiate a logged MDT procedure to a WTRU in an RRC connection by sending a LoggedMeasurementConfiguration message, which is used to convey configuration parameters for logged MDT. This is a one-way RRC signaling procedure.

[0081] The logged MDT measurement configuration may include any of: trigger of logging event (periodic / event-based); logging duration; logging area; list of neighboring frequencies and / or cells; WLAN access point name; Bluetooth beacon name; and sensor name.

[0082] For downlink pilot strength measurements, the recorded measurement report may consist of measurement results (measurement quantities) of the serving cell, available WTRU measurements performed in idle or inactive for intra-frequency / inter-frequency / cross-radio access technology (RAT), timestamp and location information. The location information may be based on the available location information in the WTRU. Thus, depending on availability, the measurement record may consist of time information and radio frequency (RF) measurements and RF fingerprint or global navigation satellite system (GNSS) information or detailed location information based on sensor information.

[0083] For logged MDT in the WTRU, there may be only one RAT-specific logged measurement configuration. The release operation of the logged measurement configuration in the WTRU may be achieved by configuration replacement only when the configuration is overwritten, or by configuration clearing if the duration timer stop or expiration condition is met. The logged measurements corresponding to the previous configuration will be cleared at the same time. It may be up to the network to retrieve any relevant data before providing a new configuration.

[0084] The WTRU may collect MDT measurements and may continue to log according to the logged measurement configuration until the WTRU memory reserved for MDT is full. In this case, the WTRU may stop logging, stop the logging duration timer and start a 48-hour timer. The network may decide to retrieve the logged measurements based on the indication. If the logged MDT measurements are retrieved before the predefined logging duration is completed, the reported measurement results may be deleted, but the MDT measurement logging may continue according to the ongoing logged measurement configuration. If the network does not retrieve the logged MDT measurements, the WTRU shall store the unretrieved measurements for 48 hours from the moment the duration timer for logging expires. There is no requirement to store the unretrieved data for more than 48 hours. In addition, all logged measurement configurations and records shall be removed by the WTRU upon shutdown or detachment. For logged MDT, the WTRU may include an indication in one of the RRC messages (RRCConnectionSetupComplete or RCSetupComplete or RRCConnectionResumeComplete or RRCResumeComplete) at each transition to RRC connected mode, even if the logging period has not ended. The measurement report is then triggered by an on-demand mechanism, for example, the network may request the WTRU to send the collected measurement logs via RRC signaling.

[0085] refer to Figure 3 , shows the timeline of the conventional MDT process. Therefore, the network may initiate the MDT process to the WTRU in the RRC connection by sending a LoggedMeasurementConfiguration message, which is used to transmit the configuration parameters of the logged MDT, such as in Figure 2 . The release of the logged measurement configuration in the WTRU may be achieved (e.g., only) by configuration replacement when the configuration is overwritten, or by configuration clearing when a duration timer stop or expiration condition is met. The logged measurements corresponding to the previous configuration will be cleared at the same time. It may be up to the network to retrieve any relevant data before providing a new configuration.

[0086] The configuration of the trigger for logging an event may include any of the following: (i) a periodic measurement trigger, where the logging interval may be configurable and the parameters may specify the periodicity for storing MDT measurement results; and an event-based trigger, where the logging interval may be configurable, which may determine the periodic logging of available data (e.g., timestamp, location information), and may support the following two types of events: (1) a measurement quantity-based event L1, where the event threshold, hysteresis, and trigger time may be configurable. If the configured trigger time is not a multiple of a discontinuous reception (DRX) cycle, the WTRU may use a multiple of the next DRX cycle duration greater than the trigger time to evaluate event L1; (2) an out-of-coverage detection trigger.

[0087] Configuration of the logging duration may include configuration of parameters defining a timer activated at the configuration moment, which continues independently of a state change, RAT or Registered Public Land Mobile Network (RPLMN) change.

[0088] Depending on the configuration of the recording duration, when the timer expires, the recording can be stopped and the configuration can be cleared (except for the parameters required for further reporting, such as network absolute timestamp, trace reference, trace recording session reference and trace collection entity (TCE) Id).

[0089] Examples of mobility states / scenarios

[0090] The WTRU mobility state / scenario may be determined based on any of the following parameters:

[0091] T CRmax : Specifies the duration used to evaluate the amount of cell reselection allowed.

[0092] N CR_M / N CR_H : Specifies the maximum number of cell reselection times for entering medium / high mobility state.

[0093] T CRmaxHsyt : Specifies the maximum number of cell reselection times for entering high mobility state.

[0094] If these parameters are broadcast in the system information for the serving cell, any of the following status detection criteria may be followed:

[0095] Normal mobility state standard: If in time period T CRmax The number of cell reselections during this period is less than N CR_M words.

[0096] Medium mobility state standard: If in time period T CRmax The number of cell reselections during the period is greater than or equal to N CR_M But less than or equal to N CR_H words.

[0097] High mobility state criteria: If in time period T CRmax The number of cell reselections during this period is greater than N CR_H words.

[0098] The mobility state is indicated as part of the RRCSetupComplete message in the mobilityState IE and just before the WTRU enters the RRC_CONNECTED state.

[0099] Examples of Federated Learning and Transfer Learning

[0100] In federated learning, a central server may train a global model by aggregating local models partially trained by each terminal device. Within each training iteration, the WTRU may perform training using local training data based on the model downloaded from the central server. The WTRU may then report interim training results (e.g., gradients for DNN) to the central server. The server aggregates the gradients from the WTRUs and updates the global model. Next, the updated global model is distributed to the WTRUs. The WTRU may then perform training for the next iteration.

[0101] In transfer learning, transfer learning is a special case of federated learning, and the idea of ​​transfer learning is to reuse previously learned knowledge (previously trained AI / ML models) for another dataset that may be different in the feature space of the already trained AI / ML model.

[0102] The difference between federated learning and transfer learning is that federated learning can leverage decentralized trained models with distributed datasets to train a global model, whereas in transfer learning, an already trained model (trained locally or downloaded from a server) can be reused / retrained to predict another feature.

[0103] The statement of the above example

[0104] For many AI / ML tasks, fragmented data collected by mobile devices is necessary to train global models. For some AI / ML model training and model inference operations, the input data may need to be continuous and a time series of information for each specific granularity. In some cases, tasks and environmental changes require different AI / ML models to perform the same feature prediction. Therefore, another training and inference cycle may be required with a different data set representing the new environmental changes. The current measurement reporting mechanism can support AI / ML at the network for training purposes. Since the measurement data provided will be non-continuous or contain past measurements, the network needs to perform AI / ML training operations first and then perform prediction / inference operations. Therefore, the traditional measurement process may not enable the network to perform predictions immediately after the WTRU provides the measurement data. Today, the computing resources used in mobile devices can undertake the execution of AI / ML operations at a certain capacity. In order to improve AI / ML operations with these capable devices and an existing or new set of measurements, the network can distribute training operations to WTRUs capable of performing AI / ML operations. The network may then request the WTRU to provide trained model parameters, which may be aggregated (e.g., immediately) by the network to derive a global, use case-specific, or region-specific AI / ML model that may be used by the network to make predictions / inferences for WTRUs with the same or similar environmental variations.

[0105] An example of a problem with the above example is how to enhance the measurement and logging process to enable the network to efficiently utilize the available measurements at the WTRU by distributing / offloading the AI / ML training operations to the WTRU. The trained AI / ML model at the WTRU can then be used by the network (e.g., immediately) to perform inference / prediction on the network side.

[0106] In the following description, the term AI / ML (artificial intelligence / machine learning) is used to describe any model and associated learning algorithm used by the WTRU and / or the network to predict future behavior (in this disclosure, the behavior at the WTRU or data arrival to be sent to the network). It is assumed that the model and associated learning algorithm utilize a set of data collected by the WTRU and / or the network.

[0107] Details on downloading AI / ML models and associated learning algorithms are beyond the scope of the following description, and the focus here is instead on effectively using already available AI / ML algorithms (vendor specific and / or downloaded from a network / server) in the WTRU. Therefore, the dependency on the required model size, its download latency, etc. is beyond the scope of this disclosure.

[0108] In the following description, it is assumed that the computing resources of the WTRU can undertake the onboard processing and execution of AI / ML model operations including training and inference.

[0109] In the following description, the terms “AI / ML model,” “AI model,” “ML model,” and “model” are used interchangeably.

[0110] Example of WTRU transmitting AI / ML capability information

[0111] In an embodiment, the WTRU may indicate to the network its ability to perform AI / ML operations.

[0112] In an embodiment, the WTRU may indicate its AI / ML capabilities to the network separately for each AI / ML operation, such as for AI / ML model training or AI / ML model validation or both.

[0113] In an embodiment, the WTRU may indicate its capabilities to the network according to traditional WTRU capability transmission (eg, the network sends a WTRUCapabilityEnquiry and the WTRU responds with a WTRUCapabilityInformation).

[0114] In an embodiment, the WTRU may indicate its AI / ML capabilities as part of a dedicated IE in the registration message during initial registration or registration update (including WTRU initiated update, NW initiated update and periodic update), i.e., WTRUAIMLTrainingCapability, WTRUAIMLValidationCapability, WTRU-AI-Capability, etc.

[0115] The proposed AI / ML capability information for AI / ML model training and AI / ML model validation may be as simple as a binary “yes / no”, or it may be detailed information including any of the following:

[0116] (i) Available AI models (e.g., vendor-specific AI models or downloaded network-provided AI models). In some solutions, the WTRU may include an ID associated with each AI model. For AI / ML model training: In the case where the AI ​​model has been downloaded from the home network (HPLMN) but training has not yet been performed, the WTRU may use the same ID provided by the network during the download process. In the case where the AI ​​model has been downloaded from the home network (HPLMN) and training has been performed, the WTRU may update the initially downloaded model ID in a predefined manner specified by the network. In the case where the AI ​​model has been downloaded from an access network (VPLMN), an equivalent network (HPLMN), or a dedicated network (including standalone networks (SNPN) and public network integration (PNI-NPN) or a third-party server) but training has not yet been performed, the WTRU may use the same ID provided by the network to which the WTRU was connected during the model download. The WTRU's home network then finds / matches the model ID by interacting with the network that provided the AI ​​model, or associates the model with the ID without any interaction. In the case where the AI ​​model has been downloaded from an access network (VPLMN), an equivalent network (HPLMN), or a dedicated network (including a standalone network (SNPN) or a public network integrated (PNI-NPN) or a third-party server) and training has been performed at the WTRU, the WTRU may update the initially downloaded model ID in a predefined manner dictated by the network to which the WTRU was connected during the model download. The WTRU's home network then finds / matches the model ID by interacting with the network that provided the AI ​​model, or associates the model with the ID without any interaction. In the case where the AI ​​model is a vendor-specific model, the WTRU may only provide the model name or vendor-specific ID, and the network may associate the model with the ID.

[0117] (ii) The accuracy level of each available AI model.

[0118] (iii) AI computation capacity (e.g., FLOPs) to perform training or validation. In various embodiments, the computation capacity may represent the current state of the total capacity or remaining capacity. In an embodiment, the WTRU may also indicate whether it can perform more than one training and / or validation operation by utilizing the remaining computation capacity.

[0119] (iv) AI-specific memory capacity (e.g., for storing training / validation data and / or model storage). In various embodiments, the memory capacity may represent the current state of the total capacity or remaining capacity. In an embodiment, the WTRU may use internal and external (e.g., SD card) storage capacity to store AI-related files (i.e., training data, validation data, model parameters, etc.).

[0120] (v) Durations during which training and / or validation may not be performed (e.g., this may be a user preference, such as during daytime hours, 08:00 to 18:00), or equivalently, durations during which the WTRU may perform training and / or validation. This may be expressed as a recommended duration that may be used for training and / or validation.

[0121] (vi) AI model switching capability / timing for onboard (another existing) AI model (e.g., the network may define various conditions for activating a different AI model among the existing AI models at the WTRU).

[0122] Examples of AI / ML configurations

[0123] In an embodiment, the WTRU may receive configuration regarding AI / ML model training and / or AI / ML model validation.

[0124] In an embodiment, the WTRU may receive the AI / ML model training and / or validation configuration as a dedicated configuration (i.e., AIMLModelTrainingConfiguration or AIMLModelValidationConfiguration). Possibly in an RRC reconfiguration message. In an example, the WTRU may receive the model training configuration as part of the MDT configuration.

[0125] In an embodiment, since the training and / or validation process requires a dataset / database, the WTRU may receive the AI / ML model training / validation configuration as part of the traditional measurement configuration (i.e., LoggedMeasurementConfiguration, measConfig).

[0126] The proposed AI / ML model training and / or validation configuration may be a detailed configuration including any of the following:

[0127] (i) Indication of an AI model (e.g., already obtained or network-provided as vendor-specific). In various embodiments, an AI model ID may be used to indicate an AI model. Possibly, the AI ​​model ID may occupy a preconfigured number space allocated for a particular vendor. For example, the model ID may be determined as a combination of one or more of the following: country ID, vendor ID, device / firmware / execution environment ID, model class ID, model version ID, etc.

[0128] (ii) One / more selection criteria for the AI ​​model. In an embodiment, the one / more selection criteria may include the mobility state / scenario of the WTRU. For example, when the mobility state of the WTRU is determined to be normal mobility, one AI model may be used, and when the mobility state of the WTRU is determined to be high mobility, another AI model may be used. Various other criteria may also be considered for the selection of the AI ​​model, either individually or in combination, such as the WTRU is not at the cell edge, etc.

[0129] (iii) Associated measurements. In an embodiment, the associated measurements may be provided as a separate parameter based on the measurement capabilities of the WTRU. In an embodiment, the associated measurements may be provided as a set of parameters based on the measurement capabilities of the WTRU. In an embodiment, the granularity of the associated measurements may be indicated as part of the configuration. In an embodiment, the filter type / averaging window for the associated measurements may be indicated as part of the configuration.

[0130] (iv) Input / output parameters. In an embodiment, the input parameters may be part of the associated measurements. It should be noted that the associated parameters do not have to be input parameters for AI / ML model training / validation. Some of the associated parameters may be used for AI / ML model lifecycle management and / or AI / ML model training / validation process. In an embodiment, the output parameters and expected format / size / length (in the case of time series prediction) may be indicated.

[0131] (v) Loss / Reward Function. Depending on the AI / ML model to be used, the network can provide a loss or reward function associated with the AI / ML model to be trained and / or validated.

[0132] (vi) Accuracy Threshold. In an embodiment, the accuracy threshold may be defined by the network. For AI / ML model training, the accuracy threshold may be used to trigger / stop the model training process, as described in detail below. For AI / ML model validation, the accuracy threshold may be used to trigger the WTRU to report the validation output to the network, as described in detail below. In an embodiment, the accuracy threshold may be used to trigger the WTRU to report the trained model parameters and / or validation output to the network, as described in detail below.

[0133] (vii) Training and / or validation data configuration (e.g., minimum dataset size for training / validation, AI / ML model-specific data batch size). In an embodiment, the training and / or validation data configuration may be provided by the network to indicate the dataset size required for training and / or validating a specific AI / ML model. The specific AI / ML model may be a model provided by the network. In an embodiment, the training and / or validation data configuration may be provided by the network to specify the batch size of the dataset required for a specific AI / ML model. In an embodiment, the training and / or validation data configuration may be provided by the network to indicate specific attributes available in an associated measurement or training and / or validation dataset.

[0134] (viii) Conditional logging configuration (e.g., based on the accuracy of the AI ​​model). In an embodiment, the conditional logging configuration may be indicated by the network as part of the AI / ML model training and / or validation configuration. The conditional logging configuration may be based on the achieved AI model accuracy and may be used by the WTRU to skip or not skip logging of measurements, as described in detail below. In an embodiment, the conditional logging configuration may be indicated by the network as a new information element (IE) within the traditional measurement configuration (e.g., LoggedMeasurementConfiguration, MeasConfig). In an embodiment, the conditional logging configuration may be indicated by the network to enable the WTRU to log not only logged MDT measurements, but also (e.g., current / immediate) MDT and connected mode measurements, as described in detail below.

[0135] (ix) Conditional training / validation configuration (e.g., based on a specific location). In an embodiment, a conditional training and / or validation configuration may be indicated by the network. The conditional training / validation configuration may be based on a specific location and may be used by the WTRU to trigger / stop the measurement logging process and / or the model training / validation process, as described in detail below.

[0136] (x) Training / Validation Timer. In an embodiment, the AI / ML model training and / or validation timer may be indicated by the network. The AI / ML model training and / or validation timer may be configured by the network based on a specific timeline to receive trained model updates and / or model validation output / results, or based on the computational capabilities of the WTRU so as not to overload the WTRU with AI / ML model training and / or validation tasks if a given training / validation timer has not achieved the expected level of accuracy. In an embodiment, the AI / ML model training / validation timer may be used to stop / abort the training / validation process running at the WTRU. In an embodiment, the AI / ML model training / validation timer may be used to remove stored AI / ML models / parameters or stored data sets used to train a particular AI / ML model or stored AI / ML model output / achieved level of accuracy, as described in detail below.

[0137] (xi) Training parameters (e.g., model hyperparameters)

[0138] In one embodiment, if model parameters need to be specified, model hyperparameters (also called training parameters) that control training can be provided by the network. Model hyperparameters can be provided as part of the input parameters or as a dedicated IE in the AI / ML model training configuration.

[0139] Example of AI / ML operation-specific measurement records

[0140] Depending on the use of available measurements at the WTRU for AI / ML model training and / or validation, conventional measurement procedures may be used. Thus, the WTRU may perform logged MDT measurements, (e.g., immediate / current) MDT measurements, and connected mode measurements.

[0141] In an embodiment, if the WTRU is configured to perform AI / ML model training and AI / ML model validation simultaneously, the WTRU may have different data sets for these two operations. These different data sets may be stored separately.

[0142] In an embodiment, if the WTRU is configured to perform AI / ML model training and validation operations simultaneously or in different time periods, the WTRU may use the same data set for both operations.

[0143] In an embodiment, the WTRU may log not only logged MDT measurements but also (e.g., immediate / current) MDT measurements and connected mode measurements to create the data set required for AI / ML model training and / or validation.

[0144] In an embodiment, (e.g., immediate / current) MDT measurements and / or connected mode measurements used for AI / ML training and / or validation procedures may be logged and stored in a memory of the WTRU reserved for logged MDT measurement storage.

[0145] In an embodiment, (e.g., immediate / current) MDT measurements and / or connected mode measurements used for AI / ML training and / or validation processes may be logged and stored in a memory of the WTRU reserved for or indicated as AI-dedicated memory.

[0146] In an embodiment, if the WTRU is configured to perform AI / ML model training and / or validation, the logged MDT measurements may be logged and stored in the WTRU's AI-dedicated memory rather than in the WTRU's memory reserved for logging MDT measurements.

[0147] In an embodiment, logged MDT measurements used for AI / ML training and / or validation procedures may be logged and stored in a memory of the WTRU that is retained as a traditional manner and also logged in an AI-dedicated memory of the WTRU.

[0148] In an embodiment, any measurements including logged MDT measurements, intermediate MDT measurements, and connected mode measurements will be stored in the AI ​​dedicated memory, and the dataset batch size provided as part of the training / validation data configuration can be used to store the measurements.

[0149] In an embodiment, any measurements including logged MDT measurements, intermediate MDT measurements and connected mode measurements will be stored in the AI ​​dedicated memory, and the WTRU may only store specific attributes provided as part of the training and / or validation data configuration.

[0150] In an embodiment, any measurements including logged MDT measurements, intermediate MDT measurements, and connected mode measurements will be stored in the AI ​​dedicated memory, and the WTRU may stop storing the measurements once the required training data set size provided as part of the training / validation data configuration has been achieved.

[0151] In an embodiment, where a conditional logging configuration is provided as part of an AI / ML training and / or validation configuration, the WTRU may skip a measurement logging opportunity when any of the following conditions is met: the AI / ML model is still in the training / validation phase utilizing existing recorded measurement data; and / or (e.g., instantaneous / current) measurements are used to determine the trained accuracy level of the AI / ML model; and / or (e.g., instantaneous / current) measurements are used to validate the trained accuracy level of the AI / ML model; and / or the trained AI / ML model reaches a configured accuracy threshold level; and / or the conditions provided as part of the conditional training / validation configuration are not met.

[0152] In an embodiment, in case a given training / validation timer fails to reach a required AI / ML model accuracy threshold, the WTRU may decide to remove / delete the stored data set used for training / validation. Deletion of the stored training / validation data set may be followed by either: the WTRU reporting to the network that the AI / ML model training / validation failed to reach a given accuracy threshold; and the WTRU to perform measurements creating a new data set based on the given associated measurements and restarting the training / validation timer.

[0153] Example of WTRU performing AI / ML operations

[0154] In an embodiment, as part of the AI / ML model training configuration, the WTRU may select an AI model for training and / or validation based on the indicated AI model.

[0155] In an embodiment, the WTRU may be configured with multiple AI models and selection criteria associated with each AI model. For example, the selection of an AI model may also depend on one / more selection criteria configured as part of the model training and / or validation configuration. Therefore, the selection of an AI model may be based on one or a combination of any of the following criteria (and / or statements): the mobility state / scenario of the WTRU is normal mobility; the mobility state / scenario of the WTRU is medium mobility; the mobility state / scenario of the WTRU is high mobility; the WTRU is detected to be not at the cell edge; the WTRU is detected to be at the cell edge; the mobility state / scenario of the WTRU is normal mobility and the UE is detected to be not at the cell edge; the mobility state / scenario of the WTRU is normal mobility or the mobility state or scenario of the UE is medium mobility; etc...

[0156] In order to use some of the above criteria, the mobility state may be evaluated not only (e.g., only) before the WTRU enters the RRC_CONNECTED state, but also during the RRC_IDLE or RRC_INACTIVE state. Thus, in an embodiment, the WTRU may perform mobility state evaluations periodically while it is in the RRC_IDLE or RRC_INACTIVE state. The WTRU may not report the mobility state evaluations periodically during the RRC_IDLE or RRC_INACTIVE state. The WTRU may save the last mobility state evaluation as an IE as part of the WTRU information and may provide the mobility state evaluations during the RRC_IDLE or RRC_INACTIVE state.

[0157] Once the WTRU selects an AI / ML model, the WTRU may start performing AI / ML model training and / or validation when one or more of the following conditions are met.

[0158] (i) The recorded measurement data (idle / inactive / connected mode measurements) in the WTRU's AI dedicated memory or the WTRU's memory reserved for storing measurements in a conventional manner satisfies the training and / or validation data configuration provided as part of the AI / ML training / validation configuration. In an embodiment, the WTRU may check the amount of data set available in the WTRU's AI dedicated memory or the WTRU's memory reserved for storing measurements. If the amount of data set is greater than the configured minimum data set size for training / validation, the WTRU may start performing AI / ML model training / validation operations. In an embodiment, once the configured minimum data set size for training is met, the WTRU may divide the data based on a given training and / or validation batch size as part of the training data configuration. In an embodiment, the WTRU may check the amount of data set available in the WTRU's AI dedicated memory or the WTRU's memory reserved for storing measurements. If the amount of data set is greater than the configured training / validation batch size, the WTRU may start performing AI / ML model training / validation operations. At the same time, the WTRU may keep the recorded measurements until the configured minimum data set size for training and / or validation is met.

[0159] (ii) Conditions provided as part of conditional training and / or validation criteria. In an embodiment, location may be provided as a conditional training / validation criterion. Location may be indicated as: coordinate range, physical cell ID, tracking area, etc.

[0160] In an embodiment, the battery status of the WTRU may be provided as a conditional training and / or validation criterion. If the battery status of the WTRU is above a given conditional threshold, the WTRU may perform AI / ML model training and / or validation.

[0161] In an embodiment, once the training and / or verification process has been started at the WTRU and the above conditions are no longer met (for example, the WTRU is not at a given location): in the case where the AI / ML operation is AI / ML model training, the WTRU can stop the training process, record the training model parameters that achieved the maximum accuracy level and the accuracy level achieved; and in the case where the AI / ML operation is AI / ML model verification, the WTRU can stop the verification process and record the maximum accuracy level.

[0162] In an embodiment, once the training and / or validation process has been started at the WTRU and the above conditions are no longer met (e.g., the WTRU is not at a given location), the WTRU may stop logging measurement data. In the event that the conditions regarding the size of the training and / or validation data have been met, the WTRU may continue the training and / or validation process even if the location conditions are not met.

[0163] In an embodiment, once the WTRU begins performing AI / ML model training and / or validation, the WTRU may start a training and / or validation timer.

[0164] In an embodiment, when the WTRU performs AI / ML model training, the WTRU may record the trained AI / ML model parameters and the accuracy achieved. The WTRU may record the trained AI / ML model parameters and the accuracy achieved after completing each epoch to the WTRU's AI-dedicated memory.

[0165] In an embodiment, during the training process, if the AI / ML model trained by the WTRU reaches a given accuracy threshold, the WTRU may stop the training process and record the trained model parameters together with the achieved accuracy to the WTRU's AI dedicated memory.

[0166] In an embodiment, during the validation process, if a given AI / ML model reaches a given accuracy threshold, the WTRU may stop the validation process and record the achieved accuracy to the WTRU's AI-dedicated memory.

[0167] In an embodiment, if the AI / ML model trained by the WTRU fails to reach a given accuracy threshold within a given training time, the WTRU may stop the training process and record the trained model parameters that reach the maximum accuracy level and the achieved accuracy level to the WTRU's AI-dedicated memory.

[0168] In an embodiment, if a given trained AI / ML model fails to reach a given accuracy threshold within a given validation time, the WTRU may stop the validation process and record the achieved accuracy level to the WTRU's AI-dedicated memory.

[0169] In an embodiment, if the AI / ML model trained by the WTRU fails to reach a given accuracy threshold when a given training and / or validation time expires, the WTRU may remove the AI / ML model from its AI-dedicated memory or recorded measurements or training and / or validation data sets.

[0170] Example of WTRU Reporting

[0171] Reports for AI / ML model training

[0172] In an embodiment, when a trained AI / ML model at the WTRU reaches a given accuracy threshold provided as part of the AI / ML training configuration, the WTRU may switch from an idle / inactive state to a connected state in order to report the AI / ML model identification, trained AI / ML model parameters, and the threshold level achieved.

[0173] In an embodiment, once the trained AI / ML model at the WTRU reaches a given accuracy threshold provided as part of the AI / ML training configuration, the WTRU may switch from an idle / inactive state to a connected state to indicate to the network that the training process is complete with the given accuracy threshold. The WTRU may receive a request from the network to collect parameters of the trained AI / ML model.

[0174] In an embodiment, the WTRU may receive a request from the network, where the network may not have information about the status of training at the WTRU. The WTRU may: (i) still be performing AI / ML model training and may send the status of the training, such as the maximum accuracy level achieved; and / or complete the AI / ML model training and may send a trained AI / ML model identity and trained AI / ML model parameters that have achieved a given accuracy threshold level provided as part of the AI / ML training configuration.

[0175] In an embodiment, the WTRU may report the recorded validity period of the trained AI / ML model that achieves a given accuracy threshold level. The recorded validity period may vary depending on the mobility state / scenario of the WTRU. For example, if the WTRU is in normal mobility, the predictions provided by the trained AI / ML model may be valid for a specific period of time. A trained model at a WTRU in high mobility may achieve a shorter validity period.

[0176] In an embodiment, the network may use the validity time to decide whether the trained AI / ML model at the WTRU should be acquired.

[0177] In an embodiment, in the event that the accuracy of the AI / ML model trained by the WTRU is below a configured accuracy threshold within a given training time, the WTRU may report to the network the maximum AI / ML model accuracy achieved. The WTRU may also report the training dataset / logged measurements used to train the AI / ML model. The WTRU may receive a request from the network to obtain trained AI / ML model parameters. The WTRU may receive a request from the network to obtain training dataset / logged measurements.

[0178] Reports for AI / ML model validation

[0179] In an embodiment, in the event that a given trained AI / ML model for the WTRU reaches a given accuracy threshold provided as part of the AI / ML validation configuration, the WTRU may switch from an idle / inactive state to a connected state in order to report the AI / ML model identification and validation output / threshold level achieved.

[0180] In an embodiment, once a given trained AI / ML model for the WTRU reaches a given accuracy threshold provided as part of the AI / ML validation configuration, the WTRU may switch from an idle / inactive state to a connected state to indicate to the network that the validation process is complete when the given accuracy threshold is reached. The WTRU may receive a request from the network to collect the validation output.

[0181] In an embodiment, the WTRU may receive a request from the network, where the network may not have information about the status of the validation at the WTRU. The WTRU may: still be performing AI / ML model validation and may send the status of the validation, such as the maximum accuracy level achieved; and / or complete the AI / ML model validation and may send a given trained AI / ML model identification and validation output / accuracy level that achieved a given accuracy threshold level provided as part of the AI / ML validation configuration.

[0182] In an embodiment, the WTRU may report a recorded validity period for a given trained AI / ML model that achieves a given accuracy threshold level. The recorded validity period may vary depending on the mobility state / scenario of the WTRU. For example, if the WTRU is in normal mobility, the predictions provided by a given trained AI / ML model may be valid for a specific period of time. A shorter validity period may be achieved for a given trained model for a WTRU in high mobility.

[0183] In an embodiment, the network may use the validity time to decide whether a given trained AI / ML model for a WTRU should be applied or not applied to WTRUs that are in similar conditions / locations or reporting similar measurements.

[0184] In an embodiment, in the event that a given trained AI / ML model accuracy is below a configured accuracy threshold within a given validation time, the WTRU may report the maximum AI / ML model accuracy achieved to the network. The WTRU may also report a validation dataset / recorded measurements used to validate the AI / ML model. The WTRU may receive a request from the network to obtain the validation dataset / recorded measurements.

[0185] In an embodiment, if a given trained AI / ML model fails to reach a given accuracy threshold when a given validation time expires, and the WTRU is capable of performing AI / ML model training, the WTRU may indicate its AI / ML training capabilities to the network. The network may initiate a retraining process at the WTRU for the given trained AI / ML model.

[0186] Example diagram

[0187] Example use case diagram: Neighboring cell prediction

[0188] refer to Figure 4 :

[0189] The network may configure a WTRU supporting AI / ML operation to train a neighbor cell prediction model based on its mobility scenario and / or location. The network may provide a pre-trained (global) model (transfer learning) to the WTRU for model training with local measurements. The WTRU may support multiple AI / ML model configurations. Depending on the state of the WTRU, the WTRU / network may decide the AI / ML model configuration.

[0190] The WTRU may train an AI / ML model for intra-frequency / inter-frequency neighbor cell prediction (training may occur only when the WTRU is located within a given area).

[0191] Depending on the mobility scenario of the WTRU (such as low / high mobility, not at the cell edge, etc.), the trained model at the WTRU may provide different reasoning outputs (with different accuracy levels) at different points shown as points #1 and #2. At point #1, the serving cell is FR1-B, and for users with high mobility, the neighbor cell prediction may not include FR2 cells. However, for low mobility users, FR2 cells C and D may be predicted as neighbor cells. At point #2, the serving cell is FR2-E, and for users with high mobility and low mobility scenarios, the neighbor cell prediction may include FR2 cells D and F and FR1 cells C and B. The trained model at the low mobility WTRU may achieve a longer validity period for prediction based on its trained model. However, the trained model at the high mobility WTRU may support a relatively shorter validity period. The trained model at the low mobility WTRU may reach a given accuracy level faster than the high mobility WTRU, which may require a longer training period to reach a given accuracy threshold in order to provide the trained model parameters to the network.

[0192] The network may use the WTRU's trained model to predict the WTRU's neighbor cell list for the same area based on measurements from any WTRU including legacy WTRUs. The WTRU's trained model may be applicable to other WTRUs with the same / similar mobility scenarios.

[0193] AI / ML model training at the WTRU

[0194] Figure 5 An example of AI / ML model training operations at a WTRU is depicted.

[0195] refer to Figure 5, assuming that various AI / ML models may (e.g., already) be available at the WTRU. Once the WTRU receives the AI / ML training configuration, the WTRU may start logging measurements to create a training database based on the given training database configuration. Depending on the given training database configuration and / or the measurements required, the WTRU may log (e.g., immediate / current) measurements to its AI dedicated memory. Once the database size provides the given training database size as part of the training configuration, the WTRU may not log further measurements and begin AI / ML training operations. During (e.g., each) training period, the WTRU may check the accuracy threshold of the trained model. If the validation does not meet the given threshold, the WTRU may continue to perform training. During the training and validation phases, if the most recently trained model at the WTRU reaches a given accuracy threshold, the AI / ML model parameters and any parameters requested as part of the AI / ML training configuration may be provided to the network by the WTRU performing the following operations: (i) (e.g., immediately / currently) transitioning to the RRC connected state; or (ii) waiting until the WTRU receives an information request message from the network. Once the WTRU provides the trained AI / ML model parameters to the network, the network may (e.g., immediately / currently) use the trained model inference / prediction for WTRUs with similar traffic and / or mobility, etc.

[0196] AI / ML Model Validation at the WTRU

[0197] Figure 6 An example of an AI / ML model validation operation at a WTRU is depicted.

[0198] refer to Figure 6 , assuming that various AI / ML models are already available at the WTRU. Once the WTRU receives the AI / ML verification configuration, the WTRU may start performing the AI / ML verification operation. During the verification operation, the WTRU may perform inference with the selected AI / ML model and monitor the accuracy level of the inference output. If the network is not interested in the measured and predicted values, the WTRU may not record the measured and predicted values ​​during the verification process. In the case where the accuracy level of the AI / ML model inference is lower than the threshold, if the network enables the WTRU to perform training when the accuracy threshold is not reached, the WTRU may initiate AI / ML model training based on the given AI / ML configuration including verification as well as training; or the WTRU may notify the network of the achieved accuracy level by transitioning to the RRC connected state to report or waiting until the network sends a WTRU information request message.

[0199] refer to Figure 7In an embodiment, a method 700 implemented in a WTRU for training an AI / ML model with measurements of a related data set may include a step 710 of receiving a first message from a network, the first message including information indicating a configuration of measurements associated with artificial intelligence / machine learning AI / ML model training. The first message may also include information indicating a logging periodicity. In an embodiment, before receiving the first message, the method 700 may include a step of transmitting AI / ML capability information to the network. The method 700 may include a step 720 of performing measurements configured for AI / ML model training in an idle state or an inactive state. The method 700 may also include a step of selecting 730 an AI / ML model for training based on the first message; and a step 740 of training the selected AI / ML model based on the measurements performed. The measurements configured for AI / ML model training may be of the type of minimization of drive tests (MDT) measurements. In response to the accuracy level of the trained AI / ML model being above a configured accuracy threshold level or in this case, the method 700 may include a step 750 of triggering a transition to a connected state, and a step of transmitting a second message to the network, the second message including information indicating an identification of the trained selected AI / ML model and AI / ML model parameters. The accuracy level of the AI / ML model may be determined based on the measurements performed.

[0200] in conclusion

[0201] Although features and elements are provided above in specific combinations, it will be understood by those skilled in the art that each feature or element can be used alone or in any combination with other features and elements. The present disclosure is not limited in terms of the specific embodiments described in the present application, which are intended to be illustrations of various aspects. Without departing from its spirit and scope, many modifications and changes can be made, as will be apparent to those skilled in the art. Any element, action or instruction used in the description of the present application should not be interpreted as being critical or necessary to the present invention unless explicitly provided as such. In addition to those listed herein, functionally equivalent methods and devices within the scope of the present disclosure are apparent to those skilled in the art from the foregoing description. Such modifications and changes are intended to fall within the scope of the appended claims. The present disclosure is limited only by the terms of the appended claims and the full scope of equivalents given by such claims. It should be understood that the present disclosure is not limited to specific methods or systems herein.

[0202] For simplicity, the foregoing embodiments are discussed with respect to terminology and structure of devices with infrared capabilities (i.e., infrared transmitters and receivers). However, the embodiments discussed are not limited to these systems, but can be applied to other systems using other forms of electromagnetic waves or non-electromagnetic waves (such as sound waves).

[0203] It will also be understood that the terms used herein are used only for the purpose of describing specific embodiments and are not intended to be limiting. As used herein, the term "video" or the term "image" may mean any of a snapshot, a single image, and / or a plurality of images displayed over a certain time basis. As another example, when referred to herein, the term "user equipment" and its abbreviation "UE", the term "remote" and / or the term "head-mounted display" or its abbreviation "HMD" may mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of many embodiments of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities (e.g., wearable) that is configured with some or all of the structure and functionality of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities that is configured with less than all of the structure and functionality of a WTRU; or (iv) a similar device. References herein to Figures 1A to 1D Details of an example WTRU are provided, which may be representative of any WTRU set forth herein. As another example, various disclosed embodiments herein are described above and below as utilizing a head mounted display. Those skilled in the art will recognize that devices other than a head mounted display may be utilized, and some or all of the present disclosure and various disclosed embodiments may be modified accordingly without undue experimentation. Examples of such other devices may include drones or other devices configured to stream information to provide an adapted reality experience.

[0204] In addition, the methods provided herein may be implemented in a computer program, software or firmware that is incorporated into a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of non-transitory computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and digital versatile disks (DVDs), processors associated with software may be used to implement a radio frequency transceiver for a WTRU, UE, terminal, base station, RNC or any host computer.

[0205] Variations of the methods, devices, and systems provided above are possible without departing from the scope of the present invention. In view of the various embodiments that may be applied, it should be understood that the embodiments shown are merely examples and should not be considered to limit the scope of the appended claims. For example, the embodiments provided herein include handheld devices that may include or be used with any suitable voltage source (such as a battery, etc.) that provides any suitable voltage.

[0206] In addition, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices including processors are mentioned. These devices may include at least one central processing unit ("CPU") and memory. According to the practice of those skilled in the art of computer programming, references to actions and symbolic representations of operations or instructions may be performed by various CPUs and memories. Such actions and operations or instructions may be referred to as "execution," "computer execution," or "CPU execution."

[0207] Those of ordinary skill in the art will appreciate that the actions and symbolic representations of operations or instructions include manipulation of electrical signals by the CPU. The electrical system represents data bits, which may cause the final conversion or reduction of electrical signals and maintain the data bits in memory locations in the storage system, thereby reconfiguring or otherwise changing the operation of the CPU and other processing of signals. The memory locations where the data bits are maintained are physical locations having specific electrical, magnetic, optical, or organic properties that correspond to or represent the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs, and other platforms and CPUs may support the provided methods.

[0208] The data bits may also be maintained on a computer-readable medium, including a magnetic disk, an optical disk, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage system readable by a CPU. The computer-readable medium may include cooperating or interconnected computer-readable media that reside only on a processing system or distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories, and other platforms and memories may support the provided methods.

[0209] In an illustrative embodiment, any operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer-readable instructions may be executed by a processor of a mobile unit, a network element, and / or any other computing device.

[0210] There is little difference between hardware and software implementations of various aspects of the system. The use of hardware or software is usually (but not always, as in some cases, the choice of hardware or software may become important) a design choice that represents a cost-efficiency trade-off. There may be various vehicles (e.g., hardware, software, and / or firmware) with which the processes and / or systems and / or other technologies described herein can be implemented, and the preferred vehicle may change with the context in which the processes and / or systems and / or other technologies are deployed. For example, if the implementer determines that speed and accuracy are most important, then the implementer may select a primary hardware and / or firmware vehicle. If flexibility is most important, then the implementer may select a primary software implementation. Alternatively, the implementer may select some combination of hardware, software, and / or firmware.

[0211] The foregoing detailed description has been described various embodiments of the apparatus and / or process by using block diagrams, flow charts and / or examples. Insofar as such block diagrams, flow charts and / or examples include one or more functions and / or operations, it will be understood by those skilled in the art that each function and / or operation within such block diagrams, flow charts or examples can be implemented individually and / or collectively by a wide range of hardware, software, firmware or indeed any combination thereof. In an embodiment, several parts of the subject matter described herein may be implemented via an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP) and / or other integrated formats. However, those skilled in the art will recognize that all or part of some aspects of the embodiments disclosed herein may be equivalently implemented in an integrated circuit, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware or almost as any combination thereof, and according to the present disclosure, designing circuit systems and / or writing codes for software and / or firmware will be completely within the skill range of those skilled in the art. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein can be distributed as a program product in a variety of forms, and that the illustrative examples of the subject matter described herein apply regardless of the particular type of signal-bearing medium used to actually carry out the distribution. Examples of signal-bearing media include, but are not limited to, the following: recordable media such as floppy disks, hard drives, CDs, DVDs, digital tapes, computer memory, etc.; and transmission media such as digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0212] Those skilled in the art will recognize that it is common in the art to describe devices and / or processes in the manner set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system by a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system can typically include a system unit housing, a video display device, a memory such as volatile and non-volatile memory, a processor such as a microprocessor and a digital signal processor, a computing entity such as an operating system, a driver, a graphical user interface, and an application, one or more interactive devices such as a touch pad or screen, and / or a control system including a feedback loop and a control motor (e.g., feedback for sensing position and / or velocity; a control motor for moving and / or adjusting components and / or quantities). A typical data processing system can be implemented using any suitable commercially available components, such as components typically found in data computing / communication and / or network computing / communication systems.

[0213] The subject matter described herein sometimes illustrates different parts that are included in different other parts or connected with different other parts.It should be understood that the architecture of such description is only an example, and many other architectures that realize the same function can actually be implemented.In a conceptual sense, any arrangement of parts for realizing the same function is effectively "associated" so that the desired function can be realized.Therefore, any two parts that are combined to realize a specific function in this article can be regarded as "associated" with each other so that no matter how the architecture or intermediate parts realize the desired function.Similarly, any two parts that are associated in this way can also be regarded as "operably connected" or "operably coupled" to realize the desired function, and any two parts that can be associated in this way can also be regarded as "operably coupled" to realize the desired function.The specific example of operable coupling includes (but is not limited to) parts that can be matched physically and / or physically interact, and / or parts that can be wirelessly interacted and / or wirelessly interacted, and / or parts that can be logically interacted and / or parts that can be logically interacted.

[0214] With respect to the use of substantially any plural and / or singular terms herein, those skilled in the art can translate from the plural to the singular and / or from the singular to the plural where appropriate to the context and / or application. For clarity, the various singular / plural arrangements may be expressly set forth herein.

[0215] Those skilled in the art will understand that, in general, the terms used herein and particularly in the appended claims (e.g., the bodies of the appended claims) are generally intended to be "open" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "includes" should be interpreted as "including but not limited to," etc.). Those skilled in the art will further understand that if a specific number of an introduced claim statement is intended, such intent will be expressly stated in the claim, and in the absence of such a statement, such intent is not present. For example, where only one item is intended, the term "single" or similar language may be used. To aid understanding, the following appended claims and / or the description herein may include the use of the introductory phrases "at least one" and "one or more" to introduce multiple claim statements. However, the use of such phrases should not be interpreted as implying that a claim recitation introduced by the indefinite article "a" or "an" will limit any particular claim including such introduced claim recitation to embodiments including only one such recitation, even if the same claim includes the introductory phrases "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and / or "an" should be interpreted as meaning "at least one" or "one or more"). The same is true for the use of definite articles to introduce claim recitations. In addition, even if a specific number of introduced claim recitations is explicitly recited, one skilled in the art will recognize that such recitation should be interpreted as meaning at least the recited number (e.g., merely reciting "two recitations" without other modifiers means at least two recitations or two or more recitations). Furthermore, in those cases where a convention similar to “at least one of A, B, and C, etc.” is used, generally, such construction is intended to represent the convention that one skilled in the art would understand (e.g., “a system having at least one of A, B, and C” would include, but is not limited to, systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). In those cases where a convention similar to “at least one of A, B, or C, etc.” is used, generally, such meaning is intended in the sense that one skilled in the art would understand the convention (e.g., “a system having at least one of A, B, or C” would include, but is not limited to, systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). One skilled in the art would further understand that any transitional words and / or phrases (whether in the specification, claims, or drawings) that actually give two or more alternatives should be understood to contemplate the possibility of including one of the items, either of the items, or both of the items.For example, the phrase "A or B" will be understood to include the possibility of "A" or "B" or "A and B." In addition, the term "any" as used herein followed by a list of multiple items and / or categories of items is intended to include "any," "any combination," "any multiple," and / or "any combination of multiples," either alone or in combination with other items and / or other categories of items. Furthermore, the term "set," as used herein, is intended to include any number of items, including zero. Additionally, the term "number," as used herein, is intended to include any number, including zero. And the term "plurality," as used herein, is intended to be synonymous with "multiple."

[0216] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0217] As will be understood by those skilled in the art, for any and all purposes, such as in providing a written description, all ranges disclosed herein also encompass any and all possible sub-ranges and combinations of sub-ranges thereof. Any listed range can be easily identified as fully describing and capable of decomposing the same range into at least equal halves, one-third, one-quarter, one-fifth, one-tenth, etc. As a non-limiting example, each range discussed herein can be easily decomposed into a lower third, a middle third, and an upper third, etc. As will be understood by those skilled in the art, all languages ​​such as "at most", "at least", "greater than", "less than", etc. include the enumerated numbers, and refer to the ranges that can be subsequently subdivided into sub-ranges as discussed above. Finally, as will be understood by those skilled in the art, the range includes each individual member. Therefore, for example, a group with 1 to 3 units refers to a group with 1, 2 or 3 units. Similarly, a group with 1 to 5 units refers to a group with 1, 2, 3, 4 or 5 units, and so on.

[0218] Furthermore, the claims should not be read as limited to the order or elements provided unless otherwise stated. In addition, the use of the term "means for..." in any claim is intended to invoke 35 U.S.C. § 112, 6 or means-plus-function claim format, and any claim without the term "means for..." is not intended to be so.

Claims

1. A method implemented by a wireless transmit receive unit WTRU, comprising: receiving a first message from a network, the first message including information indicating configuration of measurements associated with artificial intelligence / machine learning (AI / ML) model training; Perform measurements configured for AI / ML model training in idle state; selecting an AI / ML model for training based on the first message; Training the selected AI / ML model based on the measurements performed; and In response to the accuracy level of the trained AI / ML model being higher than a configured accuracy threshold level, a transition to a connected state is triggered and a second message is transmitted to the network, the second message including information indicating an identification of the trained selected AI / ML model and AI / ML model parameters.

2. The method of claim 1, wherein the level of accuracy of the AI / ML model is determined based on measurements performed.

3. The method according to any one of claims 1 and 2, comprising: Prior to receiving the first message, AI / ML capability information is transmitted to the network.

4. The method of claim 3, wherein the AI / ML capability information comprises any of the following: available AI / ML models, accuracy levels of the AI / ML models, computing power for training and validation, and AI / ML-specific memory capacity.

5. A method according to any of the preceding claims, wherein the configuration for AI / ML model training includes information indicating any of the following items: one or more AI / ML models, AI / ML selection criteria, training data configuration, conditional recording configuration, and conditional training configuration.

6. A method according to any of the preceding claims, wherein the second message further comprises recorded measurements used to train the AI / ML model.

7. The method according to any of the preceding claims, wherein the measurements configured for AI / ML model training are of the type of Minimization of Drive Tests (MDT) measurements.

8. The method of claim 7, wherein performing MDT comprises: Recording legacy MDT measurements or skipping MDT measurement recording opportunities when one or more of the following conditions are met: (i) the AI / ML model is still in the training phase with existing recorded MDT measurement data; (ii) the trained AI / ML model is validated using current MDT measurements; or (iii) the trained AI / ML learning model reaches the configured accuracy threshold level.

9. The method according to any one of claims 7 and 8, wherein in response to the recorded MDT measurement data satisfying the training data configuration, and if the training criteria are satisfied, the method comprises: Execute training of the AI / ML model; as well as Record AI / ML model parameters.

10. A method according to any one of the preceding claims, comprising: An AI / ML model is received from the network.

11. A method according to any of the preceding claims, wherein the selection of the AI / ML model for training is based on an indication of an AI model and configured selection criteria received from the network.

12. A method according to any one of the preceding claims, wherein in response to the accuracy level of the trained model being equal to or below the configured accuracy threshold level, the method comprises: Reports the recorded measurements and the maximum trained AI / ML model accuracy level achieved during training.

13. A wireless transmit / receive unit WTRU, comprising a processor, a transceiver unit and a storage unit and configured to: receiving a first message from a network, the first message including information indicating configuration of measurements associated with artificial intelligence / machine learning (AI / ML) model training; Perform measurements configured for AI / ML model training in idle state; selecting an AI / ML model for training based on the first message; Training the selected AI / ML model based on the measurements performed; and In response to the accuracy level of the trained AI / ML model being higher than a configured accuracy threshold level, a transition to a connected state is triggered and a second message is transmitted to the network, the second message including information indicating an identification of the trained selected AI / ML model and AI / ML model parameters.

14. The WTRU of claim 13, wherein the accuracy level of the AI / ML model is determined based on measurements performed.

15. The WTRU according to any one of claims 13 and 14, configured to: Transmitting AI / ML capability information to the network.

16. The WTRU of claim 15, wherein the AI / ML capability information comprises any of: available AI / ML models, accuracy levels of the AI / ML models, computing power for training and validation, and AI / ML-specific memory capacity.

17. The WTRU according to any one of claims 13 to 16, wherein the configuration for AI / ML model training includes information indicating any one of the following items: one or more AI / ML models, AI / ML selection criteria, training data configuration, conditional recording configuration, and conditional training configuration.

18. The WTRU of any one of claims 13 to 17, wherein the second message further comprises logged measurements used to train the AI / ML model.

19. The WTRU of any one of claims 13 to 18, wherein the measurements configured for AI / ML model training are of a type of Minimization of Drive Tests (MDT) measurements.

20. The WTRU of claim 19, wherein performing MDT comprises: Recording legacy MDT measurements or skipping MDT measurement recording opportunities when one or more of the following conditions are met: (i) the AI / ML model is still in the training phase with existing recorded MDT measurement data; (ii) the trained AI / ML model is validated using current MDT measurements; or (iii) the trained AI / ML learning model reaches the configured accuracy threshold level.

21. The WTRU of any one of claims 19 and 20, configured to, in response to the logged MDT measurement data satisfying a training data configuration and if a training criterion is satisfied, to: Performing training of the AI / ML model; and Record AI / ML model parameters.

22. The WTRU according to any one of claims 13 to 21, configured to: An AI / ML model is received from the network.

23. The WTRU of any one of claims 13 to 22, wherein the selection of the AI / ML model for training is based on an indication of an AI model and configured selection criteria received from the network.

24. The WTRU of any one of claims 13 to 23, wherein in response to the accuracy level of the trained model being equal to or below the configured accuracy threshold level, the WTRU is configured to: Reports the recorded measurements and the maximum trained AI / ML model accuracy level achieved during training.

Images