Method and apparatus for distributing adaptive artificial intelligence models in wireless network

Abstract

The present disclosure relates to processes, methods, architectures, apparatuses, systems, devices, and computer program products for and / or relating to distributing adaptive artificial intelligence (AI) models in a wireless network. For example, a wireless transmit / receive unit (WTRU) is configured to transmit, to a network node, information indicating one or more capabilities of the WTRU for operating an AI model; receiving, from the network node, a first subset of adaptive AI models based on a comparison of the one or more capabilities of the WTRU and a first level of accuracy, where the adaptive AI model comprises a plurality of subsets of AI models, each subset being associated with a level of accuracy; and running a first AI model subset of the adaptive AI model.

Description

Technical Field

[0001] The present disclosure relates to processes, methods, architectures, apparatuses, systems, devices, and computer program products for and / or related to distributing adaptive artificial intelligence (AI) models in wireless networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0002] A more detailed understanding can be obtained from the following detailed description given as an example in conjunction with the accompanying drawings. Like the detailed description, the figures in this drawing are exemplary. Therefore, the figures and detailed description should not be considered limiting, and other equally effective examples are possible and desirable. In addition, like reference numerals ("reference") in the various figures ("Figures") indicate similar elements, and wherein: Figure 1A is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented; Figure 1B is a diagram illustrating an embodiment of a Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within a communication system is shown in FIG. Figure 1C is a diagram illustrating an embodiment of a Figure 1A A system diagram of an example radio access network (RAN) and an example core network (CN) used within a communication system illustrated in FIG. Figure 1D is a diagram illustrating an embodiment of a Figure 1A A system diagram of a further example RAN and a further example CN for use within the communication system illustrated in FIG. Figure 2 is a diagram illustrating the composition of several adaptive AI models; Figure 3 is a signal flow diagram illustrating signal flow for a WTRU requesting a full model from a wireless network according to a WTRU-centric embodiment; Figure 4 is a signal flow diagram illustrating signal flow for a WTRU to request adaptive loading of a model from a wireless network according to a WTRU-centric embodiment; Figure 5 is a signal flow diagram illustrating signal flow for updating an AI model at a WTRU according to a network-centric embodiment; and Figure 6 is a flow chart illustrating a representative method for requesting adaptive loading of a model from a wireless network. DETAILED DESCRIPTION

[0003] 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 put into practice without some or all of the specific details set forth herein. In other instances, well-known methods, processes, components, and circuits have not yet been described in detail to avoid obscuring the following description. Further, embodiments and examples that are not specifically described herein can be put into practice in place of or in conjunction with the embodiments and other examples described herein, disclosed, or otherwise explicitly, implicitly, and / or inherently provided (collectively, "provided").

[0004] Example Communication System Figure 1A 1 is a 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 by sharing system resources (including wireless bandwidth). 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 unique word DFT spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, filter bank multi-carrier (FBMC), etc.

[0005] like Figure 1AAs shown in FIG, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RAN 104 / 113, CN 106 / 115, public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, although 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 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 smartphone, 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 equipment and applications (e.g., remote surgery), industrial equipment 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, and 102d may be interchangeably referred to as a UE.

[0006] 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 to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a home Node B, a home eNode B, a gNB, an NR NodeB, a site controller, an access point (AP), a wireless router, and the like. Although 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.

[0007] Base station 114a may be part of 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), relay nodes, etc. Base station 114a and / or 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 a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service in a specific geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, the cell associated with base station 114a may be divided into three sectors. Thus, in one embodiment, base station 114a may include three transceivers, one for each sector of the cell. In one embodiment, base station 114a may employ multiple-input multiple-output (MIMO) technology and may use multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0008] 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, millimeter wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0009] More specifically, as noted 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, and the like. 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).

[0010] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio 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-APro).

[0011] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR radio access, which may establish the air interface 116 using New Radio (NR).

[0012] In one 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, e.g., using dual connectivity (DC) principles. Thus, the air interface utilized 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).

[0013] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi)), 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.

[0014] Figure 1AThe base station 114b in the may be, for example, a wireless router, a home Node-B, a home eNode-B, or an access point, and may utilize any suitable RAT to facilitate wireless connectivity in a local area, such as a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In another 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 a picocell or a femtocell. Figure 1A As shown in FIG, base station 114b may have a direct connection to the Internet 110. Therefore, base station 114b may not be required to access the Internet 110 via CN 106 / 115.

[0015] 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, error 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 calling, Internet connectivity, video distribution, etc., and / or perform advanced security functions, such as user authentication. Although Figure 1A Not shown, but it will be appreciated, the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs, which may employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may utilize NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0016] 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) from 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 employ the same RAT as the RAN 104 / 113 or a different RAT.

[0017] 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 WTRU 102c shown in FIG. 1 may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and the base station 114b, which may employ an IEEE 802 radio technology.

[0018] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B , 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 supply 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138. It will be appreciated that the WTRU 102 may include any subcombination of the above elements while remaining consistent with an embodiment.

[0019] 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 transceiver 120 are depicted as separate components, but it will be appreciated that the processor 118 and transceiver 120 may be integrated together in an electronic package or chip.

[0020] The transmit / receive element 122 can be configured to transmit signals to a base station (e.g., base station 114a) or receive signals from the base station via the air interface 116. For example, in one embodiment, the transmit / receive element 122 can be an antenna configured to transmit and / or receive RF signals. In one embodiment, the transmit / receive element 122 can be an emitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In another embodiment, the transmit / receive element 122 can be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 can be configured to transmit and / or receive any combination of wireless signals.

[0021] Although the transmit / receive element 122 is Figure 1B Although depicted as a single element in FIG. 1 , the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one 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.

[0022] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, for example, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11.

[0023] The processor 118 of the WTRU 102 may be coupled to 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), and may receive user input data therefrom. 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 non-removable memory 130 and / or removable memory 132. The non-removable memory 130 may include random access memory (RAM), 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, or the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0024] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control power to other components in the WTRU 102. The power source 134 may be any suitable device for powering 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.

[0025] 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 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 signals received 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.

[0026] The processor 118 may be further coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth 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. The peripheral device 138 may include one or more sensors, which may be one or more of the following: a gyroscope, an accelerometer, a Hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor, a geo-location sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0027] The WTRU 102 may include a full-duplex radio, for which transmission and reception of some or all 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., a choke) or via signal processing performed by 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, for which transmission and reception of some or all 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.

[0028] Figure 1C 1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0029] The RAN 104 may include eNode-Bs 160a, 160b, 160c, although 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 one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0030] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in uplink (UL) and / or downlink (DL), etc. Figure 1C As shown in FIG, eNode-Bs 160a, 160b, 160c may communicate with each other via an X2 interface.

[0031] Figure 1C The CN 106 shown in FIG may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. Although 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 entities other than the CN operator.

[0032] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c 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, activating / deactivating bearers, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may also provide a control plane function for facilitating switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0033] 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 downlink data is available for the WTRUs 102a, 102b, 102c, managing and storing the context of the WTRUs 102a, 102b, 102c, and the like.

[0034] 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.

[0035] 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 be in communication with, an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that serves 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.

[0036] Even though the WTRU Figures 1A to 1D Although described as a wireless terminal, it is contemplated that in certain representative embodiments such a terminal may employ (eg, temporarily or permanently) a wired communication interface with a communication network.

[0037] In a representative embodiment, the other network 112 may be a WLAN.

[0038] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have access to or an interface with a distribution system (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating from outside the BSS and destined for a STA may arrive through the AP and be delivered to the STA. Traffic from a STA to a destination outside the BSS may be sent to the AP for delivery to the corresponding destination. Traffic between STAs within a BSS may be sent through the AP, for example, where a source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent between the source and destination STAs (e.g., directly between them) using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled 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.

[0039] When using 802.11ac infrastructure operation mode or a similar operation mode, the AP can transmit 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 the 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 with 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 channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA can back off. One STA (e.g., only one station) can transmit at any given time in a given BSS.

[0040] High throughput (HT) STAs may communicate using a 40 MHz wide channel, for example, via a primary 20 MHz channel combined with adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0041] Very high throughput (VHT) STAs can support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. 40 MHz and / or 80 MHz channels can be formed by combining consecutive 20 MHz channels. A 160 MHz channel can be formed by combining eight consecutive 20 MHz channels or by combining two non-contiguous 80 MHz channels (which can be referred to as an 80+80 configuration). For the 80+80 configuration, after channel coding, the data can be passed through a segment parser that can divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time domain processing can be performed separately on each stream. The streams can be mapped onto two 80 MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above operations for the 80+80 configuration can be reversed, and the combined data can be sent to the media access control (MAC).

[0042] The operating mode below 1 GHz is supported by 802.11af and 802.11ah. The channel operating bandwidth and carrier are reduced in 802.11af and 802.11ah relative to the channel operating bandwidth and carrier used in 802.11n and 802.11ac. 802.11af supports 5 MHz bandwidth, 10 MHz bandwidth and 20 MHz bandwidth in the TV White Space (TVWS) spectrum, and 802.11ah supports 1 MHz bandwidth, 2 MHz bandwidth, 4 MHz bandwidth, 8 MHz bandwidth and 16 MHz bandwidth using non-TVWS spectrum. According to a representative embodiment, 802.11ah can support meter type control / machine type communication, such as MTC devices in macro coverage areas. 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 whose battery life is above a threshold (e.g., to maintain very long battery life).

[0043] WLAN systems that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) include a channel that can be designated as a primary channel. The primary channel can have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be set and / or limited by the STA that supports the smallest bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for a STA that supports (e.g., only supports) a 1 MHz mode (e.g., an MTC-type device), the primary channel can be 1 MHz wide, even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings can depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which only supports the 1 MHz operating mode) transmitting to the AP, the entire available frequency band may be considered busy, even if most of the frequency band is still idle and may be available.

[0044] In the United States, 802.11ah can use the available frequency band from 902 MHz to 928 MHz. In South Korea, the available frequency band is from 917.5 MHz to 923.5 MHz. In Japan, the available frequency band is from 916.5 MHz to 927.5 MHz. Depending on the country code, the total available bandwidth for 802.11ah ranges from 6 MHz to 26 MHz.

[0045] Figure 1D 1 is a system diagram illustrating the RAN 113 and the CN 115 in accordance with an embodiment. As noted 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.

[0046] The RAN 113 may include gNBs 180a, 180b, 180c, although 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 one 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 gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a. In one embodiment, the gNBs 180a, 180b, and 180c may implement carrier aggregation techniques. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum, while the remaining component carriers may be on licensed spectrum. In one embodiment, the gNBs 180a, 180b, and 180c may implement coordinated multi-point (CoMP) techniques. For example, the WTRU 102a may receive coordinated transmissions from the gNB 180a and gNB 180b (and / or gNB 180c).

[0047] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable numerology. 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., containing different numbers of OFDM symbols and / or lasting for different lengths of absolute time).

[0048] 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 another RAN (e.g., such as the eNode-Bs 160a, 160b, 160c). In a standalone configuration, the WTRUs 102a, 102b, 102c may utilize 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 WTRUs 102a, 102b, 102c may communicate / connect to the gNBs 180a, 180b, 180c while also communicating / connecting to another RAN, such as the eNode-Bs 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement DC principles 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-Bs 160a, 160b, 160c may serve as mobility anchors for the WTRUs 102a, 102b, 102c and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput to serve the WTRUs 102a, 102b, 102c.

[0049] Each of the gNBs 180a, 180b, 180c may be associated with a specific cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in uplink (UL) and / or downlink (DL), support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, etc. Figure 1D As shown in , gNBs 180a, 180b, and 180c can communicate with each other via the Xn interface.

[0050] Figure 1DThe CN 115 shown in FIG may include at least one AMF 182 a, 182 b, at least one UPF 184 a, 184 b, at least one Session Management Function (SMF) 183 a, 183 b, and possibly a Data Network (DN) 185 a, 185 b. Although each of the aforementioned elements is depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by entities other than the CN operator.

[0051] 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 act as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, supporting network slicing (e.g., handling different PDU sessions with different requirements), selecting a specific SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. Network slicing may be used by the AMF 182a, 182b to customize CN support for the WTRUs 102a, 102b, 102c based on the type of services utilized by the WTRUs 102a, 102b, 102c. 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 machine type communication (MTC) access, etc. The AMF 182 a, 182 b may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies, such as WiFi.

[0052] The SMFs 183a and 183b can connect to the AMFs 182a and 182b in the CN 115 via the N11 interface. The SMFs 183a and 183b can also connect to the UPFs 184a and 184b in the CN 115 via the N4 interface. The SMFs 183a and 183b can select and control the UPFs 184a and 184b and configure traffic routing through the UPFs 184a and 184b. The SMFs 183a and 183b can perform other functions, such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing downlink data notifications. The PDU session type can be IP-based, non-IP-based, Ethernet-based, and so on.

[0053] The UPFs 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N3 interface. These gNBs 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 UPFs 184a, 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.

[0054] 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) that acts as an interface between the CN 115 and the PSTN 108. Additionally, 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 one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local data network (DN) 185a, 185b through the UPF 184a, 184b via an N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0055] Given that Figures 1A to 1D as well as Figures 1A to 1D

[0066] As described herein, one or more or all of the functionality described herein with respect to one or more of the following may be performed by one or more emulated devices (not shown) : the WTRUs 102a-d, base stations 114a-b, eNode-Bs 160a-c, MMEs 162, SGWs 164, PGWs 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other device(s) described herein. The emulated devices may be one or more devices configured to emulate one or more or all of the functionality described herein. For example, the emulated devices may be used to test other devices and / or simulate network and / or WTRU functionality.

[0056] The simulation device can be designed to implement one or more tests of other devices in a laboratory environment and / or in an operator network environment. For example, the one or more simulation devices can perform one or more or all functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more simulation devices can perform one or more or all functions while being 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.

[0057] The one or more simulation devices can perform one or more (including all) functions without being implemented / deployed as a part of a wired and / or wireless communication network. For example, the simulation device can be used in a test scenario in a test lab and / or in a non-deployed (e.g., test) wired and / or wireless communication network to realize the test of one or more components. The one or more simulation devices can be test equipment. The direct RF coupling and / or wireless communication carried out via RF circuits (e.g., which can include one or more antennas) can be used by the simulation device to transmit and / or receive data.

[0058] AI Deployment in Wireless Networks When neural networks (models) are run on WTRU devices in a wireless network (e.g., cellular), these neural networks may be delivered to the WTRU from a model repository in the wireless network. The wireless network may aim to deliver neural networks that match the resources available on the WTRU (WTRU capabilities) and the application requirements, for example, in terms of accuracy level. In the 3GPPAIML (artificial intelligence / machine learning) initiative, the network may deliver models to the WTRU, thereby selecting the model that best matches the current environmental conditions.

[0059] When available WTRU capabilities and / or application requirements change, the neural model currently used by the WTRU may no longer be the best choice and may even require resources above the current WTRU capabilities. In this case, a new, more suitable model may be delivered by the network from the model repository.

[0060] Adaptive Neural Networks An adaptive neural network is one or more neural networks that can be constructed from subsets of a set of building blocks. For example, several classes of adaptive neural networks correspond to models that can be described as sequences of subsets from 1 to n. Any sequence of subsets from 1 to k can be combined to create a functional neural network capable of performing a task. Typically, the computation, memory, energy requirements, and / or accuracy of the network increase with k. As another example, an adaptive neural network can also be a network that shares the same initial performance level. Thus, the end of the neural network can be changed based on the task, or multiple ends can reuse computations from the same initial level to more efficiently solve different tasks.

[0061] Figure 2 The diagram illustrates how different adaptation model compositions and the adapted performance level N+1 (shown in hatching) sent to the WTRU operates on top of the existing level N (shown in green). Figure 2 In

[15] , the level of inference latency can be proportional to the length of the arrow. The quality of the result can be proportional to the thickness of the arrow. The shape of the arrow indicates whether the output is (1) an intermediate or result output (represented by a solid line) or (2) intermediate data whose only purpose is to feed the next level (represented by a dashed line). The length of the vertical arrow indicates the memory usage (the amount of memory). When there are two or more different vertical arrows in a particular model, it means that the processes of running Mn and then Mn+Mn+1 are independent.

[0062] First refer to Figure 2 , there are models where when the WTRU receives a new model subset that is not stackable, the model needs to be rebuilt at the WTRU. In this type of update, the update of the model cannot be performed by stacking additional neural network layers on top of pre-existing layers, but rather the model must be rebuilt in its entirety. Unlike prunable / prunable models (where updates add neurons to neural layers, making them larger) or multi-precision quantized models (where updates provide additional bits for network weights), in this type of update, when M2 is received after M0, M1, the new model must be rebuilt in its entirety from the M0, M1, M2 subset.

[0063] For multi-precision models, the neural network is the same but with different quantization model parameters N or N + 1. Either (1) the quantization model of subset N + 1 is recompiled from subset N with different quantization parameters from subset N + 1, or (2) the new quantization parameters replace the entire previous quantization value.

[0064] Regarding the pruned model, the model network of subset N+1 contains the model network of subset N. The pruned model of subset N+1 is recompiled from subset N and the additional neurons from subset N+1.

[0065] Now refer to Figure 2 In the scalable model shown in the lower left portion of FIG, M0, M1, and M2 are stackable in memory, where each subset provides outputs / intermediate results, e.g., with an increased quality level. An example of a scalable model may be a so-called "early exit model," where the network includes an exit point before reaching the final output that generates intermediate predictions / results.

[0066] Now refer to Figure 2 These are models defined using independent model tasks, where model M1 takes input from model M0 for the purpose of improving the resulting output of model M0. For example, model M0 may be a neural network that determines whether a detected object in an image is a dog, while neural network model M1 determines the type of dog (e.g., golden retriever).

[0067] Now refer to Figure 2 In the pyramid model shown in the lower right part of FIG, specialized models M0, M1 or M0, M1' are stackable in memory, but are adapted for different device capabilities (e.g., memory usage), power consumption, energy, or tasks. New corresponding subsets M2, M2 will be stackable on M1, M1' respectively.

[0068] In the 3GPP AIML initiative, the wireless network can select the model that best matches the current environmental conditions and deliver it to the WTRU. When the environment changes, an update may be required to meet the new conditions. Updating a brand new model by downloading and / or loading a new, different model into memory may be costly in terms of time, energy, and / or bandwidth, even if the model is compressed. In addition, model updates may require establishing or maintaining a delivery session between the WTRU and the wireless network. Depending on the WTRU's location and current network conditions, updating the model may not always be feasible.

[0069] The following discloses methods and apparatus for a wireless network to provide an adaptive model adapted for a WTRU, wherein the adaptive model corresponds to a model composed of subsets with increasing levels of model performance (e.g., accuracy), possibly corresponding to the need for increasing levels of WTRU capabilities. The WTRU may send the network the adaptive model level requirements that meet different WTRU capabilities. The wireless network may transmit a general AI model description to the WTRU, including the model composition, the adaptive model type, and information for the WTRU to handle the adaptive model.

[0070] In a first set of WTRU-centric embodiments, the WTRU provides a set of different adaptation model requirements, such as performance levels (80, 90, 95% accuracy), different adaptation WTRU capability levels (X, Y, Z floating-point operations per second), and / or component types (scalable models). The wireless network begins a learning process targeting the different WTRU requirements or identifies an adaptation model that matches them as best as possible. The network may send one or several adaptation model components back to the WTRU.

[0071] In some embodiments, the WTRU may select a model and model level. The WTRU may request download of the entire model component or a subset of the adaptive portion corresponding to its current performance and capability requirements. As conditions change, the WTRU may locally select and adjust the correct level for inference, including directly loading and running another subset of the levels for inference. If necessary, it may request download of the remaining adaptive model levels from the network.

[0072] Alternatively, the WTRU may prefer to select an adaptive loading mode where it can select the model composition and request a per-level download of a subset of model levels. The network may adapt the recommendations for each model level subset on the fly.

[0073] In a second subset of network-centric embodiments, the WTRU may provide the wireless network with its current capabilities that may be assigned to a model. The wireless network may calculate and select the adapted model and recommended level that best matches the corresponding WTRU capabilities and current environmental conditions. The wireless network may assist the WTRU by sending a recommendation to the WTRU to infer (i.e., execute or run) the adapted model in whole or in part up to the optimal level. The WTRU may request and download all or part of the model. As conditions change, the wireless network may send recommendations to increase or decrease the level. The network may continuously monitor the WTRU capabilities and other environmental conditions and send recommendations when a change in such conditions is detected.

[0074] Scalable AI model encoding features The scalable adapted model may include a model composition with an increasing range of adaptive coding feature levels (levels 1 to n), where each adaptation level may be optimized for a specific set of criteria. A non-exhaustive list of potential criteria may include any of the criteria described below.

[0075] A non-exhaustive list of potential criteria may include performance levels such as any one or combination of the following: model accuracy; model precision; model recall; mean squared error; and absolute error.

[0076] A non-exhaustive list of potential criteria may include adaptive model types such as any one or combination of the following: - Scalable: Subset level N+1 can run on top of subset level N. - Specialization: The output of subset level N can feed subset N+1 or another subset N'+1. -Multi-precision model: The model graph and its internal components remain unchanged, but each level N or N+1 has different quantized model parameters N or N+1 respectively. -Pruned model: The model network of subset N+1 contains the model network of subset N.

[0077] A non-exhaustive list of potential criteria may include (eg, required) WTRU capability levels, such as any one or combination of: computing power; memory; energy; and model computation latency.

[0078] A non-exhaustive list of potential criteria may include required network bandwidth, for example, network latency.

[0079] A WTRU-centric request process according to some embodiments may involve one or more messages between the WTRU and the wireless network and operations performed at the WTRU or the wireless network, such as any of the following: the WTRU may provide information to the network about its different capability levels, such as energy, computing power, memory capacity, and possibly a current capability model to be downloaded.

[0080] The network may already be processing the adaptive training model, or may start training the adaptive model based on WTRU requirements, which include several ranges of WTRU capabilities.

[0081] The network may return to the WTRU the adaptation model composition that best suits the different adaptation level requests. The WTRU may trigger the network to train new adaptation models that meet different WTRU capability levels. The network may directly initiate a delivery session for the model that corresponds to the current WTRU capability.

[0082] If the network does not initiate the delivery, the WTRU may request download of all or part of the model components.

[0083] The WTRU may select a subset of models corresponding to its resources that are available or allocated to the AIML application.

[0084] When conditions change, the WTRU may select the portion of the model that corresponds to the requirements. If the WTRU has not yet downloaded the upper subset or if the model is a monolithic structure, it may first download the model before inference (i.e., before executing the AI ​​model).

[0085] The WTRU may dynamically process the remaining parts of the model to obtain the output results.

[0086] The WTRU may infer (i.e., perform) a first model subset before requesting a second model subset from the network. The request for the second model subset may depend on the inference result of the first model subset. For example, the WTRU may request a specialized subset or a new ad hoc subset along with transmitting updated WTRU capabilities or environmental conditions.

[0087] Figure 3 is a signal flow diagram illustrating the signal flow for a WTRU to request a full model from a wireless network in accordance with a WTRU-centric embodiment.

[0088] Step 3.1 represents the initial service announcement and provision of the AI / ML service with scalable model composition.

[0089] In step 3.2, the AI ​​application 303 at the WTRU 301 may select an AI model service.

[0090] In step 3.3, the AI ​​application 303 may trigger the AI ​​model session handler 305 to start. The AI ​​application 303 may provide application-level WTRU capabilities, such as battery status, computing power resources, and memory available to the AI ​​model session handler 305. The AI ​​application may provide a set of different adaptive model level requirements, such as different performance levels (e.g., 80%, 90%, 95% accuracy) or different adaptive WTRU capability levels (X, Y, Z floating-point operations per second) and desired composition type (scalable model).

[0091] In step 3.4, the AI ​​model session handler 305 may transmit a model service information request to the wireless network 302, for example, to the AI ​​model AS (application server) 311. This message may transmit the current WTRU capabilities related to the model to the network 302. It may request the full model.

[0092] In step 3.5, the wireless network (eg, AI Application Function (AF)) may calculate the best adapted model for the WTRU's capabilities and conditions.

[0093] In step 3.6, the network may provide the WTRU with the adapted model, including the WTRU capabilities associated with the level of the adapted model. This may include information such as any of the following: A general AI model description, such as the type of adaptive model. This may include information such as any of the following: A level description, such as describing one or more requested capabilities and / or one or more result accuracies. For example, - Level 1, requested capabilities, result accuracy. - Level 2: Requested capabilities, result accuracy. - Level 3: Requested capabilities, result accuracy.

[0094] In step 3.7, the AI ​​model session handler 305 may trigger the inference engine 307 to start a session for downloading the model from the network.

[0095] In step 3.8, the inference engine 307 may establish a transmission session with the wireless network.

[0096] In step 3.9, the inference engine may send a request for AI model download.

[0097] In step 3.10, the network may send WTRU initialization information.

[0098] In step 3.11, the inference engine can configure the loading process.

[0099] In step 3.12, the inference engine may download the full model from the wireless network.

[0100] In step 3.13, the inference engine 307 may notify the AI ​​model session handler 305 of the transmission session information and AI model content-related information.

[0101] In step 3.14, the AI ​​model session handler 305 may select a model level by comparing the WTRU capabilities provided by the AI ​​application 303 with the level description of the adapted model information received from the network.

[0102] In step 3.15, the AI ​​model session handler may trigger the inference engine to infer for the new model level.

[0103] In step 3.16, the inference engine 307 may run the model at the selected level.

[0104] In step 3.17, the AI ​​application 303 may trigger the AI ​​model session handler 305 to update. In this message, the AI ​​application may provide application-level WTRU capabilities such as battery status, computing power resources, and available memory. The selection module may be part of the AI ​​model session handler 305.

[0105] In step 3.18, the AI ​​model session handler 305 may select a new model level.

[0106] In step 3.19, the AI ​​model session handler can trigger inference for the new model level.

[0107] In step 3.20, the inference engine 307 may run the model at the selected level.

[0108] In another embodiment, the network may propose a different model alternative than the recommended solution (in step 3.6). In this case, the AI ​​model session handler 305 may trigger the AI ​​application 303 with the set of adaptive models. In turn, the AI ​​application 303 may send the selected model back to the AI ​​model session handler 305. The AI ​​model session handler 305 may select the level of operation for the model.

[0109] Figure 4 is a signal flow diagram illustrating the signal flow for a WTRU to request adaptive loading of a model from a wireless network in accordance with a WTRU-centric embodiment.

[0110] Steps 4.1 to 4.3 can be combined with Figure 3 Steps 3.1 to 3.3 are essentially the same.

[0111] In step 4.3, the AI ​​application 403 may have provided a set of different adaptive model level requirements for the adaptive model, such as different performance levels (80%, 90%, 95% accuracy) or different adaptive WTRU capability levels (X, Y, Z floating-point operations per second).

[0112] In step 4.4, the AI ​​model session handler 405 may transmit a model service information request to the wireless network 402. This message conveys to the network 402 the current WTRU capabilities related to the model and the adaptive model level requirements received from the AI ​​application.

[0113] In step 4.5, the wireless network (eg, AI AF 409) calculates the best adapted model for the WTRU capabilities and conditions.

[0114] In step 4.6, the network provides the WTRU with the adapted model, including the WTRU capabilities associated with the level of the adapted model. This may include information such as a general AI model description, such as the adaptive model type. This may include information such as a recommended model (optional), such as describing one or more requested capabilities and / or one or more result accuracy. For example, Level 1: Requested capabilities, result accuracy. This may include information such as a level description, such as describing one or more requested capabilities and / or one or more result accuracy. For example, - Level 1, requested capabilities, result accuracy. - Level 2: Requested capabilities, result accuracy. - Level 3: Requested capabilities, result accuracy.

[0115] In step 4.7, the AI ​​model session handler 405 may select a model level by comparing the WTRU capabilities provided by the AI ​​application 403 with the level description of the adapted model information received from the network.

[0116] In step 4.8, the AI ​​model session handler 405 may trigger the inference engine to start a session for downloading the recommended model from the network.

[0117] In step 4.9, the inference engine 407 may establish a transmission session with the wireless network.

[0118] In step 4.10, the inference engine 407 may send a request for the progressive download content.

[0119] In step 4.11, the network may send WTRU initialization information.

[0120] In step 4.12, the inference engine can configure the loading process.

[0121] In step 4.13, the inference engine may download the model content up to the selected level.

[0122] In step 4.14, the inference engine 403 may notify the AI ​​model session handler 405 of the transmission session information and AI model content-related information.

[0123] In step 4.15, the inference engine 407 may run the model at the selected level.

[0124] In step 4.16, the AI ​​application 403 continuously monitors the condition of the WTRU.

[0125] In step 4.17, the AI ​​application 403 may trigger the AI ​​model session handler 405 to update. The AI ​​application may provide application-level WTRU capabilities such as battery status, computing power resources, and available memory in the message. The selection module may be part of the AI ​​model session handler 405.

[0126] In step 4.18, the AI ​​model session handler 405 may select a new model level.

[0127] In step 4.19, if the model level is greater than the level of the existing running model, the AI ​​model session handler 405 may trigger the inference engine 407 to download the remaining subsets up to the selected level.

[0128] In step 4.20, the inference engine 407 may establish a transport session with the network.

[0129] In step 4.21, the inference engine 407 may send a request for the progressive download content.

[0130] In step 4.22, the network may transmit initialization information to the WTRU.

[0131] In step 4.23, the inference engine 407 may notify the AI ​​model session handler 405 and provide the transmission session information and AI model content related information.

[0132] In step 4.24, the inference engine 407 may configure the loading process.

[0133] In step 4.25, the inference engine may download model content from the current level to the newly selected level.

[0134] In step 4.26, the inference engine 407 may notify the AI ​​model session handler 405 of the transmission session information and AI model content-related information.

[0135] In step 4.27, the inference engine 407 may run the model up to the selected level.

[0136] like Figure 4 As shown at the bottom of , if it is determined that the new model level is lower than the existing running model, then in step 4.19, the AI ​​model session handler 405 can instead trigger the inference engine 407 to run inference up to the new lower selected level, all steps 4.20-4.26 are omitted (this is because downloading of model information is unnecessary), and step 4.27 is replaced by the step 4.27 alternative, in which the inference engine 407 can run the model up to the new lower selected level.

[0137] In a network-centric embodiment, the WTRU may provide its current capabilities related to the model to the network, and the network may calculate and select the best adapted model for the WTRU's capabilities. The network may indicate to the WTRU which level of adapted model the WTRU may use based on environmental conditions and WTRU capability monitoring. The network may provide the WTRU with a list of WTRU capabilities corresponding to the level of adapted model.

[0138] If the WTRU has sufficient memory, the network may provide the entire model to the WTRU, although now the WTRU may indicate to the network to send a portion of the model if current conditions do not allow for receiving the entire model.

[0139] For example, the network may transmit a subset of models up to a level corresponding to the current WTRU capabilities, and then transmit the remaining subsets of models at higher levels as the WTRU capabilities increase.

[0140] When conditions change at the WTRU, the WTRU may notify the network.

[0141] In response, the network may select and indicate to the WTRU which subset of models (ie, level) to stop at.

[0142] If the WTRU does not have the necessary model subset in memory (typically, this condition will exist when the WTRU reports to the network that its capabilities have increased), the network may transmit to the WTRU the remaining adapted model subset(s) that best suit the new conditions.

[0143] The WTRU may run the remainder of the model to obtain output results, or may run the model up to a level indicated by the network, such as level 1 instead of the full model.

[0144] Figure 5 is a signal flow diagram illustrating the signal flow for updating an AI model at a WTRU according to a network-centric embodiment.

[0145] Step 5.1 represents the initial service announcement and provision of the AI / ML service with scalable model composition.

[0146] In step 5.2, the AI ​​application 503 may select an AI model service.

[0147] In step 5.3, the AI ​​application 503 may trigger the AI ​​model session handler 505 to start. The AI ​​application 301 may provide application-level WTRU capabilities, such as battery status, computing power resources, and available memory. The AI ​​application may provide a set of different adaptive model level requirements, such as a required minimum performance (e.g., 80% for the first level) and other desired progressive performance levels (85%, 90%, 95% accuracy).

[0148] In step 5.4, the AI ​​model session handler 505 may transmit a model service information request to the wireless network 502, for example, to the AI / ML model AS 511. This message may convey the current WTRU capabilities related to the model to the network 502.

[0149] In step 5.5, the wireless network (eg, AI / ML AF 509) may select the best-fit model corresponding to the WTRU capabilities and conditions.

[0150] In step 5.6, the network provides the WTRU with a description of the adapted model, including the WTRU capabilities associated with the level of the adapted model. This may include information such as a general AI model description, such as the adaptive model type. This may include information such as the recommended model, such as a description of one or more requested capabilities and / or one or more result accuracy. For example, Level 1: Requested capabilities, result accuracy. This may include information such as a level description, such as a description of one or more requested capabilities and / or one or more result accuracy. For example, - Level 1, requested capabilities, result accuracy. - Level 2: Requested capabilities, result accuracy. - Level 3: Requested capabilities, result accuracy.

[0151] In step 5.7, the AI ​​model session handler 505 may trigger the inference engine 407 to start the session.

[0152] In step 5.8, the inference engine 507 may establish a transmission session with the wireless network.

[0153] In step 5.9, the inference engine may send a request for the progressively downloaded content.

[0154] In step 5.10, the network may send WTRU initialization information.

[0155] In step 5.11, the inference engine can configure the loading process.

[0156] In step 5.12, the inference engine 507 may notify the AI ​​model session handler 505 of the transmission session information and AI model content-related information.

[0157] In step 5.13, the inference engine can download the model from the server.

[0158] In step 5.14, the inference engine may run the model up to the selected level.

[0159] In step 5.15, the AI ​​application 503 may trigger the AI ​​model session handler 505 to update. The AI ​​application may provide new application level WTRU capabilities such as battery status, computing power resources, and available memory.

[0160] In step 5.16, the AI ​​Model Session Handler provides a Model Service Information Request to the network. This message conveys the current WTRU capabilities related to the model to the network.

[0161] In step 5.17, the network provides the WTRU with a description of the adapted model, including the WTRU capabilities associated with the level of the adapted model. This may include information such as a general AI model description, such as the adaptive model type. This may include information such as the recommended model (optional), such as a description of one or more requested capabilities and / or one or more result accuracy. For example, Level 2: Requested capabilities, result accuracy. This may include information such as a level description, such as a description of one or more requested capabilities and / or one or more result accuracy. For example, - Level 1, requested capabilities, result accuracy. - Level 2: Requested capabilities, result accuracy. - Level 3: Requested capabilities, result accuracy.

[0162] If the WTRU capability increases, the network selects the description of the remaining adapted model subset that best suits the new conditions and may transmit this description to the WTRU if necessary. If the WTRU capability decreases, the network indicates to the WTRU which model subset to stop at.

[0163] In step 5.18, if the level of the AI ​​model is increased, the AI ​​model session handler 505 can trigger the inference engine 507 to download the remaining model parts. If the level is decreased, then steps 18 and 19 are not necessary.

[0164] In step 5.19, the inference engine 507 may download the remaining model parts from the server.

[0165] In step 5.20, the inference engine may run the model up to the selected level.

[0166] WTRU subscription with network capability monitoring As an alternative to the previous embodiment, the network may continuously monitor environmental conditions and the capabilities of the WTRU.

[0167] The WTRU may subscribe to obtain the best-fit model from the network, including increasing or decreasing the level of an already selected AI model.

[0168] Thus, as such conditions and / or capabilities change, the network may inform the WTRU of the best adapted model and model level. The network may assist the WTRU and send a recommendation to the WTRU to run all or part of the adapted model up to the optimal level.

[0169] If the WTRU does not have all AI model subsets, the WTRU will download the remaining adapted model parts.

[0170] Figure 6 is a flow chart illustrating a representative method 600 implemented by a WTRU. Figure 6 , the representative method 600 may include, at block 610, transmitting information indicating one or more capabilities of the WTRU to run an AI model to a network node.

[0171] At block 620, the representative method 600 may include receiving, from a network node, a first AI model subset of an adaptive AI model based on a comparison of the one or more capabilities of the WTRU and the first level of accuracy, wherein the adaptive AI model may include a plurality of AI model subsets, each subset associated with a level of accuracy.

[0172] At block 630 , the representative method 600 may include running a first subset of the adaptive AI models.

[0173] In certain representative embodiments, the representative method 600 may include any of the following steps: receiving, from a network node, AI model information associated with a plurality of adaptive AI models based on the one or more capabilities, wherein each adaptive AI model in the plurality of adaptive AI models includes a plurality of AI model subsets, and wherein each AI model subset is associated with an accuracy level; selecting an adaptive AI model from the plurality of adaptive AI models, e.g., based on a first accuracy level; and transmitting, to the network node, a request to receive a first AI model subset of the adaptive AI models.

[0174] In certain representative embodiments, the one or more capabilities of the WTRU include any of: a battery status at the WTRU, computing power resources at the WTRU, and available memory at the WTRU.

[0175] In certain representative embodiments, the representative method 600 may include any of the following steps: receiving a second AI model subset of the adaptive AI model from the network node based on a comparison of the one or more capabilities of the WTRU and the second accuracy level, wherein the second accuracy model is higher than the first accuracy level; and running the second AI model subset of the adaptive AI model.

[0176] In certain representative embodiments, the representative method 600 may include sending a request to receive a second subset of AI models based on a change in the one or more capabilities of the WTRU.

[0177] In certain representative embodiments, the representative method 600 may include any of the following steps: determining an improvement in the one or more capabilities of the WTRU; and running a second AI model subset of the adaptive AI model.

[0178] In certain representative embodiments, the representative method 600 may include any of the following steps: determining a reduction in the one or more capabilities of the WTRU; and running a first AI model subset of the adaptive AI model.

[0179] Although features and elements are provided above in specific combinations, it will be appreciated 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 this application, which are intended to be illustrative of various aspects. Many modifications and variations can be made without departing from its spirit and scope, which will be obvious to those skilled in the art. None of the elements, actions or instructions used in the specification of this application should be understood as being essential or essential to the present invention unless so explicitly stated. In addition to those listed herein, functionally equivalent methods and devices within the scope of the present disclosure will be obvious to those skilled in the art from the description above. Such modifications and variations 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 to which such claims are entitled. It should be understood that the present disclosure is not limited to a particular method or system.

[0180] For simplicity, the above embodiments are discussed with respect to the terminology and structure of infrared-enabled devices (i.e., infrared transmitters and receivers). However, the embodiments discussed are not limited to these systems, but can be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves (such as sound waves).

[0181] It should also be understood that the terms used herein are used only to describe specific embodiments and are not intended to be limiting. As used herein, the term "video" or the term "imagery" may mean any of a snapshot, a single image, and / or a plurality of images displayed on a 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 wirelessly enabled and / or wired enabled device (e.g., shareable via a mobile phone) configured with, among other things, some or all of the structure and functionality of a WTRU; (iii) a wirelessly enabled and / or wired enabled device configured with less than all of the structure and functionality of a WTRU; (iv) and the like. This document is about Figures 1A to 1DDetails are provided for an example WTRU that can represent any WTRU described herein. As another example, various disclosed embodiments are described above and below herein as utilizing a head-mounted display. Those skilled in the art will appreciate that devices other than head-mounted displays can be utilized and that some or all of the present disclosure and various disclosed embodiments can 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.

[0182] In addition, the method provided herein can be incorporated into a computer program, software or firmware for a computer or processor to perform. The example of a computer readable medium includes an electronic signal (transmitted by a wired or wireless connection) and a computer readable storage medium. The example of a computer readable storage medium includes but is not limited to a read-only memory (ROM), a random access memory (RAM), a register, a cache memory, a semiconductor memory device, a magnetic medium (such as an internal hard disk and a removable disk), a magneto-optical medium and an optical medium (such as a CD-ROM disk and a digital versatile disk (DVD)). The processor associated with the software can be used to implement a radio frequency transceiver for WTRU, UE, terminal, base station, RNC, MME, EPC, AMF or any host computer.

[0183] Variations of the methods, devices, and systems provided above are possible without departing from the scope of the present invention. In view of the wide variety of embodiments that can be applied, it should be understood that the illustrated embodiments are merely examples and should not be considered as limiting the scope of the appended claims. For example, the embodiments provided herein include handheld devices that can include or be utilized with any suitable voltage source (such as a battery, etc.) to provide any suitable voltage.

[0184] 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, reference to the symbolic representation of actions and operations or instructions can be performed by various CPUs and memories. Such actions and operations or instructions can be referred to as "being executed," "being executed by a computer," or "being executed by a CPU."

[0185] Those skilled in the art will appreciate that actions and symbolically represented operations or instructions comprise manipulation of electrical signals by the CPU. The electrical system represents data bits, which can result in a resulting transformation or reduction of the electrical signal and maintain the data bits at memory locations in the memory system, thereby reconfiguring or otherwise changing the operation of the CPU, as well as other processing of the signal. The memory location where the data bits are maintained is a physical location having specific electrical, magnetic, optical, or organic properties corresponding to or representing the data bits. It should be understood that the embodiments are not limited to the platforms or CPUs mentioned above, and other platforms and CPUs may support the provided methods.

[0186] The data bits may also be maintained on computer-readable media, including magnetic disks, optical disks, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage systems that can be read by a CPU. The computer-readable media may include cooperating or interconnected computer-readable media that reside exclusively on the 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 memories mentioned above, and other platforms and memories may support the provided methods.

[0187] 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.

[0188] There is little distinction between hardware and software implementations of aspects of the system. The use of hardware or software is typically (but not always, as the choice between hardware and software may become important in certain contexts) a design choice that represents a cost versus efficiency trade-off. There may be a variety of vehicles by which the processes and / or systems and / or other technologies described herein can be implemented (e.g., hardware, software, and / or firmware), and the preferred vehicle may vary with the context in which the processes and / or systems and / or other technologies are deployed. For example, if an implementer determines that speed and accuracy are most important, the implementer may select a primarily hardware and / or firmware vehicle. If flexibility is most important, the implementer may select a primarily software implementation. Alternatively, the implementer may select some combination of hardware, software, and / or firmware.

[0189] The above detailed description has been described using block diagrams, flow charts and / or examples to illustrate various embodiments of the device and / or process. Since such block diagrams, flow charts and / or examples include one or more functions and / or operations, those skilled in the art will understand that each function and / or operation within such block diagrams, flow charts or examples can be implemented individually and / or collectively by a variety of hardware, software, firmware or almost any combination thereof. In one embodiment, several portions of the subject matter described herein can 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 some aspects of the embodiments disclosed herein can be equivalently implemented in whole or in part in an integrated circuit as one or more computer programs running on one or more computers (e.g., implemented 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., implemented as one or more programs running on one or more microprocessors), as firmware or almost any combination thereof, and in view of the present disclosure, designing circuits and / or writing code for software and / or firmware will be well within the skills 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 embodiments of the subject matter described herein are applicable regardless of the particular type of signal-bearing medium used to actually implement 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 memories, and the like; and transmission media such as digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, and the like).

[0190] 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 subsequently 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 data processing systems via a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system can typically include one or more of the following: 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 touchpad or screen) and / or a control system including a feedback loop and a control motor (e.g., feedback for sensing position and / or speed, a control motor for moving and / or adjusting components and / or quantity). A typical data processing system can be implemented using any suitable commercially available component, such as those components typically found in data computing / communication and / or network computing / communication systems.

[0191] The subject matter described herein sometimes illustrates different components that are included in or connected to different other components. It should be understood that this depicted architecture is merely an example, and in fact, many other architectures that implement the same function can be implemented. In a conceptual sense, any arrangement of components that implement the same function is effectively "associated" so that the desired function can be achieved. Therefore, any two components that are combined to implement a specific function herein can be considered to be "associated" with each other so that the desired function is achieved, regardless of the architecture or intermediate components. Similarly, any two components that are so associated can also be considered to be "operably connected" or "operably coupled" to each other to achieve the desired function, and any two components that can be so associated can also be considered to be "operably coupled" to each other to achieve the desired function. The specific examples of operable coupling include, but are not limited to, components that can be physically paired and / or physically interacted and / or components that can be wirelessly interacted and / or wirelessly interacted and / or components that logically interact and / or can logically interact.

[0192] 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 as appropriate to the context and / or application. For purposes of clarity, various singular / plural permutations may be expressly set forth herein.

[0193] Those skilled in the art will understand that, in general, the terms used herein, and especially 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 “comprising” should be interpreted as “including but not limited to,” etc.) and / or “permissive” terms (e.g., the term “is” can be interpreted as “can be” and / or “may be,” the term “refers to” can be interpreted as “can refer to” and / or “may refer to,” the term “receive” can be interpreted as “can receive” and / or “may receive,” the term “supports” can be interpreted as “can support” and / or “may support,” the term “interface” can be interpreted as “can interface” and / or “may interface,” The term "transmit" may be interpreted as "may dock" and / or "may dock", "may transmit" and / or "may transmit", the term "send" may be interpreted as "may send" and / or "may send", the term "do not refer" (etc.) may be interpreted as "may not refer" and / or "may not refer", the term "do not receive" (etc.) may be interpreted as "may not receive" and / or "may not receive", the term "do not support" (etc.) may be interpreted as "may not support" and / or "may not support", the term "do not dock" (etc.) may be interpreted as "may not dock" and / or "may not dock", the term "do not transmit" (etc.) may be interpreted as "may not transmit" and / or "may not transmit", the term "do not send" (etc.) may be interpreted as "may not send" and / or "may not send", etc.). It will be further understood by those skilled in the art that if a specific number of claims recited in the introduction is intended, such intention will be explicitly recorded in the claims, and if no such recording is made, such intention does not exist. For example, where only one item is intended, the term "single" or similar language may be used. As an aid to understanding, the appended claims and / or the description herein may include the use of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed as implying that the introduction of a claim recitation by the indefinite article "a" or "an" will limit any particular claim that includes such introduced claim recitation to embodiments that include only one such recitation, even when 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 to mean "at least one" or "one or more"). The same applies to the use of definite articles used to introduce claim recitations.In addition, even if specific numbers are explicitly recited in the claims described in the introduction, those skilled in the art will recognize that such recitation should be interpreted as meaning at least the recited numbers (for example, the unmodified recitation of "two recitations" without other modifiers means at least two recitations or two or more recitations). In addition, in those instances where a convention similar to "at least one of A, B, and C, etc." is used, generally speaking, such construction is intended in the sense that those skilled in the art will understand the convention (for example, "a system having at least one of A, B, and C" will include but is not limited to a system having only A, a system having only B, a system having only C, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.). In those instances where a convention similar to "at least one of A, B, or C, etc." is used, generally such construction is intended in a 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, a system having only A, a system having only B, a system having only C, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.). One skilled in the art would further understand that virtually any disjunctive word and / or phrase, whether in the specification, claims, or drawings, presenting two or more alternative terms should be understood to contemplate the possibility of including one, either, or both of the terms. For example, the phrase "A or B" would be understood to include the possibility of "A" or "B" or "A and B." Further, as used herein, the term "any of" followed by a listing of a plurality of items and / or categories of items is intended to include "any of," "any combination," "any plurality," and / or "any combination of a plurality" of the items and / or categories of items, alone or in combination with other items and / or items of other categories. Moreover, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, the term "number" is intended to include any number, including zero. Moreover, as used herein, the term "plurality" is intended to be synonymous with "plurality."

[0194] 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.

[0195] As will be understood by those skilled in the art, for any and all purposes, such as providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations thereof. Any listed range can be easily identified as fully describing the same range and enabling the same range to be decomposed into at least equal halves, thirds, quarters, fifths, tenths, 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 language such as "up to," "at least," "greater than," and "less than" includes the recited number and refers to a range that can subsequently be decomposed into the subranges discussed above. Finally, as will be understood by those skilled in the art, a range includes each individual member. Thus, for example, a group having 1 to 3 units refers to a group having 1, 2, or 3 units. Similarly, a group having 1 to 5 units refers to a group having 1, 2, 3, 4, or 5 units, and so on.

[0196] Furthermore, the claims should not be read as limited to the order or elements provided unless so stated. Furthermore, 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.

[0197] By way of example, suitable processors include a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), an application specific standard product (ASSP); a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), and / or a state machine.

[0198] The WTRU may be used in conjunction with modules implemented in hardware and / or software including software defined radio (SDR), and other components such as a camera, a video recorder module, a video phone, a speaker phone, a vibration device, a speaker, a microphone, a television transceiver, a hands-free handset, a keyboard, a Bluetooth module, a frequency modulation (FM) radio unit, a near field communication (NFC) module, a liquid crystal display (LCD) display unit, an organic light emitting diode (OLED) display unit, a digital music player, a media player, a video game player module, an Internet browser, and / or any wireless local area network (WLAN) or ultra-wideband (UWB) module.

[0199] Although various embodiments have been described in terms of a communication system, it is contemplated that the system may be implemented in software on a microprocessor / general purpose computer (not shown). In certain embodiments, one or more of the functions of the various components may be implemented in software that controls a general purpose computer.

[0200] Furthermore, although the invention has been illustrated and described herein with reference to specific embodiments, it is not intended that the invention be limited to the details shown. Rather, various modifications may be made in the details within the scope and range of equivalents of the claims and without departing from the invention.

Claims

1. A method implemented in a wireless transmit / receive unit (WTRU), the method comprising: transmitting information indicating one or more capabilities of the WTRU to run an AI model to a network node; receiving, from the network node, a first AI model subset of an adaptive AI model based on the comparison of the one or more capabilities of the WTRU and the first level of accuracy, wherein the adaptive AI model comprises a plurality of AI model subsets, each subset being associated with a level of accuracy; and A first AI model subset of the adaptive AI model is run.

2. The method of claim 1 , wherein receiving the first AI model subset comprises: receiving, from the network node, AI model information associated with a plurality of adaptive AI models based on the one or more capabilities, wherein each adaptive AI model in the plurality of adaptive AI models is comprised of a plurality of AI model subsets, and wherein each AI model subset is associated with an accuracy level; selecting an adaptive AI model from the plurality of adaptive AI models based on the first level of accuracy; and A request is transmitted to the network node to receive a first AI model subset of the adaptive AI model.

3. The method of any one of claims 1-2, wherein the one or more capabilities of the WTRU include any one of: a battery status at the WTRU, computing power resources at the WTRU, and available memory at the WTRU.

4. The method according to any one of claims 1 to 3, further comprising: receiving, from the network node, a second subset of AI models of the adaptive AI model based on a comparison of the one or more capabilities of the WTRU and a second level of accuracy, wherein the second accuracy model is higher than the first level of accuracy; and A second AI model subset of the adaptive AI model is run.

5. The method of claim 4, further comprising: The request to receive the second subset of AI models is sent based on the change in the one or more capabilities of the WTRU.

6. The method according to any one of claims 4 to 5, further comprising: determining an improvement in the one or more capabilities of the WTRU; as well as A second AI model subset of the adaptive AI model is run.

7. The method of any one of claims 4-5, further comprising: determining a reduction in the one or more capabilities of the WTRU; as well as A first AI model subset of the adaptive AI model is run.

8. A wireless transmit / receive unit (WTRU) comprising circuitry including a transmitter, a receiver, a processor, and a memory, the WTRU being configured to: transmitting information indicating one or more capabilities of the WTRU to operate an AI model to a network node; receiving a first AI model subset of an adaptive AI model from the network node based on a comparison of the one or more capabilities of the WTRU and a first level of accuracy, wherein the adaptive AI model includes a plurality of AI model subsets, each subset being associated with a level of accuracy; and A first AI model subset of the adaptive AI model is run.

9. The WTRU of claim 8, wherein the WTRU is configured to: receiving, from the network node, AI model information associated with a plurality of adaptive AI models based on the one or more capabilities, wherein each adaptive AI model in the plurality of adaptive AI models includes a plurality of AI model subsets, and wherein each AI model subset is associated with an accuracy level; selecting an adaptive AI model from the plurality of adaptive AI models based on the first level of accuracy; and A request is transmitted to the network node to receive a first AI model subset of the adaptive AI model.

10. The WTRU of any one of claims 8-9, wherein the one or more capabilities of the WTRU include any one of: a battery status at the WTRU, computing power resources at the WTRU, and available memory at the WTRU.

11. The WTRU of any one of claims 9-10, wherein the WTRU is configured to: receiving, from the network node, a second subset of AI models of the adaptive AI model based on a comparison of the one or more capabilities of the WTRU and a second level of accuracy, wherein the second accuracy model is higher than the first level of accuracy; and A second AI model subset of the adaptive AI model is run.

12. The WTRU of claim 11 , wherein the WTRU is configured to: The request to receive the second subset of AI models is sent based on the change in the one or more capabilities of the WTRU.

13. The WTRU of any one of claims 11-12, wherein the WTRU is configured to: determining an improvement in the one or more capabilities of the WTRU; and A second AI model subset of the adaptive AI model is run.

14. The WTRU of any one of claims 11-12, wherein the WTRU is configured to: determining a reduction in the one or more capabilities of the WTRU; and A first AI model subset of the adaptive AI model is run.

Images