Methods, architectures, devices and systems for distributed artificial intelligence

Abstract

A process, method, architecture, apparatus, system, apparatus, and computer program product for distributed artificial intelligence (AI). A first device receives information indicating a plurality of distributed artificial intelligence (AI) models from a second device, where each model of the plurality of distributed AI models corresponds to a same AI service; transmitting a message to the second device, the message including information indicating a selected distributed AI model from among the plurality of distributed AI models, where the selected distributed AI model includes a plurality of model subsets constituting the AI service; receiving information corresponding to the selected model subset of the distributed AI model; and running the model subset of the selected distributed AI model based on the information corresponding to the model subset.

Description

Background Art

[0001] The present disclosure relates generally to the fields of communications, software, and coding, including, for example, methods, architectures, devices, and systems related to collaborative artificial intelligence (AI). Summary of the invention

[0002] In a first aspect, the present invention relates to a method, wherein a first device: receives information indicating multiple distributed artificial intelligence (AI) models from a second device, wherein each of the multiple distributed AI models corresponds to the same AI service; sends a message to the second device, wherein the message includes information indicating a selected distributed AI model from among the multiple distributed AI models, wherein the selected distributed AI model includes multiple model subsets that constitute the AI ​​service; receives information corresponding to a model subset of the selected distributed AI model; and runs the model subset of the selected distributed AI model based on the information corresponding to the model subset.

[0003] In a second aspect, the principles of the present invention relate to a first device, comprising: a memory storing program instructions executable by a processor; and at least one hardware processor configured to execute the program instructions to: receive information indicating multiple distributed artificial intelligence (AI) models from a second device, wherein each of the multiple distributed AI models corresponds to the same AI service; send a message to the second device, the message comprising information indicating a selected distributed AI model from the multiple distributed AI models, wherein the selected distributed AI model comprises multiple model subsets constituting the AI ​​service; and receive information corresponding to a model subset of the selected distributed AI model; and run the model subset of the selected distributed AI model based on the information corresponding to the model subset. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] A more detailed understanding may be obtained from the following detailed description given by way of example in conjunction with the accompanying drawings. As with the detailed description, each of the figures in such drawings is an example. Therefore, the drawings (figures) and detailed description should not be considered limiting, and other equally effective examples are possible and possible. In addition, the same reference numerals ("labels") in the various figures indicate the same elements, and wherein:

[0005] Figure 1A is a system diagram illustrating an example communication system;

[0006] Figure 1B It shows that it can be Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within a communication system is shown;

[0007] Figure 1C It shows that it can be Figure 1A A system diagram of an example radio access network (RAN) and an example core network (CN) used within the illustrated communication system;

[0008] Figure 1D It shows that it can be Figure 1A A system diagram of yet another example RAN and yet another example CN used within the communication system shown;

[0009] Figure 2 Different examples of segmentation of AI / ML models are shown;

[0010] Figure 3 An example of a split topology is shown where a UE acquires sensing data and acts as an uplink data source;

[0011] Figure 4 shows an example of a split topology where the sensing data comes from a content provider / remote UE via a cloud / edge server acting as a downlink data source;

[0012] Figure 5A and Figure 5B Together, a flowchart for distributed AI / ML according to an embodiment is shown;

[0013] Figure 6 An example of a split node configuration is shown;

[0014] Figure 7 shows a flow chart for split node configuration and session establishment according to an embodiment;

[0015] Figure 8 Yet another example of a split node configuration is shown;

[0016] Fig. 9 shows a flow chart for split node configuration and session establishment according to yet another embodiment;

[0017] Fig. 10A and Fig. 10B together showing a flow chart for splitting node configuration and session establishment according to yet another embodiment; and

[0018] Fig.11 An example of data transmission between AI / ML segmentation devices is shown. DETAILED DESCRIPTION

[0019] In the following detailed description, many specific details are set forth to provide a thorough understanding of the embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples can be practiced without some or all of the specific details set forth herein. In other cases, well-known methods, programs, components and circuits are not described in detail to avoid blurring the following description. In addition, the embodiments and examples not specifically described herein can replace the embodiments and other examples explicitly, implicitly and / or inherently described, disclosed or otherwise provided (collectively referred to as "providing") herein to practice or practice in combination with them. Although various embodiments in which equipment, systems, devices, etc. and / or any of its elements perform operations, processes, algorithms, functions, etc. and / or any part thereof are described and / or claimed herein, it should be understood that any embodiment described and / or claimed herein assumes that any equipment, systems, devices, etc. and / or any of its elements are configured to perform any operations, processes, algorithms, functions, etc. and / or any part thereof.

[0020] Example Communication System

[0021] The methods, devices, and systems provided herein are well suited for communications involving both wired and wireless networks. Figures 1A to 1D An overview of various types of wireless devices and infrastructure is provided in which various elements of the network can utilize, perform, be arranged according to, and / or be adapted and / or configured for the methods, devices, and systems provided herein.

[0022] Figure 1A is a system diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, broadcast, etc. to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content by sharing system resources, including wireless broadband. For example, the communication system 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single carrier FDMA (SC-FDMA), zero tail (ZT) unique word (UW) discrete Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, filter bank multi-carrier (FBMC), etc.

[0023] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110 and other networks 112, but it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d (any of which may be referred to as a “station” and / or “STA”) may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, a personal digital assistant (PDA), a smart phone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automated process chain), a consumer electronic device, a device operating on a commercial and / or industrial wireless network, etc. Any of the WTRUs 102a, 102b, 102c, 102d may be interchangeably referred to as a UE.

[0024] The communication system 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, for example, to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the network 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B (NB), an eNode-B (eNB), a Home Node-B (HNB), a Home eNode-B (HeNB), a gNode-B (gNB), a NR Node-B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0025] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), a relay node, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in a licensed spectrum, an unlicensed spectrum, or a combination of a licensed spectrum and an unlicensed spectrum. A cell may provide coverage of wireless services to a specific geographic area that may be relatively fixed or may vary over time. The cell may also be divided into cell sectors. For example, a cell associated with the base station 114a may be divided into three sectors. Therefore, in an embodiment, the base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple-output (MIMO) technology, and may use multiple transceivers for each sector or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in a desired spatial direction.

[0026] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0027] More specifically, as described above, the communication system 100 may be a multiple-access system and may employ one or more channel access schemes such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA) that 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).

[0028] In an 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).

[0029] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as New Radio (NR) to establish NR radio access over the air interface 116.

[0030] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may jointly implement LTE radio access and NR radio access, for example using dual connectivity (DC) principles. Thus, the air interface used by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0031] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE), GSM Evolution (GERAN), etc.

[0032] Figure 1AThe base station 114b in the example 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 location, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-a, LTE-a Pro, NR, etc.) to establish any of a small cell, a pico cell, or a femto cell. As Figure 1A As shown, base station 114b may be directly connected to Internet 110. Therefore, base station 114b may not need to access Internet 110 via CN 106 / 115.

[0033] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications and / or Voice over Internet Protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calls, Internet connectivity, video distribution, etc., and / or perform advanced security functions, such as user authentication. Although Figure 1A Not shown, but it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT or a different RAT as the RAN 104 / 113. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing an NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) that employs any of GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technologies.

[0034] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network that provides plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols such as the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), and / or the Internet Protocol (IP) in the TCP / IP Internet protocol suite. The networks 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may use the same RAT as the RAN 104 / 114 or a different RAT.

[0035] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communication system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). Figure 1A The illustrated WTRU 102c may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0036] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B As shown, the WTRU 102 may include, among other things, a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0037] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. Although Figure 1B The processor 118 and the transceiver 120 are depicted as separate components, but it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, such as in an electronic package or chip.

[0038] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., base station 114a) via an air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be a transmitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF signals and optical signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0039] Although the transmit / receive element 122 is Figure 1B Although depicted as a single element in the figure, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0040] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and to demodulate signals received by the transmit / receive element 122. As described above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs (e.g., such as NR and IEEE 802.11).

[0041] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from: a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an organic light emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from and store data in any type of suitable memory, such as a non-removable memory 130 and / or a removable memory 132. The non-removable memory 130 may include a random access memory (RAM), a read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from and store data in a memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0042] The processor 118 may receive power from the power source 134 and may be configured to distribute the power to and / or control power to other components in the WTRU 102. The power source 134 may be any suitable device for 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.

[0043] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to or in lieu of the information from the GPS chipset 136, the WTRU 102 may receive location information from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of receiving signals from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by any suitable location-determination method while remaining consistent with an embodiment.

[0044] The processor 118 may also be coupled to other components / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality, and / or wired or wireless connectivity. For example, the components / peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (e.g., for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, module, a frequency modulation (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, etc. Components / peripherals 138 may include one or more sensors, which may be gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors; geolocation sensors; altimeters, light sensors, touch sensors, magnetometers, barometers, gesture sensors, biometric sensors, and / or humidity sensors.

[0045] The WTRU 102 may include a full-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) and downlink (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and / or substantially eliminate self-interference via hardware (e.g., choke) or signal processing via a processor (e.g., a separate processor (not shown) or via the processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) or downlink (e.g., for reception)) may be concurrent and / or simultaneous.

[0046] Figure 1C 1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As described above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0047] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, for example, the eNode-B 160a may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0048] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in uplink (UL) and / or downlink (DL), etc. Figure 1C As shown, eNode-Bs 160a, 160b, 160c may communicate with each other via an X2 interface.

[0049] Figure 1C The illustrated CN 106 may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements is depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0050] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, etc. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0051] 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 or from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing the context of the WTRUs 102a, 102b, 102c, and the like.

[0052] 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.

[0053] 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) 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.

[0054] Although the WTRU Figures 1A to 1D Although depicted as a wireless terminal, it is contemplated that in certain representative embodiments such a terminal may (eg, temporarily or permanently) employ a wired communications interface utilizing a communications network.

[0055] In a representative embodiment, other network 112 may be a WLAN.

[0056] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STA) associated with the AP. The AP may have access or an interface to another type of wired / wireless network that reaches a distribution system (DS) or loads traffic into and / or out of the BSS. Traffic originating from outside the BSS to the STA may be reached by the AP and may be delivered to the STA. Traffic originating from the STA to a destination outside the BSS may be sent to the AP to be delivered to the corresponding destination. Traffic between STAs within the BSS may be sent by the AP, for example, where the source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as point-to-point traffic. Point-to-point traffic may be sent between the source STA and the destination STA using a direct link setup (DLS) (e.g., directly sent between them). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunnel DLS (TDLS). A WLAN using an independent BSS (IBSS) mode may not have an AP, and STAs (eg, all STAs) within or using the IBSS may communicate directly with each other. The IBSS communication mode may sometimes be referred to herein as an "ad hoc" communication mode.

[0057] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, the AP can send beacons on a fixed channel, such as a primary channel. The primary channel can be a fixed width (e.g., a 20 MHz wide bandwidth) or a width dynamically set via signaling. The primary channel can be an operating channel of the BSS and can be used by STAs to establish a connection with the AP. In certain representative embodiments, carrier sense multiple access collision avoidance (CSMA / CA) can be implemented, for example, in an 802.11 system. For CSMA / CA, STAs (e.g., each STA), including the AP, can sense the primary channel. If the primary signal is sensed / detected by a particular STA and / or is determined to be busy, the particular STA can back off. One STA (e.g., only one station) can transmit in a given BSS at any given time.

[0058] A high throughput (HT) STA may communicate using a 40 MHz wide channel, for example, via a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0059] Very high throughput (VHT) STA can support 20MHz, 40MHz, 80MHz and / or 160MHz wide channels. 40MHz and / or 80MHz channels can be formed by combining continuous 20MHz channels. 160MHz channels can be formed by combining 8 continuous 20MHz channels, or by combining two discontinuous 80MHz channels, which can be referred to as 80+80 configuration. For 80+80 configuration, data can be passed through a fragment parser after channel coding, which can divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time domain processing can be performed on each stream respectively. The stream can be mapped to two 80MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above-mentioned operation of the 80+80 configuration can be reversed, and the combined data can be sent to the media access control (MAC) layer, entity, etc.

[0060] 802.11af and 802.11ah support operating modes below 1 GHz. The channel operating bandwidth and carrier are reduced in 802.11af and 802.11ah relative to those used in 802.11n and 802.11ac. 802.11af supports 5MHz, 10MHz and 20MHz bandwidths in TV white space (TVWS) spectrum, and 802.11ah supports 1MHz, 2MHz, 4MHz, 8MHz and 16MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah can support meter type control / machine type communication (MTC), such as MTC devices in macro coverage. MTC devices may have certain capabilities, for example, limited capabilities, including support for (e.g., only support for) certain and / or limited bandwidths. MTC devices may include batteries with battery life above a threshold (e.g., to maintain very long battery life).

[0061] A WLAN system that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) includes a channel that can be designated as a primary channel. The primary channel may have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by the STA that supports the minimum bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for STAs (e.g., MTC-type devices) that support (e.g., only support) a 1MHz mode, the primary channel may be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the state of the primary channel. If the primary channel is busy, for example, due to a STA (which only supports a 1MHz operating mode) transmitting to the AP, the entire available band may be considered busy even if most of the band remains idle and may be available.

[0062] In the United States, the available frequency band that can be used by 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz, depending on the country code.

[0063] Figure 1D1 is a system diagram showing the RAN 113 and the CN 115 according to an embodiment. As described above, the RAN 113 may employ NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0064] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, for example, the gNB 180a may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation 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 located on an unlicensed spectrum, while the remaining component carriers may be located on a licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement coordinated multi-point (CoMP) techniques. For example, the WTRU 102a may receive coordinated transmissions from the gNB 180a and gNB 180b (and / or gNB 180c).

[0065] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with a scalable digital architecture. For example, the OFDM symbol spacing and / or the 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 various or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0066] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as the eNode Bs 160a, 160b, 160c). In a standalone configuration, the WTRUs 102a, 102b, 102c may use one or more of the gNBs 180a, 180b, 180c as mobility anchors. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration, the WTRU 102a, 102b, 102c may communicate / connect with the gNB 180a, 180b, 180c while also communicating / connecting with another RAN, such as the eNode-B 160a, 160b, 160c. For example, the WTRU 102a, 102b, 102c may implement the DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNode-B 160a, 160b, 160c may serve as a mobility anchor for the WTRU 102a, 102b, 102c, and the gNB 180a, 180b, 180c may provide additional coverage and / or throughput to serve the WTRU 102a, 102b, 102c.

[0067] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, support for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards a user plane function (UPF) 184a, 184b, routing of control plane information towards an access and mobility management function (AMF) 182a, 182b, etc. Figure 1D As shown, gNB180a, 180b, and 180c can communicate with each other through the Xn interface.

[0068] Figure 1DThe illustrated CN 115 may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and at least one data network (DN) 185a, 185b. Although each of the foregoing elements is depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0069] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRU 102a, 102b, 102c, supporting network slicing (e.g., handling different protocol data unit (PDU) sessions with different requirements), selecting a specific SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. The AMF 182a, 182b may use network slicing, for example, to customize CN support for the WTRU 102a, 102b, 102c based on the type of service the WTRU 102a, 102b, 102c is utilizing. For example, different network slices may be established for different use cases, such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, etc. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies (such as LTE, LTE-A, LTE-A Pro) and / or non-3GPP access technologies (such as Wi-Fi).

[0070] The SMF 183a, 183b may be connected to the AMF 182a, 182b in the CN 115 via the N11 interface. The SMF 183a, 183b may also be connected to the UPF 184a, 184b in the CN 115 via the N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b, and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0071] The UPF 184a, 184b may be connected via the N3 interface to one or more of the gNBs 180a, 180b, 180c in the RAN 113, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, for example, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-connection PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, etc.

[0072] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b via 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.

[0073] Given that Figures 1A to 1D and Figures 1A to 1D 102a to 102d, base stations 114a to 114b, eNode-Bs 160a to 160c, MMEs 162, SGWs 164, PGWs 166, gNBs 180a to 180c, AMFs 182a to 182b, UPFs 184a to 184b, SMFs 183a to 183b, DNs 185a to 185b, and / or any other elements / devices described herein. A simulation device may be one or more devices configured to simulate one or more or all of the functions described herein. For example, a simulation device may be used to test other devices and / or simulate network and / or WTRU functions.

[0074] The simulation device can be designed to implement one or more tests of other devices in a laboratory environment and / or an operator network environment. For example, one or more simulation devices can perform one or more or all functions when fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. One or more simulation devices can perform one or more or all functions when temporarily implemented / deployed as part of a wired and / or wireless communication network. The simulation device can be directly connected to another device for testing purposes, and / or can use over-the-air wireless communication to perform testing.

[0075] One or more simulation devices can perform one or more (including all) functions when not implemented / deployed as part of a wired and / or wireless communication network. For example, the simulation device can be used in a test scenario in a test laboratory and / or a wired and / or wireless communication network that is not deployed (e.g., tested) to enable testing of one or more components. One or more simulation devices can be test equipment. The simulation device can transmit and / or receive data using direct RF connection and / or wireless communication via RF circuits (e.g., which can include one or more antennas).

[0076] introduce

[0077] While artificial intelligence (AI), and in particular machine learning (ML), can be very powerful tools in various devices, it will be appreciated that for devices with relatively limited resources, the resource (e.g., processing) requirements can be too great. Such devices, denoted UE in this specification, can be end-user devices, in particular mobile devices such as smartphones and tablets. For this reason, a common solution is to have one or more other devices perform at least part of the computation. It should be noted that in this context, a "device" (also referred to as a "node") can mean a plurality of devices as a whole, such as in the case of server groups and cloud computing.

[0078] Thus, for a certain AI / ML application that may be based on a deep neural network (DNN), for example, the AI / ML reasoning may be divided (i.e., partitioned) at different points (e.g., from the UE to the edge or cloud device). For example, the AI / ML application may be partitioned along the interface between two layers in the DNN, or partitioned between different parts, where one part (e.g., a part that detects facial features) may provide results as input to a later part (e.g., using the detected facial features as input to a person's emotions). Thus, the corresponding AI / ML model (i.e., a computer program (e.g., trained, i.e., with appropriate parameters)) may be divided into several AI / ML model subsets to run on different devices / servers. Each AI / ML model subset is independent software to run on a partition node (e.g., such as a UE, an edge device), in the cloud, or in an access network.

[0079] Figure 2 Different examples of segmentation of AI / ML models are shown. The example AI / ML models can be segmented in different ways. For example, a segmentation model M may include the AI / ML model subsets {M0, M1, M2}. Similarly, a segmentation model M' may include {M'0, M'1, M'2} and a segmentation model M" may include {M0", M1", M2", M3"}. These three examples of segmentation models M, M', M" provide the same service and, as can be seen, may be segmented into a different number of subsets. The boundaries between different subsets will be referred to as segmentation points (segmentation points, partition points), which in one instance are indicated by illustrative arrows.

[0080] In addition, different subsets may run or be intended to run on different devices. Which device a subset runs on may depend on different conditions. Example conditions include device capabilities, device load, and network load. Thus, a specific subset (such as M0) may run on an edge device or on a UE.

[0081] Figure 3 An example of a split topology is shown in which a UE acquires sensing data and acts as an uplink data source.

[0082] Assume that an AI / ML model subset has been obtained (e.g., downloaded, streamed) from a device such as a cloud or edge server node. Sensory data is provided to subset M0 by a UE (e.g., an application that captures video). In the example, assume that M0 processes the sensory data and outputs the AI ​​data to subset M1. M1 can process (i.e., reason) the AI ​​data to obtain a result, or forward different AI data to M2, which in turn processes different AI data to obtain a result. The result may be returned to the UE via the subset with the next lower number (e.g., M1 may provide the result via M0). The result may be provided to an application or used directly by the UE.

[0083] In example (a), M0 resides on the UE and M1 resides on the edge device (node).

[0084] In example (b), M0 resides on the UE and M1 resides in the cloud.

[0085] In example (c), M0 resides on an edge device and M1 resides in the cloud.

[0086] In example (d), M0 resides on the UE, M1 resides on the edge device, and M2 resides in the cloud.

[0087] The results can be presented in various ways, for example, as a video or as textual information snippets.

[0088] Figure 4 An example of a split topology is shown where the sensing data comes from the content provider / remote UE via a cloud / edge server acting as a downlink data source.

[0089] You can refer to Figure 3 Obtain an AI / ML model subset as described.

[0090] The sensory data comes from a content provider device (not shown).

[0091] As in Figure 3 In the example, the sensory data is processed (e.g., inferred) by M0, which then provides AI / ML data to the next subset M1, which obtains a result or provides AI data to the next subset M2, which in turn obtains a result.

[0092] It should be noted that since the application on the UE is the intended target of the result, this will not be as Figure 3 However, it should also be noted that in cases where other devices (e.g., sources) may be interested in the results, the results may still be returned as Figure 3 Return as shown.

[0093] The results can be as follows Figure 3As presented in .

[0094] In example (a), M0 resides on an edge device (node) and M1 resides on a UE.

[0095] In example (b), M0 resides in the cloud and M1 resides on the UE.

[0096] In example (c), M0 resides in the cloud, M1 resides on an edge device (node), and M2 resides on a UE.

[0097] In example (d), M0 resides in the cloud and M1 resides on an edge device (node).

[0098] It should be noted that a device (ie, a node) may run more than one subset. For example, M1 and M2 may run on the same device.

[0099] As shown in the figure, the split point can change depending on the model, the split model topology, the processing power of each component (UE, edge, cloud device) that plays a role in the split model topology, and the real-time network condition fluctuations used to transmit AI / ML data.

[0100] The diversity of topologies and the heterogeneity of the devices involved may raise many requirements and questions, such as:

[0101] – In order for the UE to determine the partitioning model and the devices involved, it should know which AI / ML models are applicable to its device characteristics and how to decompose the models. For example, what are the possible partitioning points and what model subsets are required to execute the model?

[0102] – How can a UE know which servers (edge / cloud / proximity) can provide a specific service by running a specific subset of models for the UE?

[0103] – How the UE can interact with applications (control plane) and edge devices to apply the selected end-to-end segmentation model, establish links between the UE and local segmentation nodes (e.g., edge, cloud, and local links), and establish intermediate links between segmentation nodes hidden from the UE.

[0104] - How can the UE interact with the application (server) to establish the relevant data path? This may include a direct data path between the UE and the local split node.

[0105] Overview

[0106] According to the principles of the present invention, at a high level, a UE can select a split model topology among multiple split model topologies available for a given AI / ML service (e.g., an application). The split model arrangement includes the selection of a split node running one or several model subsets with split node connections.

[0107] The UE may also request configuration of the selected split nodes and establishment of a data transfer session between the selected split nodes, including configuration of AI / ML specific metadata identification. Depending on the selected model, the data transfer session between the split nodes may be downlink or uplink (or both downlink and uplink).

[0108] The UE may also initiate a data streaming service to the segmentation nodes of the sensed data to trigger data transmission between the selected segmentation nodes, which may include AI / ML specific metadata including a global AI / ML model stream identifier and a specific data / stream identifier.

[0109] Model selection

[0110] Depend on Figure 5A and Figure 5B FIG5 shows an example flow chart for distributed AI / ML according to an embodiment.

[0111] FIG. 5 shows multiple split node candidates in a network: a UE 52 , an edge device 54 , and a cloud (eg, access network) device 56 .

[0112] UE 52 includes AI / ML application 52a and AI / ML model session processor 52b. AI / ML model session processor 52b is configured to interact with AI / ML application function (AF) 51 to discover and select models. AI / ML application provider 55 is configured to interact with AI / ML model application server (AS) 53 to provide AI / ML models and model subsets to split node applications.

[0113] In step S501, the AI / ML application provider 55 sends a message related to service announcement and configuration, which indicates, for at least one AI / ML service, an alternative architecture topology that the application provider can provide to the UE, for example, through 5GS. The message may include the AI / ML service name (e.g., segmented AI / ML image recognition, enhanced media recognition, media quality enhancement) and information about the segmented mode capability (i.e., an indication of whether the segmented mode is allowed).

[0114] In step S502, the AI / ML AF 51 and the AI / ML AS 53 interact with the AI / ML application provider 55 to obtain the AI / ML model and the related AI / ML subsets that make up the proposed AI / ML model. As already mentioned, the AI / ML subset is the basic software that can run independently on a UE, edge or cloud device. A UE, edge or cloud device can run one or more AI / ML subsets. For example, a UE may host AI / ML model subsets M0, M0' or M0", where each model subset is related to the same AI / ML model but has been generated from a different partitioning point. The same technology extends to the edge and the cloud. The main condition is that the subsets running on the UE and / or edge and / or cloud are complementary.

[0115] In step S503, the UE 52 selects an AI / ML model service from among those proposed by the AI / ML application provider in step S501. The UE 52 may, for example, select "segmentation AI / ML image recognition".

[0116] In step S504, the AI / ML application 52a of the UE 52 uses the AI / ML model session processor 52b to initiate the selection of the AI / ML model service. The selection may, for example, indicate one or more of the following:

[0117] Service Request Information , including, for example, one or more of the following:

[0118] -Service name, e.g., Segmentation AI / ML Image Recognition,

[0119] - Service specific information, such as the resolution ratio requested for the enhanced media recognition service and the animal to be recognized for the object recognition service,

[0120] - Quality of service, e.g. accuracy or precision of requests,

[0121] -Service requirements, including for example:

[0122] - Maximum expected latency for end-to-end inference, for example, maximum expected latency result: 20ms,

[0123] - A specific task assigned by the UE, for example, a task to be performed by the UE, such as a privacy protection service task or a delay sensitive service task.

[0124] Model Request Information , including, for example, one or more of the following:

[0125] - Model type,

[0126] - Model identifier,

[0127] - Identified model parts self-assigned to the UE; the UE may be aware of the model decomposition structure and may send indications to the network of the model parts to be processed locally, e.g. regarding service requirements for UE-specific tasks:

[0128] - the UE minimum starting model portion up to a defined and known split point,

[0129] - the UE end model part starting from the known split point,

[0130] - Identified model parts assigned to the network; the UE may know the model decomposition structure and it cannot process the identified model parts, e.g. computationally intensive parts:

[0131] - the smallest starting model part of the network up to a defined and known split point,

[0132] - The minimum end model portion of the network starting from the known split point.

[0133] UE AI / ML Engine , that is, the engine used to run the AI / ML application, including the engine version.

[0134] UE profile, including, for example, its OS and UE capabilities , including maximum allocation, availability, average, and capacity, for example:

[0135] - Available memory allocated for AI / ML services,

[0136] - Processing power available for UE inference (CPU / GPU / TPU / NPU),

[0137] - maximum available energy consumption,

[0138] - Computational performance capabilities (e.g., floating point operations per second, also known as flops).

[0139] Network Capabilities , including, for example, the available bandwidth between the UE and the network nodes (RAN / edge / cloud / application server / core network nodes).

[0140] Distributed Configuration (preferred or available), for example:

[0141] - Delivery mode, including progressive download, DASH streaming, or real-time delivery (e.g., RTP),

[0142] - Distribution mode on devices, such as unicast / multicast / broadcast.

[0143] Split mode UE support , indicating whether the UE supports AI / ML subset reasoning.

[0144] Split Mode Service Support Type : Edge, cloud, or edge and cloud.

[0145] Estimated bandwidth of sensor data (In the case of UE source, such as Figure 3 middle).

[0146] In step S505 , the AI / ML model session processor 52 b sends an AI / ML model service request to the AI / ML AF 51 , the request including the information received from the AI / ML application 52 a in step S504 .

[0147] In step S506, the AI / ML AF 51 calculates an AI / ML model service response based at least on the information received in step S505. The information (which may also include additional information) may also include, for example, the capabilities of the segmentation node (e.g., for at least one of the edge device and the cloud device, depending on the configuration) and the network conditions. The network selects a set of adapted models for the UE. If the model is not available, the network may build or acquire a new model.

[0148] The information to be included in the response may include one or more of the following: a service description, split combination alternatives, and conditions when an AI / ML subset is inferred on a particular split node. Each of these will now be described.

[0149] Service Description

[0150] The service description may be a model identifier assigned by the AI / ML AF 51 directly or on behalf of the AI / ML application provider 55 .

[0151] Split and combine alternatives

[0152] These include different AI / ML model alternatives corresponding to the request. It can list subset combinations including different split nodes for different alternatives. Figure 2 For the example shown, the models could be M, M', M":

[0153] Model Identifier Model subset M {M0, M1, M2} M’ {M0', M1', M2'} M” {M0”, M1”, M2”, M3”}

[0154] The split combination alternative can also include the ability to run different split nodes for subsets of AI / ML models. For example, a split node can serve subsets of models from different models M, M', M", as follows:

[0155]

[0156] Split composition alternatives can also include splitting subsets of AI / ML models that are currently being served by the node. This means that these subsets do not need to be provisioned in advance:

[0157]

[0158]

[0159] The split combination alternative may also include model subset information. This information may include information about the model, such as direction (uplink / downlink), size, and bandwidth, for example. This information may also include network information to download, such as link and network address, for example.

[0160] Conditions when inferring AI / ML subsets on specific split nodes.

[0161] For each candidate selection pair (split node, AI / ML subset), the conditions may include one or more of the following (example units of measurement are in parentheses):

[0162] – Output data bandwidth (Mb / s): The bandwidth required to send outgoing AI / ML data, which can be uplink or downlink (or both), depending on the chosen topology.

[0163] – Inference latency (ms): The latency from receiving input AI / ML data to serving output AI / ML data.

[0164] Inference setup time (ms): This may indicate the average time to download, possibly compile to the AI / ML engine, load in memory, and run inference. When the split node is already running an AI / ML subset as described above, setup may be instant, as doing it once may be sufficient.

[0165] Energy consumption (mJ): This may indicate a quantitative estimate of the energy required to run the inference. This may be of particular interest for UEs predicting battery depletion.

[0166] Table 1: Example requirements

[0167]

[0168] The distribution configuration of a model or a subset of models, including for example the mean of each distribution, is as follows:

[0169] - Delivery mode, such as progressive download or DASH streaming, real-time transport (e.g. RTP), - Application server information, such as information for connecting to the server to obtain a subset of UE models. - Distribution mode, such as unicast / multicast / broadcast

[0170] Table 1 below depicts example conditions required to run a given AI / ML subset on a target split node for a selected service, including, for example, combinations of M, M', and M".

[0171] In step S507 , the AI / ML AF 51 sends the calculated response to the AI / ML model conversation processor 52 b .

[0172] In step S508, UE 52 processes the information from AI / ML AF and selects (picks) a segmentation model with a specific decomposition. The selection can be based on its own environmental conditions (e.g., bandwidth, latency requirements, energy requirements, and / or security / privacy considerations). For example, UE 52 can select model M (M0, M1, M2) so that UE segmentation node #504 will infer the M0 subset, edge segmentation node #6 will infer M1, and cloud segmentation node #1 will infer M2. In addition to selecting segmentation decomposition / configuration candidates, the UE can also select a corresponding distribution configuration for the UE model subset. In other words, in this example, the following items are selected:

[0173]

[0174] As an example, assume that the UE chooses to run M0 locally on the UE for security or privacy reasons. In the absence of these reasons, the UE may instead choose to run M0 reasoning on edge server #6 to optimize performance criteria.

[0175] In step S509 , the AI / ML model conversation processor 52 b sends the selected combination to the AI / ML AF 51 .

[0176] In step S510 , the AI / ML AF 51 triggers the AI / ML model AS 53 to deploy the selected AI / ML model subset to each target segmentation point server.

[0177] The AF notifies the AI / ML application provider of the model selection, and in step S511, the AI / ML application provider instructs the edge segmentation node 54 and the cloud segmentation node 56 to obtain the network AI / ML model subset.

[0178] In step S512, UE 52 initiates model delivery through the AI / ML model session processor 52a. In step S513, the AI / ML model session processor establishes one or more transmission sessions with the AI / ML model AS 53. In step S514, the AI / ML model AS transmits a UE model subset that can be divided into multiple parts (sent in steps S514_1...S514_i...S514n respectively) toward the UE segmentation node 52.

[0179] In step S515 , the AI / ML model conversation processor 52 b notifies the AI / ML application 52 a of the completion of the delivery.

[0180] Continuing with the example, M0 is provided to UE 52, M1 is provided to edge device 54, and M2 is provided to cloud device 56. Note that M0 may be provided to the UE at an earlier point in time, for example by providing a link for downloading the subset in a response sent in step S507, for example.

[0181] In an embodiment, the UE 52 may request to establish a transport session to download or stream the relevant AI / ML subset, such as M0.

[0182] In another embodiment, the AI / ML AF 51 may provide UE identification, UE authorization, and other features to the AS 53.

[0183] In yet another embodiment, in step S506, the AI / ML AF 51 calculates a response to the UE based on a list of criteria, for example, ordered by latency, energy or bandwidth. An example of such a list is:

[0184] Low latency, low energy, UE BW = 1Mbps

[0185] Default #0: {#504:M0, #6:M1, #1M2},

[0186] Alternative #1: {#6:M0, #6:M1, #1M2},

[0187] Low latency, low energy, BW=8Mbps

[0188] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0189] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0190] High latency, low energy, BW=15Mbps

[0191] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0192] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0193] Low latency, medium energy, BW=4Mbps

[0194] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0195] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0196] Low latency, medium energy, BW=12Mbps

[0197] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0198] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0199] Medium latency, medium energy, BW=4Mbps

[0200] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0201] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0202] Medium latency, medium energy, BW=20Mbps

[0203] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0204] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0205] High latency, medium energy, BW = 0.5 Mbps

[0206] Default #0: {# <x> ：M0，# <y> ：M1，# <z>M2},

[0207] Alternative #1: {# ：M0，# <v> ：M1，# <w>M2},

[0208] …

[0209] In this embodiment, in step S508, the UE interprets the received information with respect to its own environmental conditions (eg, bandwidth, delay requirements, energy requirements), and selects an appropriate option, for example, providing a formula that best matches its conditions.

[0210] In another embodiment, the service announcement step S501 may indicate which optimization criteria (e.g., latency, energy, bandwidth) the UE may select. The AI / ML application may be configured with preferred criteria so that the UE pre-selects its best criteria when requesting a model from the AI / ML AF in steps S504 and S505.

[0211] Split Node Configuration and Session Establishment

[0212] Embodiment with Service Provider Origin

[0213] Figure 6 An example of a split node configuration is shown. In this example, the AF has requested to run the AI / ML subset M0 in the cloud (i.e., split node #2) and the subset M1 on the UE (i.e., split node #504). The AF also requests to establish two data transfer sessions. The first session (session ID #0611) is established to enable data acquisition to the cloud application server (AS) (e.g., data acquisition from the AI / ML application provider or another source). The second session (session ID #0622) is a downlink data session from the cloud to the UE for carrying AI / ML data, i.e., data output from M0 will be used as input by M1. It should be noted that this example uses a cloud split node (see Figure 4 (b)), but it will be understood that, as an alternative (see Figure 4 (a)) or alternatively (see Figure 4 (c)), it is also possible to use edge splitting nodes.

[0214] Figure 7 A flow chart for split node configuration and data session establishment according to an embodiment is shown.

[0215] In step S702, the AI / ML AF 74 sends a split node configuration request to the first selected split node (in this example, cloud split node #1). The request includes information for configuring and running the selected and configured AI / ML subset M0, such as information for establishing a data session and metadata identifiers for identifying data types (sensing data, AI / ML data, result data), and model identifiers.

[0216] In step S704 , the cloud segmentation node 76 configures and runs the configured AI / ML subset ( M0 in this example).

[0217] In step S706 , the cloud segmentation node 76 sends a segmentation node configuration response to the AI / ML AF 74 to notify the completion of the request.

[0218] Steps S708 to S712 are similar to steps S702 to S706, but are directed to UE splitting nodes.

[0219] In step S708, the AI / ML AF 74 sends a split node configuration request to the second selected split node (in this example, the AI / ML data session processor 72a of the UE split node #504). The request includes information for configuring and running the selected and configured AI / ML subset M1, such as information for establishing a data session and metadata identifiers for identifying data types (sensing data, AI / ML data, result data), and model identifiers.

[0220] In step S710 , the UE segmentation node 72 configures and runs the configured AI / ML subset ( M1 in this example).

[0221] In step S712 , the AI / ML data session processor 72 a sends a split node configuration response to the AI / ML AF 74 to notify the completion of the request.

[0222] At this point, the AI / ML AF 74 has received notification of successful configuration notification from the involved split nodes.

[0223] The following table shows an example of configuration information:

[0224]

[0225]

[0226] In step S714, the AI / ML AF 74 sends a split node session establishment request to establish a transport session between the cloud split node 76 as a source split node and the UE 72 as a target split node. As will be appreciated, a source split node provides data to a target split node.

[0227] In an alternative embodiment, the AI / ML AF 74 sends the split node session establishment request to the target split node instead of the source split node. In yet another alternative, the AI / ML AF 74 sends the split node session establishment request to both the target split node and the source split node, for example, to ensure secure identification and registration of peer split nodes.

[0228] In step S716, the source split node creates a data / streaming transmission session with the target split node according to the split configuration received in step S702. In this example, there is one transmission session, i.e., a downlink cloud-UE session for AI / ML data (session ID #0622; see Figure 6 ).

[0229] In step S718, the target split node sends a message to the source split node to confirm that the data session is successfully established.

[0230] In step S720, after receiving the “success message”, the source split node sends a split node session establishment response back to the AI / ML AF 74 to signal that the session establishment is successful.

[0231] In step S722, after receiving the successful establishment notification, the AI / ML AF 74 sends a segmentation model establishment notification to the source segmentation node that can receive the sensing data. The notification triggers the AI / ML application provider (or other source) to start sensing data.

[0232] It should be noted that, for example, if M0, M1, and M2 are reasoned on different devices, the method can be easily extended to include additional devices. It will be understood that a device (e.g., a device having M1) can be both a source and a target, receiving AI / ML data from one device and sending AI / ML data to another device.

[0233] Embodiment with UE source

[0234] Figure 8 Yet another example of a split node configuration is shown. In this example, the AF has requested to run the AI / ML subset M0 on the UE (i.e., split node #504) and to run the subset M1 in the cloud (i.e., split node #6). The AF also requests to establish three data transfer sessions. The first session (session ID #0811) is established to enable data acquisition from the UE (e.g., from a camera). The second session (session ID #0822) is an uplink data session from the UE to the cloud split node to carry the AI / ML data, i.e., the data output from M0 will be used as input by M1. The third session (session ID #0833) is a downlink data session from the cloud split device to the UE. It should be noted that this example uses a cloud split node (see Figure 3 (b)), but it will be understood that, as an alternative (see Figure 3 (a)) or alternatively (see Figure 3 (d)), it is also possible to use edge splitting nodes.

[0235] Fig. 9 A flow chart for splitting node configuration and session establishment according to yet another embodiment is shown.

[0236] In steps S902 and S910, the AI / ML AF 94 sends a split node configuration request to the AI / ML data session processor 92b in the UE 92 and the AI / ML data session reasoner 96a in the cloud split node #1, respectively. It will be appreciated that these steps are similar to Figure 7 Here, a "reasoner" is an entity (e.g., a processor) that performs reasoning (i.e., uses at least one AI / ML subset to process sensory data or intermediate data to perform AI / ML processing to obtain intermediate data or results).

[0237] The following table shows an example of configuration information:

[0238]

[0239]

[0240] In steps S904 and S910 , the segmentation nodes (ie, UE 92 and cloud segmentation node 96 ) respectively configure and run the configured AI / ML subsets (M1 for cloud AS, M0 for UE).

[0241] In steps S906 and S912 , the split node sends a split node configuration response to the AI / ML AF 94 to notify the completion of the request.

[0242] As can be seen, steps S902 to S912 are similar to Figure 7 At this point, the AI / ML AF 94 has received notification of successful configuration notification from the involved split nodes.

[0243] In steps S914 and S922, the AI / ML AF 94 sends a split node session establishment request to the AI / ML data session reasoner 92c in the UE 92 and the AI / ML data reasoner 96a in the cloud split server 96, respectively, to establish a transport session between the source split node in the UE and the target split node in the cloud split node. In this example, a request is sent to the source split node, i.e., data is sent, to create a transport data session with its target split node. As shown in FIG. Figure 7 As described above, the request may be sent to both the source split node and the target split node.

[0244] In steps S916 and S924, the source split node creates a data transmission session with its corresponding target split node according to the split configuration received in steps S902 and S908 respectively. Figure 8 , three transport sessions are established, namely, the uplink UE streamer-cloud (session ID#0822) for carrying AI / ML data and the downlink cloud-UE player (session ID#0833) for result data. The data session ID for running the model is ID#0800.

[0245] In steps S918 and S926 , the target split node confirms the success of establishing the data session to the source split node respectively.

[0246] In steps S920 and S928, in response to the “success message” (in steps S918 and S926, respectively), the source split node sends a split node session establishment response to the AI / ML AF 94, respectively.

[0247] In step S930, after receiving the "success message", the AI / ML AF 94 sends a segmentation model establishment notification to the source segmentation node 92a of the sensing data (ie, the AI / ML application in the UE in this example). The notification triggers the AI / ML application 92a to start sensing and providing data.

[0248] Split node configuration and session establishment using edge devices

[0249] Embodiment with UE source

[0250] This embodiment corresponds to Figure 3 (d) is the embodiment shown.

[0251] In this example, the AF has requested to run the AI / ML subset M0 on the UE, M1 on the edge device, and M2 in the cloud. The AI / ML AF also requests to establish four data transmission sessions. The first session #1011 is used for data acquisition from the UE. The second session #1022 is an uplink data session from the UE to the edge device for carrying AI / ML data. The third session #1033 is an uplink data session from the edge device to the cloud for carrying AI / ML data. The fourth session #1044 is a downlink data session from the cloud AS to the UE for carrying the results.

[0252] Depend on Fig. 10A and Fig. 10B FIG10 shows a flowchart for splitting node configuration and session establishment according to yet another embodiment.

[0253] In step S1002 , the AI / ML model AS configures the AI / ML subset to the target segmentation node.

[0254] In steps S1004 to S1008 , accordingly, the AI / ML AF 1005 sends a split node configuration request to the AI / ML data session processor 1001b in the UE 1001 , the AI / ML data session processor 1001b starts the AI / ML subset reasoning M0 , and sends a split node configuration response to the AI / ML AF 1005 .

[0255] The request provides information for configuring and running the configured AI / ML subset. This information can be used to establish a transmission data session, for example, see step S1022, including metadata identifiers for identifying data, such as data type (sensing data, AI / ML data, result data), data session (global and public data identifiers that define the entire path M0, M1, M2 of the model instance in use, and session-specific data session identifiers.

[0256] Steps S1004 to S1008 are similar to Fig. 9 Steps S902 to S906 in .

[0257] Steps S1010 to S1014 are substantially the same, except that they include the edge splitting node 1003 and the subset M1.

[0258] In a similar manner, steps S1016 to S1020 are substantially the same, except that they include the cloud segmentation node 1005 and the subset M2.

[0259] The following table shows an example of configuration information:

[0260]

[0261] At this point, if everything goes well, the AI / ML AF 1005 has received successful configuration notifications from the three split nodes.

[0262] In steps S1022, S1030 and S1038, the AI / ML AF sends split node session establishment requests to the AI / ML data session reasoners 1001c, 1003b and 1007a, respectively, to establish a transmission session between the corresponding source split node and the target split node. In this embodiment, the request is sent to the corresponding source split device, that is, the data is sent, which is responsible for creating a transmission data session with the next split device. As already described, the request can be sent to both the source split device and the target split device.

[0263] In this embodiment, the AI / ML AF plays a central role. In other embodiments ("direct mode"), the source split node (e.g., UE) directly sends a split node session establishment request to the target split node before notifying the AI / ML AF. In another embodiment ("recursive mode"), the source split node sends a split node session establishment request to its target split node, which in turn, as the source split node, sends further split node session establishment requests to its target split node until the end.

[0264] In steps S1024, S1032 and S1040, the corresponding source segmentation nodes create data transmission sessions with their corresponding target segmentation nodes according to the received segmentation configuration. In this example, three transmission sessions are established:

[0265] Uplink UE to edge for first AI / ML data (session ID #1022).

[0266] Uplink edge to cloud for second AI / ML data (session ID #1033).

[0267] Downlink cloud for result data to UE player (session ID #1044).

[0268] In steps S1026, S1034 and S1042, the corresponding target segmentation node sends a message indicating that the data session is successfully established to the corresponding source segmentation device.

[0269] In steps S1028 , S1036 , and S1044 , after receiving the message indicating success, the source segmentation device sends a segmentation device session establishment response to the AI / ML AF 1005 , respectively.

[0270] In step S1046, after receiving the successful establishment notification, the AI / ML AF 1005 sends a segmentation model establishment notification to the source server of the sensing data (ie, the UE in this example), which triggers the AI / ML application to start sensing data.

[0271] AI / ML data transfer including AI / ML metadata

[0272] AI / ML specific metadata identifiers may, for example, include one or more of the following:

[0273] • Model flow identifier: An identifier carried along with all data transfer sessions assigned to a model instance.

[0274] ○ Model Identifier: A common identifier that identifies the model within each data transfer session.

[0275] ○ Input Model Rate: Indicates the possible evolving input sensing data rate, e.g., 50%, 100%.

[0276] ● Data transfer session identifier: An identifier specific to a single data transfer session established between two split devices, for example:

[0277] ○AI / ML subset source identifier

[0278] ○AI / ML Subset Target Identifier

[0279] ○ AI / ML data transmission format, for example, 8, 16 or 32 bits

[0280] ○ AI / ML data transmission types, such as:

[0281] ■Sensory media data (e.g., image / video capture)

[0282] AI / ML data, also known as intermediate data (e.g., image / video latent codes)

[0283] ■Result data: Output "readable" data and result data types, for example:

[0284] ●Text type (e.g., text prediction cat vs. dog)

[0285] Media type (e.g., augmented video AR, video overlay), such as:

[0286] ○Video Type

[0287] ○Audio Type

[0288] ○Others…

[0289] ○ Model rate adaptation: The split device can adjust the frame rate output of the resource allocation and indicate this ratio in the entire stream, e.g. 50%, 100%

[0290] ○ AI / ML data transmission packages, such as:

[0291] ■Compressed Data Indicator

[0292] ■Compression algorithm indication

[0293] It should be noted that the result data may originate from a possible early / mid-term exit of the AI / ML model. Such result data may be fed to another AI / ML subset and thus also brought to the split node.

[0294] Fig.11 The protocol for data transmission between AI / ML segmentation devices is shown. The AI / ML application provider (#8) sends sensory data to the cloud segmentation node #1. The metadata for transmission is: model ID#1100, stream ID#1111. The cloud segmentation node uses the AI / ML subset M0 to reason about the received sensory data to obtain AI / ML data, which is sent to the AI / ML data session reasoner in the UE segmentation node #504. The metadata for transmission is: model ID#1100 (i.e., the same as the previous transmission), stream ID#1122. The UE then uses the AI / ML subset M1 to obtain the result data, which is provided to the AI / ML application in the UE.

[0295] It should be noted that although the description mentions the AI ​​ML application provider as the source of sensory data in some places, this data may also be provided by another device.

[0296] in conclusion

[0297] Although features and elements are provided above in a specific combination, it will be understood by those skilled in the art that each feature or element can be used alone or in any combination with other features and elements. The present disclosure is not limited in terms of the specific embodiments described in the present application, which are intended to be illustrations of various aspects. Without departing from its spirit and scope, many modifications and changes can be made, as will be apparent to those skilled in the art. Any element, action or instruction used in the description of the present application should not be interpreted as being critical or necessary to the present invention unless explicitly provided as such. In addition to those listed herein, functionally equivalent methods and devices within the scope of the present disclosure will be apparent to those skilled in the art according to the preceding description. Such modifications and changes are intended to fall within the scope of the appended claims. The present disclosure is limited only by the terms of the appended claims and the full scope of equivalents given by such claims. It should be understood that the present disclosure is not limited to specific methods or systems herein.

[0298] For simplicity, the foregoing embodiments are discussed with respect to terminology and structure of devices with infrared capabilities (i.e., infrared transmitters and receivers). However, the embodiments discussed are not limited to these systems, but can be applied to other systems using other forms of electromagnetic waves or non-electromagnetic waves (such as sound waves).

[0299] It will also be understood that the terms used herein are used only for the purpose of describing particular embodiments and are not intended to be limiting. As used herein, the term "video" or the term "image" may mean any of a snapshot, a single image, and / or a plurality of images displayed over a time basis. As another example, when referred to herein, the term "user equipment" and its abbreviation "UE", the term "remote" and / or the term "head mounted display" or its abbreviation "HMD" may mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of many embodiments of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities (e.g., wearable) that is configured with some or all of the structure and functionality of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities that is configured with less than all of the structure and functionality of a WTRU; or (iv) the like. References herein to Figures 1A to 1D Details of an example WTRU are provided, which may be representative of any WTRU set forth herein. As another example, various disclosed embodiments herein are described above and below as utilizing a head mounted display. Those skilled in the art will recognize that devices other than a head mounted display may be utilized, and some or all of the present disclosure and various disclosed embodiments may be modified accordingly without undue experimentation. Examples of such other devices may include drones or other devices configured to stream information to provide an adapted reality experience.

[0300] In addition, the methods provided herein may be implemented in a computer program, software, or firmware that is incorporated into a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and digital versatile disks (DVDs). A processor associated with the software may be used to implement a radio frequency transceiver for a WTRU, UE, terminal, base station, RNC, or any host computer.

[0301] Variations of the methods, devices, and systems provided above are possible without departing from the scope of the present invention. In view of the various embodiments that may be applied, it should be understood that the embodiments shown are merely examples and should not be considered to limit the scope of the appended claims. For example, the embodiments provided herein include handheld devices that may include or be used with any suitable voltage source (such as a battery, etc.) that provides any suitable voltage.

[0302] In addition, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices including processors are mentioned. These devices may include at least one central processing unit ("CPU") and memory. According to the practice of those skilled in the art of computer programming, references to actions and symbolic representations of operations or instructions may be performed by various CPUs and memories. Such actions and operations or instructions may be referred to as "execution", "computer execution", or "CPU execution".

[0303] Those of ordinary skill in the art will appreciate that the actions and symbolic representations of operations or instructions include manipulation of electrical signals by the CPU. The electrical system represents data bits, which may cause the final conversion or reduction of electrical signals and maintain the data bits in memory locations in the storage system, thereby reconfiguring or otherwise changing the operation of the CPU and other processing of signals. The memory locations where the data bits are maintained are physical locations having specific electrical, magnetic, optical, or organic properties that correspond to or represent the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs, and other platforms and CPUs may support the provided methods.

[0304] The data bits may also be maintained on a computer-readable medium, including a magnetic disk, an optical disk, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage system readable by a CPU. The computer-readable medium may include cooperating or interconnected computer-readable media that reside only on a processing system or distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories, and other platforms and memories may support the provided methods.

[0305] 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.

[0306] There is little difference between hardware and software implementations of various aspects of the system. The use of hardware or software is often (but not always, as in some cases, the choice of hardware or software may become important) a design choice that represents a cost-efficiency trade-off. There may be various vehicles (e.g., hardware, software, and / or firmware) with which the processes and / or systems and / or other technologies described herein can be implemented, and the preferred vehicle may change with the context in which the processes and / or systems and / or other technologies are deployed. For example, if the implementer determines that speed and accuracy are most important, then the implementer may select primarily hardware and / or firmware vehicles. If flexibility is most important, then the implementer may select primarily software implementations. Alternatively, the implementer may select some combination of hardware, software, and / or firmware.

[0307] The foregoing detailed description has been described various embodiments of the apparatus and / or process by using block diagrams, flow charts and / or examples. Insofar as such block diagrams, flow charts and / or examples include one or more functions and / or operations, it will be understood by those skilled in the art that each function and / or operation within such block diagrams, flow charts or examples can be implemented individually and / or collectively by a wide range of hardware, software, firmware or indeed any combination thereof. In an embodiment, several parts of the subject matter described herein may be implemented via an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP) and / or other integrated formats. However, those skilled in the art will recognize that all or part of some aspects of the embodiments disclosed herein may be equivalently implemented in an integrated circuit, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware or almost as any combination thereof, and according to the present disclosure, designing circuit systems and / or writing codes for software and / or firmware will be completely within the skill range of those skilled in the art. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein can be distributed as a program product in a variety of forms, and that the illustrative examples of the subject matter described herein apply regardless of the particular type of signal-bearing medium used to actually carry out the distribution. Examples of signal-bearing media include, but are not limited to, the following: recordable media such as floppy disks, hard drives, CDs, DVDs, digital tapes, computer memory, etc.; and transmission media such as digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0308] Those skilled in the art will recognize that it is common in the art to describe devices and / or processes in the manner set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system by a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system can typically include a system unit housing, a video display device, a memory such as volatile and non-volatile memory, a processor such as a microprocessor and a digital signal processor, a computing entity such as an operating system, a driver, a graphical user interface, and an application, one or more interactive devices such as a touch pad or screen, and / or a control system including a feedback loop and a control motor (e.g., feedback for sensing position and / or velocity; a control motor for moving and / or adjusting components and / or quantities). A typical data processing system can be implemented using any suitable commercially available components, such as components typically found in data computing / communication and / or network computing / communication systems.

[0309] The subject matter described herein sometimes illustrates different parts that are included in different other parts or connected with different other parts.It should be understood that the architecture of such description is only an example, and many other architectures that realize the same function can actually be implemented.In a conceptual sense, any arrangement of parts for realizing the same function is effectively "associated", so that the desired function can be realized.Therefore, any two parts that are combined to realize a specific function in this article can be regarded as "associated" with each other, so that no matter how the architecture or intermediate parts realize the desired function.Similarly, any two parts that are so associated can also be regarded as "operably connected" or "operably connected" to realize the desired function, and any two parts that can be so associated can also be regarded as "operably connected" to realize the desired function.The specific example that can be operably connected includes (but is not limited to) parts that can be matched physically and / or physically interact, and / or parts that can be wirelessly interacted and / or wirelessly interacted, and / or parts that can be logically interacted and / or parts that can be logically interacted.

[0310] With respect to the use of substantially any plural and / or singular terms herein, those skilled in the art can translate from the plural to the singular and / or from the singular to the plural where appropriate to the context and / or application. For clarity, the various singular / plural arrangements may be expressly set forth herein.

[0311] Those skilled in the art will understand that, in general, the terms used herein and particularly in the appended claims (e.g., the bodies of the appended claims) are generally intended to be "open" terms (e.g., the term "comprising" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "including" should be interpreted as "including but not limited to," etc.). Those skilled in the art will further understand that if a specific number of an introduced claim recitation is intended, such intent will be expressly stated in the claim, and in the absence of such a statement, such intent is not present. For example, where only one clause is intended, the term "single" or similar language may be used. To aid understanding, the following appended claims and / or the description herein may include the use of the introductory phrases "at least one" and "one or more" to introduce multiple claim recitations. However, the use of such phrases should not be interpreted as implying that a claim recitation introduced by the indefinite article "a" or "an" will limit any particular claim including such introduced claim recitation to embodiments including only one such recitation, even if the same claim includes the introductory phrases "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and / or "an" should be interpreted as meaning "at least one" or "one or more"). The same is true for the use of definite articles to introduce claim recitations. In addition, even if a specific number of introduced claim recitations is explicitly recited, one skilled in the art will recognize that such recitation should be interpreted as meaning at least the recited number (e.g., merely reciting "two recitations" without other modifiers means at least two recitations or two or more recitations). Furthermore, in those cases where a convention similar to "at least one of A, B, and C, etc." is used, generally, such construction is intended to represent the convention that one skilled in the art would understand (e.g., "a system having at least one of A, B, and C" would include but is not limited to systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). In those cases where a convention similar to "at least one of A, B, or C, etc." is used, generally, such meaning is intended in the sense that one skilled in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but is not limited to systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). One skilled in the art would further understand that any transitional words and / or phrases (whether in the specification, claims, or drawings) that actually give two or more alternatives should be understood to contemplate the possibility of including one of the items, either of the items, or both of the items. For example, the phrase "A or B" will be understood to include the possibilities of "A" or "B" or "A and B."Furthermore, as used herein, the term "any" followed by a plurality of items and / or a listing of items in a plurality of categories is intended to include "any," "any combination," "any plurality," and / or "any combination of plurality," either alone or in combination with other items and / or items in other categories. Furthermore, 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. And as used herein, the term "plurality" is intended to be synonymous with "plurality."

[0312] 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.

[0313] As will be understood by those skilled in the art, for any and all purposes, such as in providing a written description, all ranges disclosed herein also encompass any and all possible sub-ranges and combinations of sub-ranges thereof. Any listed range can be easily identified as fully describing and capable of decomposing the same range into at least equal halves, one-third, one-quarter, one-fifth, one-tenth, etc. As a non-limiting example, each range discussed herein can be easily decomposed into a lower third, a middle third, and an upper third, etc. As will be understood by those skilled in the art, all languages ​​such as "at most", "at least", "greater than", "less than", etc. include the enumerated numbers, and refer to the ranges that can be subsequently subdivided into sub-ranges as discussed above. Finally, as will be understood by those skilled in the art, the range includes each individual member. Therefore, for example, a group with 1 to 3 units refers to a group with 1, 2 or 3 units. Similarly, a group with 1 to 5 units refers to a group with 1, 2, 3, 4 or 5 units, and so on.

[0314] Furthermore, the claims should not be read as limited to the order or elements provided unless otherwise stated. In addition, the use of the term "means for..." in any claim is intended to invoke 35 U.S.C. § 112, 6 or means-plus-function claim format, and any claim without the term "means for..." is not intended to be so.< / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x> < / w> < / v> < / z> < / y> < / x>

Claims

1. A method comprising: Receiving, at the first device, information indicating a plurality of distributed artificial intelligence (AI) models from a second device, wherein each model of the plurality of distributed AI models corresponds to the same AI service; Sending a message from the first device to the second device, the message including information indicating a selected distributed AI model from among the plurality of distributed AI models, wherein the selected distributed AI model includes a plurality of model subsets constituting the AI ​​service; Receiving, at the first device, information corresponding to the selected model subset of the distributed AI model; as well as The model subset of the selected distributed AI model is run on the first device based on the information corresponding to the model subset.

2. The method according to claim 1, comprising: Prior to the receiving, information indicating a request for the AI ​​service is sent from the first device to the second device.

3. The method according to claim 1 or 2, comprising: Information indicative of the AI ​​service is received at the first device.

4. The method according to claim 3, wherein the information indicating the AI ​​service comprises: A service identifier and an indication of whether the AI ​​model for that service can be distributed across multiple devices.

5. The method of claim 1 , wherein the message further comprises information indicating at least one of: an AI engine used by the first device, whether the first device supports distributed AI models, types of devices that are allowed to execute a subset of models, and an estimated bandwidth of sensory data originating at the first device.

6. The method of claim 1, wherein the information indicating the plurality of distributed AI models comprises: Information indicating a device that already has a model subset.

7. The method according to claim 1, comprising: The selected distributed AI model is determined by the first device based on at least one environmental condition of the first device.

8. The method of claim 7, wherein the at least one environmental condition comprises: At least one of bandwidth, latency requirements, energy requirements, security considerations, and privacy considerations.

9. The method of claim 1 , wherein the subset of models is run using sensory data as input to obtain intermediate results; the method comprising: The intermediate result is outputted by the first device to a third device for running another model subset.

10. The method according to claim 9, comprising: The final result is received by the first device from a device that has inferred the final result of the selected distributed AI model.

11. The method according to claim 10, wherein: The third means is the same as the means which has inferred the final result.

12. The method according to claim 10, wherein the final result is received from the third device through the established transmission session, the method further comprising: Metadata associated with the transport session is received by the first device.

13. The method according to claim 9, wherein the intermediate result is provided to the third device through the established transmission session, the method further comprising: Metadata associated with the transport session is received by the first device.

14. The method according to claim 9, wherein the intermediate results include: Intermediate data and metadata indicating properties of the intermediate data.

15. The method of claim 1, wherein the model subset is run using an intermediate result as input to obtain a final result, the intermediate result being obtained from a third device that has inferred the intermediate result using another model subset; the method comprising: The final result is output by the first device.

16. The method of claim 1, wherein the model subset of the distributed AI model is configured for execution on at least two different devices. The method of claim 16 , wherein the boundaries between the model subsets are defined by split points.

18. The method of claim 1, wherein the message further comprises: Information indicating the selected model subset of the selected distributed AI model.

19. A first device, comprising: a memory storing program instructions executable by the processor; as well as at least one hardware processor configured to execute the program instructions to: receiving information indicating a plurality of distributed artificial intelligence (AI) models from a second device, wherein each model of the plurality of distributed AI models corresponds to the same AI service; Sending a message to the second device, the message including information indicating a selected distributed AI model from among the plurality of distributed AI models, wherein the selected distributed AI model includes a plurality of model subsets constituting the AI ​​service; as well as receiving information corresponding to the model subset of the selected distributed AI model; and The model subset of the selected distributed AI model is run based on the information corresponding to the model subset.

20. The first device of claim 19, wherein the at least one hardware processor is further configured to: Prior to the receiving, information indicating a request for the AI ​​service is sent to the second device.

21. The first device according to claim 19 or 20, wherein the at least one hardware processor is further configured to: Information indicative of the AI ​​service is received.

22. The first device according to claim 21, wherein the information indicating the AI ​​service comprises: A service identifier and an indication of whether the AI ​​model for that service can be distributed across multiple devices.

23. The first device of claim 19, wherein the message further comprises information indicating at least one of: an AI engine used by the first device, whether the first device supports distributed AI models, types of devices allowed to execute a subset of models, and an estimated bandwidth of sensory data originating at the first device.

24. The first device of claim 19, wherein the information indicating the plurality of distributed AI models comprises: Information indicating a device that already has a model subset.

25. The first device of claim 19, wherein the at least one hardware processor is further configured to: The selected distributed AI model is determined based on at least one environmental condition of the first device.

26. The first device of claim 25, wherein the at least one environmental condition comprises: At least one of bandwidth, latency requirements, energy requirements, security considerations, and privacy considerations.

27. The first apparatus of claim 19, wherein the subset of models is run using sensory data as input to obtain intermediate results, and wherein the at least one hardware processor is further configured to: The intermediate results are output to a third device for running another model subset.

28. The first device of claim 27, wherein the at least one hardware processor is further configured to: The final result of the selected distributed AI model is received from a device that has inferred the final result.

29. The first device according to claim 28, wherein: The third means is the same as the means which has inferred the final result.

30. The first device of claim 28, wherein the final result is received from the third device via an established transport session, and wherein the at least one hardware processor is further configured to receive metadata associated with the transport session.

31. The first device of claim 27, wherein the intermediate result is provided to the third device via an established transport session, and wherein the at least one hardware processor is further configured to receive metadata associated with the transport session.

32. The first apparatus of claim 27, wherein the intermediate result comprises: Intermediate data and metadata indicating properties of the intermediate data.

33. The first device of claim 19, wherein the subset of models is run using an intermediate result as input to obtain a final result, the intermediate result being obtained from a third device that has inferred the intermediate result using another subset of models, and wherein the at least one hardware processor is further configured to: The final result is output.

34. The first device of claim 19, wherein the model subset of the distributed AI model is configured for execution on at least two different devices.

35. The first apparatus of claim 34, wherein boundaries between the model subsets are defined by segmentation points.

36. The first device of claim 19, wherein the message further comprises: Information indicating the selected model subset of the selected distributed AI model.

37. The first device of claim 19, wherein the first device is a wireless transmit / receive unit (WTRU).

Images