Methods, media and apparatus for substream differentiation

Abstract

By distinguishing between important data and less important data in a data packet, the important data may be transmitted more reliably than data identified as less important. This differentiation may be particularly useful when the data is part of the data exchange related to the training and use of the AI / ML model. By establishing a higher priority, a higher reliability, or a higher degree of protection for data determined to be more important, processing dependent on the important data may be shown to be completed at a higher efficiency.

Description

Technical Field

[0001] The present disclosure relates generally to data communications and, in particular embodiments, to distinguishing an important data substream from another data substream within a data stream and sending the important data substream with higher reliability than the other data substreams. Background Art

[0002] In wireless communication networks, user equipment (UE) is typically served by a base station (BS). Artificial intelligence (AI) strategies, particularly machine learning (ML) strategies, are currently being researched to enhance communication between UE and BS. One specific type of ML is associated with the "wireless federated learning (FL)" model.

[0003] Wireless FL technology can be understood as a machine learning technology that can be used to train models, generally referred to as AI / ML models, on multiple distributed edge nodes (e.g., UEs, next-generation NodeBs, "gNBs"). According to wireless FL technology, the base station can provide a set of model parameters (e.g., weights, biases, gradients) describing the global AI / ML model to the UE. The UE can initialize a local AI / ML model using the received global AI / ML model parameters. The UE can then train the local AI / ML model using local data samples, thereby generating a trained local AI / ML model. The UE can then provide a set of AI / ML model parameters describing the local AI / ML model to the base station.

[0004] This single round trip (from the BS to the UE) and back (from the UE to the BS) of AI / ML model parameters can be understood as just one exchange of AI / ML model parameters within multiple exchanges of AI / ML model parameters. Multiple exchanges of AI / ML model parameters can be associated with performing iterative wireless FL techniques. It should be noted that wireless FL techniques do not involve the exchange of local data samples. In fact, the local data samples remain on the corresponding UE.

[0005] Upon receiving multiple sets of AI / ML model parameters describing the corresponding local AI / ML models at multiple UEs from multiple UEs, the BS can aggregate the local AI / ML model parameters reported by the multiple UEs and update the global AI / ML model based on this aggregation. The subsequent iterations proceed in a very similar manner to the first iteration. The BS and UEs can then perform multiple iterations until the global AI / ML model is considered finalized. Summary of the Invention

[0006] By distinguishing between important and less important substreams of a data stream, the important substreams can be sent more reliably than substreams identified as less important. This distinction can be particularly useful when the data is part of a data exchange related to the training and use of AI / ML models. By establishing a higher priority, higher reliability, or higher degree of protection for data identified as more important, processing that relies on the important data can be shown to be completed with greater efficiency.

[0007] It can be considered that the amount of data exchanged when the BS and the UE exchange AI / ML model parameters is too high. In addition, it can be shown that a large part of the data exchanged when the BS and the UE exchange AI / ML model parameters is redundant.

[0008] Various aspects of this application relate to identifying important data within a data stream, particularly when the data within the data stream represents AI / ML model parameters. Various aspects of this application relate to defining a format for local services. Various aspects of this application relate to designs for prioritizing the sending of data identified as important data. That is, important data can receive a first priority, and less important data can receive a second priority. The second priority can be, for example, a best-effort priority.

[0009] Various aspects of this application relate to the design of a local service format for air interface transmission. This design enables transmission of sub-streams with unequal protection. Conveniently, it can be shown that by using such a design, air interface overhead is significantly reduced without significantly degrading AI / ML model performance.

[0010] Conveniently, various aspects of the present application relate to supporting dynamic indication of classification of data into category A and data into category B. It can be shown that by dynamically changing the importance of given data, the performance of training AI models can be improved.

[0011] Various aspects of the present disclosure may be illustrated to reduce air interface overhead by using a differentiated transmission scheme based on an identification of the quality of data carried by a superframe.

[0012] According to one aspect of the present disclosure, a method is provided. The method includes receiving a data packet, the data packet including a first portion, wherein the first portion of the data packet is represented by bits of a first category; and a second portion, wherein the second portion of the data packet is represented by bits of a second category. The method also includes transmitting the bits of the first category using a first air interface configuration; and transmitting the bits of the second category using a second air interface configuration.

[0013] According to one aspect of the present disclosure, a device is provided. The device includes a memory storing instructions and a processor. The processor can execute the instructions to: receive a data packet, the data packet including: a first portion, wherein the first portion of the data packet is represented by bits of a first category; a second portion, wherein the second portion of the data packet is represented by bits of a second category; transmit the bits of the first category using a first air interface configuration; and transmit the bits of the second category using a second air interface configuration.

[0014] According to one aspect of the present disclosure, a method is provided, wherein the method includes sending a superframe to a user equipment (UE), wherein the superframe includes bits of a first category and bits of a second category.

[0015] According to one aspect of the present disclosure, a device is provided. The device includes a memory storing instructions and a processor. The processor can execute the instructions to send a superframe to user equipment (UE), wherein the superframe includes bits of a first category and bits of a second category.

[0016] According to one aspect of the present disclosure, a method is provided, comprising: indicating the quality of a superframe to a user equipment (UE), wherein the quality of the superframe is related to the importance of content of the superframe as the content is applied to system performance; and sending the superframe to the UE.

[0017] According to one aspect of the present disclosure, a device is provided. The device includes a memory storing instructions and a processor. The processor can execute the instructions to indicate the quality of a superframe to user equipment (UE), wherein the quality of the superframe is related to the importance of content of the superframe as the content is applied to system performance; and transmit the superframe to the UE.

[0018] According to one aspect of the present disclosure, a method is provided, comprising: indicating a quality of a superframe to a user equipment (UE); and sending the superframe to the UE.

[0019] According to one aspect of the present disclosure, a method is provided, comprising: receiving configuration information from a base station; generating a superframe according to the configuration information, the superframe having quality; indicating the quality of the superframe to the base station; and sending the superframe to the base station.

[0020] According to one aspect of the present disclosure, a method is provided, comprising: receiving configuration information from a base station; generating a superframe according to the configuration information, the superframe having a type; indicating the type of the superframe to the base station; and sending the superframe to the base station. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] For a more complete understanding of the embodiments of the present disclosure and their advantages, the following description is given below with reference to the accompanying drawings, by way of example, wherein:

[0022] Figure 1 A communication system in which embodiments of the present disclosure may occur is shown in a schematic diagram, the communication system including a plurality of exemplary electronic devices and a plurality of exemplary transmission reception points and various networks;

[0023] Figure 2 The block diagram shows Figure 1 A communication system comprising a plurality of exemplary electronic devices, exemplary terrestrial transmission and reception points, exemplary non-terrestrial transmission and reception points, and various networks;

[0024] Figure 3 As a block diagram showing various aspects of the present application provided Figure 2 Elements of an exemplary electronic device, Figure 2 Elements of an exemplary terrestrial transmission reception point and Figure 2 Elements of an exemplary non-terrestrial transmission reception point;

[0025] Figure 4 As a block diagram, various modules provided by various aspects of the present application that may be included in an exemplary electronic device, an exemplary terrestrial transmission and reception point, and an exemplary non-terrestrial transmission and reception point are shown;

[0026] Figure 5 As a block diagram, the perception management functionality provided by various aspects of the present application is shown;

[0027] Figure 6 Exemplary steps in the method for transmitting data provided in various aspects of the present application are shown;

[0028] Figure 7 shows a table filled with examples of Category A data and Category B data provided in various aspects of the present application;

[0029] Figure 8 The structure of the superframe format provided by various aspects of the present application is shown;

[0030] Figure 9 A diagram is shown providing various aspects of the present application, the diagram including exemplary aspects of transmission protection in a network cross-referenced with data categories;

[0031] Figure 10 An example of a joint instruction table provided in various aspects of the present application is shown;

[0032] Figure 11A It shows that various aspects of this application provide Figure 8 The local service superframe is generated in a manner consistent with the local service superframe format shown;

[0033] Figure 11B The local service superframe of FIG. 11 is shown divided into three segments as provided in various aspects of the present application;

[0034] Figure 11C The local traffic superframe of FIG. 11 is shown divided into two segments as provided in various aspects of the present application;

[0035] Figure 12 Exemplary steps in the method for transmitting data provided in various aspects of the present application are shown;

[0036] Figure 13 A superframe type table provided in various aspects of the present application is shown;

[0037] Figure 14 Exemplary steps in the method for transmitting data provided in various aspects of the present application are shown;

[0038] Figure 15 An exemplary unified table provided by various aspects of the present application is shown;

[0039] Figure 16A An exemplary table provided by various aspects of the present application for the case where the local business type is AI / ML data is shown;

[0040] Figure 16B An exemplary table for the case where the local service type is sensing data provided by various aspects of the present application is shown;

[0041] Figure 17 An exemplary air interface transmission configuration table provided in various aspects of the present application is shown. DETAILED DESCRIPTION

[0042] For illustrative purposes, specific exemplary embodiments will be explained in greater detail below with reference to the accompanying drawings.

[0043] The embodiments described herein represent information sufficient to practice the claimed subject matter and illustrate methods for practicing such subject matter. After reading the following description in light of the accompanying drawings, those skilled in the art will understand the concepts of the claimed subject matter and will recognize that applications of these concepts are not specifically mentioned herein. It should be understood that these concepts and applications are within the scope of this disclosure and the appended claims.

[0044] Furthermore, it should be understood that any module, component, or device disclosed herein that executes instructions may include or otherwise access one or more non-transitory computer / processor readable storage media for storing information, such as computer / processor readable instructions, data structures, program modules, and / or other data. A non-exhaustive list of examples of non-transitory computer / processor readable storage media includes magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices, compact disc read-only memory (CD-ROM), digital video disc or digital versatile disc (DVD), Blu-ray disc, and the like. TM Optical discs, or other optical storage, volatile and non-volatile, removable and non-removable media implemented in any method or technology, random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other storage technology. Any of these non-transitory computer / processor storage media can be part of a device or can be accessed or connected by a device. Computer / processor readable / executable instructions for implementing the applications or modules described herein can be stored or otherwise maintained by such non-transitory computer / processor readable storage media.

[0045] refer to Figure 1, a simplified schematic diagram of a communication system is provided as an illustrative example and not by way of limitation. Communication system 100 includes a radio access network 120. Radio access network 120 may be a next generation (e.g., sixth generation (6G) or higher) radio access network, or a legacy (e.g., 5G, 4G, 3G, or 2G) radio access network. One or more communication electrical devices (EDs) 110a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, 110j (generally referred to as 110) may be interconnected with one another or connected to one or more network nodes (170a, 170b, generally referred to as 170) in radio access network 120. Core network 130 may be part of the communication system and may be dependent on or independent of the radio access technology used in communication system 100. Furthermore, communication system 100 includes a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160.

[0046] Figure 2 An exemplary communication system 100 is shown. Generally, the communication system 100 enables multiple wireless or wired elements to transmit data and other content. The purpose of the communication system 100 may be to provide content such as voice, data, video, and / or text via broadcast, multicast, and unicast. The communication system 100 may operate by sharing resources (e.g., carrier spectrum bandwidth) among its components. The communication system 100 may include a terrestrial communication system and / or a non-terrestrial communication system. The communication system 100 may provide a wide range of communication services and applications (e.g., earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery and mobility, etc.). The communication system 100 may provide high availability and robustness through the joint operation of terrestrial and non-terrestrial communication systems. For example, integrating a non-terrestrial communication system (or its components) into a terrestrial communication system may enable a heterogeneous network comprising multiple layers. Compared to traditional communication networks, heterogeneous networks can achieve better overall performance through efficient multi-link joint operation, more flexible function sharing, and faster physical layer link switching between terrestrial and non-terrestrial networks.

[0047] Ground communication systems and non-ground communication systems can be considered as subsystems of the communication system. Figure 2In the example shown in FIG, a communication system 100 includes electronic devices (EDs) 110a, 110b, 110c, and 110d (generally referred to as EDs 110), radio access networks (RANs) 120a and 120b, a non-terrestrial communication network 120c, a core network 130, a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160. RANs 120a and 120b include respective base stations (BSs) 170a and 170b, which may be generally referred to as terrestrial transmit and receive points (T-TRPs) 170a and 170b. Non-terrestrial communication network 120c includes an access node 172, which may be generally referred to as a non-terrestrial transmit and receive point (NT-TRP) 172.

[0048] Any ED 110 may alternatively or additionally be configured to connect, access, or communicate with any T-TRP 170a and 170b, NT-TRP 172, the Internet 150, core network 130, PSTN 140, other network 160, or any combination thereof. In some examples, ED 110a may communicate uplink and / or downlink with T-TRP 170a via terrestrial air interface 190a. In some examples, EDs 110a, 110b, 110c, and 110d may also communicate directly with one another via one or more sidelink air interfaces 190b. In some examples, ED 110d may communicate uplink and / or downlink with NT-TRP 172 via non-terrestrial air interface 190c.

[0049] The air interfaces 190a and 190b may utilize similar communication technologies, such as any suitable radio access technology. For example, the communication system 100 may implement one or more channel access methods in the air interfaces 190a and 190b, such as code division multiple access (CDMA), space division multiple access (SDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), or direct Fourier transform spread OFDMA (DFT-OFDMA). The air interfaces 190a and 190b may utilize other high-dimensional signal spaces, which may involve a combination of orthogonal and / or non-orthogonal dimensions.

[0050] The non-terrestrial air interface 190c may enable communication between ED 110d and one or more NT-TRPs 172 via a wireless link or a simple link. For some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection between a group of EDs 110 and one or more NT-TRPs 175 for multicast transmission.

[0051] The RANs 120a and 120b communicate with the core network 130 to provide various services, such as voice, data, and other services, to the EDs 110a, 110b, and 110c. The RANs 120a and 120b and / or the core network 130 may communicate directly or indirectly with one or more other RANs (not shown), which may or may not be directly served by the core network 130 and may or may not employ the same radio access technology as the RANs 120a and / or RANs 120b. The core network 130 may also serve as a gateway access between (i) the RANs 120a and 120b and / or the EDs 110a, 110b, and 110c and (ii) other networks, such as the PSTN 140, the Internet 150, and other networks 160. Furthermore, some or all of the EDs 110a, 110b, and 110c may include functionality for communicating with different wireless networks over different wireless links using different radio technologies and / or protocols. Instead of (or in addition to) wireless communication, EDs 110a, 110b, and 110c may also communicate with a service provider or switch (not shown) and with the Internet 150 via wired communication channels. PSTN 140 may include a circuit-switched telephone network for providing plain old telephone service (POTS). Internet 150 may include computer networks and / or subnets (intranets) and include protocols such as the Internet Protocol (IP), Transmission Control Protocol (TCP), and User Datagram Protocol (UDP). EDs 110a, 110b, and 110c may be multimode devices capable of operating in accordance with multiple wireless access technologies and include multiple transceivers necessary to support these wireless access technologies.

[0052] Figure 3Another example of an ED 110 and base stations 170a, 170b, and / or 170c is shown. ED 110 is used to connect people, objects, machines, and the like. ED 110 can be used in a wide variety of scenarios, such as cellular communications, device-to-device (D2D), vehicle-to-everything (V2X), peer-to-peer (P2P), machine-to-machine (M2M), machine-type communication (MTC), the Internet of Things (IoT), virtual reality (VR), augmented reality (AR), mixed reality (MR), virtual reality, digital twins, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearable devices, smart transportation, smart cities, drones, robotics, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery and mobility, and the like.

[0053] Each ED 110 represents any suitable end-user device for wireless operation and may include devices such as (or may be referred to as) user equipment / device (UE), wireless transmit / receive unit (WTRU), mobile station, fixed or mobile subscriber unit, cellular phone, station (STA), machine type communication (MTC) device, personal digital assistant (PDA), smartphone, laptop, computer, tablet, wireless sensor, consumer electronic device, wearable device (e.g., watch, head-mounted device, glasses), smart book, vehicle, car, truck, bus, train or IoT device, industrial equipment or devices in the above devices (e.g., communication module, modem, or chip), etc. The next generation ED 110 may be referred to using other terms. Base stations 170a and 170b are each T-TRPs, hereinafter referred to as T-TRPs 170. Also in Figure 3, the NT-TRP is hereinafter referred to as NT-TRP 172. Each ED 110 connected to T-TRP 170 and / or NT-TRP 172 may be dynamically or semi-statically turned on (i.e., established, activated, or enabled), turned off (i.e., released, deactivated, or disabled), and / or configured in response to one or more of connection availability and connection necessity.

[0054] ED 110 includes a transmitter 201 and a receiver 203 coupled to one or more antennas 204. Only one antenna 204 is shown. Alternatively, one, some, or all of the antennas 204 may be panels. Transmitter 201 and receiver 203 may be integrated into, for example, a transceiver. A transceiver is used to modulate data or other content for transmission by the at least one antenna 204 or a network interface controller (NIC). A transceiver may also be used to demodulate data or other content received by the at least one antenna 204. Each transceiver includes any suitable structure for generating signals for wireless or wired transmission and / or for processing signals received wirelessly or wired. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals.

[0055] ED 110 includes at least one memory 208. Memory 208 stores instructions and data used, generated, or collected by ED 110. For example, memory 208 may store software instructions or modules for implementing some or all of the functionality and / or embodiments described herein and executed by one or more processing units (e.g., processor 210). Each memory 208 includes any suitable one or more volatile and / or non-volatile storage and retrieval devices. Any suitable type of memory may be used, such as random access memory (RAM), read-only memory (ROM), a hard disk, an optical disk, a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, an on-processor cache, and the like.

[0056] ED 110 may also include one or more input / output devices (not shown) or interfaces (e.g., Figure 1The input / output devices can interact with users or other devices in the network. Each input / output device includes any suitable structure for providing information to or receiving information from a user, such as a speaker, microphone, keypad, keyboard, display, or touch screen, including network interface communications.

[0057] ED 110 includes a processor 210 for performing operations, including those related to preparing transmissions for uplink transmission to NT-TRP 172 and / or T-TRP 170, processing downlink transmissions received from NT-TRP 172 and / or T-TRP 170, and processing sidelink transmissions to and from another ED 110. Processing operations related to preparing transmissions for uplink transmission may include operations such as encoding, modulation, transmit beamforming, and generating symbols for transmission. Processing operations related to processing downlink transmissions may include operations such as receive beamforming, demodulating, and decoding received symbols. Depending on the embodiment, the downlink transmission may be received by receiver 203, possibly using receive beamforming, and processor 210 may extract signaling from the downlink transmission (e.g., by detecting and / or decoding the signaling). An example of signaling may be a reference signal transmitted by NT-TRP 172 and / or T-TRP 170. In some embodiments, processor 210 implements transmit beamforming and / or receive beamforming based on an indication of a beam direction, such as beam angle information (BAI), received from T-TRP 170. In some embodiments, processor 210 may perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as operations related to detecting synchronization sequences, decoding, and acquiring system information. In some embodiments, processor 210 may perform channel estimation, for example, using reference signals received from NT-TRP 172 and / or T-TRP 170.

[0058] Although not shown, the processor 210 may form part of the transmitter 201 and / or the receiver 203. Although not shown, the memory 208 may form part of the processor 210.

[0059] The processor 210 and the processing components of the transmitter 201 and the processing components of the receiver 203 may each be implemented by one or more processors that are the same or different and are used to execute instructions stored in a memory (e.g., the memory 208). Alternatively, the processor 210 and some or all of the processing components of the transmitter 201 and the processing components of the receiver 203 may each be implemented using dedicated circuits, such as a programmed field-programmable gate array (FPGA), a central processing unit (CPU), a graphics processing unit (GPU), or an application-specific integrated circuit (ASIC).

[0060] In some implementations, the T-TRP 170 may use other names, such as base station, base transceiver station (BTS), wireless base station, network node, network device, network-side device, transmitting / receiving node, Node B, evolved NodeB (eNodeB or eNB), Home eNodeB, next generation NodeB (gNB), transmission point (TP), site controller, access point (AP), wireless router, relay station, remote radio head, ground node, ground network device, ground base station, base band unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), centralized unit (CU), distributed unit (DU), positioning node, etc. The T-TRP 170 may be a macro BS, a micro BS, a relay node, a host node, etc., or a combination thereof. T-TRP 170 may refer to the aforementioned device or to a means (eg, a communication module, a modem, or a chip) in the aforementioned device.

[0061] In some embodiments, various components of the T-TRP 170 may be distributed. For example, some modules of the T-TRP 170 may be located remotely from the device housing the antenna 256 of the T-TRP 170 and may be coupled to the device housing the antenna 256 via a communication link (not shown) (sometimes referred to as a fronthaul, such as a common public radio interface (CPRI)). Thus, in some embodiments, the term T-TRP 170 may also refer to network-side modules that perform processing operations such as ED 110 location determination, resource allocation (scheduling), message generation, and encoding / decoding, and these modules are not necessarily part of the device housing the antenna 256 of the T-TRP 170. These modules may also be coupled to other T-TRPs. In some embodiments, the T-TRP 170 may actually be multiple T-TRPs that operate together to serve the ED 110, for example, by using coordinated multi-point transmission.

[0062] like Figure 3As shown, the T-TRP 170 includes at least one transmitter 252 and at least one receiver 254 coupled to one or more antennas 256. Only one antenna 256 is shown. Alternatively, one, some, or all of the antennas 256 may be panels. The transmitter 252 and receiver 254 may be integrated into a transceiver. The T-TRP 170 also includes a processor 260 for performing operations, including operations related to preparing transmissions for downlink transmission to the ED 110, processing uplink transmissions received from the ED 110, preparing transmissions for backhaul transmission to the NT-TRP 172, and processing transmissions received from the NT-TRP 172 via the backhaul. Processing operations related to preparation for downlink or backhaul transmissions may include operations such as coding, modulation, precoding (e.g., multiple input multiple output (MIMO) precoding), transmit beamforming, and generating symbols for transmission. Processing operations associated with processing transmissions received in uplink transmissions or via backhaul transmissions may include operations such as receive beamforming, demodulation, and decoding of received symbols. Processor 260 may also perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as generating the content of a synchronization signal block (SSB) and generating system information. In some embodiments, processor 260 also generates an indication of a beam direction (e.g., a BAI), which may be scheduled by scheduler 253 for transmission. Processor 260 performs other network-side processing operations described herein, such as determining the location of ED 110 and determining the location to deploy NT-TRP 172. In some embodiments, processor 260 may generate signaling, such as configuring one or more parameters of ED 110 and / or one or more parameters of NT-TRP 172. Any signaling generated by processor 260 is transmitted by transmitter 252. It should be noted that the term "signaling" as used herein may also be referred to as control signaling. Dynamic signaling can be transmitted in a control channel (e.g., physical downlink control channel (PDCCH)), and static or semi-static high-layer signaling can be included in packets transmitted in a data channel (e.g., physical downlink shared channel (PDSCH)).

[0063] Scheduler 253 may be coupled to processor 260. Scheduler 253 may be included within T-TRP 170 or operate separately from T-TRP 170. Scheduler 253 may schedule uplink transmissions, downlink transmissions, and / or backhaul transmissions, including issuing scheduling grants and / or configuring scheduling-free (“configured grants”) resources. T-TRP 170 also includes memory 258 for storing information and data. Memory 258 stores instructions and data used, generated, or collected by T-TRP 170. For example, memory 258 may store software instructions or modules executed by processor 260 for implementing some or all of the functionality and / or embodiments described herein.

[0064] Although not shown, the processor 260 may form part of the transmitter 252 and / or the receiver 254. Furthermore, although not shown, the processor 260 may implement the scheduler 253. Although not shown, the memory 258 may form part of the processor 260.

[0065] The processor 260, the scheduler 253, and the processing components of the transmitter 252 and the processing components of the receiver 254 may each be implemented by the same or different one or more processors that execute instructions stored in a memory (e.g., the memory 258). Alternatively, some or all of the processor 260, the scheduler 253, and the processing components of the transmitter 252 and the processing components of the receiver 254 may be implemented using dedicated circuits (e.g., an FPGA, a CPU, a GPU, or an ASIC).

[0066] It should be noted that the NT-TRP 172 is shown as a drone only as an example, and the NT-TRP 172 can be implemented in any suitable non-ground form, such as a high-altitude platform, a satellite, a high-altitude platform serving as an international mobile communication base station, and an unmanned aerial vehicle, which will be discussed below. In addition, in some implementations, the NT-TRP 172 may use other names, such as a non-ground node, a non-ground network device, or a non-ground base station. The NT-TRP 172 includes a transmitter 272 and a receiver 274 coupled to one or more antennas 280. Only one antenna 280 is shown. One, some, or all of the antennas may alternatively be a panel. The transmitter 272 and the receiver 274 may be integrated into a transceiver. NT-TRP 172 also includes a processor 276 for performing operations, including those related to preparing transmissions for downlink transmission to ED 110, processing uplink transmissions received from ED 110, preparing transmissions for backhaul transmission to T-TRP 170, and processing transmissions received from T-TRP 170 via the backhaul. Processing operations related to preparing transmissions for downlink or backhaul transmissions may include encoding, modulation, precoding (e.g., MIMO precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing transmissions received in uplink transmissions or via the backhaul may include receive beamforming, demodulating received signals, and decoding received symbols. In some embodiments, processor 276 implements transmit beamforming and / or receive beamforming based on beam direction information (e.g., BAI) received from T-TRP 170. In some embodiments, processor 276 may generate signaling, such as to configure one or more parameters of ED 110. In some embodiments, NT-TRP 172 implements physical layer processing but does not implement higher-layer functionality, such as media access control (MAC) or radio link control (RLC) layer functionality. This is merely an example; more generally, NT-TRP 172 may implement higher-layer functionality in addition to physical layer processing.

[0067] The NT-TRP 172 also includes a memory 278 for storing information and data. Although not shown, the processor 276 may form part of the transmitter 272 and / or the receiver 274. Although not shown, the memory 278 may form part of the processor 276.

[0068] Processor 276 and the processing components of transmitter 272 and receiver 274 can each be implemented by one or more processors, either the same or different, that execute instructions stored in memory (e.g., memory 278). Alternatively, processor 276 and some or all of the processing components of transmitter 272 and receiver 274 can be implemented using dedicated circuitry (e.g., a programmed FPGA, CPU, GPU, or ASIC). In some embodiments, NT-TRP 172 can actually be multiple NT-TRPs that operate together to serve ED 110, for example, via coordinated multi-point transmission.

[0069] The T-TRP 170 , NT-TRP 172 , and / or ED 110 may include other components, but these components are omitted for clarity.

[0070] according to Figure 4 , one or more steps of the methods of each embodiment provided herein may be performed by corresponding units or modules. Figure 4 Units or modules in a device are shown, such as units or modules in ED 110, T-TRP 170, or NT-TRP 172. For example, a signal can be sent by a sending unit or sending module. A signal can be received by a receiving unit or receiving module. A signal can be processed by a processing unit or processing module. Other steps can be performed by an artificial intelligence (AI) or machine learning (ML) module. The corresponding units or modules can be implemented using hardware, one or more components or devices that execute software, or a combination thereof. For example, one or more of the units or modules can be an integrated circuit, such as a programmed FPGA, CPU, GPU, or ASIC. It should be understood that if the above modules are implemented using software for execution by a processor, etc., these modules can be retrieved by the processor in whole or in part as needed, retrieved individually or collectively for processing, retrieved in one or more instances as needed, and these modules themselves can include instructions for further deployment and instantiation.

[0071] Other details about ED 110, T-TRP 170, and NT-TRP 172 are known to those skilled in the art. Therefore, these details are omitted here.

[0072] An air interface typically includes a number of components and associated parameters that together specify how transmissions are sent and / or received over a wireless communication link between two or more communication devices. For example, an air interface may include one or more components that define one or more waveforms, one or more frame structures, one or more multiple access schemes, one or more protocols, one or more coding schemes, and / or one or more modulation schemes for transmitting information (e.g., data) over a wireless communication link. A wireless communication link may support a link between a radio access network and a user equipment (e.g., a "Uu" link), and / or a wireless communication link may support a link between devices, such as a link between two user equipment (e.g., a "sidelink"), and / or a wireless communication link may support a link between a non-terrestrial (NT) communication network and a user equipment (UE). The following are some examples of the aforementioned components.

[0073] The waveform component can specify the shape and form of the transmitted signal. Waveform options can include orthogonal multiple access waveforms and non-orthogonal multiple access waveforms. Non-limiting examples of such waveform options include orthogonal frequency division multiplexing (OFDM), direct Fourier transform spread OFDM (DFT-OFDM), filtered OFDM (f-OFDM), time-domain windowed OFDM, filter bank multicarrier (FBMC), universal filtered multicarrier (UFMC), generalized frequency division multiplexing (GFDM), wavelet packet modulation (WPM), faster than Nyquist (FTN) waveforms, and low peak-to-average power ratio waveforms (low PAPR WF).

[0074] The frame structure component may specify the configuration of a frame or a group of frames. The frame structure component may indicate one or more of the time, frequency, pilot signature, code, or other parameters of the frame or group of frames. Further details of the frame structure will be discussed below.

[0075] The multiple access scheme component can specify multiple access technology options, including technologies that define how communication devices share a common physical channel, such as: TDMA; FDMA; CDMA; SDMA; OFDMA; SC-FDMA; low-density signature multicarrier CDMA (LDS-MC-CDMA); non-orthogonal multiple access (NOMA); pattern division multiple access (PDMA); lattice partition multiple access (LPMA); resource spread multiple access (RSMA); and sparse code multiple access (SCMA). In addition, the multiple access technology options can include: scheduled access versus unscheduled access, also known as unlicensed access; non-orthogonal multiple access versus orthogonal multiple access, for example, via dedicated channel resources (e.g., not shared between multiple communication devices); contention-based shared channel resources versus non-contention-based shared channel resources; and cognitive radio-based access.

[0076] The hybrid automatic repeat request (HARQ) protocol component may specify how transmission and / or retransmissions are performed. Non-limiting examples of transmission and / or retransmission mechanism options include a mechanism for specifying a scheduling data pipe size, a signaling mechanism for transmission and / or retransmission, and a retransmission mechanism.

[0077] The coding and modulation component can specify how the information being transmitted is encoded / decoded and modulated / demodulated for transmission / reception. Coding can refer to error detection and forward error correction methods. Non-limiting examples of coding options include turbo trellis codes, turbo product codes, fountain codes, low-density parity-check codes, and polar codes. Modulation can simply refer to the constellation (including, for example, the modulation technique and order), or more specifically to various types of advanced modulation methods, such as layered modulation and low PAPR modulation.

[0078] In some embodiments, the air interface can be a "one size fits all" concept. For example, once the air interface is defined, the components within the air interface may not be able to be changed or adjusted. In some implementations, only limited air interface parameters or modes can be configured, such as the cyclic prefix (CP) length or the MIMO mode. In some embodiments, the air interface design can provide a unified or flexible framework to support frequencies below the known 6 GHz band and frequencies above the 6 GHz band (e.g., millimeter wave bands) for authorized access and unauthorized access. For example, scalable system parameters and symbol durations provide flexibility for the configurable air interface, thereby supporting transmission parameter optimization for different spectrum bands and different services / devices. For another example, the unified air interface can be self-contained in the frequency domain, and the frequency domain self-contained design can support more flexible RAN slicing by sharing channel resources between different services in frequency and time.

[0079] The frame structure is a characteristic of the wireless communication physical layer that defines the structure of time-domain signal transmission. For example, it supports timing reference and timing adjustment for basic time-domain transmission units. Wireless communications between communication devices can occur over time-frequency resources controlled by the frame structure. The frame structure is sometimes referred to as the radio frame structure.

[0080] Depending on the frame structure and / or the frame configuration in the frame structure, frequency division duplex (FDD) and / or time division duplex (TDD) and / or full duplex (FD) communication can be performed. FDD communication means that transmissions in different directions (e.g., uplink and downlink) occur on different frequency bands. TDD communication means that transmissions in different directions (e.g., uplink and downlink) occur in different durations. FD communication means that transmission and reception occur on the same time-frequency resources, that is, the device can send and receive on the same frequency resources at the same time.

[0081] An example of a frame structure is a frame structure specified for a known long-term evolution (LTE) cellular system, which has the following specifications: each frame has a duration of 10 ms; each frame has 10 subframes, each subframe has a duration of 1 ms; each subframe includes two time slots, each time slot has a duration of 0.5 ms; each time slot is used to transmit 7 OFDM symbols (assuming a normal CP); each OFDM symbol has a symbol duration and a specific bandwidth (or partial bandwidth or bandwidth partition) related to the number of subcarriers and the subcarrier spacing; the frame structure is based on OFDM waveform parameters such as subcarrier spacing and CP length (wherein the CP has a fixed length or a finite length option); the switching gap between the uplink and downlink in TDD is specified to be an integer multiple of the OFDM symbol duration.

[0082] Another example of a frame structure is the frame structure specified for a known new radio (NR) cellular system, which has the following specifications: multiple subcarrier spacings are supported, each subcarrier spacing corresponds to a corresponding system parameter; the frame structure depends on the system parameters, but in any case, the frame length is set to 10ms, each frame consists of 10 subframes, and each subframe has a duration of 1ms; a time slot is defined as 14 OFDM symbols; the time slot length depends on the system parameters. For example, the NR frame structure for a normal CP 15kHz subcarrier spacing ("system parameter 1") and the NR frame structure for a normal CP 30kHz subcarrier spacing ("system parameter 2") are different. For a 15kHz subcarrier spacing, the time slot length is 1ms; for a 30kHz subcarrier spacing, the time slot length is 0.5ms. The NR frame structure can have higher flexibility than the LTE frame structure.

[0083] Another example of a frame structure is for example used in 6G networks or higher versions of networks. In a flexible frame structure, a symbol block can be defined as having a duration that is the shortest duration that can be scheduled in the flexible frame structure. A symbol block can be a transmission unit with an optional redundant part (e.g., a CP part) and an information (e.g., data) part. An OFDM symbol is an example of a symbol block. A symbol block may also be referred to as a symbol alternatively. Embodiments of the flexible frame structure include different configurable parameters, such as frame length, subframe length, symbol block length, etc. In some embodiments of the flexible frame structure, a non-exhaustive list of possible configurable parameters includes: frame length; subframe duration; time slot configuration; subcarrier spacing (SCS); flexible transmission duration of a basic transmission unit; and flexible switching gap.

[0084] The frame length does not need to be limited to 10ms, and the frame length can be configurable and change over time. In some embodiments, each frame includes one or more downlink synchronization channels and / or one or more downlink broadcast channels, and each synchronization channel and / or broadcast channel can be transmitted in different directions through different beamforming. The frame length can be multiple possible values ​​and is configured according to the application scenario. For example, an autonomous vehicle may require relatively fast initial access, in which case the frame length corresponding to the autonomous vehicle application can be set to 5ms. For another example, a smart meter on a house may not require fast initial access, in which case the frame length corresponding to the smart meter application can be set to 20ms.

[0085] Depending on the implementation, subframes may or may not be defined in the flexible frame structure. For example, a frame may be defined to include time slots but not subframes. In frames where subframes are defined, for example, for time domain alignment, the subframe duration may be configurable. For example, the subframe length may be configured to be 0.1ms, 0.2ms, 0.5ms, 1ms, 2ms, 5ms, etc. In some embodiments, if subframes are not required in a particular scenario, the subframe length may be defined to be the same as the frame length, or it may be undefined.

[0086] Depending on the implementation, time slots may or may not be defined in a flexible frame structure. In a frame where time slots are defined, the definition of the time slots (e.g., in terms of duration and / or number of symbol blocks) may be configurable. In one embodiment, the time slot configuration is common to all UEs 110 or a group of UEs 110. For this case, time slot configuration information may be sent to UE 110 in a broadcast channel or one or more common control channels. In other embodiments, the time slot configuration may be UE-specific, in which case the time slot configuration information may be transmitted in a UE-specific control channel. In some embodiments, time slot configuration signaling may be transmitted together with frame configuration signaling and / or subframe configuration signaling. In other embodiments, the time slot configuration may be transmitted independently of the frame configuration signaling and / or subframe configuration signaling. Typically, the time slot configuration may be system-shared, base station-shared, UE group-shared, or UE-specific.

[0087] The SCS ranges from 15 KHz to 480 KHz. The SCS can vary with spectrum frequency and / or maximum UE speed to minimize the effects of Doppler shift and phase noise. In some examples, there can be separate transmit and receive frames, and the SCS of the symbols in the receive frame structure can be configured independently of the SCS of the symbols in the transmit frame structure. The SCS in the receive frame can be different from the SCS in the transmit frame. In some examples, the SCS of each transmit frame can be half the SCS of each receive frame. If the SCS between the receive frame and the transmit frame is different, the difference does not have to be scaled by a factor of 2, for example, if an inverse discrete Fourier transform (IDFT) is used instead of a fast Fourier transform (FFT) to achieve a more flexible symbol duration. Additional examples of frame structures can be used with different SCSs.

[0088] The basic transmission unit can be a symbol block (also alternatively referred to as a symbol), which generally includes a redundant portion (referred to as a CP) and an information (e.g., data) portion. In some embodiments, the CP can be omitted from the symbol block. The CP length can be flexible and configurable. The CP length can be fixed within a frame or flexible within a frame, and the CP length can change with changes in frames, or with changes in frame groups, or with changes in subframes, or with changes in time slots, or dynamically with changes in scheduling. The information (e.g., data) portion can be flexible and configurable. Another possible parameter related to the symbol block that can be defined is the ratio of the CP duration to the information (e.g., data) duration. In some embodiments, the symbol block length can be adjusted based on: channel conditions (e.g., multipath delay, Doppler); and / or delay requirements; and / or available time. For another example, the symbol block length can be adjusted to adapt to the available time in the frame.

[0089] A frame may include a downlink portion for downlink transmissions from base station 170 and an uplink portion for uplink transmissions from UE 110. There is a gap between each uplink portion and the downlink portion, referred to as a switching gap. The length (duration) of the switching gap may be configurable. The switching gap duration may be fixed or flexible within a frame. The switching gap duration may change with changes in frames, frame groups, subframes, time slots, or dynamically with changes in scheduling.

[0090] Equipment such as base station 170 can provide coverage for the cell. Wireless communication with the device can be carried out over one or more carrier frequencies. A carrier frequency is called a carrier. A carrier can also be referred to as a component carrier (CC) alternatively. A carrier can be characterized by its bandwidth and a reference frequency (e.g., the center frequency, the lowest frequency, or the highest frequency of the carrier). A carrier can be on a licensed spectrum or on an unlicensed spectrum. Wireless communication with the device can also or alternatively occur on one or more bandwidth parts (BWPs). For example, a carrier can have one or more BWPs. More generally, wireless communication with the device can occur on a spectrum. The spectrum can include one or more carriers and / or one or more BWPs.

[0091] A cell may include one or more downlink resources, and optionally, one or more uplink resources. A cell may include one or more uplink resources, and optionally, one or more downlink resources. A cell may include one or more downlink resources and one or more uplink resources. For example, a cell may include only one downlink carrier / BWP, or only one uplink carrier / BWP, or multiple downlink carriers / BWPs, or multiple uplink carriers / BWPs, or one downlink carrier / BWP and one uplink carrier / BWP, or one downlink carrier / BWP and multiple uplink carriers / BWPs, or multiple downlink carriers / BWPs and one uplink carrier / BWP, or multiple downlink carriers / BWPs and multiple uplink carriers / BWPs. In some embodiments, a cell may alternatively or additionally include one or more sidelink resources, including sidelink transmit and receive resources.

[0092] A BWP is a set of continuous or non-contiguous frequency subcarriers on one carrier, or a set of continuous or non-contiguous frequency subcarriers on multiple carriers, or a set of non-contiguous or continuous frequency subcarriers, and may have one or more carriers.

[0093] In some embodiments, a carrier may have one or more BWPs. For example, a carrier may have a bandwidth of 20 MHz and consist of one BWP, or a carrier may have a bandwidth of 80 MHz and consist of two adjacent BWPs, etc. In other embodiments, a BWP may have one or more carriers. For example, a BWP may have a bandwidth of 40 MHz and consist of two adjacent continuous carriers, each with a bandwidth of 20 MHz. In some embodiments, a BWP may include non-contiguous spectrum resources consisting of multiple non-contiguous multi-carriers, wherein the first carrier in the non-contiguous multi-carriers may be in the mmW frequency band, the second carrier may be in the low frequency band (e.g., the 2 GHz frequency band), the third carrier (if present) may be in the THz frequency band, and the fourth carrier (if present) may be in the visible light band. The resources belonging to a BWP in a carrier may be contiguous or non-contiguous. In some embodiments, a BWP has non-contiguous spectrum resources on a carrier.

[0094] Wireless communications can be performed over an occupied bandwidth. The occupied bandwidth can be defined as the width of the frequency band such that below a lower frequency limit and above an upper frequency limit, the average power transmitted is each equal to a specified percentage β / 2 of the total average transmit power, for example, 0.5%.

[0095] The carrier, BWP or occupied bandwidth may be indicated by a network device (e.g., by base station 170) dynamically (e.g., in physical layer control signaling, e.g., in a known downlink control channel (DCI)), or semi-statically (e.g., in radio resource control (RRC) signaling or in signaling in the medium access control (MAC) layer), or may be predefined based on an application scenario; or may be defined by UE 110 as a function of other parameters known to UE 110, or may be fixed by, for example, a standard.

[0096] UE location information is commonly used in cellular communication networks to improve various network performance metrics. For example, such performance metrics can include capacity, agility, and efficiency. Improvements can be achieved when network elements utilize the UE's location, behavior, mobility patterns, and other information within the context of a priori information describing the wireless environment in which the UE operates.

[0097] Perception systems can be used to help collect UE pose information, including the UE's position in a global coordinate system, the UE's speed and direction of movement in a global coordinate system, directional information, and information about the wireless environment. "Position" is also referred to as "orientation," and the two terms are used interchangeably in this article. Examples of well-known perception systems include radio detection and ranging (RADAR) and light detection and ranging (LIDAR). Although perception systems are typically separate from communication systems, it can be advantageous to use an integrated system to collect information, which reduces the hardware (and cost) in the system and the time, frequency, or space resources required to perform both functions. However, using communication system hardware to perform perception of UE pose and environmental information is a very challenging problem to be solved. The difficulty of this problem is related to factors such as the limited resolution of the communication system, the dynamics of the environment, and the large number of objects whose electromagnetic properties and orientations need to be estimated.

[0098] Therefore, synaesthesia (also called telepathy) is a desired feature in existing and future communication systems.

[0099] Any or all of ED 110 and BS 170 may be sensing nodes in system 100. A sensing node is a network entity that performs sensing by sending and receiving sensing signals. Some sensing nodes are communication devices that perform both communication and sensing. However, some sensing nodes may not perform communication but are dedicated to sensing. Sensing agent 174 is an example of a sensing node dedicated to sensing. Unlike ED 110 and BS 170, sensing agent 174 does not send or receive communication signals. However, sensing agent 174 can transmit configuration information, sensing information, signaling information, or other information within communication system 100. Sensing agent 174 can communicate with core network 130 to communicate information with the rest of the devices in communication system 100. For example, sensing agent 174 can determine the location of ED 110a and send that information to base station 170a via core network 130. Although Figure 2 Only one awareness proxy 174 is shown, but any number of awareness proxies may be implemented in the communication system 100. In some embodiments, one or more awareness proxies may be implemented at one or more RANs 120.

[0100] The sensing node can combine the sensing-based technology with the reference signal-based technology to enhance the UE posture determination. This type of sensing node can also be referred to as a sensing management function (SMF). In some networks, SMF can also be referred to as a location management function (LMF). SMF can be implemented as a physically independent entity, located at the core network 130, and connected to multiple BS170. In other aspects of the present application, SMF can be implemented as a logical entity co-located inside the BS170 by the logic executed by the processor 260.

[0101] like Figure 5As shown, SMF 176, when implemented as a physically separate entity, includes at least one processor 290, at least one transmitter 282, at least one receiver 284, one or more antennas 286, and at least one memory 288. Transceivers (not shown) may be used in place of transmitter 282 and receiver 284. A scheduler 283 may be coupled to processor 290. Scheduler 283 may be included within SMF 176 or operate separately from SMF 176. Processor 290 implements various processing operations of SMF 176, such as signal decoding, data processing, power control, input / output processing, or any other functions. Processor 290 may also be used to implement some or all of the functions and / or embodiments described in more detail above. Each processor 290 comprises any suitable processing or computing device for performing one or more operations. For example, each processor 290 may comprise a microprocessor, a microcontroller, a digital signal processor, a field programmable gate array, or an application-specific integrated circuit.

[0102] Reference signal-based pose determination techniques belong to the "active" pose estimation paradigm. In the active pose estimation paradigm, the interrogator of pose information (e.g., UE 110) participates in the process of determining the interrogator's pose. The interrogator can send or receive (or both) signals specific to the pose determination process. Positioning techniques based on global navigation satellite systems (GNSS), such as the well-known Global Positioning System (GPS), are other examples of the active pose estimation paradigm.

[0103] In contrast, perception techniques such as radar-based ones can be considered to belong to the “passive” pose determination paradigm, where the target is completely unaware of the pose determination process.

[0104] By integrating perception and communication into one system, the system does not need to operate according to only one paradigm. Therefore, the combination of perception-based techniques and reference signal-based techniques can produce enhanced pose determination.

[0105] Enhanced pose determination may, for example, include obtaining UE channel subspace information, which is particularly useful for UE channel reconstruction at the sensing node, especially for beam-based operation and communication. The UE channel subspace is a subset of the entire algebraic space defined in the spatial domain, in which the entire channel from TP to UE lies. Therefore, the UE channel subspace defines the TP to UE channel with very high accuracy. The impact of signals sent on other subspaces on the UE channel is negligible. Understanding the UE channel subspace helps reduce the work required for channel measurement at the UE and channel reconstruction at the network side. Therefore, compared with traditional methods, the combination of sensing-based techniques and reference signal-based techniques can achieve UE channel reconstruction with less overhead. Subspace information can also facilitate subspace-based sensing to reduce sensing complexity and improve sensing accuracy.

[0106] In some embodiments of synaesthesia, the same radio access technology (RAT) is used for both sensing and communication, which avoids the need to reuse two different RATs on one carrier spectrum, or to use two different carrier spectrums for the two different RATs.

[0107] In an embodiment where one RAT is used to integrate sensing and communication, a first set of channels may be used to send sensing signals and a second set of channels may be used to send communication signals. In some embodiments, each channel in the first set of channels and each channel in the second set of channels is a logical channel, a transport channel, or a physical channel.

[0108] At the physical layer, communication and sensing can be performed using separate physical channels. For example, a first physical downlink shared channel (PDSCH-C) is defined for data communication, while a second physical downlink shared channel (PDSCH-S) is defined for sensing. Similarly, separate physical uplink shared channels (PUSCHs) can be defined for uplink communication and sensing: PUSCH-C and PUSCH-S.

[0109] In another example, the same PDSCH and PUSCH can also be used for communication and sensing, where separate logical layer channels and / or transport layer channels are defined for communication and sensing. It should also be noted that one or more control channels and one or more data channels used for sensing can have the same or different channel structures (formats) and occupy the same or different frequency bands or bandwidth portions.

[0110] In another example, a common physical downlink control channel (PDCCH) and a common physical uplink control channel (PUCCH) can be used to carry control information for sensing and communication. Alternatively, separate physical layer control channels can be used to carry separate control information for communication and sensing. For example, PUCCH-S and PUCCH-C can be used for uplink control for sensing and communication, respectively, and PDCCH-S and PDCCH-C can be used for downlink control for sensing and communication, respectively.

[0111] At each of the physical, transport, and logical layers, different combinations of shared and dedicated channels for sensing and communication may be used.

[0112] Terrestrial communication systems can also be referred to as land-based or ground-based communication systems, but terrestrial communication systems can also or instead be implemented on or in water. Non-terrestrial communication systems can extend the coverage of cellular networks by using non-terrestrial nodes to fill coverage gaps in underserved areas. This is crucial for establishing seamless global coverage and providing mobile broadband services to unserved / underserved areas. Currently, it is difficult to implement terrestrial access point / base station infrastructure in oceans, mountains, forests, or other remote areas.

[0113] A terrestrial communication system may be a wireless communication system that uses 5G technology and / or newer generation wireless technology (e.g., 6G or higher). In some examples, the terrestrial communication system may also accommodate some traditional wireless technologies (e.g., 3G or 4G wireless technologies). A non-terrestrial communication system may be a communication system that uses a satellite constellation, such as a traditional geostationary orbit (GEO) satellite, which utilizes broadcast public / popular content to a local server. A non-terrestrial communication system may be a communication system that uses low earth orbit (LEO) satellites, which are known to provide a better balance between large coverage areas and propagation path loss / delay. A non-terrestrial communication system may be a communication system that uses stabilized satellites in very low earth orbit (VLEO) technology, thereby significantly reducing the cost of launching satellites into lower orbits. A non-terrestrial communication system may be a communication system that uses a high altitude platform (HAP), which is known to provide a low path loss air interface for users with limited power budgets. Non-terrestrial communication systems can be communication systems that use unmanned aerial vehicles (UAVs) (or unmanned aerial systems (UASs)) to achieve dense deployment because their coverage can be limited to a local area, such as airborne, balloon, quadcopter, drone, etc. In some examples, GEO satellites, LEO satellites, UAVs, HAPs, and VLEOs can be horizontal and two-dimensional. In some examples, UAVs, HAPs, and VLEOs can be coupled to integrate satellite communications into cellular networks. Emerging 3D vertical networks consist of many mobile (except geostationary satellites) and high-altitude access points (such as UAVs, HAPs, and VLEOs).

[0114] MIMO technology enables antenna arrays consisting of multiple antennas to transmit and receive signals, meeting high transmission rate requirements. ED 110 and T-TRP 170 and / or NT-TRP can use MIMO to communicate using radio resource blocks. MIMO uses multiple antennas at the transmitter to transmit radio resource blocks on parallel radio signals. This allows the use of multiple antennas at the receiver. MIMO can beamform parallel radio signals for reliable multipath transmission of radio resource blocks. MIMO can also bundle parallel radio signals transmitting different data to increase the data rate of the radio resource blocks.

[0115] In recent years, a MIMO (massive MIMO) wireless communication system in which a large number of antennas are configured in the T-TRP 170 and / or NT-TRP 172 has attracted wide attention from academia and industry. In a massive MIMO system, the T-TRP 170 and / or NT-TRP 172 is usually configured with more than 10 antenna elements (see Figure 3 Antenna 256 and antenna 280 in the T-TRP 170). The T-TRP 170 and / or NT-TRP 172 are typically operable to serve dozens (e.g., 40) EDs 110. The large number of antenna elements of the T-TRP 170 and NT-TRP 172 can greatly improve the spatial freedom of wireless communication, greatly improve the transmission rate, spectrum efficiency, and power efficiency, and greatly reduce interference between cells. The increase in the number of antennas can enable each antenna element to be made with a smaller size and lower cost. Using the spatial freedom provided by the large-scale antenna elements, the T-TRP 170 and NT-TRP 172 of each cell can communicate with multiple EDs 110 in the cell simultaneously on the same time-frequency resources, thereby greatly improving spectrum efficiency. The large number of antenna elements of the T-TRP 170 and / or NT-TRP 172 also enables each user to have better spatial directivity for uplink and downlink transmissions, thereby reducing the transmit power of the T-TRP 170 and / or NT-TRP 172 and ED 110 and correspondingly improving power efficiency. When the number of antennas in T-TRP 170 and / or NT-TRP 172 is sufficient, the random channels between each ED 110 and T-TRP 170 and / or NT-TRP 172 can be nearly orthogonal, thereby reducing interference between cells and users and the impact of noise. These advantages make massive MIMO promising for broad application prospects.

[0116] A MIMO system may include a receiver connected to a receive (Rx) antenna, a transmitter connected to a transmit (Tx) antenna, and a signal processor connected to the transmitter and receiver. Each of the Rx antenna and the Tx antenna may include multiple antennas. For example, the Rx antenna may have a uniform linear array (ULA) antenna, in which multiple antennas are arranged in a straight line at equal intervals. When a radio frequency (RF) signal is transmitted through the Tx antenna, the Rx antenna may receive the reflected and returned signal from the forward target.

[0117] In some embodiments of a MIMO system, a non-exhaustive list of possible elements or possible configurable parameters includes: a panel; and a beam.

[0118] A panel is a unit of an antenna group or antenna array or antenna subarray that can independently control a Tx beam or a Rx beam.

[0119] The beam can be formed by performing amplitude and / or phase weighting on the data sent or received by at least one antenna port. The beam can be formed by other methods such as adjusting the relevant parameters of the antenna unit. The beam may include a Tx beam and / or an Rx beam. The transmit beam indicates the signal strength distribution formed in different directions in space after the signal is transmitted through the antenna. The receive beam indicates the signal strength distribution of the wireless signal received from the antenna in different directions in space. The beam information may include a beam identifier, an antenna port identifier, a channel state information reference signal (CSI-RS) resource identifier, an SSB resource identifier, a sounding reference signal (SRS) resource identifier, or other reference signal resource identifiers.

[0120] In a single iteration of wireless FL technology, the UE provides the base station with a set of AI / ML model parameters describing the local AI / ML model. This can be considered to involve the transmission of a relatively large number of parameters. The large number of parameters can be understood as being due to the relatively large number of neural nodes and connections (between neural nodes) in the local AI / ML model.

[0121] It can be shown that relatively small AI / ML models can be described using approximately millions of parameters. It can be shown that relatively large AI / ML models can be described using approximately billions of parameters. An exemplary AI / ML model can be found in the bidirectional encoder representations from transformers (BERT), proposed in a paper by Google AI Language researchers. The BERT AI / ML model can be shown to be described using 340 million parameters.

[0122] It can be shown that most parameters exchanged (e.g., as part of wireless FL techniques) are redundant. In Lin, Y., Han, S., Mao, H., Wang, Y., and Dally, W.J., "Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training" (2017), arXiv (available at doi.org / 10.48550 / arXiv.1712.01887), it was found that 99.9% of the gradients exchanged can be considered redundant. In an image classification example, it was shown that the amount of exchanged gradient data can be reduced from 97MB to 0.35MB.

[0123] That is, by exchanging only the data deemed important to improving the operation of a given AI / ML model, the amount of data exchanged can be reduced.

[0124] Various aspects of the present application relate to identifying important data (e.g., important parameters) within a data packet. In addition, various aspects of the present application relate to a design scheme that involves using priority transmission for data identified as important and using "best effort" transmission for data identified as less important. In fact, in the following, "local business data packets" are often mentioned. However, it should be clear that various aspects of the present application can be applied to scenarios involving data packets that are not local business data packets. In the other two examples, the data packet can be uplink control information or downlink control information.

[0125] Since various aspects of the present application are described below with respect to local traffic, it seems useful to define local traffic. Local traffic can be defined to include those messages, such as signaling messages or data messages, that are transmitted so that the messages can be recognized and interpreted by the RAN 120. For example, the signaling messages or data messages can be transmitted using a standard protocol or a standard air interface, either of which can be defined by the 3GPP RAN (available at 3gpp.org). It can be seen that the signaling messages or data messages are visible in the RAN 120, and the data format and data transmission scheme are within the scope of 3GPP standardization. In future generations of wireless communication networks, including, for example, sixth generation (6G) wireless communication networks, it is envisioned that message transmission will be provided within the RAN 120. These messages can be generated at the BS 170 and sent to the UE 110.

[0126] Local services can be defined as including AI model services, AI data services, AI parameter services, perception data services, positioning data services, etc.

[0127] According to various aspects of the present application, BS 170 or UE 110 can divide a local traffic flow into multiple traffic sub-flows (multiple classes) based on the determined subjective importance of the data within the local traffic flow. In cases where the local traffic flow is part of a DL transmission, BS 170 performs the step of dividing the local traffic flow into multiple traffic sub-flows. In cases where the local traffic flow is part of an UL transmission, UE 110 performs the step of dividing the local traffic flow into multiple traffic sub-flows.

[0128] Figure 6 Exemplary steps in a method for transmitting data are shown. The method can be considered to be performed by an entity, wherein the entity can be BS170 or UE 110. Initially, the entity can receive (step 602) a local business data packet as part of a data stream. Similarly, the entity can generate (step 602) a local business data packet as part of a data stream. For example, the data stream can represent parameters describing an artificial intelligence model. The local business data packet can include first data and second data. In response to receiving (step 602) the local business data packet, the entity can divide (step 604) the local business data packet into a first substream including the first data and a second substream including the second data. The entity can then send (step 606) the first substream with a first reliability and send (step 608) the second substream with a second reliability, which is lower than the first reliability.

[0129] The local traffic flow may contain data identified as "Class A" data. Class A data can be defined as the most important data. In other words, Class A data can be defined as the data most sensitive to errors. In fact, in various aspects of this application, it is not the data that is "sensitive." It is more accurate to say that after receiving the data, the AI / ML model that utilizes the data is highly sensitive to errors in Class A data. Therefore, Class A data should be associated with the highest reliability among multiple types of data.

[0130] There may be data in the local traffic flow that is determined to be "Class B" data. Class B data can be defined as data associated with normal importance. After receiving the data, the AI / ML model of the data should be generally sensitive to errors in Class B data. It can be seen that Class B data should be associated with normal reliability among multiple types of data. In other aspects of the present application, Class A data and Class B data can be distinguished by determining that the target block error rate (BLER) associated with Class A data is lower than the target BLER associated with Class B data. In other aspects of the present application, Class A data and Class B data can be distinguished by determining that the residual BLER associated with Class A data is lower than the residual BLER associated with Class B data.

[0131] Data determined to be "Class C" data may be present in the local traffic flow. Class C data may be defined as data associated with lower importance. Upon receiving the data, the AI / ML model that is to utilize the data is less sensitive to errors in the Class C data. That is, some errors in the reception of Class C data will not significantly reduce (i.e., may slightly affect) the performance metrics of training the AI / ML model. Furthermore, some errors in the reception of Class C data will not significantly reduce the performance metrics of the inference obtained from the AI / ML model. Furthermore, some errors in the reception of Class C data will not significantly reduce the performance metrics derived from the perception results obtained from the AI / ML model. It can be seen from this that Class C data should be associated with lower reliability among multiple classes of data.

[0132] The foregoing discussion envisions three types of data. It should be clear that various aspects of the present application can operate based on as few as two types of data. In addition, various aspects of the present application can operate based on four or more types of data.

[0133] For an exemplary scenario, consider that a given local traffic flow includes data that can be divided into the following two classes: Class A and Class B. Figure 7 An example table 700 is shown populated with Class A data and Class B data. Figure 7 In table 700 , the importance of category A data is greater than that of category B data.

[0134] When the given local service flow is information related to training an AI / ML model, the given local service flow may be a gradient update. It is expected that the gradient update can be represented by 8 bits: 7 bits representing the absolute value of the gradient update; and a single bit representing the sign of the gradient update. Figure 7 In Table 700 , the sign bit of the gradient update is presented as type A data, and the set of 7 bits representing the absolute value of the gradient update is presented as type B data. It should be noted that the gradient update does not necessarily have to be represented using 8 bits.

[0135] It can be shown that the direction of the gradient update (i.e., the sign bit) is more important than the absolute value of the gradient update. That is, the change in the gradient (which can be an increase or decrease) is more important than the degree of the gradient change. Consider a scenario where the absolute value of the gradient update is lost in transmission, i.e., the learning node (BS 170 or UE 110 receiving the gradient update) determines (e.g., using a cyclic redundancy check) that the received bits do not match the transmitted bits. In this scenario, the learning node can use a predefined or preconfigured value, e.g., a smaller absolute value, for the gradient update for the current iteration of learning. Alternatively, in this scenario, the learning node can use the absolute value of the gradient update received for the previous iteration.

[0136] When a given local service flow is information related to training an AI / ML model, the given local service flow can be a weight. Figure 7 In Table 700 of , it is proposed that for weights, symbols are type A data, while the set of bits representing absolute values ​​is type B data. Figure 7 Table 700 shows that when a weight is shared across multiple layers, the data can be classified as Class A data. In contrast, when a weight is a separate weight for a single layer, the data can be classified as Class B data. This indicates that the loss of shared weights can affect the performance of multiple layers. Accordingly, shared weights can be classified as Class A data.

[0137] When the given local service flow is information related to training an AI / ML model, the given local service flow can be a neural network (NN) parameter. It can be shown that the NN parameter can be a parameter of a convolutional neural network (CNN) layer or a parameter of a dense layer. An exemplary parameter of a CNN layer is a kernel. In the exemplary image classification AI / ML model, a kernel is a filter used to extract features from an image. Figure 7 Table 700 shows that the parameters of the CNN layer can be used to determine the data as Class A data, and the parameters of the dense layer can be used to determine the data as Class B data. In fact, it can be shown that the CNN layer is very important for extracting features from the input data. In addition, it can be shown that the parameters of the CNN layer can be much fewer than those of the dense layer.

[0138] When the given local service flow is information related to training an AI / ML model, the given local service flow can be a weight matrix. It can be shown that the weight matrix can be a low-rank weight matrix or a high-rank weight matrix. Figure 7 Table 700 of [ 0055 ] suggests that when the data is a low-rank weight matrix, the data can be determined as Class A data, and when the data is a high-rank weight matrix, the data can be determined as Class B data. It can be shown that a low-rank matrix contains fewer non-zero parameters than a high-rank matrix. A small number of non-zero parameters may prove to be important for an AI / ML model. In contrast, it can be shown that a high-rank matrix contains more parameters than a low-rank matrix. Therefore, some errors in the reception of a high-rank matrix can be considered acceptable.

[0139] When a given local service flow is training data for training an AI / ML model, the given local service flow can be a data label or input data for supervised learning. Figure 7 Table 700 shows that when the data is a data label for supervised learning, the data can be determined as type A data, and when the data is input data, the data can be determined as type B data.

[0140] We can simply consider a scenario where the data is divided into three categories. For a gradient update with an absolute value of N bits, this paper proposes that the sign bit is Category A data, the K most significant bits (MSBs) of the absolute value are Category B data, and the N–K least significant bits (LSBs) of the absolute value are Category C data. It should be noted that the value represented by the MSB is larger than the LSB, so the value represented by the K MSBs is closer to the true absolute value than the value represented by the N–K LSBs.

[0141] It is expected that the local service data packet is encoded into a local service superframe, which can also be called a super packet. For example, the data in the local service data packet can be data representing an AI / ML model, AI data, or perception data. The format of the superframe can follow Figure 8 The local service superframe format 800 is shown as including a superframe header 802, auxiliary information 804, class A data 806A, class B data 806B, and optionally, data of less important classes starting with class C data 806C. It should be noted that auxiliary information 804 can be considered optional, as the information in auxiliary information 804 can be included in the superframe header 802 instead.

[0142] The superframe header 802 may include one or more of a superframe ID, a local service type, and a superframe quality indicator. For two non-limiting examples, the local service type may be AI / ML data or perception data. The quality indicator, described in detail below, may be understood to refer to the importance of the superframe content when applied to network / system performance, such as AI / ML performance (AI training, reasoning) or perception performance (deriving perception information). An indication of relatively high quality may be understood to correspond to content that is relatively more important to performance.

[0143] Auxiliary information 804 may include one or more of an NN model indicator, hyperparameters of the NN model, the task of the local service, the classification of Class A data 806A and Class B data 806B, and optionally data of other classes. The hyperparameters of the NN model may be an activation function or a learning rate, to name two examples. For example, the task of the local service may indicate whether the local service is related to abnormality perception or environmental perception.

[0144] The local service superframe 800 may be divided into a plurality of segments. Each of the plurality of segments may be shown as including a superframe ID. Typically, transmission of Class A data 806A has a higher priority than transmission of Class B data 806B.

[0145] Optionally, multiple transport blocks (TBs) can be constructed for Class A data, and separate multiple TBs can be constructed for Class B data. A first transmission mode can be used to transmit TBs carrying Class A data 806A. A second transmission mode can be used to transmit TBs carrying Class B data 806B. The first transmission mode can be selected to have higher reliability than the second transmission mode. If Class A data 806A in the local service superframe 800 is not successfully received, the transmission of Class B data 806B can be suspended.

[0146] To achieve more protection for Class A data 806A, different classes of data may undergo different transmission protections in the network.

[0147] Figure 9 A diagram 900 is shown including exemplary aspects of transmission protection in a network cross-referenced with data classes.

[0148] The first aspect of transport protection is source compression. Figure 9 As shown in graph 900, the Class A data may undergo a relatively low compression ratio, allowing the Class A data to be transmitted as high-definition data. The compression ratio may be defined as according to Figure 9 As shown in diagram 900, Class B data may be subjected to a relatively high compression ratio, causing the Class B data to be transmitted as low-resolution data. That is, the compression ratio and / or compression algorithm used for Class A data may be different from the compression ratio and / or compression algorithm used for Class B data. The source compression configuration (compression ratio and / or compression algorithm) may be indicated by BS 170 to UE 110. The source compression configuration (compression ratio and / or compression algorithm) may be indicated in superframe header 802 or auxiliary information 804 (see Figure 8 ).

[0149] The second aspect of transport protection is header compression. Figure 9 As shown in diagram 900 , Class A data may experience less header overhead than Class B data. For example, Class A data may be carried by Layer 1 (L1) messages. For another example, Class A data may be carried by RRC signaling with robust header compression (ROHC). In contrast, Class B data may be carried by RRC signaling messages.

[0150] The third aspect of transmission protection is the modulation coding scheme (MCS). Figure 9As shown in diagram 900, Class A data may be subjected to a robust MCS. Examples of robust MCS include using a robust channel quality indicator (CQI) table with a target block error rate (BLER) of 1% and / or using a relatively low modulation order (e.g., up to 64 quadrature amplitude modulation - also known as 64QAM). Figure 9 As shown in graph 900, Class B data may be subjected to a best-effort MCS. Examples of a best-effort MCS include using a CQI table with a 10% target BLER and / or using a relatively high modulation order (e.g., up to 1024QAM).

[0151] The fourth aspect of transmission protection is retransmission. Figure 9 As shown in diagram 900, Class A data may undergo retransmission using automatic repeat request (ARQ) and / or hybrid ARQ (HARQ). Figure 9 As shown in diagram 900 , Class B data may not benefit from retransmissions. Alternatively, Class B data may undergo retransmissions without HARQ and / or ARQ. Still alternatively, Class B data may undergo retransmissions, but with a maximum number of retransmissions. The maximum number of retransmissions for Class B data may be less than the maximum number of retransmissions for Class A data. In practice, the maximum number of retransmissions may be configured or predefined separately for Class A and Class B data.

[0152] The fifth aspect of transmission protection is scheduling. Figure 9 As shown in the diagram 900, in logical channel (LC) multiplexing ("muxing"), Class A data may have a relatively higher priority. Figure 9 As shown in diagram 900 , in LC multiplexing, Class B data may have a relatively low priority.

[0153] The sixth aspect of transmission protection is misconduct. Figure 9 As shown in graph 900 , when bit decoding of Class A data fails at the receiver, the receiver may discard the Class A data. In contrast, when bit decoding of Class B data fails at the receiver, the receiver may use the Class B data even though the Class B data is known to be corrupted data.

[0154] Various aspects of the present application relate to configuring one or more of the following parameters for Class A data and Class B data, respectively: source compression; header compression; modulation and channel coding; retransmission; scheduling; and error behavior. The individual configurations can be indicated jointly for Class A and Class B data, or through separate signaling for configuring parameters for Class A and Class B data. Figure 10 An example of a joint indication table 1000 is shown, where each row of the table 1000 includes an indication of a particular configuration of one of the parameters of the Class A data and the Class B data.

[0155] Figure 11A Shown with Figure 8 The local service superframe 1100 is generated in a manner consistent with the local service superframe format 800. The local service superframe 1100 includes a superframe header 1102, auxiliary information 1104, type A data 1106A, and type B data 1106B.

[0156] The sending entity may divide the local service superframe 1100 into three segments. Figure 11B The three segments are shown in FIG. The first of the three segments may be referred to as “Segment 0” 1110-0. Segment 0 1110-0 includes a Segment 0 header 1112-0, a superframe header 1102, and auxiliary information 1104. The second of the three segments may be referred to as “Segment A” 1110-A. Segment 0 header 1112-0 may include an indication of a local service sequence number (SN). Segment A 1110-A includes a Segment A header 1112-A and Class A data 1106A. Segment A header 1112-A may include an indication of a local service SN. The third of the three segments may be referred to as “Segment B” 1110-B. Segment B 1110-B includes a Segment B header 1112-B and Class B data 1106B. Segment B header 1112-B may include an indication of a local service SN.

[0157] The indication of the same local service SN in the segment 0 header 1112-0, segment A header 1112-A and segment B header 1112-B may be shown to support the receiving device in determining that segment 0 1110-0, segment A 1110-A and segment B 1110-B are from the same local service superframe, i.e., Figure 11A Local service superframe 1100.

[0158] As an alternative to dividing the local service superframe 1100 into three segments, the local service superframe 1100 may be divided into two segments. Figure 11C. The two segments are shown in FIG. The first of the two segments may be referred to as "Segment 0A" 1110-0A. Segment 0A 1110-0A includes a Segment 0A header 1112-0A, a superframe header 1102, auxiliary information 1104, and Class A data 1106A. Segment 0A header 1112-0A may include an indication of a local service SN. The second of the two segments may be referred to as "Segment B" 1110-B. Segment B 1110-B includes a Segment B header 1112-B and Class B data 1106B. Segment B header 1112-B may include an indication of a local service SN.

[0159] An indication of the same local service SN in the segment 0A header 1112-0A and the segment B header 1112-B may be shown to support the receiving device in determining that segment 0A 1110-0A and segment B 1110-B are from the same local service superframe, i.e. Figure 11A Local service superframe 1100.

[0160] It should be noted that further segmentation may occur when the local service superframe 1100 is processed by the 5G / NR wireless protocol stack architecture (or future protocol stack architecture, such as the 6G protocol stack architecture). The 5G / NR wireless protocol stack architecture includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a medium access control (MAC) layer, and a physical (PHY) layer. The degree of further segmentation depends on the specific layer that processes the local service superframe 1100. For example, if the local service superframe 1100 is processed and generated in the SDAP layer, the local service is sent from the SDAP layer to the PDCP layer, then to the RLC layer, then to the MAC layer, and then to the PHY layer. Further segmentation may be performed in the layers during processing. For example, an RLC segment may be generated at the RLC layer.

[0161] After being processed by the 5G / NR wireless protocol stack, the local service superframe 1100 can be understood as being carried on multiple TBs. For MAC multiplexing on TBs with Class A data and Class B data, Class A data can be shown as having a higher priority.

[0162] Various aspects of the present application are directed to configuring intra-superframe unequal protection transmission that supports dynamic indication of classification of Class A data and Class B data.

[0163] According to various aspects of the present application, the BS 170 may indicate the classification of the class A sub-flow and the class B sub-flow to the UE 110, for example, through RRC, MAC-CE, or DCI signaling.

[0164] According to another aspect of the present application, BS 170 may use the superframe header or auxiliary information in the superframe to indicate the classification of sub-flows of type A and type B. Furthermore, it is contemplated that the superframe header or auxiliary information may be used to indicate the nature of the superframe contents.

[0165] In one example, the classification of the sub-flows of type A and type B may be referred to as “task-oriented” classification. That is, the classification of the sub-flows of type A and type B may be associated with specific tasks.

[0166] By indicating the tasks to UE 110, BS 170 may support UE 110 in predetermining the classification of the class A sub-flows and the class B sub-flows.

[0167] For example, BS 170 may indicate to UE 110 that a given superframe is associated with an anomaly sensing task. Accordingly, UE 110 may expect that all data in the given superframe is Class A data.

[0168] For another example, BS 170 may indicate to UE 110 that a given superframe is associated with an environment awareness task. Accordingly, UE 110 may expect that most of the data in the given superframe is Class B data.

[0169] Figure 12 Exemplary steps in a method for transmitting data are shown. The method can be considered to be performed by an entity, wherein the entity can be BS170 or UE 110. Initially, the entity can receive / generate (step 1202) a Class A data substream. The entity can also receive / generate (step 1204) a Class B data substream. In the case where steps 1202 and 1204 are receiving steps, the entity can receive a local service data packet, and the local service data packet can include a Class A data substream in the first part and a Class B data substream in the second part. The entity can then generate (step 1206) a superframe, which includes the Class A data substream and the Class B data substream. The entity can then send (step 1208) the superframe. If the entity is BS170, the BS can send (step 1208) the superframe to UE 110.

[0170] Figure 13 A superframe type table 1300 is shown. Figure 13 The superframe type table 1300 provides an example of a configuration option, wherein, through the indication of the superframe type, the BS 170 can provide the UE 110 with a joint indication of the superframe content and the classification of the type A sub-flow and the type B sub-flow.

[0171] according to Figure 13When BS 170 indicates that a given superframe is a type 2 superframe, UE 110 may expect the contents of the given superframe to be NN parameters. In addition, UE 110 may expect the given superframe to include hidden layers (layers 2 to 4) as type A data and other layers as type B data. Figure 13 , when BS 170 indicates that a given superframe is a type 3 superframe, UE 110 may expect the content of the given superframe to be NN parameters. In addition, UE 110 may expect the given superframe to include hidden layers (layers 5 to 7) as class A data and other layers as class B data. The distinction between type 2 superframes and type 3 superframes stems from the observation that for a particular learning phase, the hidden layers from layer 2 to layer 4 are almost converged. Therefore, it can be understood that it is prudent to assign the hidden layers (layers 2 to 4) as class A data so that they can be transmitted with high priority to achieve correct transmission. For different learning phases, the hidden layers from layer 5 to layer 7 are almost converged. Therefore, it can be understood that it is prudent to assign the hidden layers (layers 5 to 7) as class A data so that they can be transmitted with high priority to achieve correct transmission.

[0172] according to Figure 13 When BS 170 indicates that a given superframe is a type 6 superframe, UE 110 may expect that the content of the given superframe is related to a gradient update. In addition, UE 110 may expect that the given superframe includes the sign of the gradient update as type A data and the absolute value of the gradient update as type B data. Figure 13 , when BS 170 indicates that a given superframe is a type 7 superframe, UE 110 may expect the content of the given superframe to be a gradient update. In addition, UE 110 may expect the given superframe to include the sign of the gradient update and the absolute value of the gradient update as Class A data. The distinction between Type 6 superframes and Type 7 superframes stems from the observation that in the early stages of training, a particular model may not be sensitive to the size of the gradient update. Accordingly, only the sign of the gradient update may be considered as important data, such as Class A data. In the later stages of training, a particular model may be understood to be close to convergence. Therefore, the particular model may be understood to be sensitive to the absolute value of the gradient update. Accordingly, both the sign of the gradient update and the absolute value of the gradient update may be considered as important data, such as Class A data.

[0173] As mentioned above, with Figure 13In contrast to the joint indication of superframe content and substream classification as shown in superframe type table 1300, BS 170 can separately indicate to UE 110 the nature of a given superframe content and the classification of class A substreams and class B substreams. This separate indication can be accomplished using, for example, RRC signaling, MAC-CE signaling, or DCI signaling. Alternatively, the separate indication can be accomplished using auxiliary information in the superframe header or superframe.

[0174] Various aspects of the present application are directed to configuring unequal protection transmission across superframes to support different priorities for different types of local traffic.

[0175] Figure 14 Exemplary steps in a method for transmitting data are shown. The method may be considered to be performed by an entity, which may be a BS 170 or a UE 110. Initially, the entity may receive / generate (step 1402) a superframe that includes an indication of the quality of the superframe. The quality of the superframe may be understood to refer to the importance of the content of the superframe when applied to network / system performance such as AI / ML performance (AI training, reasoning) or perceptual performance (deriving perceptual information). An indication of relatively higher quality may be understood to correspond to content that is relatively more important to performance.

[0176] The entity may then transmit (step 1406) the superframe to the receiving device. Furthermore, the entity may indicate the quality of the superframe to the receiving device. In one aspect of the present disclosure, the entity may indicate (step 1404) the quality of the superframe prior to transmitting (step 1406) the superframe. In another aspect of the present disclosure, the entity may indicate the quality of the superframe as part of transmitting (step 1406) the superframe.

[0177] For downlink (DL) transmission, BS 170 may indicate the superframe type and / or superframe quality to UE 110. In one aspect of the present disclosure, UE 110 may extract the superframe type and / or superframe quality indication from the superframe header or from auxiliary information in the superframe.

[0178] For uplink (UL) transmissions, BS 170 may configure UE 110 to report data of the indicated superframe type. In response, UE 110 may be shown reporting corresponding data, optionally with an indication of superframe quality.

[0179] In another aspect of the present application, UE 110 may independently determine the quality of a given superframe. In conjunction with the UL transmission of the given superframe, UE 110 may report an indication of the quality of the given superframe to BS 170. For example, UE 110 may report the indication of the quality of the given superframe in an UL channel. For another example, UE 110 may report the indication of the quality of the given superframe in a header of the given superframe or in auxiliary information of the given superframe. Alternatively, UE 110 may also report the quality indication of the superframe.

[0180] In various aspects of the present application, a superframe quality indicator may be used to indicate the quality of the data.

[0181] The first option, which may be considered useful for local services with multiple local service types, involves using a "unified table" to define data of varying quality. That is, upon receiving a first superframe with a first superframe quality indicator, the entity can consult the unified table to associate a first quality of data with the first superframe. Subsequently, upon receiving a second superframe with a second superframe quality indicator, the entity can consult the unified table to associate a second quality of data with the second superframe. The entity can then determine which of the first and second superframes carries data of higher quality. Based on this determination, the entity can then process the two superframes differently. Figure 15 An exemplary unified table 1500 is shown.

[0182] The second option involves separately indicating the data quality within a type of local service. That is, an entity can first determine the type of local service represented by a particular superframe. Then, the entity can determine the quality of the data carried by the particular superframe. The entity can then treat the particular superframe differently from other superframes of the same type of local service. Figure 16A An exemplary table 1600A is shown for the case where the local traffic type is AI / ML data. Figure 16B An exemplary table 1600B is shown for the case where the local traffic type is sensing data.

[0183] Rules for defining the data quality of a specific substream may be pre-established at BS 170. Alternatively or additionally, BS 170 may configure specific rules.

[0184] A first exemplary rule may be defined as depending on the accuracy confidence. That is, superframes carrying sensory data associated with a relatively high accuracy confidence may be associated with a higher superframe quality indicator than superframes carrying sensory data associated with a relatively low accuracy confidence.

[0185] A second exemplary rule may be defined as depending on an inference performance metric (e.g., inference accuracy). That is, superframes carrying AI / ML model data with relatively high inference accuracy may be associated with a higher superframe quality metric than superframes carrying AI / ML model data with relatively low inference accuracy.

[0186] A third exemplary rule can be defined as depending on the sensing task associated with the sensing data. That is, superframes carrying sensing data for anomaly detection can be associated with a higher superframe quality metric than superframes carrying sensing data for environmental sensing. This definition stems from the fact that the latency and reliability requirements of the anomaly detection task are more stringent than those associated with environmental sensing.

[0187] A fourth exemplary rule may be defined as depending on the reporting delay of the sensing data. That is, a superframe carrying sensing data whose reporting delay is relatively close to the delay threshold may be associated with a higher superframe quality indicator than a superframe carrying sensing data whose reporting delay is relatively far from the delay threshold.

[0188] A fifth exemplary rule may be defined based on the importance of the data used for sensing data fusion. It is known that BS 170 may collect sensing data from multiple UEs 110 and perform sensing data fusion to obtain a so-called "big picture" sensing result. Therefore, superframes carrying data determined to be more important for sensing data fusion may be associated with a higher superframe quality indicator than superframes carrying data determined to be less important for sensing data fusion. Determining the importance associated with data may be performed using predefined rules. In one example, importance may be identified using a common semantic graph.

[0189] A sixth exemplary rule may be defined as depending on data diversity and / or data uncertainty. That is, superframes carrying data determined to be more diverse and / or having higher uncertainty may be associated with a higher superframe quality indicator than superframes carrying data determined to be less diverse and / or having lower uncertainty.

[0190] A seventh exemplary rule can be defined as depending on the training phase. That is, superframes carrying data used in later training phases can be associated with a higher superframe quality metric than superframes carrying data used in earlier training phases. This definition stems from the understanding that a given AI / ML model may be more sensitive to errors in later training phases.

[0191] In establishing a quality level for each of the various superframes, it is contemplated that the quality level may be used to determine whether the quality level is to be transmitted (step 1208, Figure 12)Specific air interface transmission configuration to be used in a specific superframe.

[0192] For air interface transmission, separate transmission configurations can be configured for data of different qualities. Generally, a more robust transmission configuration can be used to send superframes carrying higher quality data, which may include Class A sub-streams and Class B sub-streams. Figure 17 An exemplary air interface transmission configuration table 1700 shows separate transmission configurations for transmitting a superframe carrying local service data of quality level 0 and a superframe carrying local service data of quality level 1.

[0193] according to Figure 17 According to the air interface transmission configuration table 1700, when the quality of data carried by a given superframe is level 0, the available source compression ratios are 0.8 and 0.9. For UL transmission, the UE 110 may indicate to the BS 170 using a single bit whether to use a compression ratio of 0.8 or 0.9.

[0194] according to Figure 17 According to the air interface transmission configuration table 1700 , when the quality of data carried by a given superframe is level 0, the maximum number of available retransmissions is 1 and 2. The BS 170 can determine whether to use level 1 or 2.

[0195] according to Figure 17 In the air interface transmission configuration table 1700, when the quality of the data carried by a given superframe is level 1, the available source compression ratios are 0.4 and 0.6. It should be noted that 0.4 and 0.6 are much lower than 0.8 and 0.9. For UL transmission, UE 110 can be configured to use a single bit to indicate to BS 170 whether to use a compression ratio of 0.4 or 0.6. In practice, there can be a single bit associated with each class of data. For example, UE 110 can indicate to BS 170 that Class A data will be compressed using a compression ratio of 0.4, and indicate to BS 170 that Class B data will be compressed using a compression ratio of 0.6.

[0196] according to Figure 17 According to the air interface transmission configuration table 1700, when the quality of data carried by a given superframe is level 1, the maximum number of available retransmissions is 3 and 4. It should be noted that 3 and 4 are greater than 1 and 2. This shows that the maximum number of available retransmissions when the quality of data carried by a given superframe is level 1 can achieve more robust transmission than transmission associated with a case where the quality of data carried by the given superframe is level 0.

[0197] It should be understood that one or more steps in the embodiment methods provided herein can be performed by corresponding units or modules. For example, data can be sent by a sending unit or a sending module. Data can be received by a receiving unit or a receiving module. Data can be processed by a processing unit or a processing module. The corresponding units / modules can be hardware, software, or a combination thereof. For example, one or more units / modules can be integrated circuits, such as field programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). It should be understood that if these modules are software, these modules can be retrieved in whole or in part by a processor as needed, retrieved individually or collectively for processing, retrieved in one or more instances as needed, and these modules themselves can include instructions for further deployment and instantiation.

[0198] Although combinations of features are shown in the illustrated embodiments, not all features need to be combined to achieve the advantages of the various embodiments of the present disclosure. In other words, a system or method designed according to an embodiment of the present disclosure does not necessarily include all features shown in any of the figures or all parts schematically shown in the figures. In addition, selected features of one exemplary embodiment may be combined with selected features of other exemplary embodiments.

[0199] Although the present disclosure has been described with reference to illustrative embodiments, this description is not to be construed in a limiting sense. Various modifications and combinations of the illustrative embodiments, as well as other embodiments of the present disclosure, will become apparent to those skilled in the art upon reference to this description. Therefore, the appended claims are intended to cover any such modifications or embodiments.

Claims

1. A method comprising: Receive a data packet, the data packet comprising: a first portion, wherein the first portion of the data packet is represented by bits of a first type; a second portion, wherein the second portion of the data packet is represented by bits of a second type; Sending bits of the first category using a first air interface configuration; The second type of bits are sent using a second air interface configuration.

2. The method according to claim 1, wherein The data packets also include local service data packets.

3. The method according to claim 1, wherein The data packet also includes uplink control information.

4. The method according to claim 1, wherein The data packet also includes downlink control information.

5. The method according to any one of claims 1 to 4, wherein The first air interface configuration and the second air interface configuration are predefined.

6. The method according to any one of claims 1 to 4, further comprising: Before the sending, an indication of the first air interface configuration and the second air interface configuration is received.

7. The method according to any one of claims 1 to 6, wherein The first air interface configuration and the second air interface configuration include at least one of the following: Source compression; Header compression; Modulation and channel coding; retransmission; Scheduling; Wrong behavior.

8. The method of any one of claims 1 to 7, further comprising determining that bits of the first class are more susceptible to errors than bits of the second class.

9. The method according to claim 8, wherein The determining includes determining that a first reliability associated with bits of the first class is higher than a second reliability associated with bits of the second class.

10. The method according to claim 8, wherein The determining includes determining that a first target transmission block error rate associated with bits of the first class is lower than a second target transmission block error rate associated with bits of the second class.

11. The method according to claim 8, wherein The determining includes determining that a first target residual block error rate associated with bits of the first class is lower than a second target residual block error rate associated with bits of the second class.

12. The method according to claim 8, wherein The determination includes: determining that the bits of the first category are associated with a first indication; determining that the bit of the second category is associated with a second indication; Based on a comparison of the first indication and the second indication, it is determined that the bits of the first category are more sensitive to errors than the bits of the second category.

13. The method according to claim 5, wherein: The determination includes: determining that the bit of the first category includes a sign bit of the gradient; The bit determining the second class includes the absolute value of the gradient.

14. The method according to claim 5, wherein: The determination includes: determining that the bits of the first category include a sign bit of the weight; The bit determining the second class includes the absolute value of the weight.

15. The method according to claim 5, wherein: The determination includes: determining that the bits of said first category include a shared weight; Determining the bits of the second category includes individual weights.

16. The method according to claim 5, wherein The determination includes: determining that the bits of the first class include parameters for a convolutional neural network layer of an artificial intelligence model; The bits determining the second category include parameters for a dense layer of an artificial intelligence model.

17. The method according to claim 5, wherein The determination includes: determining that the bits of the first class include a low-rank weight matrix; The bits determining the second class include a high rank weight matrix.

18. The method according to claim 5, wherein: The determination includes: determining that the bits of the first category comprise data labels for training data for an artificial intelligence model; The bits determining the second category include input data associated with the data tag.

19. The method according to any one of claims 1 to 18, wherein The data packet is part of a local traffic flow representing: Parameters describing the AI ​​model; AI training data; sensory data; or Perception related parameters.

20. The method according to claim 19, wherein The local traffic includes messages generated and transmitted only within a Radio Access Network (RAN) of a wireless communication network and between two RAN nodes.

21. An apparatus comprising: Memory, which stores instructions; A processor, wherein the processor executes the instructions to: Receive a data packet, the data packet including: a first portion, wherein the first portion of the data packet is represented by bits of a first type; a second portion, wherein the second portion of the data packet is represented by bits of a second type; Sending bits of the first category using a first air interface configuration; The second type of bits are sent using a second air interface configuration.

22. A method comprising: Sending a superframe to a user equipment (UE); The superframe includes: Bits of the first kind; The second type of bits.

23. The method according to claim 22, wherein The sending a superframe to a user equipment (UE) includes: Sending bits of the first category using a first type of air interface configuration; The second type of bits are sent using a second type of air interface configuration.

24. The method according to claim 22 or claim 23, wherein The type of air interface configuration includes one or more of the following: Source compression; Header compression; Modulation and channel coding; The number of retransmission attempts allowed; Scheduling; Error handling behavior.

25. An apparatus comprising: Memory, which stores instructions; A processor, wherein the processor executes the instructions to: Sending a superframe to a user equipment (UE); The superframe includes: Bits of the first kind; The second type of bits.

26. A method comprising: indicating a quality of a superframe to a user equipment (UE), wherein the quality of the superframe is related to the importance of content of the superframe as applied to system performance; Sending the superframe to the UE.

27. The method according to claim 26, wherein The systems include systems related to artificial intelligence and machine learning.

28. The method according to claim 26 or 27, wherein The performance includes training performance.

29. The method according to claim 28, wherein The performance includes inference performance.

30. The method of claim 26, wherein: The systems include systems related to perception.

31. The method of claim 26, wherein: The performance includes deriving sensory information.

32. The method of claim 26, wherein: The indicating comprises including an indication in the superframe.

33. The method of claim 32, further comprising: The indication is included in a header of the superframe.

34. The method of claim 32, further comprising: The indication is included in auxiliary information of the superframe.

35. The method of claim 26, further comprising: The superframe is divided into a plurality of segments.

36. The method of claim 35, further comprising: A superframe identifier is included in each of the plurality of segments.

37. The method of claim 36, further comprising: constructing a first plurality of transport blocks for the first category of data; A second plurality of transport blocks is constructed for the second category of data.

38. The method of claim 26, wherein: The sending includes: sending the first plurality of transport blocks using a first transmission mode; The second plurality of transport blocks are sent using a second transmission mode.

39. The method of claim 38, further comprising: In response to determining that a transport block of the first plurality of transport blocks has not been successfully received, suspending the sending of the second plurality of transport blocks.

40. The method of claim 38, further comprising: In response to determining that a transport block of the first plurality of transport blocks has not been successfully received, the sending of the second plurality of transport blocks is stopped.

41. An apparatus comprising: Memory, which stores instructions; A processor, wherein the processor is configured to perform the method according to any one of claims 1 to 40 by executing the instructions.

42. A computer readable medium comprising instructions which, when executed by a processor of a handheld device, cause the handheld device to perform the method of any one of claims 1 to 40.

Images