Methods and systems for user equipment capability reporting and machine-learning based channel state information configuration

The method of UE capability reporting and AI/ML-based CSI configuration addresses inefficiencies in payload size management by using pairing IDs and feature groups, ensuring efficient and compatible AI/ML-based CSI reporting, thus improving communication efficiency.

WO2024241222A1PCT designated stage expired Publication Date: 2024-11-28TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
PCT/IB2024/054940
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-22
Filing Date
2024-05-22
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Current communication systems face challenges in efficiently configuring and reporting user equipment (UE) capabilities for artificial intelligence/machine learning (AI/ML)-based channel state information (CSI) compression, leading to inefficiencies in payload size management and compatibility between UE and network nodes.

Method used

The method involves UE sending an indication of its capabilities, including maximum payload sizes or ranges, to network nodes, which then configure AI/ML-based CSI reports, ensuring compatibility and optimal resource allocation by using pairing IDs and feature groups to align payload sizes and quantization methods.

Benefits of technology

This approach enables proper configuration of AI/ML-based CSI reports, reducing the probability of CSI omission and optimizing resource allocation, thereby enhancing communication efficiency and compatibility between UE and network nodes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IB2024054940_28112024_PF_FP_ABST
    Figure IB2024054940_28112024_PF_FP_ABST
Patent Text Reader

Abstract

A method performed by a user equipment (UE) is provided. The method comprises sending an indication of one or more UE capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression to a network node. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report. The method further comprises receiving an AI / ML-based CSI report configuration, and sending the AI / ML-based CSI report to a network node. The AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE. The one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration.
Need to check novelty before this filing date? Find Prior Art

Description

METHODS AND SYSTEMS FOR USER EQUIPMENT CAPABILITY REPORTING AND MACHINE-EEARNING BASED CHANNEL STATE INFORMATION CONFIGURATIONCROSS REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 468,241 filed on May 22, 2023, titled “METHODS FOR CSI CONFIGURATION FOR AI-CSI”, and U.S. Provisional Patent Application No. 63 / 468,245 filed on May 22, 2023, titled “DEFINITION OF USER EQUIPMENT CAPABILITY REPORTING FOR AI-CSI”. The contents of both applications are hereby incorporated by reference in its entirety for all purposes.FIELD

[0002] The present disclosure relates generally to communication systems and, more specifically, to methods and systems for definition of user equipment (UE) capability reporting and channel state information (CSI) configuration for artificial intelligence / machine learning (AI / ML) based CSI.BACKGROUND

[0003] Artificial intelligence and machine learning technologies are being developed as tools to enhance the design of air-interfaces in wireless communication networks. Example use cases of Al and ML technologies include using autoencoders for channel state information compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying line of sight (LOS) and non-LOS (NLOS) conditions to enhance the positioning accuracy; using reinforcement learning for beam selection at the network node side and / or the user equipment (UE) side to reduce the signaling overhead and beam alignment latency; and using deep reinforcement learning to learn an optimal precoding policy for complex multiple input multiple output (MIMO) precoding problems.

[0004] In 3rd Generation Partnership Project (3GPP) new radio (NR) technology development, the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead have been, and are still being, explored. By analyzing a few selected use cases (e.g., CSI feedback, beam management, and positioning, etc.), the technology development work aims at laying the foundation for future air-interface use cases leveraging AI / ML techniques.SUMMARY

[0005] Various computer-implemented systems, methods, and articles of manufacture for definition of UE capability reporting and CSI configuration for AI / ML-based CSI are described herein.

[0006] In one embodiment, a method performed by a user equipment (UE) is provided. The method comprises sending an indication of one or more UE capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression to a network node. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report.

[0007] In one embodiment, a method performed by a network node is provided. The method comprises receiving an indication of one or more UE capabilities of performing AI / ML-based CSI report compression from a UE. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report. The method further comprises sending an AI / ML-based CSI report configuration to the UE.

[0008] In one embodiment, a method performed by a UE is provided. The method comprises receiving an AI / ML-based CSI report configuration. The AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE. The one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration. The method further comprises sending the AI / ML-based CSI report to a network node.

[0009] In one embodiment, a method performed by a network node is provided. The method comprises sending an AI / ML-based channel state information (CSI) report configuration to a UE. The AI / ML based CSI report configuration comprises information for identifying one or more AI / ML models of the UE. The one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration. The method further comprises receiving the AI / ML-based CSI report from the UE.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] For a beter understanding of the various described embodiments, reference should be made to the Detailed Description below, in conjunction with the following drawings in which like reference numerals refer to corresponding parts throughout the figures.

[0011] Figure 1 illustrates exemplary AI / ML model training and inference pipelines and their interactions within an AI / ML model lifecycle management procedure, in accordance with some embodiments.

[0012] Figure 2 illustrates an example of a communication system in accordance with some embodiments.

[0013] Figure 3 illustrates an exemplary user equipment in accordance with some embodiments.

[0014] Figure 4 illustrates an exemplary network node in accordance with some embodiments.

[0015] Figure 5 is a block diagram of an exemplary host, which may be an embodiment of the host of Figure 2, in accordance with various aspects described herein.

[0016] Figure 6 is a block diagram illustrating an exemplary virtualization environment in which functions implemented by some embodiments may be virtualized.

[0017] Figure 7 illustrates a communication diagram of an exemplary host communicating via a network node with a UE over a partially wireless connection in accordance with some embodiments.

[0018] Figure 8 illustrates a functional framework that can be used for different network nodes-UE collaboration levels for the AI / ML model lifecycle management (LCM) according to some embodiments.

[0019] Figure 9 illustrates an example of a joint AI / ML operation between network nodes and UEs for two-sided models according to some embodiments.

[0020] Figure 10 illustrates a flowchart showing an example method performed by a UE for reporting UE capabilities of performing artificial intelligence / machine learning (AI / ML)-based CSI report compression according to some embodiments.

[0021] Figure 11 illustrates a flowchart showing an example method performed by a network node for receiving a report of UE capabilities of performing artificial intelligence / machine learning (AI / ML)-based CSI report compression according to some embodiments.

[0022] Figure 12 illustrates three example joint training sessions between network nodes andUEs according to some embodiments.

[0023] Figure 13 illustrates a flowchart showing an example method performed by a UE for receiving an AI / ML-based CSI report configuration and sending the AI / ML-based CSI report according to some embodiments.

[0024] Figure 14 illustrates a flowchart showing an example method performed by a network node for sending an AI / ML-based CSI report configuration and receiving the AI / ML-based CSI report according to some embodiments.DETAILED DESCRIPTION

[0025] To provide a more thorough understanding of the present invention, the following description sets forth numerous specific details, such as specific configurations, parameters, examples, and the like. It should be recognized, however, that such description is not intended as a limitation on the scope of the present invention but is intended to provide a better description of the exemplary embodiments.

[0026] Throughout the specification and claims, the following terms take the meanings explicitly associated herein, unless the context clearly dictates otherwise:

[0027] The phrase “in one embodiment” as used herein does not necessarily refer to the same embodiment, though it may. Thus, as described below, various embodiments of the invention may be readily combined, without departing from the scope or spirit of the invention.

[0028] As used herein, the term “or” is an inclusive “or” operator and is equivalent to the term “and / or,” unless the context clearly dictates otherwise.

[0029] The term “based on” is not exclusive and allows for being based on additional factors not described unless the context clearly dictates otherwise.

[0030] As used herein, and unless the context dictates otherwise, the term “coupled to” is intended to include both direct coupling (in which two elements that are coupled to each other contact each other) and indirect coupling (in which at least one additional element is located between the two elements). Therefore, the terms “coupled to” and “coupled with” are used synonymously. Within the context of a networked environment where two or more components or devices are able to exchange data, the terms “coupled to” and “coupled with” are also used to mean “communicatively coupled with”, possibly via one or more intermediary devices.

[0031] In addition, throughout the specification, the meaning of “a”, “an”, and “the” includes plural references, and the meaning of “in” includes “in” and “on”.

[0032] Although some of the various embodiments presented herein constitute a single combination of inventive elements, it should be appreciated that the inventive subject matter isconsidered to include all possible combinations of the disclosed elements. As such, if one embodiment comprises elements A, B, and C, and another embodiment comprises elements B and D, then the inventive subject matter is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly discussed herein. Further, the transitional term “comprising” means to have as parts or members, or to be those parts or members. As used herein, the transitional term “comprising” is inclusive or open-ended and does not exclude additional, unrecited elements or method steps.

[0033] A functional framework for AI / ML model lifecycle management (LCM) is described using Figure 1.

[0034] Building an (AI / ML) model includes several development steps where the actual training of the AI / ML model is one step in a training pipeline. Developing an AI / ML model also involves the AI / ML model’s lifecycle management. This is illustrated in Figure 1, which illustrates exemplary AI / ML model training and inference pipelines, and their interactions within a model lifecycle management procedure. As illustrated in Figure 1, an AI / ML model lifecycle management typically comprises a training (re-training) pipeline 120, a model deployment stage 130, an inference pipeline 140, and a drift detection stage 150.

[0035] In some embodiments, training (re-training) pipeline 120 includes several steps such as a data ingestion step 122, a data pre-processing step 124, a model training step 126, a model evaluation step 128, and a model registration step 129. In the data ingestion step 122, a device operating an AI / ML model (e.g., a user equipment (UE), a server, or a network node) gathers raw data (e.g., training data) from a data storage such as a database. Training data can be used by the AI / ML model to learn patterns and relationships that exist within the data, so that a trained AI / ML model can make accurate predictions of classifications on inference data (e.g., new data). Training data may include input data and corresponding output data. In some examples, after the ingestion of data to the device, there may also be an additional step that controls the validity of the gathered data. In the data pre-processing step 124, the device can apply some feature engineering to the gathered data. The feature engineering may include data normalization and possibly a data transformation required for the input data of the AI / ML model. In the model training phase 126, the AI / ML model can be trained based on the pre-processed data.

[0036] With reference still to Figure 1, in the model evaluation step 128, the AI / ML model’s performance is evaluated (e.g., benchmarked with respect to certain modal baseline performance). The performance evaluation results can be used to make adjustments of the model training. Thus, the model training step 126 and the model evaluation step 128 can be iteratively performed untilan acceptable level of performance (as previously exemplified) is achieved. Afterwards, the AI / ML model is considered to be sufficiently trained to satisfy a performance requirement. The model registration step 129 then registers the AI / ML model, including any corresponding AI / ML meta data that provides information on how the AI / ML model was developed, and possibly AI / ML model evaluations performance outcomes.

[0037] Figure 1 further illustrates that an AI / ML model deployment stage 130, in which the trained (or re-trained) AI / ML model are deployed as a part of the inference pipeline 140. For example, the trained (or re-trained) AI / ML model may be deployed to a UE for making inferences or predictions based on certain collected data. In one embodiment, the inference pipeline 140 includes a data ingestion step 142, a data pre-processing step 144, a model operation step 146, and data and model monitoring step 148. In the data ingestion step 142, a device operating an AI / ML model (e.g., a UE, a server, or a network node) gathers raw data (e.g., inference data) from a data storage. Unlike training data, raw data or inference data can be new data that have not been encountered or used by the AI / ML model. A trained AI / ML model can make predictions or classifications based on the raw data or inference data.

[0038] The data pre-processing step 144 is typically identical to corresponding data preprocessing step 124 that occurs in the training pipeline 120. In the model operation step 146, the AI / ML model uses the trained and deployed model in an operational mode, such that it makes predictions or classifications from the pre-processed inference data (and / or any features obtained based on the raw inference data). In the data and model monitoring step 148, the device can validate that the inference data are from a distribution that aligns well with the training data, as well as monitor the AI / ML model outputs for detecting any performance drifts or operational drifts. At the drift detection stage 150, the device can provide information about any drifts in the model operations. For instance, the device can provide such information to a device implementing the training pipeline 120 such that the AI / ML model can be retrained to at least partially correcting the performance drifts or operational drifts.

[0039] Figure 2 shows an example of a communication system 200 in accordance with some embodiments.

[0040] In the example, the communication system 200 includes a telecommunication network 202 that includes an access network 204, such as a radio access network (RAN), and a core network 206, which includes one or more core network nodes 208. The access network 204 includes one or more access network nodes, such as network nodes 210a and 210b (one or more of which may be generally referred to as network nodes 210), or any other similar 3rdGeneration PartnershipProject (3GPP) access node or non-3GPP access point. The network nodes 210 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 212a, 212b, 212c, and 212d (one or more of which may be generally referred to as UEs 212) to the core network 206 over one or more wireless connections.

[0041] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 200 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 200 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0042] The UEs 212 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 210 and other communication devices. Similarly, the network nodes 210 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 212 and / or with other network nodes or equipment in the telecommunication network 202 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 202.

[0043] In the depicted example, the core network 206 connects the network nodes 210 to one or more hosts, such as host 216. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 206 includes one more core network nodes (e.g., core network node 208) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 208. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0044] The host 216 may be under the ownership or control of a service provider other than an operator or provider of the access network 204 and / or the telecommunication network 202, and may be operated by the service provider or on behalf of the service provider. The host 216 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0045] As a whole, the communication system 200 of Figure 2 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0046] In some examples, the telecommunication network 202 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 202 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 202. For example, the telecommunications network 202 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC)ZMassive loT services to yet further UEs.

[0047] In some examples, the UEs 212 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 204 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 204. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configuredfor multi -radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0048] In the example, the hub 214 communicates with the access network 204 to facilitate indirect communication between one or more UEs (e.g., UE 212c and / or 212d) and network nodes (e.g., network node 210b). In some examples, the hub 214 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 214 may be a broadband router enabling access to the core network 206 for the UEs. As another example, the hub 214 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 210, or by executable code, script, process, or other instructions in the hub 214. As another example, the hub 214 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 214 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 214 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 214 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 214 acts as a proxy server or orchestrator for the UEs, in particular in if one or more of the UEs are low energy loT devices.

[0049] The hub 214 may have a constant / persistent or intermittent connection to the network node 210b. The hub 214 may also allow for a different communication scheme and / or schedule between the hub 214 and UEs (e.g., UE 212c and / or 212d), and between the hub 214 and the core network 206. In other examples, the hub 214 is connected to the core network 206 and / or one or more UEs via a wired connection. Moreover, the hub 214 may be configured to connect to an M2M service provider over the access network 204 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 210 while still connected via the hub 214 via a wired or wireless connection. In some embodiments, the hub 214 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 210b. In other embodiments, the hub 214 may be a nondedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 210b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0050] Figure 3 shows a UE 300 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelesslywith network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop -mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3 GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0051] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to- everything (V2X) . In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0052] The UE 300 includes processing circuitry 302 that is operatively coupled via a bus 304 to an input / output interface 306, a power source 308, a memory 310, a communication interface 312, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 3. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0053] The processing circuitry 302 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 310. The processing circuitry 302 may be implemented as one or more hardware -implemented state machines (e.g., in discrete logic, field- programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 302 may include multiple central processing units (CPUs).

[0054] In the example, the input / output interface 306 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 300. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0055] In some embodiments, the power source 308 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 308 may further include power circuitry for delivering power from the power source 308 itself, and / or an external power source, to the various parts of the UE 300 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 308. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 308 to make the power suitable for the respective components of the UE 300 to which power is supplied.

[0056] The memory 310 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 310 includes one or more application programs 314, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 316. The memory 310 may store, for use by the UE 300, any of a variety of various operating systems or combinations of operating systems.

[0057] The memory 310 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) opticaldisc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 310 may allow the UE 300 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 310, which may be or comprise a device-readable storage medium.

[0058] The processing circuitry 302 may be configured to communicate with an access network or other network using the communication interface 312. The communication interface 312 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 322. The communication interface 312 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 318 and / or a receiver 320 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 318 and receiver 320 may be coupled to one or more antennas (e.g., antenna 322) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0059] In the illustrated embodiment, communication functions of the communication interface 312 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short- range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0060] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 312, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0061] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0062] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non -limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or itemtracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 300 shown in Figure 3.

[0063] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As oneparticular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0064] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0065] Figure 4 shows a network node 400 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NRNodeBs (gNBs)).

[0066] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0067] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes,Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0068] The network node 400 includes a processing circuitry 402, a memory 404, a communication interface 406, and a power source 408. The network node 400 may be composed of multiple physically separate components (e.g., aNodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 400 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 400 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 404 for different RATs) and some components may be reused (e.g., a same antenna 410 may be shared by different RATs). The network node 400 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 400, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 400.

[0069] The processing circuitry 402 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 400 components, such as the memory 404, to provide network node 400 functionality.

[0070] In some embodiments, the processing circuitry 402 includes a system on a chip (SOC). In some embodiments, the processing circuitry 402 includes one or more of radio frequency (RF) transceiver circuitry 412 and baseband processing circuitry 414. In some embodiments, the radio frequency (RF) transceiver circuitry 412 and the baseband processing circuitry 414 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 412 and baseband processing circuitry 414 may be on the same chip or set of chips, boards, or units.

[0071] The memory 404 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 402. The memory 404 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 402 and utilized by the network node 400. The memory 404 may be used to store any calculations made by the processing circuitry 402 and / or any data received via the communication interface 406. In some embodiments, the processing circuitry 402 and memory 404 are integrated.

[0072] The communication interface 406 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 406 comprises port(s) / terminal(s) 416 to send and receive data, for example to and from a network over a wired connection. The communication interface 406 also includes radio front-end circuitry 418 that may be coupled to, or in certain embodiments a part of, the antenna 410. Radio front-end circuitry 418 comprises filters 420 and amplifiers 422. The radio front-end circuitry 418 may be connected to an antenna 410 and processing circuitry 402. The radio front-end circuitry may be configured to condition signals communicated between antenna 410 and processing circuitry 402. The radio front-end circuitry 418 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 418 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 420 and / or amplifiers 422. The radio signal may then be transmitted via the antenna 410. Similarly, when receiving data, the antenna 410 may collect radio signals which are then converted into digital data by the radio front-end circuitry 418. The digital data may be passed to the processing circuitry 402. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0073] In certain alternative embodiments, the network node 400 does not include separate radio front-end circuitry 418, instead, the processing circuitry 402 includes radio front-end circuitry and is connected to the antenna 410. Similarly, in some embodiments, all or some of theRF transceiver circuitry 412 is part of the communication interface 406. In still other embodiments, the communication interface 406 includes one or more ports or terminals 416, the radio front-end circuitry 418, and the RF transceiver circuitry 412, as part of a radio unit (not shown), and the communication interface 406 communicates with the baseband processing circuitry 414, which is part of a digital unit (not shown).

[0074] The antenna 410 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 410 may be coupled to the radio front-end circuitry 418 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 410 is separate from the network node 400 and connectable to the network node 400 through an interface or port.

[0075] The antenna 410, communication interface 406, and / or the processing circuitry 402 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 410, the communication interface 406, and / or the processing circuitry 402 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0076] The power source 408 provides power to the various components of network node 400 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 408 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 400 with power for performing the functionality described herein. For example, the network node 400 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 408. As a further example, the power source 408 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0077] Embodiments of the network node 400 may include additional components beyond those shown in Figure 4 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 400 may include user interfaceequipment to allow input of information into the network node 400 and to allow output of information from the network node 400. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 400.

[0078] Figure 5 is a block diagram of a host 500, which may be an embodiment of the host 216 of Figure 2, in accordance with various aspects described herein. As used herein, the host 500 may be or comprise various combinations hardware and / or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, container, or processing resources in a server farm. The host 500 may provide one or more services to one or more UEs.

[0079] The host 500 includes processing circuitry 502 that is operatively coupled via a bus 504 to an input / output interface 506, a network interface 508, a power source 510, and a memory 512. Other components may be included in other embodiments. Features of these components may be substantially similar to those described with respect to the devices of previous figures, such as Figures 3 and 4, such that the descriptions thereof are generally applicable to the corresponding components of host 500.

[0080] The memory 512 may include one or more computer programs including one or more host application programs 514 and data 516, which may include user data, e.g., data generated by a UE for the host 500 or data generated by the host 500 for a UE. Embodiments of the host 500 may utilize only a subset or all of the components shown. The host application programs 514 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (A VC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of UEs (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application programs 514 may also provide for user authentication and licensing checks and may periodically report health, routes, and content availability to a central node, such as a device in or on the edge of a core network. Accordingly, the host 500 may select and / or indicate a different host for over-the-top services for a UE. The host application programs 514 may support various protocols, such as the HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), Dynamic Adaptive Streaming over HTTP (MPEG-DASH), etc.

[0081] Figure 6 is a block diagram illustrating a virtualization environment 600 in which functions implemented by some embodiments may be virtualized. In the present context,virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 600 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized.

[0082] Applications 602 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 600 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0083] Hardware 604 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 606 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 608a and 608b (one or more of which may be generally referred to as VMs 608), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 606 may present a virtual operating platform that appears like networking hardware to the VMs 608.

[0084] The VMs 608 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 606. Different embodiments of the instance of a virtual appliance 602 may be implemented on one or more of VMs 608, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0085] In the context of NFV, a VM 608 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Eachof the VMs 608, and that part of hardware 604 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 608 on top of the hardware 604 and corresponds to the application 602.

[0086] Hardware 604 may be implemented in a standalone network node with generic or specific components. Hardware 604 may implement some functions via virtualization. Alternatively, hardware 604 may be part of a larger cluster of hardware (e.g., such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 610, which, among others, oversees lifecycle management of applications 602. In some embodiments, hardware 604 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 612 which may alternatively be used for communication between hardware nodes and radio units.

[0087] Figure 7 shows a communication diagram of a host 702 communicating via a network node 704 with a UE 706 over a partially wireless connection in accordance with some embodiments. Example implementations, in accordance with various embodiments, of the UE (such as a UE 212a of Figure 2 and / or UE 300 of Figure 3), network node (such as network node 210a of Figure 2 and / or network node 400 of Figure 4), and host (such as host 216 of Figure 2 and / or host 500 of Figure 5) discussed in the preceding paragraphs will now be described with reference to Figure 7.

[0088] Like host 500, embodiments of host 702 include hardware, such as a communication interface, processing circuitry, and memory. The host 702 also includes software, which is stored in or accessible by the host 702 and executable by the processing circuitry. The software includes a host application that may be operable to provide a service to a remote user, such as the UE 706 connecting via an over-the-top (OTT) connection 750 extending between the UE 706 and host 702. In providing the service to the remote user, a host application may provide user data which is transmitted using the OTT connection 750.

[0089] The network node 704 includes hardware enabling it to communicate with the host 702 and UE 706. The connection 760 may be direct or pass through a core network (like corenetwork 206 of Figure 2) and / or one or more other intermediate networks, such as one or more public, private, or hosted networks. For example, an intermediate network may be a backbone network or the Internet.

[0090] The UE 706 includes hardware and software, which is stored in or accessible by UE 706 and executable by the UE’s processing circuitry. The software includes a client application, such as a web browser or operator-specific “app” that may be operable to provide a service to a human or non-human user via UE 706 with the support of the host 702. In the host 702, an executing host application may communicate with the executing client application via the OTT connection 750 terminating at the UE 706 and host 702. In providing the service to the user, the UE's client application may receive request data from the host's host application and provide user data in response to the request data. The OTT connection 750 may transfer both the request data and the user data. The UE's client application may interact with the user to generate the user data that it provides to the host application through the OTT connection 750.

[0091] The OTT connection 750 may extend via a connection 760 between the host 702 and the network node 704 and via a wireless connection 770 between the network node 704 and the UE 706 to provide the connection between the host 702 and the UE 706. The connection 760 and wireless connection 770, over which the OTT connection 750 may be provided, have been drawn abstractly to illustrate the communication between the host 702 and the UE 706 via the network node 704, without explicit reference to any intermediary devices and the precise routing of messages via these devices.

[0092] As an example of transmitting data via the OTT connection 750, in step 708, the host 702 provides user data, which may be performed by executing a host application. In some embodiments, the user data is associated with a particular human user interacting with the UE 706. In other embodiments, the user data is associated with a UE 706 that shares data with the host 702 without explicit human interaction. In step 710, the host 702 initiates a transmission carrying the user data towards the UE 706. The host 702 may initiate the transmission responsive to a request transmitted by the UE 706. The request may be caused by human interaction with the UE 706 or by operation of the client application executing on the UE 706. The transmission may pass via the network node 704, in accordance with the teachings of the embodiments described throughout this disclosure. Accordingly, in step 712, the network node 704 transmits to the UE 706 the user data that was carried in the transmission that the host 702 initiated, in accordance with the teachings of the embodiments described throughout this disclosure. In step 714, the UE 706 receives the userdata carried in the transmission, which may be performed by a client application executed on the UE 706 associated with the host application executed by the host 702.

[0093] In some examples, the UE 706 executes a client application which provides user data to the host 702. The user data may be provided in reaction or response to the data received from the host 702. Accordingly, in step 716, the UE 706 may provide user data, which may be performed by executing the client application. In providing the user data, the client application may further consider user input received from the user via an input / output interface of the UE 706. Regardless of the specific manner in which the user data was provided, the UE 706 initiates, in step 718, transmission of the user data towards the host 702 via the network node 704. In step 720, in accordance with the teachings of the embodiments described throughout this disclosure, the network node 704 receives user data from the UE 706 and initiates transmission of the received user data towards the host 702. In step 722, the host 702 receives the user data carried in the transmission initiated by the UE 706.

[0094] One or more of the various embodiments improve the performance of OTT services provided to the UE 706 using the OTT connection 750, in which the wireless connection 770 forms the last segment. More precisely, the teachings of these embodiments may improve the data rate, date communication efficiencies, real-time communication capabilities, and reduce power consumption, and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, improved content resolution, better responsiveness, reduced error rate or performance degradations, improved collaboration between network and UEs, and extended battery lifetime] .

[0095] In an example scenario, factory status information may be collected and analyzed by the host 702. As another example, the host 702 may process audio and video data which may have been retrieved from a UE for use in creating maps. As another example, the host 702 may collect and analyze real-time data to assist in controlling vehicle congestion (e.g., controlling traffic lights). As another example, the host 702 may store surveillance video uploaded by a UE. As another example, the host 702 may store or control access to media content such as video, audio, VR or AR which it can broadcast, multicast or unicast to UEs. As other examples, the host 702 may be used for energy pricing, remote control of non-time critical electrical load to balance power generation needs, location services, presentation services (such as compiling diagrams etc. from data collected from remote devices), or any other function of collecting, retrieving, storing, analyzing and / or transmitting data.

[0096] In some examples, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.There may further be an optional network functionality for reconfiguring the OTT connection 750 between the host 702 and UE 706, in response to variations in the measurement results. The measurement procedure and / or the network functionality for reconfiguring the OTT connection may be implemented in software and hardware of the host 702 and / or UE 706. In some embodiments, sensors (not shown) may be deployed in or in association with other devices through which the OTT connection 750 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software may compute or estimate the monitored quantities. The reconfiguring of the OTT connection 750 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not directly alter the operation of the network node 704. Such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary UE signaling that facilitates measurements of throughput, propagation times, latency and the like, by the host 702. The measurements may be implemented in that software causes messages to be transmitted, in particular empty or ‘dummy’ messages, using the OTT connection 750 while monitoring propagation times, errors, etc.

[0097] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may beimplemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0098] UE-NW (network) collaboration levels for one-sided and two-sided AI / ML models are described next with reference to Figure 8.

[0099] In general, the AI / ML models being developed for new radio (NR) air interface can be categorized into the following two types: a one-sided AI / ML model and a two-sided AI / ML model.

[0100] A one-sided AI / ML model can be a UE-sided AI / ML model or a network (NW)-sided AI / ML model. For a UE-sided AI / ML model, an inference is performed entirely at the UE side. For a NW-sided AI / ML model, an inference is performed entirely at the NW side.

[0101] A two-sided AI / ML model refers to a paired AI / ML model(s), over which a joint inference is performed across the UE and the network node. For example, a part of the joint inference is performed by a UE, and another part of the joint inference is performed by a network node, such as a next generation Node B (gNB), or vice versa.

[0102] When applying AI / ML technologies to air interface cases, different levels of collaboration between network nodes and UEs can be considered. Figure 8 shows a functional framework that can be used for different network nodes-UE collaboration levels for the AI / ML model lifecycle management (LCM) aspects for physical layer (PHY) cases.

[0103] As shown in Figure 8, the model LCM 810 comprises data collection configuration 811, model training configuration 812, model deploy, update, and transfer 813, model selection, activation, deactivation, model switching, and fallback operation 814, and model monitoring configuration 815. The data collection configuration 811 is used for data collection 821. The model training configuration 812 is used for model training 822. The model deploy, update, and transfer 813 is used for model deployment 823. The model selection, activation, deactivation, model switching, and fallback operation 814 is used for model inference 824. The model monitoring configuration 815 is used for model monitoring 825.

[0104] As shown in Figure 8, for different network nodes-UE collaboration levels, collected data provided by the data collection 821 can be used for the model training 822, the model inference 824, or the model monitoring 825. A trained model provided by the model training 822 can be used for the model deployment 823. A deployed model provided by the model deployment 823 can be used for the model inference 824. In some embodiments, the model inference 824 can provide an inference output using a one-sided AI / ML model or a joint inference output using a two-sided AI / ML model. Inference outputs provided by the model inference 824 can be providedto the model monitoring 825. The model monitoring 825 can provide key performance indicator (KPI) statistics 816 associated with the models to the model LCM 810.

[0105] In one embodiment, there may be no collaboration between network nodes and UEs. In this scenario, a proprietary AI / ML model operating with existing standard air interfaces is applied at one end of the communication link (e.g., at a UE side, or at a network node side). A model LCM (e.g., model selection / training, model monitoring, model retraining, model update) is performed at this node without an inter-node assistance. For example, a proprietary AI / ML model is operating at the UE side, the model LCM is performed at the UE side without assistance information provided from a network node.

[0106] In another embodiment, there may be limited collaboration between network nodes and UEs for one-sided models. In this scenario, an AI / ML model is operating at one end of the communication link (e.g., at a UE side, or at a network node side), and this node can also get assistance from node(s) at the other end of the communication channel for its AI / ML model LCM to some extent (e.g., model training / retraining, model update, model monitoring, model selection / fallback / switching). For example, an AI / ML model is operating at the UE side, and the UE also gets assistance from a network node (e.g., a gNB) for its AI / ML model LCM.

[0107] In another embodiment, there may be a joint AI / ML operation between network nodes and UEs for two-sided models. In this scenario, it is assumed that an AI / ML model is split with one part located at the network (NW) side, and the other part located at the UE side. Hence, the AI / ML model requires joint inferences between the NW and the UE, and the AI / ML model LCM involves both ends of a communication link.

[0108] Figure 9 shows an example of a joint AI / ML operation between network nodes and UEs for two-sided models. As shown in Figure 9, in an autoencoder-based CSI feedback / report, after a wireless channel associated to multiple subcarriers (sc), multiple base station transmission ports and multiple UE receiving ports is measured (901), an encoder 902 (e.g., at the UE-part of the two-sided autoencoder model) is operated at a UE to compress the estimated wireless channel. An output of the encoder 902 (e.g., the compressed wireless channel information estimates) is reported from the UE to a network node (e.g., a gNB). As shown in Figure 9, the network node uses a decoder 903 (e.g., the NW-part of the two-sided AE model) to reconstruct the estimated wireless channel information (904). In this disclosure, this type of use cases is referred to as a two-sided CSI-compression use case.

[0109] Functionality-based model life cycle management is described next.

[0110] With respect to AI / ML functionality identification and functionality-based LCM of UE -sided models and / or UE-part of two-sided models, functionality refers to an AI / ML-enabled feature / feature -group (FG) enabled by configuration(s), where one or more configurations are supported based on conditions indicated by a UE’s capability. Correspondingly, functionalitybased LCM operates based on at least one configuration of AI / ML-enabled feature / FG or specific configurations of an AI / ML-enabled feature / FG.

[0111] The existing UE capability framework defined in 3GPP for existing features can be used as a starting point for AI / ML functionality-based LCM of UE-sided models and / or the UE- part of two-sided models. The name of the feature group and the component(s) with candidate values may correspond to the functionality identification. From an operational point of view, the network node needs to know that the UE supports a certain functionality, and this information can be obtained via UE capability signalling.

[0112] For two-sided model cases, a network node (e.g., a gNB) can operate with a single network-part of the model (e.g., a decoder 903 shown in Figure 9 for the CSI-compression uses case), irrespective of the provider of the UE part of the model (e.g., an encoder 902 shown in Figure 9 for the CSI-compression uses case). In this scenario, a UE may need to support multiple UE -parts of models to pair with different network-parts of models that are trained by different network providers. Hence, there is a need to support selecting a UE part of the model (e.g., the encoder 902 shown in Figure 9) that is compatible with the network -part of the model (e.g., the decoder 903 shown in Figure 9 used in the connected gNB) of a specific network provider. Here, being compatible means, for example, that the encoder and decoder are trained together, and the encoder / decoder pair can pass the core performance test (if any) defined for this AI / ML-based feature.

[0113] In some examples, for UE capability reporting, the UE sends an indication of one or more UE capabilities of performing AI / ML-based CSI report compression to a network node. Then the network node sends an AI / ML-based CSI report configuration to the UE. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report. In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one pairing identification (PID). The PID identifies one or multiple pairs of two-sided models jointly trained in a model training session. The one or multiple pairs of two-sided models can be used for pairing of the UE-part and network-part of atwo-sided model. In some embodiments, a PID can be defined or agreed betweenthe UE side and network side after completion of a joint training session. In some embodiments, a PID can be assigned by a central entity, which manages, registers, or maintains a list of global PIDs for AI / ML models.

[0114] As described above, there currently exist certain challenge(s). A UE, which is capable for two-sided Al-CSI-compression-based CSI reporting, can be deployed with multiple AI / ML UE-part models. And these different AI / ML models deployed at the UE side can have different capabilities. For example, a UE-part model at the UE may only work with network nodes (e.g., gNBs) from a certain network provider and / or under a certain scenario (e.g., LoS or NLoS, high rise building scenario or urban macro scenario, high UE speed or low UE speed, NW antenna configuration 1 or NW antenna configuration 2, etc.). Hence, different UE-part models deployed at the UE can be associated with different AI-CSI reports that have different payload sizes or payload size ranges. Therefore, to align the payload size of the AI-CSI report sent from the UE to the network node, it is desired to enable the UE to indicate its UE capability in terms of supported AI-CSI report payload sizes for the Al-CSI-compression feature.

[0115] Certain aspects of the present disclosure and their embodiments may provide solutions to these or other challenges. This disclosure proposes methods for defining one or more UE capabilities for two-sided AI-CSI compression use cases. Based on the definition of the one or more UE capabilities, the UE indicates its supported payload sizes or payload size ranges of AI- CSI report for the two-sided AI-CSI compression feature to the network node. This disclosure further provides solutions for supporting a UE to report its capability of supporting different functionalities / feature groups (FGs) associated with one or multiple PIDs to the network node, so that the network node can compare the UE capability information with the NW-part model and properly configure the AI / ML-based CSI compression related parameters for model inference. In the below descriptions, Figures 10 and 11 are flowcharts providing an overview of methods for a UE to report its capabilities and for a network node to receive the UE reported capabilities. Detailed examples follow the description of Figures 10 and 11.

[0116] Figure 10 illustrates a flowchart showing an example method 1000 performed by a UE for reporting UE capability of performing artificial intelligence / machine learning (AI / ML)- based CSI report compression according to some embodiments. In block 1010 of method 1000, the UE sends an indication of one or more UE capabilities of performing AI / ML-based CSI report compression to a network node. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report.

[0117] In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one PID. Examples of the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges are described in greater detail below in connection with Tables 1-4. In some embodiments, the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression. In some embodiments, the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group. In one embodiment, the first feature group is supported by an AI / ML model of a first type of UE, and the second feature group is supported by an AI / ML model of a second type of UE. The first type of UE has reduced capabilities compared to the second type of UE. In one embodiment, the second type of UE comprises one or more AI / ML models supporting the first feature group and one or more AI / ML models supporting the second feature group. This is described in greater detail below in connection with Figure 12.

[0118] In some embodiments, the indication of the one or more UE capabilities further comprises at least one of a PID related to compatibility of AI / ML models of the UE, and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

[0119] In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits. In some embodiments, if scalar quantization (SQ) is used in an AI / ML model, the information comprises information for identifying one or more supported numbers of nodes in an output layer of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE. In some embodiments, if vector quantization (VQ) is used in an AI / ML model, the information comprises information for identifying a codebook related to a VQ of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE. In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations. In some embodiments, theone or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: SQ, VQ, or supported codebook(s) for the VQ.

[0120] In some embodiments, the one or more UE capabilities of performing AI / ML-based CSI report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks; restrictions on channel measurement resource (CMR) and interference measurement resource (IMR); and a new feature group that defines one or more features of an AI / ML framework.

[0121] With reference back to Figure 10, in block 1020 of method 1000, the UE receives configuration parameters from the network node. The UE comprises one or more AI / ML models configured to generate the compressed CSI report. The configuration parameters are set such that at least one of the one or more AI / ML models of the UE is compatible with at least one of AI / ML models of the network node. Examples of the configuration parameters are associated with one or more feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

[0122] Figure 11 illustrates a flowchart showing an example method 1100 performed by a network node for receiving a report of UE capability for performing artificial intelligence / machine learning (AI / ML)-based CSI report compression according to some embodiments. In block 1110 of method 1100, the network node receives an indication of one or more UE capabilities of performing AI / ML-based CSI report compression from a UE. The indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report.

[0123] In block 1120 of method 1100, the network node sends an AI / ML-based CSI report configuration to the UE.

[0124] In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one PID. In some embodiments, the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression. In some embodiments, the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group. In one embodiment, the first feature group is supported by an AI / ML model of a first type of UE, and the second feature group is supported by an AI / ML model of a second type of UE. The first type of UE has reduced capabilities compared to the second type of UE. In one embodiment, the second type of UE comprises one or more AI / ML modelssupporting the first feature group and one or more AI / ML models supporting the second feature group.

[0125] In some embodiments, the indication of the one or more UE capabilities further comprises at least one of a PID related to compatibility of AI / ML models of the UE, and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

[0126] In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits. In some embodiments, if SQ is used in an AI / ML model, the information comprises information for identifying one or more supported numbers of nodes in an output layer of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE. In some embodiments, if VQ is used in an AI / ML model, the information comprises information for identifying a codebook related to a vector quantization of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE. In some embodiments, the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations. In some embodiments, the one or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: SQ, VQ, or supported codebook(s) for the VQ.

[0127] In some embodiments, the one or more UE capabilities of performing AI / ML-based CSI report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks; restrictions on CMR and IMR; and a new feature group that defines one or more features of an AI / ML framework.

[0128] In some examples, at least the value or value range of one UE capability information / parameter / FG is defined in 3GPP Technical Specification (TS) 38.306.

[0129] Certain embodiments described herein may provide one or more of the following technical advantage(s). The proposed solution enables a UE to indicate its UE capabilities in terms of AI-CSI report payload size(s) for the Al-based two-sided CSI-compression feature. Based on the reported UE capabilities, the network node can set proper configuration parameter(s) (e.g.,CSI-RS measurement, and / or AI-CSI reporting, and / or UE-part model output quantization) for the UE-part model inference.

[0130] As mentioned above, a UE capability can be defined based on the UE’s capability of performing two-sided AI-CSI compression at the fimctionality / FG level, which may be different from the physical AI / ML model level capability at the UE. For example, a UE provider may train multiple physical UE-part AI / ML models for the same fimctionality / FG together with a network provider. Based on the scenario / condition in the real-world operation, the UE can select one of the models to use. In such a case, the UE-side physical model selection / switching operations within the same functionality is transparent to the network node. Also, if multiple UE providers participated in the same two-sided model training session with a network provider, different UE providers may train different physical AI / ML models for the same fimctionality / FG, but how the UE providers implement such models may not be seen at the functionality level.

[0131] Figure 12 illustrates three examples of joint training sessions according to some embodiments. Pairing IDs (or PIDs) are used in these example training sessions. A PID, which identifies one or more pairs of two-sided models jointly trained in a model training session, can be used for pairing of the UE-part and NW-part of a two-sided model. As shown in Figure 12, three example PIDs are obtained, one from each session. As shown in Figure 12, at least one PID represents an identification of at least one of a first FG (e.g., FG#1) or a second FG (e.g., FG#2). The UE may have one or more AI / ML models supporting at least one of the first FG or the second FG. In one embodiment, the first FG is supported by an AI / ML model of a first type of UE, and the second FG is supported by an AI / ML model of a second type of UE. The first type of UE has reduced capabilities compared to the second type of UE. In one embodiment, the second type of UE comprises one or more AI / ML models supporting the first FG and one or more AI / ML models supporting the second FG. In Figure 12, the first type of UE is shown as, for example, a low-end UE; and the second type of UE is shown as, for example, a high-end UE. A high-end UE generally supports more functionalities / FGs compared to a low-end UE.

[0132] In the first training session shown in Figure 12, there is a single NW-side model. While on the UE side, there are multiple UE-side models trained for two functionalities / feature- groups (FGs), e.g., FG#1 and FG#2. After the first training session, one or more UE providers have trained UE-part models that support two fimctionalities / FGs, and all these UE- side models are assigned with the same PID (e.g., Pairing ID #1). As shown in Figure 12, the PID represents an identification of a first FG (functionality / FG # 1) and a second FG (fimctionality / FG #2). Then, a UE provider may decide to implement the model(s) trained for fimctionality / FG # 1 in a first typeof UE. As shown in Figure 12, the first type of UE is a low-end UE shown in a dished line box. The first type of UE has reduced capabilities compared to a second type of UE, which is a high- end UE shown in a solid line box. As shown in Figure 12, for high-end UEs, the UE provider may implement model(s) supporting both functionality / FG #1 and functionality / FG #2.

[0133] In the second and third training sessions, two FGs (e.g., FG#1 and FG#2) are trained separately at a UE provider with the network provider. Two separate PIDs, e.g., Pairing ID #2 and Pairing ID #3, are assigned to the models trained for the two FGs after the training session. As shown in Figure 12, Pairing ID #2 is assigned to the first FG (fimctionality / FG #1). Pairing ID #3 is assigned to the second FG (functionality / FG #2). Then a low-end UE may implement model(s) trained only for the first FG (functionality / FG #1), while a high-end UE may implement model(s) trained for both FGs (functionality / FG # 1 and functionality / FG #2). In this case, different FGs have different PIDs.

[0134] Based on the above example, there are several embodiments related to the PID and functionality / FG. First, a PID and a fimctionality / FG can be at the same level. For example, one PID may represent, identify, or correspond to one or more FGs. Second, a UE may have one or multiple PIDs. Third, for a given PID, a UE may support one or multiple FGs. Fourth, a UE may have one or multiple AI / ML models for each FG. The number of AI / ML models for each FG supported by a UE may be UE specific and transparent to the network node.

[0135] In some embodiments, the UE capability signaling can be on the fimctionality / FG level but may not be tied to the physical AI / ML model deployed by the UE, meaning that the capability signaling may be defined according to different FGs.

[0136] As described above, this disclosure provides solutions for supporting a UE to report its capability of supporting different fimctionalities / FGs associated with one or multiple PIDs to the network node, so that the network node can compare the UE capability information with the NW-part model and properly configure the AI / ML-based CSI compression related parameters for model inference. Two scenarios are described below.

[0137] First, according to the above, if the network node can differentiate a first type of UE (e.g., a low-end UE) and a second type of UE (e.g., a high-end UE) from the same UE / chipset provider (e.g., via other UE capability reporting parameter(s)), and if the network node can differentiate the UEs from different UE / chipset providers (e.g., via UE provider / chipset ID reporting), the supported one or more functionalities / FGs by a UE for the two-sided CSI- compression use case can be identified, once the one or more supported PIDs are reported to the network node. The network node can first check if it can identify the same PID(s) stored duringits model training session. If so, the network node can continue checking the stored meta data for the model training session associated to these PID(s) and identify the one or more supported functionalities / FGs that the UE supports for this two-sided CSI-compression use case. Otherwise, the UE needs to report both the one or more supported PIDs and the one or more supported functionalities / FGs per PID to the network node. For both cases, the supported PIDs for AI / ML- based CSI compression can be included in the UE capability signaling.

[0138] In one embodiment, the UE indicates the one or more supported PIDs for the two- sided Al -CSI compression use case in UE capability reporting, based on which the network node determines valid PID(s) and one or more valid functionalities / FGs per valid PID at the UE for model inference.

[0139] In another embodiment, in addition to PID(s) for the two-sided CSI compression use case, the UE indicates information like the high-end UE type or the low-end UE type, UE vendor ID, and / or UE chipset ID in UE capability reporting, based on which the network node determines valid PID(s) and one or more valid functionalities / FGs per valid PID at the UE for model inference.

[0140] In another embodiment, in addition to PID(s) for the two-sided AI-CSI compression use case, the UE indicates the supported one or more functionalities / FGs per PID in UE capability reporting, based on which the network node determines valid PID(s) and one or more valid functionalities / FGs per valid PID at the UE for model inference.

[0141] In one embodiment, a PID is indicated as a separate UE capability parameter (FG) for the two-sided AI-CSI compression use case. In another embodiment, a PID is indicated as a definition parameter for one or more Al-CSI-compression related FGs.

[0142] Second, based on the one or more valid FGs at the UE, the network node can configure the UE performing model inference operations under this FG(s). For AI / ML-based CSI compression, the network node can efficiently configure the UE to provide an AI / ML CSI report. Configuring such a report requires knowledge of the possible payload size (PS) for transmitting the report. Otherwise, there will be a waste of resources if too many resources are allocated. On the contrary, the UE may not be able to transmit the CSI report if the allocated resources are not enough. Therefore, for each supported FG, the network node can calculate the maximum possible payload size (PS), or at least an approximation of the maximum possible PS, of the configured AI / ML-based CSI report.

[0143] Based on the above two scenarios, in a preferred embodiment, capability information about supported PID(s) and the supported maximum AI-CSI PS(s) (or an approximation thereof) per AI-CSI related FG per PID, are included in the UE capability signaling.

[0144] The following examples are provided by formulating the UE capability signaling using the legacy UE capability reporting framework / table in 3GPP TR 38.822. Some columns of the table in 3GPP TR 38.822 have been removed for better formatting. The examples are divided into two cases, depending on whether the candidate values of PS or payload size range (PSR) of model output generated from a UE-part model (e.g., encoder) is explicitly specified in 3GPP specifications. Note that these examples are non-limiting, they are mainly for explanation purposes. The exact formulation in 3GPP specifications may vary.

[0145] The PS and PSR can be interpreted as a factor of AI-CSI PS (not necessarily exactly the same as the actual AI-CSI PS / PSR), which can be used to determine the actual maximum PS of a configured AI / ML-based CSI report. It may be scaled with other reporting configuration parameters (such as rank, sub-band size, etc.). For example, in some cases, a PS / PSR is only defined for the payload for rank 1 transmission. When there are higher ranks configured, the actual maximum PS may also scale with the PS / PSR and the rank. In another example, auxiliary bits that relate to pre- / post-processing are also transmitted in the CSI report. As a result, the PS / PSR may either not take these bits into account, or the PS / PSR is only an affine function with respect to these bits.

[0146] The following examples illustrate scenarios when candidate output PS(s) / PSR(s) of a UE-side encoder model is explicitly specified in 3GPP specifications.

[0147] The PS or PSR of a model output generated from a UE-part model (e.g., encoder) can be explicitly specified in 3GPP specifications. In this case, the maximum PS associated with one or more FGs can be directly obtained from the specifications.

[0148] In one embodiment, candidate PS and PSR values can be explicitly specified in 3GPP, where each FG can be associated with one or multiple candidate PSs or PSRs. One or multiple PIDs are also included in the capability reporting, where each pairing is associated with one or more FGs.

[0149] In one example, a UE (e.g., a low-end UE) may only support a single PID and the supported PID only supports a single PS / PSR. As a result, Table 1 can be used for signaling the UE capability (e.g., sending an indication of one or more UE capabilities of performing artificial intelligence / machine learning (AI / ML)-based channel state information (CSI) report compression to a network node). This may be for example a basic component for the AI / ML-based CSI FG, so that all UEs that support an AI / ML-based CSI compression use case can have this basic functionality implemented.

[0150] In some cases, there is a one-to-one mapping between the PID and the PS / PSR, which for example is obtained during offline training. As a result, signaling only the supported PID is sufficient for the basic component.

[0151] Note that Table 1 is just an example, signaling of supported PID can also happen in another FG. For example, there may be a dedicated FG that signals supported PIDs, or there may be a general Al framework FG, wherein the supported PIDs are signaled.Table 1

[0152] In another example, a UE may support multiple PIDs and each PID may support only a single PS / PSR. One way to signal this is to perform in a similar way as in the previous example, but extend the basic component to support multiple PIDs and PS / PSRs. Another way is to treat supporting more than one PIDs and PS / PSRs as an optional feature which is in a new FG, as shown in Table 2.Table 2

[0153] In another example, a UE may support a single PID but multiple PS / PSRs. Then, this can be signaled to the network node using Table 3 (still treating support of single PID and PS / PSR as basic component)Table 3

[0154] The following examples illustrate scenarios when candidate output PS(s) / PSR(s) of a UE-side encoder model is not explicitly specified in 3GPP specifications.

[0155] In this case, the output PS(s) and PSR(s) can be determined for each FG, with possible dependency on pre-requisite FGs.

[0156] In one embodiment, a parameter combination is used for UE capability signaling, based on which the maximum PS for a configured AI / ML-based CSI report can be derived.

[0157] One solution is to specify a quantization method and include information about the quantization method in the said parameter combination. To facilitate disclosure of proposed solutions, one can denote the dimension of the complex latent space (e.g., the number of complex output nodes from the UE-side encoder) as K (for real latent space / output node, the corresponding value is 2K). Moreover, when scalar quantization (SQ) is used, the number of bits for quantizing each complex coefficient is denoted as Q; when vector quantization (VQ) is used, the size of the codebook being used for VQ is denoted as N.

[0158] In some cases, the SQ is specified in 3GPP, then the said parameter combination may contain at least supported values of K and / or Q. In some cases, the VQ is specified in 3GPP, then the said parameter combination may contain at least supported values of K and / or N. In some embodiment, supported VQ codebook is also included in the parameter combination. In some cases, both SQ and VQ are specified in 3GPP, then the said parameter combination may contain supported values of K, N, and Q. In some embodiment, supported VQ codebook is also included in the parameter combination.

[0159] In some cases, additional parameters, besides quantization-related, are also included in the said parameter combination as part of the UE capability. For example, if beam and / or delay domain pre-processing (e.g., selecting a subset of beams and / or delays) is performed for the input to the UE-sided encoder, then they may also need to be a part of the parameter combination of the UE capability.

[0160] Table 4 shows an example on how the UE capability can be signaled for the above cases.Table 4: Example of feature group indicating model based on TR 38.822 (note some columns that should be in this table have been removed for easier illustration).

[0161] In some examples, the FGs defined for the AI-CSI compression use case may be implemented in TS 38.306 with the corresponding ASN. l signaling defined as RRC (radio resource configuration) parameters for it. In the ASN.1 signaling, one or more FGs defined for the Al-CSI-compression use case in Table 5 based on TR 38.822 can be mapped to an AI-CSI compression related UE capability RRC parameter in TS 38.306. The associated parameters defined in “Components” and the associated parameter candidate values defined in “Note” in the Table 5 based on TR 38.822 can be used for the definition of the RRC parameter in TS 38.306.Table 5

[0162] It is understood that, for all of the above tables, there might be more components in the “Components” column, where applicable. For example, the “Components” column may also contain parameters related to measurement resource, such as the maximum number of CSI-RS ports per CSI-RS resource, the maximum number of CSI-RS resources, etc.

[0163] As described above, the usage of PID is mainly for selecting a UE-part model that is compatible with the NW-part model used at a network node (e.g., a gNB). Depending on the signaling design, the UE-part model selection can be done either at the UE or at the network node.

[0164] In some scenarios, configuring a CSI report using only a PID may result in uncertainty in the maximum payload size, as a PID may be associated with multiple pairs of two-sided models that have different sizes of the UE-part model (e.g., encoder) output, and / or different quantization methods and / or quantization levels of the UE-part model output. This could make it challenging for the network node to schedule and allocate proper and / or sufficient uplink (UL) resources for transmitting the CSI report. Hence, for two-sided AI / ML model cases (e.g., AI / ML based CSI- report feedback), a mechanism for aligning the AI-CSI report payload size between the UE and the network node is desired.

[0165] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. A network node configures a UE to transmit an Al-based CSI report using a PID for the AI / ML model and optionally together with configuration(s) associated with the corresponding AI / ML feature-group and / or configurations(s) associated with pre-requisite feature group(s). In the below descriptions, Figures 13 and 14 are flowcharts providing an overview ofmethods for a UE to receive AI / ML-based CSI report configuration and for the network node to send such configuration. Detailed examples follow the description of Figures 13 and 14.

[0166] Figure 13 illustrates a flowchart showing an example method 1300 performed by a UE for receiving an AI / ML-based CSI report configuration and sending a report to the network node according to some embodiments. In block 1310 of method 1300, the UE receives an AI / ML- based CSI report configuration. The AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE. The one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration.

[0167] In some embodiments, the information for identifying the one or more AI / ML models of the UE comprises at least one PID. In some embodiments, identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

[0168] In some embodiments, the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

[0169] In some embodiments, the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; an identifier used to determine the maximum payload size or the payload size range of the AI / ML- based CSI report; a number of nodes in an output layer of at least one of the one or more AI / ML models of the UE; one or more numbers of quantization bits per node in the output layer of at least one of the one or more AI / ML models of the UE; a codebook for vector quantization (VQ); a codebook size for the VQ; a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-based CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

[0170] In some embodiments, the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

[0171] In block 1320 of method 1300, the UE sends the AI / ML-based CSI report to a network node. In some embodiments, the AI / ML-based CSI report comprises at least one of: a selected PID; one or more selected feature groups; one or more selected configuration parameters; or an identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

[0172] Figure 14 illustrates a flowchart showing an example method 1400 performed by a network node for sending an AI / ML-based CSI report configuration to a UE and for receiving a CSI report from the UE according to some embodiments. In block 1410 of method 1400, the network node sends an AI / ML-based CSI report configuration to a UE. The AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE. The one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration.

[0173] In some embodiments, the information for identifying the one or more AI / ML models of the UE comprises at least one PID. In some embodiments, identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

[0174] In some embodiments, the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

[0175] In some embodiments, the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; an identifier used to determine the maximum payload size or the payload size range of the AI / ML-based CSI report; a number of nodes in an output layer of at least one of the one or more AI / ML models of the UE; one or more numbers of quantization bits per node in the output layer of at least one of the one or more AI / ML models of the UE; a codebook for vector quantization (VQ); a codebook size for the VQ; a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-bascd CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

[0176] In some embodiments, the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

[0177] In block 1420 of method 1400, the network node receives the AI / ML-based CSI report from the UE. In some embodiments, the AI / ML-based CSI report comprises at least one of: a selected PID; one or more selected feature groups; one or more selected configuration parameters; or an identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

[0178] Certain embodiments may provide one or more of the following technical advantage(s). The proposed solution allows the network node to select a proper UE-part model for the UE to use for the Al -CSI use case; and it allows the network node to allocate proper / sufficient resource for transmitting a CSI report, which reduces probability of CSI omission at the UE side. Detailed examples of the proposed solution are described next.

[0179] When configuring a CSI report, a network node needs to know the payload size, or the maximum payload size, of the configured CSI report. Then, the network node can schedule and allocate reasonable amount of resource (e.g., Physical Uplink Shared Channel -PUSCH), a proper Modulation and Coding Scheme (MCS), etc., for a UE to transmit the CSI report.

[0180] In the existing 3 GPP NR with non-AI based CSI reporting framework, the maximum payload size can be determined by the CSI reporting setting, which is a higher layer configured via the CSI-ReportConfig IE (Information Element) in an RRC (Radio Resource Control) message. Factors that affect the maximum payload size may be a codebook type, a codebook parameter setting, a rank restriction, a sub-band size, etc. When a CSI report has been configured, the said factors, hence the maximum payload size, are deterministic. Therefore, the network node can allocate resources for transmitting the CSI report accordingly.

[0181] For AI / ML-based CSI with two-sided models, a number of factors may affect the CSI payload size. First, a PID may be obtained after a joint offline training, which is both known to the network node and the UE. However, a PID may be associated with a number of AI / ML FGs, since for example one decoder can work with multiple encoders. In addition, there may be different configurations for the components within each FGs, and different configurations may result in different payloads. Furthermore, the AI / ML FG may have dependencies on pre-requisite FGs, which may also have an impact on the payload size. Hence, the network node needs to configure all the above properly to determine the maximum payload size, which is essential for allocating resources for CSI report.

[0182] In many cases, a UE needs to train the AI / ML model with multiple network providers and for varies scenarios. As a result, it is likely that a UE supports multiple PIDs. Sometimes, each paring ID may also support multiple FGs. Hence, in such scenarios, in a preferred embodiment, one paring ID together with one or more configuration parameters, associated with one or more supported FG(s) or UE capability parameter(s) for AI-CSI report, are configured by the network node to the UE in a CSI report configuration.

[0183] In some examples, the UE may perform AI-CSI payload calculation with the configuration parameter(s), since that is configured by the network node according to the UE capability signaling. Some non-limiting examples are shown below to further explain how the above methods and / or processes can be implemented. Some examples are based on the UE capability signaling technologies, which are disclosed above.

[0184] In one example, the PID and a parameter associated with an AI-CSI related FG can both be configured directly in the CSI-ReportConfig IE based on 3GPP NR TS 38.331 vl7.4. 1, as illustrated below. In this example, the paring ID is configured as an index, which can be used to identify the supported FGs from at the UE. Then a configuration parameter on payload size range is used to configure the CSI report format, which can be used by the UE to identify which FG to use, and which AI / ML model to use.- unchanged text -}

[0185] In another example, the paring ID and a parameter associated to an AI-CSI related FG can both be configured in the CodebookConfig IE from 3GPP NR TS 38.331 vl7.4.1, which is part of the CSI-ReportConfig IE, as illustrated below.CodebookConfig : := SEQUENCE { codebookType CHOICE { ai-csi SEQUENCE { paring ID INTEGER (0. .maxNrofParingIDs -1) , pa yl oadS iz eRange INTEGER ( 0. .maxPayloadSizeRangelDs -1) ,}

[0186] In another example, one PID and more than one configuration parameter associated to one or more AI-CSI related FG(s) can be configured to the UE. For example, the UE may decide what is the best quantization scheme to use (e.g., the number of nodes in the output layer of the UE-part model, K, and the number of bits per node, Q). One can define a set of configuration IDs that are associated with different sizes of K-Q. Then, this can be the CodebookConfig IE from 3GPP NR TS 38.331 vl7.4.1, which is apart of the CSI-ReportConfig IE, as illustrated below. In this case, the UE selects one configuration ID and reports the selected configuration ID as a part of the CSI report to the network node. In this example, the network node (e.g., gNB) may need to allocated UL resource for the CSI report according to the maximum payload from all configured pairs.CodebookConfig : := SEQUENCE { codebookType CHOICE { ai-csi SEQUENCE { paring ID INTEGER ( 0. .maxNrof ParingIDs -1) ,K-Q CHOICE { configuration 1 SEQUENCE] 32, 4} , configuration 2 SEQUENCE] 32, 8} ,Configuration N SEQUENCE] 16, 8} ,} ,}

[0187] In some examples, the configured PID and the configuration parameters are jointly used by the UE to determine the AI / ML model to use for calculating the configured CSI report. The AI / ML model selection can be transparent to the network node.

[0188] The configured PID and the configuration parameters are jointly used by the network node to determine the maximum payload size, which is used to determine the UL resource allocation for transmitting the configured CSI report.

[0189] In one embodiment, more than one PIDs and more than one configuration parameters are provided to the UE by the network node. The UE selects one PID and one configuration parameter combination (in this case one method to quantize UE-side encoder outputs), and reports the selected PID, where applicable, to the network node, as illustrated below.Codeboo kConfi g : : = S EQUENCE { codebookType CHOICE { ai- cs i SEQUENCE { paring ID CHOICE { SEQUENCE R , 1 , ... }} , K-Q CHOI CE { confi gurati on 1 SEQUENCE { 32 , 4 } , confi gurati on 2 SEQUENCE { 32 , 8 } ,Confi gurati on N SEQUENCE ! 16 , 8 } ,} , }

[0190] For any of the above embodiment, the PID(s), one or more parameters in the configuration parameter(s), can be configured to the UE via MAC-CE (Medium Access Control- Control Element) or DCI (Downlink Control Information), or a combination of MAC-CE and DCI, in addition to RRC (optional). For example, if MAC-CE and DCI are both used to configure the quantization method, then MAC-CE may configured a number of methods, e.g., {K, Q} = {32, 4}, {32, 8}, {16, 4}, { 16, 8}; then, DCI is used to indicate to the UE which pair of {K, Q} shall be used for a specific CSI report. For any of the above embodiments, supported combinations of CSI configuration and / or configured paring ID and / or configuration parameter(s) can be pre-defined in 3GPP specifications. Hence, each combination can be used by the network node to determine the maximum payload size of a configured CSI report, and by the UE to determine the CSI report format.

[0191] For any of the above embodiments, a configuration parameter for a dependent / pre- requisite FG can be configured together with the paring ID and / or the parameter combinations for the FGs of AI / ML-based CSI compression. Parameters for the pre-requisite FG may contain one or multiple of the following: a sub-band size; a rank restriction, and / or any information that is needed to determine the CSI reporting format and the maximum payload size of the configured CSI report.

[0192] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining,calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0193] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer- readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device -readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0194] ADDITIONAL EMBODIMENTS

[0195] Group A Embodiments

[0196] 1. A method performed by a user equipment (UE), the method comprising: sending an indication of one or more UE capabilities of performing artificial intelligence / machine learning (AI / ML)-based channel state information (CSI) report compression to a network node, wherein the indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of acompressed CSI report.

[0197] 2. The method of embodiment 1, wherein the UE comprises one or more AI / ML models configured to generate the compressed CSI report, further comprising: receiving, from the network node, configuration parameters, wherein the configuration parameters are set such that at least one of the one or more AI / ML models of the UE is compatible with at least one of AI / ML models of the network node.

[0198] 3. The method of embodiment 1, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one pairing identification (PID).

[0199] 4. The method of embodiment 3, wherein the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression.

[0200] 5. The method of embodiment 3, wherein the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group.

[0201] 6. The method of embodiment 5, wherein the first feature group is supported by anAI / ML model of a first type of UE and the second feature group is supported by an AI / ML model of a second type of UE, the first type of UE having reduced capabilities compared to the second type of UE.

[0202] 7. The method of embodiment 6, wherein the second type of UE comprises one or more AI / ML models supporting the first feature group and one or more AI / ML models supporting the second feature group.

[0203] 8. The method of embodiment 1, wherein the indication of the one or more UE capabilities further comprises at least one of a pairing identification (PID) related to compatibility of AI / ML models of the UE and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

[0204] 9. The method of embodiment 1, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits.

[0205] 10. The method of embodiment 1, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported numbers of nodes in an output layer of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE.

[0206] 11. The method of embodiment 1, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying a codebook related to a vector quantization of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE.

[0207] 12. The method of embodiment 1, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations.

[0208] 13. The method of embodiment 12, wherein the one or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: scalar quantization (SQ), vector quantization (VQ), or supported codebook(s) for the VQ.

[0209] 14. The method of embodiment 1, wherein the one or more UE capabilities of performing AI / ML-based CSI report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks; restrictions on channel measurement resource (CMR) and interference measurement resource (IMR); and a new feature group that defines one or more features of an AI / ML framework.

[0210] 15. The method of any of the previous embodiments, further comprising:providing user data; and forwarding the user data to a host via the transmission to the network node.

[0211] Group B Embodiments

[0212] 16. A method performed by a network node, the method comprising: receiving an indication of one or more user equipment (UE) capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression from a UE, wherein the indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report; and sending an AI / ML-based CSI report configuration to the UE.

[0213] 17. The method of embodiment 16, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one pairing identification (PID).

[0214] 18. The method of embodiment 17, wherein the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression.

[0215] 19. The method of embodiment 17, wherein the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group.

[0216] 20. The method of embodiment 19, wherein the first feature group is supported by an AI / ML model of a first type of UE and the second feature group is supported by an AI / ML model of a second type of UE, the first type of UE having reduced capabilities compared to the second type of UE.

[0217] 21. The method of embodiment 20, wherein the second type of UE comprises one or more AI / ML models supporting the first feature group and one or more AI / ML models supporting the second feature group.

[0218] 22. The method of embodiment 16, wherein the indication of the one or more UE capabilities further comprises at least one of a pairing identification (PID) related to compatibility of AI / ML models of the UE and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

[0219] 23. The method of embodiment 16, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of:information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits.

[0220] 24. The method of embodiment 16, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported numbers of nodes in an output layer of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE.

[0221] 25. The method of embodiment 16, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying a codebook related to a vector quantization of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE.

[0222] 26. The method of embodiment 16, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations.

[0223] 27. The method of embodiment 26, wherein the one or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: scalar quantization (SQ), vector quantization (VQ), or supported codebook(s) for the VQ.

[0224] 28. The method of embodiment 16, wherein the one or more UE capabilities of performing AI / ML-based CSI report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks;restrictions on channel measurement resource (CMR) and interference measurement resource (IMR); and a new feature group that defines one or more features of an AI / ML framework.

[0225] 29. The method of any of the previous embodiments 16-28, further comprising: obtaining user data; and forwarding the user data to a host or a user equipment.

[0226] Group C Embodiments

[0227] 30. A method performed by a user equipment (UE), the method comprising: receiving an artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report configuration, wherein the AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE, wherein the one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration; and sending the AI / ML-based CSI report to a network node.

[0228] 31. The method of embodiment 30, wherein the information for identifying the one or more AI / ML models of the UE comprises at least one pairing identification (PID).

[0229] 32. The method of embodiment 31, wherein the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

[0230] 33. The method of embodiment 32, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; or an identifier used to determine the maximum payload size or the payload size range of the AI / ML-based CSI report.

[0231] 34. The method of embodiment 32, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a number of nodes in an output layer of at least one of the one or more AI / ML models ofthe UE; one or more numbers of quantization bits per node in the output layer of at least one of the one or more AI / ML models of the UE; a codebook for vector quantization (VQ); or a codebook size for the VQ.

[0232] 35. The method of embodiment 32, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-based CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

[0233] 36. The method of embodiment 32, wherein identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

[0234] 37. The method of embodiment 32, wherein the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

[0235] 38. The method of embodiment 30, wherein the AI / ML-based CSI report comprises at least one of: a selected paring identification (PID); one or more selected feature groups; one or more selected configuration parameters; or an identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

[0236] 39. The method of any of the previous embodiments 30-38, further comprising:providing user data; and forwarding the user data to a host via the transmission to the network node.

[0237] Group D Embodiments

[0238] 40. A method performed by a network node, the method comprising: sending an artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report configuration to a user equipment (UE), wherein the AI / ML based CSI report configuration comprises information for identifying one or more AI / ML models of the UE, wherein the one or more AEML models of the UE are configured to generate an AI / ML- based CSI report based on the AI / ML-based CSI report configuration; and receiving the AI / ML-based CSI report from the UE.

[0239] 41. The method of embodiment 40, wherein the information for identifying the one or more AI / ML models of the UE comprises at least one pairing identification (PID).

[0240] 42. The method of embodiment 41, wherein the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

[0241] 43. The method of embodiment 42, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; or an identifier used to determine the maximum payload size or the payload size range of the AI / ML-based CSI report.

[0242] 44. The method of embodiment 42, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a number of nodes in an output layer of at least one of the one or more AI / ML models of the UE; one or more numbers of quantization bits per node in the output layer of at least one of the one or more AEML models of the UE; a codebook for vector quantization (VQ); ora codebook size for the VQ.

[0243] 45. The method of embodiment 42, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-based CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

[0244] 46. The method of embodiment 42, wherein identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

[0245] 47. The method of embodiment 42, wherein the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

[0246] 48. The method of embodiment 40, wherein the AI / ML-based CSI report comprises at least one of: a selected paring identification (PID); one or more selected feature groups; one or more selected configuration parameters; or an identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

[0247] 49. The method of any of the previous embodiments 39-46, further comprising: obtaining user data; and forwarding the user data to a host or a user equipment.

[0248] Group E Embodiments

[0249] 50. A user equipment for artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report, comprising: processing circuitry configured to perform any of the steps of any of the Group A embodiments or the Group C embodiments; and power supply circuitry configured to supply power to the processing circuitry.

[0250] 51. A network node for artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report, the network node comprising: processing circuitry configured to perform any of the steps of any of the Group B embodiments or the Group D embodiments; power supply circuitry configured to supply power to the processing circuitry.

[0251] 52. A user equipment (UE) for artificial intelligence / machine learning (AI / ML)- based channel state information (CSI) report, the UE comprising: an antenna configured to send and receive wireless signals; radio front-end circuitry connected to the antenna and to processing circuitry, and configured to condition signals communicated between the antenna and the processing circuitry; the processing circuitry being configured to perform any of the steps of any of the Group A embodiments or the Group C embodiments; an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and a battery connected to the processing circuitry and configured to supply power to the UE.

[0252] 53. A host configured to operate in a communication system to provide an over-the- top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), wherein the UE comprises a communication interface and processing circuitry, the communication interface and processing circuitry of the UE being configured to perform any of the steps of any of the Group A embodiments or the Group C embodiments to receive the user data from the host.

[0253] 54. The host of the previous embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit the user data to the UE from the host.

[0254] 55. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application, thereby providing the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0255] 56. A method implemented by a host operating in a communication system that further includes a network node and a user equipment (UE), the method comprising: providing user data for the UE; and initiating a transmission carrying the user data to the UE via a cellular network comprising the network node, wherein the UE performs any of the operations of any of the Group A embodiments or the Group C embodiments to receive the user data from the host.

[0256] 57. The method of the previous embodiment, further comprising: at the host, executing a host application associated with a client application executing on the UE to receive the user data from the UE.

[0257] 58. The method of the previous embodiment, further comprising: at the host, transmitting input data to the client application executing on the UE, the input data being provided by executing the host application, wherein the user data is provided by the client application in response to the input data from the host application.

[0258] 59. A host configured to operate in a communication system to provide an over-the- top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a cellular network for transmission to a user equipment (UE), wherein the UE comprises a communication interface and processing circuitry, the communication interface and processing circuitry of the UE being configured to perform any of the steps of any of the Group A embodiments or the Group C embodiments to transmit the user data to the host.

[0259] 60. The host of the previous embodiment, wherein the cellular network further includes a network node configured to communicate with the UE to transmit the user data from the UE to the host.

[0260] 61. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application, thereby providing the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0261] 62. A method implemented by a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: at the host, receiving user data transmitted to the host via the network node by the UE, wherein the UE performs any of the steps of any of the Group A embodiments or the Group C embodiments to transmit the user data to the host.

[0262] 63. The method of the previous embodiment, further comprising: at the host, executing a host application associated with a client application executing on the UE to receive the user data from the UE.

[0263] 64. The method of the previous embodiment, further comprising: at the host, transmitting input data to the client application executing on the UE, the input data being provided by executing the host application, wherein the user data is provided by the client application in response to the input data from the host application.

[0264] 65. A host configured to operate in a communication system to provide an over-the- top (OTT) service, the host comprising: processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a network node in a cellular network for transmission to a user equipment (UE), the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments or the Group D embodiments to transmit the user data from the host to the UE.

[0265] 66. The host of the previous embodiment, wherein: the processing circuitry of the host is configured to execute a host application that provides the user data; and the UE comprises processing circuitry configured to execute a client applicationassociated with the host application to receive the transmission of user data from the host.

[0266] 67. A method implemented in a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: providing user data for the UE; and initiating a transmission carrying the user data to the UE via a cellular network comprising the network node, wherein the network node performs any of the operations of any of the Group B embodiments or the Group D embodiments to transmit the user data from the host to the UE.

[0267] 68. The method of the previous embodiment, further comprising, at the network node, transmitting the user data provided by the host for the UE.

[0268] 69. The method of any of the previous 2 embodiments, wherein the user data is provided at the host by executing a host application that interacts with a client application executing on the UE, the client application being associated with the host application.

[0269] 70. A communication system configured to provide an over-the-top service, the communication system comprising: a host comprising: processing circuitry configured to provide user data for a user equipment (UE), the user data being associated with the over-the-top service; and a network interface configured to initiate transmission of the user data toward a cellular network node for transmission to the UE, the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments or the Group D embodiments to transmit the user data from the host to the UE.

[0270] 71. The communication system of the previous embodiment, further comprising: the network node; and / or the user equipment.

[0271] 72. A host configured to operate in a communication system to provide an over-the- top (OTT) service, the host comprising: processing circuitry configured to initiate receipt of user data; and a network interface configured to receive the user data from a network node in a cellular network, the network node having a communication interface and processing circuitry, the processing circuitry of the network node configured to perform any of the operations of any of the Group B embodiments or the Group D embodiments to receive the user data from a userequipment (UE) for the host.

[0272] 73. The host of the previous 2 embodiments, wherein: the processing circuitry of the host is configured to execute a host application, thereby providing the user data; and the host application is configured to interact with a client application executing on the UE, the client application being associated with the host application.

[0273] 74. The host of the any of the previous 2 embodiments, wherein the initiating receipt of the user data comprises requesting the user data.

[0274] 75. A method implemented by a host configured to operate in a communication system that further includes a network node and a user equipment (UE), the method comprising: at the host, initiating receipt of user data from the UE, the user data originating from a transmission which the network node has received from the UE, wherein the network node performs any of the steps of any of the Group B embodiments or the Group D embodiments to receive the user data from the UE for the host.

[0275] 76. The method of the previous embodiment, further comprising at the network node, transmitting the received user data to the host.

[0276] The foregoing specification is to be understood as being in every respect illustrative and exemplary, but not restrictive, and the scope of the disclosure herein is not to be determined from the specification, but rather from the claims as interpreted according to the full breadth permitted by the patent laws. It is to be understood that the embodiments shown and described herein are only illustrative of the principles of the present disclosure and that various modifications may be implemented by those skilled in the art without departing from the scope and spirit of the present disclosure. Those skilled in the art could implement various other feature combinations without departing from the scope and spirit of the disclosure.

Claims

CLAIMSWhat is claimed is:1 . A method performed by a user equipment (UE), the method comprising: sending (1010) an indication of one or more UE capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression to a network node, wherein the indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report.

2. The method of claim 1, wherein the UE comprises one or more AI / ML models configured to generate the compressed CSI report, further comprising:Receiving (1020), from the network node, configuration parameters, wherein the configuration parameters are set such that at least one of the one or more AI / ML models of the UE is compatible with at least one of AI / ML models of the network node.

3. The method of any of claims 1 or 2, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one pairing identification (PID).

4. The method of claim 3, wherein the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression.

5. The method of claim 3, wherein the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group.

6. The method of claim 5, wherein the first feature group is supported by an AI / ML model of a first type of UE and the second feature group is supported by an AI / ML model of a second type of UE, the first type of UE having reduced capabilities compared to the second type of UE.

7. The method of claim 6, wherein the second type of UE comprises one or more AI / ML models supporting the first feature group and one or more AI / ML models supporting the second feature group.

8. The method of any of claims 1-7, wherein the indication of the one or more UE capabilities further comprises at least one of a pairing identification (PID) related to compatibility of AI / ML models of the UE and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

9. The method of any of claims 1-8, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits.

10. The method of any of claims 1-9, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported numbers of nodes in an output layer of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE.

11. The method of any of claims 1-10, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying a codebook related to a vector quantization of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE.

12. The method of any of claims 1-11, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations.

13. The method of claim 12, wherein the one or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: scalar quantization (SQ), vector quantization (VQ), or supported codebook(s) for the VQ.

14. The method of any of claims 1-13, wherein the one or more UE capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks; restrictions on channel measurement resource (CMR) and interference measurement resource (IMR); and a new feature group that defines one or more features of an AI / ML framework.

15. A method performed by a network node, the method comprising: receiving ( 1110) an indication of one or more user equipment (UE) capabilities of performing artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report compression from a UE, wherein the indication of one or more UE capabilities comprises information for identifying one or more maximum payload sizes, or one or more payload size ranges, of a compressed CSI report; and sending (1120) an AI / ML-based CSI report configuration to the UE.

16. The method of claim 15, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report is represented by at least one pairing identification (PID).

17. The method of claim 16, wherein the at least one PID represents an identification of one or more feature groups related to AI / ML-based CSI report compression.

18. The method of claim 16, wherein the at least one PID represents an identification of at least one of a first feature group or a second feature group, the UE having one or more AI / ML models supporting at least one of the first feature group or the second feature group.

19. The method of claim 18, wherein the first feature group is supported by an AI / ML model of a first type of UE and the second feature group is supported by an AI / ML model of a second type of UE, the first type of UE having reduced capabilities compared to the second type of UE.

20. The method of claim 19, wherein the second type of UE comprises one or more AI / ML models supporting the first feature group and one or more AI / ML models supporting the second feature group.

21. The method of any of claims 15-20, wherein the indication of the one or more UE capabilities further comprises at least one of a pairing identification (PID) related to compatibility of AI / ML models of the UE and AI / ML models of the network node, a type of the UE, a vendor ID of the UE, or a chipset ID of the UE.

22. The method of any of claims 15-21, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported fixed and pre-determined payload sizes of the UE in bits; or information for identifying one or more supported pre-determined payload size ranges of the UE in bits.

23. The method of any of claims 15-22, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported numbers of nodes in an output layer ofat least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in the output layer of the at least one AI / ML model of the UE.

24. The method of any of claims 15-23, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying a codebook related to a vector quantization of at least one AI / ML model of the UE; or information for identifying one or more supported numbers of quantization bits per node in an output layer of at least one AI / ML model of the UE.

25. The method of any of claims 15-24, wherein the information for identifying the one or more maximum payload sizes, or the one or more payload size ranges, of the compressed CSI report comprises at least one of: information for identifying one or more supported methods for quantizing an output of at least one AI / ML model of the UE; or one or more supported parameter combinations.

26. The method of claim 25, wherein the one or more supported methods for quantizing the output of the at least one of AI / ML model of the UE comprises: scalar quantization (SQ), vector quantization (VQ), or supported codebook(s) for the VQ.

27. The method of any of claims 15-26, wherein the one or more UE capabilities of performing AI / ML-based CSI report compression further comprise one or more parameters including: one or more CSI feedback parameters; a CSI report framework; one or more supported ranks; restrictions on channel measurement resource (CMR) and interference measurement resource (IMR); and a new feature group that defines one or more features of an AI / ML framework.

28. A method performed by a user equipment (UE), the method comprising: receiving (1310) an artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report configuration, wherein the AI / ML-based CSI report configuration comprises information for identifying one or more AI / ML models of the UE, wherein the one or more AI / ML models of the UE are configured to generate an AI / ML-based CSI report based on the AI / ML-based CSI report configuration; and sending (1320) the AI / ML-based CSI report to a network node.

29. The method of claim 28, wherein the information for identifying the one or more AI / ML models of the UE comprises at least one pairing identification (PID).

30. The method of claim 29, wherein the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

31. The method of claim 30, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; or an identifier used to determine the maximum payload size or the payload size range of the AI / ML-based CSI report.

32. The method of any of claims 30 or 31, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a number of nodes in an output layer of at least one of the one or more AI / ML models of the UE; one or more numbers of quantization bits per node in the output layer of at least one ofthe one or more AI / ML models of the UE; a codebook for vector quantization (VQ); or a codebook size for the VQ.

33. The method of any of claims 30-32, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-based CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

34. The method of any of claims 30-33, wherein identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

35. The method of any of claims 30-34, wherein the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

36. The method of any of claims 28-35, wherein the AI / ML-based CSI report comprises at least one of: a selected paring identification (PID); one or more selected feature groups; one or more selected configuration parameters; oran identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

37. A method performed by a network node, the method comprising: sending (1410) an artificial intelligence / machine learning (AIZML)-based channel state information (CSI) report configuration to a user equipment (UE), wherein the AI / ML based CSI report configuration comprises information for identifying one or more AI / ML models of the UE, wherein the one or more AEML models of the UE are configured to generate an AI / ML- based CSI report based on the AI / ML-based CSI report configuration; and receiving (1420) the AI / ML-based CSI report from the UE.

38. The method of claim 37, wherein the information for identifying the one or more AI / ML models of the UE comprises at least one pairing identification (PID).

39. The method of claim 38, wherein the AI / ML-based CSI report configuration further comprises at least one of: one or more configuration parameters associated with one or more supported feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report; or one or more configuration parameters associated with one or more pre-requisite feature groups and / or one or more UE capability parameters related to the AI / ML-based CSI report.

40. The method of claim 39, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: an actual payload size or a payload size range for the AI / ML-based CSI report; a maximum payload size for the AI / ML-based CSI report; or an identifier used to determine the maximum payload size or the payload size range of the AI / ML-based CSI report.

41. The method of any of claims 39 or 40, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a number of nodes in an output layer of at least one of the one or more AI / ML models ofthe UE; one or more numbers of quantization bits per node in the output layer of at least one of the one or more AI / ML models of the UE; a codebook for vector quantization (VQ); or a codebook size for the VQ.

42. The method of any of claims 39-41, wherein the one or more configuration parameters associated with the one or more supported feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a parameter combination associated with determining a maximum payload size or a payload size range of the AI / ML-based CSI report; an identifier associated with the parameter combination; or information associated with determining an AI / ML-based CSI reporting format and the maximum payload size of the AI / ML-based CSI report.

43. The method of any of claims 39-42, wherein identifying the one or more AI / ML models of the UE configured to generate the AI / ML-based CSI report comprises: identifying at least one of the one or more AI / ML models of the UE according to the at least one PID, one or more supported feature groups, the one or more configuration parameters associated with the one or more UE capability parameters related to the AI / ML-based CSI report, or a combination thereof.

44. The method of any of claims 39-43, wherein the one or more configuration parameters associated with the one or more pre-requisite feature groups and / or the one or more UE capability parameters related to the AI / ML-based CSI report comprise at least one of: a sub-band size; a rank restriction; or information associated with determining an AI / ML-based CSI reporting format and a maximum payload size of the AI / ML-based CSI report.

45. The method of any of claims 37-44, wherein the AI / ML-based CSI report comprises at least one of: a selected paring identification (PID);one or more selected feature groups; a selected parameter configuration; or an identifier associated with determining an actual AI / ML-based CSI report payload, or a segment thereof.

46. A user equipment for providing an artificial intelligence / machine learning (AI / ML)- based channel state information (CSI) report, comprising: processing circuitry configured to perform any of the steps of any of the claims 1-14 or28-36; and power supply circuitry configured to supply power to the processing circuitry.

47. A network node for configuring an artificial intelligence / machine learning (AI / ML)- based channel state information (CSI) report configuration, the network node comprising: processing circuitry configured to perform any of the steps of any of the claims 15-27 or 37-45; and power supply circuitry configured to supply power to the processing circuitry.

Citation Information

Patent Citations

  • Method and apparatus for support of machine learning or artificial intelligence techniques for CSI feedback in FDD MIMO systems

    US20220338189A1