Adapting artificial intelligence / machine learning model based on site-specific data

Abstract

Systems and techniques for wireless communication are described herein. For example, a process for wireless communication at a first network entity includes obtaining site-specific data associated with a geographic location, and adapting, at the first network entity, a machine learning model based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the first network entity and one or more network entities. The first network entity may experience a trigger event that causes the first network entity to send a request for the site-specific data. The trigger event may be based on at least one of a location of the first network entity in the geographic location or a movement of the first network entity to the geographic location, or based on other factors such as a change in a physical characteristic of the location.

Description

Technical Field

[0001] The present disclosure generally relates to machine learning (ML) systems for wireless communications. For example, aspects of the present disclosure relate to systems and techniques for adapting artificial intelligence / machine learning models implemented by user equipment (UE) based on site-specific data. Background Art

[0002] Wireless communication systems are deployed to provide a variety of telecommunication and data services including telephone, video, data, messaging, and broadcasting. Broadband wireless communication systems have evolved over several generations, including first generation analog wireless telephone service (1G), second generation (2G) digital wireless telephone service (including transitional 2.5G networks), third generation (3G) high-speed data wireless services with Internet capabilities, and fourth generation (4G) services (e.g., Long Term Evolution (LTE), WiMax). Examples of wireless communication systems include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, global system for mobile communications (GSM) systems, and the like. Other wireless communication technologies include 802.11 Wi-Fi, Bluetooth, and the like.

[0003] The fifth generation (5G) mobile standard calls for higher data speeds, a greater number of connections, and better coverage, among other improvements. According to the Next Generation Mobile Networks Alliance, the 5G standard (also known as "new radio" or "NR") is designed to provide tens of megabits per second of data rates to each of tens of thousands of users, and 1 gigabit per second of bandwidth to dozens of employees on an office floor. To support large sensor deployments, hundreds of thousands of simultaneous connections should be supported. Summary of the invention

[0004] The following presents a simplified summary of the invention related to one or more aspects disclosed herein. Thus, the following summary of the invention should neither be considered as an exhaustive overview related to all conceived aspects, nor should it be considered to identify key or decisive elements related to all conceived aspects or to delineate the scope associated with any particular aspect. Accordingly, the following summary of the invention presents certain concepts related to one or more aspects of the mechanisms disclosed herein in a simplified form before the detailed description presented below.

[0005] Described herein are systems and techniques for adapting (e.g., via online adaptation or fine-tuning) an artificial intelligence / machine learning model implemented by a user equipment (UE) based on site-specific data (e.g., data corresponding to a geographic location at which the UE is located). In some cases, the UE may receive or download the site-specific data based on a trigger condition. Once the site-specific data is obtained, the UE may use the site-specific data to fine-tune the artificial intelligence / machine learning model on the UE. The apparatus, methods, and other aspects described herein may be described from the perspective of a base station (or a portion thereof, such as a central unit (CU), a distributed unit (DU), a radio unit (RU), or other portion of a base station having a decomposed architecture), a UE, other network entities or devices, or a combination of devices.

[0006] In one illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: at least one memory; and at least one processor (e.g., implemented in circuitry) coupled to the at least one memory and configured to: obtain site-specific data associated with a geographic location; adapt a machine learning model based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communication between the apparatus and one or more network entities, and send an indication associated with adapting the machine learning model based on the site-specific data. In one example, the apparatus is a first network entity, such as a user equipment.

[0007] In another example, a method for wireless communication at a first network entity is provided. The method includes: obtaining site-specific data associated with a geographic location; adapting a machine learning model based on the site-specific data at the first network entity to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communication between the first network entity and one or more network entities, and sending an indication associated with adapting the machine learning model based on the site-specific data. In one example, the method can be performed by a user equipment.

[0008] The first network entity may be located in the geographic location. The method may include determining, at the first network entity, one or more estimates or predictions of at least one characteristic associated with wireless communications between the first network entity and one or more network entities using an updated machine learning model based on data received by the first network entity at the geographic location.

[0009] The method may further include sending a request for site-specific data from the first network entity to the second network entity.Sending the request for site-specific data may be triggered based on at least one of a location of the first network entity in the geographic location or movement of the first network entity to the geographic location.

[0010] The apparatus and method may also be described from the perspective of an apparatus such as a base station (e.g., gNB, which stands for next generation node B. A gNB is a 3GPP 5G next generation base station that supports 5G new radio). An apparatus for wireless communication may include at least one memory and at least one processor, the at least one processor being coupled to the memory and configured to: obtain site-specific data associated with a geographic location; and send the site-specific data to a network entity such as a UE or a mobile device.

[0011] A method may include obtaining, at a first network entity, site-specific data associated with a geographic location; and sending the site-specific data from the first network entity to a second network entity, wherein a machine learning model is adapted based on the site-specific data for estimating or predicting at least one characteristic associated with wireless communications between the first network entity and one or more network entities.

[0012] A wireless communication method may include one or more of the following: indicating, by a user equipment, to a network entity an ability to update a trained artificial intelligence / machine learning (AI / ML) model, sending, in response to the indication, site-specific data associated with the trained AI / ML model, and sending, from the user equipment to the network entity, an indication associated with adapting the AI / ML model based on the site-specific data.

[0013] An apparatus for wireless communication may include: at least one memory; and at least one processor, the at least one processor coupled to the memory and configured to: indicate to a network entity an ability to update a trained AI / ML model, in response to the indication, send site-specific data associated with the trained AI / ML model, and send to the network entity an indication associated with adapting the AI / ML model based on the site-specific data.

[0014] A non-transitory computer-readable storage medium includes instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to any of the methods, operations, or processes disclosed herein. An apparatus for wireless communication may include one or more components for performing operations according to any of the methods, operations, or processes disclosed herein.

[0015] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer readable media, user equipment, base stations, wireless communication devices and / or processing systems as fully described herein with reference to and as illustrated by the accompanying drawings and description.

[0016] The features and technical advantages of examples according to the present disclosure have been outlined quite broadly above so that the following specific embodiments may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. When considered in conjunction with the accompanying drawings, the characteristics of the concepts disclosed herein, both in terms of their organization and method of operation, and the associated advantages will be better understood from the following description. Each of the figures in the accompanying drawings is provided for the purpose of illustration and description, and not as a definition of limitations of the claims.

[0017] Although various aspects are described in the present disclosure by illustrating some examples, it will be understood by those skilled in the art that such aspects can be implemented in many different arrangements and scenarios. The technology described herein can be implemented using different platform types, devices, systems, shapes, sizes and / or packaging arrangements. For example, some aspects can be implemented via integrated chip implementations or other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / shopping equipment, medical equipment and / or artificial intelligence devices). Various aspects can be implemented in chip-level components, modular components, non-modular components, non-chip-level components, device-level components and / or system-level components. The equipment incorporating the various aspects and features described may include additional components and features for implementing and practicing the various aspects claimed and described. For example, the transmission and reception of wireless signals may include one or more components for analog and digital purposes (e.g., hardware components, including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders and / or summers). The various aspects described herein are intended to be practiced in various devices, components, systems, distributed arrangements and / or end-user devices of various sizes, shapes and configurations.

[0018] Other objects and advantages associated with the various aspects disclosed herein will be apparent to those skilled in the art based on the drawings and detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Examples of various specific implementations are described in detail below with reference to the following drawings:

[0020] Figure 1 is a block diagram illustrating an example of a wireless communication network according to some examples;

[0021] Figure 2 is a diagram illustrating a design of a base station and a user equipment (UE) device according to some examples, which enables sending and processing of signals exchanged between the UE and the base station;

[0022] Figure 3 is a diagram illustrating an example of a decomposed base station according to some examples;

[0023] Figure 4 is a block diagram illustrating components of user equipment according to some examples;

[0024] Figure 5 illustrates an example architecture of a neural network that may be used in accordance with some aspects of the present disclosure;

[0025] Figure 6 is a block diagram illustrating a machine learning engine according to aspects of the present disclosure;

[0026] Fig. 7A is a flow chart illustrating a process of sending site-specific data to a user equipment for use by the user equipment to fine-tune an artificial intelligence / machine learning (AI / ML) model according to some examples;

[0027] Figure 7B is a flow chart illustrating a process of sending site-specific data to fine-tune an AI / ML model according to some examples;

[0028] Fig. 8A is a flow chart illustrating a process of sending site-specific data to a user equipment for fine-tuning an AI / ML model according to some examples;

[0029] Figure 8B is a flow chart illustrating a process of receiving site-specific data at a user equipment for adapting an AI / ML model according to some examples;

[0030] Figure 8C illustrates a communication flow between a UE and a gNB regarding requesting and receiving site-specific data for fine-tuning an AI / ML model on the UE; and

[0031] Fig. 9 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. DETAILED DESCRIPTION

[0032] Some aspects and embodiments of the present disclosure are provided below. Some aspects and embodiments of these aspects and embodiments can be applied independently, and some of them can be applied in combination, which is obvious to those skilled in the art. In the following description, specific details are set forth for explanation purposes in order to provide a thorough understanding of each embodiment of the application. However, it will be apparent that each embodiment can be put into practice without these specific details. Each drawing and description are not intended to be restrictive.

[0033] The following description only provides example embodiments and is not intended to limit the scope, applicability or configuration of the present disclosure. On the contrary, the following description of the exemplary embodiments will provide an enabling description for implementing the exemplary embodiments to those skilled in the art. It should be understood that various changes may be made to the function and arrangement of elements without departing from the essence and scope of the present application as set forth in the appended claims.

[0034] Various aspects are provided herein with reference to wireless technologies (e.g., third generation partnership project (3GPP) 5G / new radio (NR) standards) to improve wireless communications. As described above, systems and techniques are described herein for adapting (e.g., via online adaptation or fine-tuning) an artificial intelligence / machine learning (ML) model implemented by a user equipment (UE) based on site-specific data (e.g., data corresponding to a geographic location at which the UE is located). In some cases, the UE may receive, download, or collect the site-specific data (e.g., locally at the geographic location) based on a triggering condition. The triggering condition may be, for example, the UE moving into a new geographic region, where data associated with the geographic region will help adapt or fine-tune the ML model implemented on the UE, the ML model being configured to (e.g., trained using supervised learning, unsupervised learning, semi-supervised learning, or other learning / training) estimate or predict at least one characteristic associated with wireless communications between the UE and one or more network entities (e.g., a base station or a portion thereof, such as a CU, DU, etc.). Once the site-specific data is obtained, the UE may use the site-specific data to fine-tune the ML model on the UE. At least one characteristic that the ML model is trained to estimate or predict may include temporal beam prediction, spatial beam prediction, positioning aided beam prediction, channel state prediction (e.g., for channel state information (CSI) or channel state feedback (CSF)), any combination thereof, and / or other predictions.

[0035] Additional aspects of the disclosure are described in more detail below with reference to the accompanying drawings.

[0036] Wireless networks are deployed to provide various communication services, such as voice, video, packet data, messaging, broadcast, etc. A wireless network may support two access links for communication between wireless devices. An access link may refer to any communication link between a client device (e.g., a user equipment (UE), a station (STA), or other client device) and a base station (e.g., a 3GPP gNodeB (gNB) for 5G / NR, a 3GPP eNodeB (eNB) for LTE, a Wi-Fi access point (AP), or other base station) or a component of a decomposed base station (e.g., a central unit, a distributed unit, and / or a radio unit). In one example, the access link between the UE and the 3GPP gNB may be on the "Uu interface," which is also referred to as the Universal Mobile Telecommunications System (UMTS) air interface. In some cases, the access link may support uplink signaling, downlink signaling, connection procedures, etc.

[0037] In some aspects, the wireless communication network may be implemented using one or more modulation schemes. For example, the wireless communication network may be implemented using a quadrature amplitude modulation (QAM) scheme such as 16QAM, 32QAM, 64QAM, etc.

[0038] As used herein, the terms "user equipment" (UE) and "network entity" are not intended to be dedicated to or otherwise limited to any particular radio access technology (RAT), unless otherwise specified. In general, a UE can be any wireless communication device (e.g., a mobile phone, a router, a tablet computer, a laptop computer, and / or a tracking device, etc.), a wearable device (e.g., a smart watch, smart glasses, a wearable ring, and / or an extended reality (XR) device (such as a virtual reality (VR) headset, an augmented reality (AR) headset or glasses, or a mixed reality (MR) headset)), a vehicle (e.g., a car, a motorcycle, a bicycle, etc.), and / or an Internet of Things (IoT) device, etc., for a user to communicate on a wireless communication network. A UE can be mobile or can be stationary (e.g., at certain times) and can communicate with a radio access network (RAN). As used herein, the term "UE" may be interchangeably referred to as an "access terminal" or "AT," "client device," "wireless device," "subscriber equipment," "subscriber terminal," "subscriber station," "user terminal" or "UT," "mobile device," "mobile terminal," "mobile station," or variations thereof. Generally speaking, a UE may communicate with a core network via a RAN, and through the core network, the UE may connect to external networks such as the Internet and to other UEs. Of course, other mechanisms for connecting to the core network and / or the Internet are also possible for the UE, such as through a wired access network, a wireless local area network (WLAN) network (e.g., based on IEEE 802.11 communication standards, etc.), and the like.

[0039] The network entity may be implemented in a converged or monolithic base station architecture, or alternatively, in a disaggregated base station architecture, and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near-RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. A base station (e.g., having a converged / monolithic base station architecture or a disaggregated base station architecture) may operate in communication with a UE according to one of several RATs depending on the network in which the base station is deployed, and may alternatively be referred to as an access point (AP), a network node, a node B (NB), an evolved node B (eNB), a next generation eNB (ng-eNB), a new radio (NR) node B (also referred to as a gNB or gNodeB), etc. A base station may be primarily used to support wireless access for UEs, including supporting data, voice, and / or signaling connections for supported UEs. In some systems, a base station may provide edge node signaling functionality, while in other systems, a base station may provide additional control and / or network management functionality. The communication link that a UE can use to transmit signals to a base station can be referred to as an uplink (UL) channel (e.g., a reverse traffic channel, a reverse control channel, an access channel, etc.). The communication link that a base station can use to transmit signals to a UE can be referred to as a downlink (DL) or forward link channel (e.g., a paging channel, a control channel, a broadcast channel, or a forward traffic channel, etc.). As used herein, the term traffic channel (TCH) can refer to an uplink, a reverse or downlink, and / or a forward traffic channel.

[0040] The term "network entity" or "base station" (e.g., having an aggregated / monolithic base station architecture or a decomposed base station architecture) may refer to a single physical transmit receive point (TRP) or multiple physical TRPs that may or may not be co-located. For example, where the term "network entity" or "base station" refers to a single physical TRP, the physical TRP may be a base station antenna corresponding to a cell (or several cell sectors) of the base station. Where the term "network entity" or "base station" refers to multiple co-located physical TRPs, these physical TRPs may be antenna arrays of the base station (e.g., as in a multiple-input multiple-output (MIMO) system or where the base station employs beamforming). Where the term "base station" refers to multiple non-co-located physical TRPs, the physical TRP may be a distributed antenna system (DAS) (a network of spatially separated antennas connected to a common source via a transmission medium) or a remote radio head (RRH) (a remote base station connected to a serving base station). Alternatively, the non-co-located physical TRPs may be a serving base station that receives measurement reports from a UE and a neighbor base station whose reference radio frequency (RF) signal (or "reference signal" for short) the UE is measuring. Because as used herein, a TRP is the point through which a base station transmits and receives wireless signals, references to transmitting from or receiving at a base station should be understood to refer to the specific TRP of a base station.

[0041] In some specific implementations of supporting UE positioning, a network entity or base station may not support wireless access for the UE (e.g., may not support data, voice, and / or signaling connections for the UE), but may instead send a reference signal to the UE to be measured by the UE, and / or may receive and measure a signal sent by the UE. Such a base station may be referred to as a positioning beacon (e.g., in the case of sending a signal to the UE) and / or as a position measurement unit (e.g., in the case of receiving and measuring a signal from the UE).

[0042] RF signals include electromagnetic waves of a given frequency that transmit information through the space between a transmitter and a receiver. As used herein, a transmitter may send a single "RF signal" or multiple "RF signals" to a receiver. However, due to the propagation characteristics of RF signals through multipath channels, a receiver may receive multiple "RF signals" corresponding to each transmitted RF signal. The same transmitted RF signal on different paths between a transmitter and a receiver may be referred to as a "multipath" RF signal. As used herein, an RF signal may also be referred to as a "wireless signal" or simply a "signal" where it is clear from the context that the term "signal" refers to a wireless signal or an RF signal.

[0043] Various aspects of the systems and techniques described herein are discussed below with respect to the accompanying drawings. According to various aspects, Figure 1An example of a wireless communication system 100 is illustrated. The wireless communication system 100 (which may also be referred to as a wireless wide area network (WWAN)) may include one or more base stations 102 (reference numeral 102 may refer to a single base station or multiple base stations) and one or more UEs 104 (reference numeral 104 may refer to a single UE or multiple UEs). In some aspects, the base station 102 may also be referred to as a "network entity" or a "network node". One or more UEs 104 may also be referred to as a "network entity" or a "network node". One or more of the base stations 102 may be implemented in an aggregated or monolithic base station architecture. Additionally or alternatively, one or more of the base stations 102 may be implemented in a decomposed base station architecture and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near-RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. The base station 102 may include a macro cell base station (high power cellular base station) and / or a small cell base station (low power cellular base station). In one aspect, the macro cell base station may include an eNB (e.g., the eNB may be a base station connected to a network for wireless communication with a mobile handset in a 4G LTE network or a 5G non-standalone (NSA) mode) and / or an ng-eNB (e.g., the ng-eNB may be an enhanced version of a 4G eNodeB), where the wireless communication system 100 corresponds to a long term evolution (LTE) network, or a gNB (where the wireless communication system 100 corresponds to an NR network), or a combination of both, and the small cell base station may include a femto cell, a pico cell, a micro cell, etc.

[0044] The base stations 102 may collectively form a RAN and interface with a core network 170 (e.g., an evolved packet core (EPC) or a 5G core (5GC)) through a backhaul link 122, and interface to one or more location servers 172 (which may be part of the core network 170 or may be external to the core network 170) through the core network 170. Among other functions, the base stations 102 may perform functions related to one or more of the following: delivering user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, RAN sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (e.g., through the EPC or 5GC) through a backhaul link 134 (which may be wired and / or wireless).

[0045] Base station 102 may communicate wirelessly with UE 104. Each of base stations 102 may provide communication coverage for a corresponding geographic coverage area 110. In one aspect, one or more cells may be supported by a base station in base station 102 in each corresponding geographic coverage area 110. A "cell" is a logical communication entity for communicating with base station 102 (e.g., on a certain frequency resource, referred to as a carrier frequency, component carrier, carrier, frequency band, etc.), and may be associated with an identifier (e.g., a physical cell identifier (PCI), a virtual cell identifier (VCI), a cell global identifier (CGI)) to distinguish cells operating via the same or different carrier frequencies. In some cases, different cells may be configured according to different protocol types (e.g., machine type communication (MTC), narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB), or other protocol types) that may provide access to different types of UE 104. Because a cell is supported by a specific base station, the term "cell" may refer to either or both of the logical communication entity and the base station supporting it, depending on the context. In addition, since the TRP is generally the physical transmission point of the cell, the terms "cell" and "TRP" may be used interchangeably. In some cases, the term "cell" may also refer to a geographic coverage area (e.g., a sector) of a base station, as long as a carrier frequency can be detected within a portion of the corresponding geographic coverage area 110 and is used for communication within that portion.

[0046] Although the corresponding geographic coverage areas 110 of neighboring macrocell base stations of the base station 102 may partially overlap (e.g., in a handover area), a portion of the corresponding geographic coverage areas 110 may substantially overlap with the larger corresponding geographic coverage area 110. For example, a small cell (SC) base station 102' may have a coverage area 110' that substantially overlaps with the corresponding geographic coverage areas 110 of one or more macrocell base stations of the base station 102. A network that includes both small cell base stations and macrocell base stations may be referred to as a heterogeneous network. A heterogeneous network may also include a home eNB (HeNB) that may provide services to a restricted group referred to as a closed subscriber group (CSG).

[0047] The communication link 120 between the base station 102 and the UE 104 may include uplink (also referred to as reverse link) transmissions from a UE in the UE 104 to a base station in the base station 102 and / or downlink (also referred to as forward link) transmissions from a base station in the base station 102 to a UE in the UE 104. The communication link 120 may use MIMO antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link 120 may be over one or more carrier frequencies. The allocation of carriers may be asymmetric for the downlink and uplink (e.g., more or fewer carriers may be allocated to the downlink than to the uplink).

[0048] The wireless communication system 100 may further include a WLAN access point (AP) 150 that communicates with a WLAN station (STA) 152 via a communication link 154 in an unlicensed spectrum (e.g., 5 gigahertz (GHz)). When communicating in the unlicensed spectrum, the WLAN STA 152 and / or the WLAN AP 150 may perform a clear channel assessment (CCA) or a listen-before-talk (LBT) process before communicating to determine whether a channel is available. In some examples, the wireless communication system 100 may include a device (e.g., UE, etc.) that communicates with one or more of the UEs 104, the base station 102, the WLAN AP 150, etc. using an ultra-wideband (UWB) spectrum. The UWB spectrum may range from 3.1 GHz to 10.5 GHz, or may include spectrum outside of these ranges.

[0049] The SC base station 102' can operate in licensed and / or unlicensed spectrum. When operating in the unlicensed spectrum, the SC base station 102' can adopt LTE or NR technology and use the same 5GHz unlicensed spectrum used by the WLAN AP 150. The SC base station 102' adopting LTE and / or 5G in the unlicensed spectrum can improve the coverage of the access network and / or increase the capacity of the access network. NR in the unlicensed spectrum can be referred to as NR-U. LTE in the unlicensed spectrum can be referred to as LTE-U, License Assisted Access (LAA) or MulteFire.

[0050] The wireless communication system 100 may also include a millimeter wave (mmW) base station 180, which may operate at mmW frequencies and / or near mmW frequencies to communicate with UE 182 via mmW communication links 184. The mmW base station 180 may be implemented in an aggregated or monolithic base station architecture, or alternatively, in a decomposed base station architecture (e.g., including one or more of CU, DU, RU, near RT RIC, or non-RT RIC). Extremely high frequency (EHF) is a portion of RF in the electromagnetic spectrum. EHF has a range of 30 GHz to 300 GHz and a wavelength between 1 mm and 10 mm. Radio waves in the 30 GHz to 300 GHz band may be referred to as millimeter waves. Near mmW may extend downward to a frequency of 3 GHz, and a wavelength of 100 mm. Super high frequency (SHF) bands extend between 3 GHz and 30 GHz, and are also referred to as centimeter waves. Communications using mmW and / or near mmW radio frequency bands have high path loss and relatively short distances. The mmW base station 180 and the UE 182 may utilize beamforming (transmit and / or receive) on the mmW communication link 184 to compensate for the extremely high path loss and short distance. In addition, it should be understood that in alternative configurations, one or more of the base stations 102 may also transmit using mmW or near-mmW and beamforming. Therefore, it should be understood that the foregoing illustrations are merely examples and should not be construed as limiting the various aspects disclosed herein.

[0051] In some aspects related to 5G, the spectrum in which a wireless network node or entity (e.g., base station 102 / 180, UE 104 / 182) operates is divided into multiple frequency ranges: FR1 (from 450 megahertz (MHz) to 6000 MHz), FR2 (from 24250 MHz to 52600 MHz), FR3 (above 52600 MHz), and FR4 (between FR1 and FR2). In a multi-carrier system such as 5G, one of the carrier frequencies is referred to as a "primary carrier" or "anchor carrier" or "primary serving cell" or "PCell", and the remaining carrier frequencies are referred to as "secondary carriers" or "secondary serving cells" or "SCells". In carrier aggregation, the anchor carrier is a carrier operating on a primary frequency (e.g., FR1) used by a UE in UE104 / 182 and a cell in which a UE in UE104 / 182 performs an initial radio resource control (RRC) connection establishment procedure or initiates an RRC connection reestablishment procedure. The primary carrier carries all common and UE-specific control channels and may be a licensed carrier in some cases. A secondary carrier is a carrier operating on a second frequency (e.g., FR2), which may be configured and used to provide additional radio resources once an RRC connection is established between a UE in UE 104 and an anchor carrier. In some cases, a secondary carrier may be a carrier in an unlicensed frequency. The secondary carrier may contain only necessary signaling information and signals, for example, since the primary uplink carrier and the primary downlink carrier are typically UE-specific, those signaling information and signals specific to the UE may not be present in the secondary carrier. Different UEs 104 / 182 in a cell may have different downlink primary carriers. The same is true for the uplink primary carrier. The network is able to change the primary carrier of any UE in UE 104 / 182 at any time. Changing the primary carrier is performed, for example, to balance the load on different carriers. Because a "serving cell" (whether PCell or SCell) corresponds to a carrier frequency and / or component carrier that some base stations are using to communicate, the terms "cell", "serving cell", "component carrier", "carrier frequency", etc. may be used interchangeably.

[0052] For example, still refer to Figure 1, one of the frequencies used by the macrocell base station of base station 102 may be an anchor carrier (or "PCell"), and the other frequencies used by the macrocell base station of base station 102 and / or the mmW base station 180 may be secondary carriers ("SCells"). In carrier aggregation, base station 102 and / or UE 104 may use spectrum of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz) bandwidth per carrier, with up to a total of Yx MHz (x component carriers) in each direction for transmission. Component carriers may be adjacent to each other or may not be adjacent to each other in the spectrum. The allocation of carriers may be asymmetric with respect to the downlink and uplink (e.g., more or fewer carriers may be allocated to the downlink compared to the uplink). Simultaneous transmission and / or reception of multiple carriers enables UEs in UE 104 / 182 to significantly increase their data transmission and / or reception rates. For example, two 20 MHz aggregated carriers in a multi-carrier system would theoretically result in a doubled data rate (ie, 40 MHz) compared to the data rate achieved by a single 20 MHz carrier.

[0053] To operate on multiple carrier frequencies, a base station in base station 102 and / or a UE in UE 104 may be equipped with multiple receivers and / or transmitters. For example, a UE in UE 104 may have two receivers, namely, "receiver 1" and "receiver 2", where "receiver 1" is a multi-band receiver that can be tuned to band (i.e., carrier frequency) 'X' or band 'Y', and "receiver 2" is a single-band receiver that can be tuned to only band 'Z'. In one example, if UE 104 is being served in band 'X', band 'X' will be referred to as the PCell or active carrier frequency, and "receiver 1" will need to tune from band 'X' to band 'Y' (SCell) to measure band 'Y' (and vice versa). In contrast, regardless of whether the UEs in UE 104 are being served in band 'X' or band 'Y', due to separate "receiver 2", the UEs in UE 104 can measure band 'Z' without interrupting service on band 'X' or band 'Y'.

[0054] The wireless communication system 100 may further include a UE 164 that may communicate with a macrocell base station of the base station 102 over the communication link 120 and / or communicate with an mmW base station 180 over the mmW communication link 184. For example, the macrocell base station of the base station 102 may support a PCell and one or more SCells for the UE 164, and the mmW base station 180 may support one or more SCells for the UE 164.

[0055] The wireless communication system 100 may also include one or more UEs, such as UE 190, which are indirectly connected to one or more communication networks via one or more device-to-device (D2D) peer-to-peer (P2P) links (referred to as “side links”). Figure 1 In the example of FIG. 1 , UE 190 has a D2D P2P link 192 with one of UEs 104 connected to one of base stations 102 (e.g., UE 190 can indirectly obtain cellular connectivity through the D2D P2P link), and has a D2D P2P link 194 with a WLAN STA 152 connected to WLAN AP 150 (UE 190 can indirectly obtain WLAN-based Internet connectivity through the D2D P2P link). In an example, D2D P2P links 192 and 194 can use any well-known D2DRAT (such as LTE Direct (LTE-D), WiFi Direct (Wi-Fi-D), etc.) to support.

[0056] Figure 2 A block diagram of a system 200 for a base station in base station 102 and a UE in UE 104 is shown, which enables sending and processing of signals exchanged between UE 104 and base station 102 according to some aspects of the present disclosure. System 200 includes components of a base station in base station 102 and a UE in UE 104, which may be Figure 1 One of base stations 102 and one of UE 104. A base station in base stations 102 may be equipped with T antennas 234a through 234t, and a UE in UE 104 may be equipped with R antennas 252a through 252r, where in general T≥1 and R≥1.

[0057] At a base station in base station 102, a transmit processor 220 may receive data for one or more UEs from a data source 212, select one or more modulation and coding schemes (MCS) for each UE based at least in part on a channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) data for each UE based at least in part on the MCS selected for the UE, and provide data symbols for all UEs. The transmit processor 220 may also process system information (e.g., for semi-static resource partitioning information (SRPI), etc.) and control information (e.g., CQI requests, grants, upper layer signaling, etc.), and provide overhead symbols and control symbols. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS)) and synchronization signals (e.g., primary synchronization signals (PSS) and secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols where applicable, and may provide T output symbol streams to T modulators 232a to 232t. The modulators 232a to 232t are shown as combined modulator-demodulators (MOD-DEMOD). In some cases, the modulator and demodulator may be separate components. Each modulator in the modulators 232a to 232t may process a corresponding output symbol stream (e.g., for an orthogonal frequency division multiplexing (OFDM) scheme, etc.) to obtain an output sample stream. Each modulator in the modulators 232a to 232t may further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The T downlink signals may be sent from the modulators 232a to 232t via T antennas 234a to 234t, respectively. According to certain aspects described in greater detail below, position encoding may be utilized to generate a synchronization signal to convey additional information.

[0058] At the UE in UE 104, R antennas 252a to 252r can receive downlink signals from the base station in base station 102 and / or other base stations, and can provide the received signals to demodulators 254a to 254r respectively. There can be R demodulators 254a to 254r. Demodulators 254a to 254r are shown as combined modulator-demodulators (MOD-DEMOD). In some cases, the modulator and demodulator can be separate components. Each demodulator in demodulators 254a to 254r can condition (e.g., filter, amplify, down-convert, and digitize) the received signal to obtain input samples. Each demodulator in demodulators 254a to 254r can further process the input samples (e.g., for OFDM, etc.) to obtain received symbols. A MIMO detector 256 may obtain received symbols from all demodulators 254a through 254r, perform MIMO detection on the received symbols if applicable, and provide detected symbols. A receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide decoded data for UEs in UE 104 to a data sink 260, and provide decoded control information and system information to a controller / processor 280. A channel processor may determine a reference signal received power (RSRP), a received signal strength indicator (RSSI), a reference signal received quality (RSRQ), a channel quality indicator (CQI), etc.

[0059] On the uplink, at a UE in UE 104, a transmit processor 264 may receive and process data from a data source 262 and control information (e.g., for reports including RSRP, RSSI, RSRQ, CQI, etc.) from a controller / processor 280. The transmit processor 264 may also generate reference symbols for one or more reference signals (e.g., based at least in part on a beta value or set of beta values ​​associated with the one or more reference signals). The symbols from the transmit processor 264 may be pre-decoded by the TX MIMO processor 266 where applicable, further processed by the modulators 254a through 254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to a base station in base station 102. At the base station in base station 102, uplink signals from UEs in UE 104 and other UEs may be received by T antennas 234a to 234t, processed by modulators 232a to 232t (which may act as demodulators), detected by MIMO detector 236 where applicable, and further processed by receive processor 238 to obtain decoded data and control information transmitted by UEs in UE 104. Receive processor 238 may provide decoded data to data sink 239 and decoded control information to controller 240 (which may be referred to as a processor). The base station in base station 102 may include a communication unit 244 and communicate with network controller 231 via communication unit 244. Network controller 231 may include communication unit 294, controller / processor 290, and memory 292.

[0060] In some aspects, one or more components of the UE in UE 104 may be included in a housing. The controller 240 of the base station in base station 102, the controller / processor 280 of the UE in UE 104, and / or Figure 2 Any other component of may perform one or more techniques associated with implicit UCI β value determination for NR.

[0061] Memories 242 and 282 may store data and program codes for a base station in base station 102 and a UE in UE 104, respectively. A scheduler 246 may schedule UEs for data transmission on the downlink, uplink, and / or sidelink.

[0062] In some aspects, the deployment of a communication system such as a 5G New Radio (NR) system can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element, or a network equipment (such as a base station (BS), or one or more units (or one or more components) that perform base station functionality can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP), or a cell, etc.) can be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0063] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0064] Base station type operations or network designs may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configurations such as those initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0065] Figure 3A diagram illustrating an example decomposed base station 300 architecture is shown. The decomposed base station 300 architecture may include one or more central units (CUs) 310 that may communicate directly with a core network 320 via a backhaul link, or indirectly with the core network 320 through one or more decomposed base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) or a near-RT RIC 325 via an E2 link, or a non-real-time (non-RT) RIC 315 associated with a service management and orchestration (SMO) framework 305, or both. The one or more CUs 310 may communicate with one or more distributed units (DUs) 330 via respective midhaul links, such as an F1 interface. The one or more DUs 330 may communicate with one or more radio units (RUs) 340 via respective fronthaul links. The one or more RUs 340 may communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE in the UE 104 may be served simultaneously by multiple RUs in the one or more RUs 340.

[0066] Each of these units (e.g., one or more CUs 310, one or more DUs 330, one or more RUs 340), as well as the near-RT RIC 325, the non-RT RIC 315, and the SMO framework 305, may include one or more interfaces, or may be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface that is configured to receive a signal or send a signal to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) that is configured to receive a signal or send a signal to one or more of the other units via a wireless transmission medium, or both.

[0067] In some aspects, one or more CUs 310 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by one or more CUs 310. One or more CUs 310 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, one or more CUs 310 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface such as an E1 interface. As needed, one or more CUs 310 may be implemented to communicate with one or more DUs 330 for network control and signaling.

[0068] One or more DUs 330 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 340. In some aspects, one or more DUs 330 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation, and demodulation, etc.) at least in part according to a functional split such as defined by the Third Generation Partnership Project (3GPP). In some aspects, one or more DUs 330 may further host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by one or more DUs 330 or with control functions hosted by one or more CUs 310.

[0069] The lower layer functionality may be implemented by one or more RUs 340. In some deployments, a RU in one or more RUs 340 controlled by one or more DUs 330 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on functional splitting (such as lower layer functional splitting). In such an architecture, one or more RUs 340 may be implemented to handle over-the-air (OTA) communications with one or more UEs in UE 104. In some implementations, real-time and non-real-time aspects of control and user plane communications with one or more RUs 340 may be controlled by corresponding one or more DUs 330. In some scenarios, the configuration may enable one or more DUs 330 and one or more CUs 310 to be implemented in a cloud-based RAN architecture such as a vRAN architecture.

[0070] The SMO framework 305 may be configured to support RAN deployment and configuration of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 305 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 305 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 390) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, one or more CUs 310, one or more DUs 330, one or more RUs 340, and near-RT RICs 325. In some specific implementations, the SMO framework 305 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 311) via the O1 interface. Additionally, in some specific implementations, the SMO framework 305 may communicate directly with one or more RUs 340 via the O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305 .

[0071] The non-RT RIC 315 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 325. The non-RT RIC 315 may be coupled to or communicate with the near-RT RIC 325 (such as via an A1 interface). The near-RT RIC 325 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 310, one or more DUs 330, or both, and the O-eNB with the near-RT RIC 325.

[0072] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 325, the non-RT RIC 315 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 325 and may be received from a non-network data source or from a network function at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or the near-RT RIC 325 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 305 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0073] Figure 4An example of a computing system 470 of a wireless device 407 is illustrated. The wireless device 407 may include a client device such as a UE (e.g., a UE in UE 104, a WLAN STA 152, a UE 190) or other types of devices that can be used by an end user (e.g., a station (STA) configured to communicate using a Wi-Fi interface). For example, the wireless device 407 may include a mobile phone, a router, a tablet computer, a laptop computer, a tracking device, a wearable device (e.g., a smart watch, glasses, an extended reality (XR) device (such as a virtual reality (VR), augmented reality (AR) or mixed reality (MR) device), etc.), an Internet of Things (IoT) device, an access point, and / or another device configured to communicate via a wireless communication network. The computing system 470 includes software and hardware components that can be electrically coupled or communicatively coupled via a bus 489 (or can communicate in other ways, as the case may be). For example, the computing system 470 includes one or more processors 484. One or more processors 484 may include one or more CPUs, ASICs, FPGAs, APs, GPUs, VPUs, NSPs, microcontrollers, dedicated hardware, any combination thereof, and / or other processing devices or systems. One or more processors 484 may use a bus 489 to communicate between cores and / or with one or more memory devices 486.

[0074] The computing system 470 may also include one or more memory devices 486, one or more digital signal processors (DSPs) 482, one or more subscriber identity modules (SIMs) 474, one or more modems 476, one or more wireless transceivers 478, one or more antennas 487, one or more input devices 472 (e.g., a camera, a mouse, a keyboard, a touch-sensitive screen, a touchpad, a keypad, a microphone, etc.), and one or more output devices 480 (e.g., a display, a speaker, a printer, etc.).

[0075] In some aspects, the computing system 470 may include one or more RF interfaces configured to send and / or receive radio frequency (RF) signals. In some examples, the RF interface may include components such as one or more modems 476, one or more wireless transceivers 478, and / or antennas 487. One or more wireless transceivers 478 may send and receive wireless signals (e.g., wireless signals 488) from one or more other devices via antennas 487, such as other wireless devices, network devices (e.g., base stations such as eNBs and / or gNBs, Wi-Fi access points (APs) such as routers, range extenders, etc.), cloud networks, etc. In some examples, the computing system 470 may include multiple antennas or antenna arrays that can facilitate simultaneous transmission and reception functionality. Antenna 487 may be an omnidirectional antenna so that radio frequency (RF) signals can be received from all directions and transmitted in all directions. Wireless signals 488 may be sent via a wireless network. The wireless network can be any wireless network, such as a cellular or telecommunication network (e.g., 3G, 4G, 5G, etc.), a wireless local area network (e.g., a WiFi network), a Bluetooth™ network, and / or other networks.

[0076] In some examples, wireless signals 488 may be transmitted directly to other wireless devices using sidelink communications (e.g., using a PC5 interface, using a DSRC interface, etc.). One or more wireless transceivers 478 may be configured to transmit RF signals via antenna 487 for performing sidelink communications according to one or more transmit power parameters that may be associated with one or more regulatory modes. One or more wireless transceivers 478 may also be configured to receive sidelink communication signals having different signal parameters from other wireless devices.

[0077] In some examples, one or more wireless transceivers 478 may include an RF front end that includes one or more components such as an amplifier, a mixer for down-converting a signal (also known as a signal multiplier), a frequency synthesizer (also known as an oscillator) that provides a signal to the mixer, a baseband filter, an analog-to-digital converter (ADC), one or more power amplifiers, and other components. The RF front end may generally handle the selection of wireless signals 488 and the conversion of the wireless signals to baseband frequencies or intermediate frequencies, and may convert the RF signals to the digital domain.

[0078] In some cases, computing system 470 may include a coding-decoding device (or CODEC) configured to encode and / or decode data transmitted and / or received using one or more wireless transceivers 478. In some cases, computing system 470 may include an encryption-decryption device or component configured to encrypt and / or decrypt data transmitted and / or received by one or more wireless transceivers 478 (e.g., according to the AES and / or DES standards).

[0079] One or more SIMs 474 may each securely store an International Mobile Subscriber Identity (IMSI) number and associated keys assigned to a user of the wireless device 407. The IMSI and keys may be used to identify and authenticate a subscriber when accessing a network provided by a network service provider or operator associated with one or more SIMs 474. One or more modems 476 may modulate one or more signals to encode information for transmission using one or more wireless transceivers 478. One or more modems 476 may also demodulate signals received by one or more wireless transceivers 478 in order to decode the transmitted information. In some examples, one or more modems 476 may include a Wi-Fi modem, a 4G (or LTE) modem, a 5G (or NR) modem, and / or other types of modems. One or more modems 476 and one or more wireless transceivers 478 may be used to communicate data of one or more SIMs 474.

[0080] The computing system 470 may also include (and / or be in communication with) one or more non-transitory machine-readable storage media or storage devices (e.g., one or more memory devices 486), which may include, but are not limited to, local and / or network accessible storage, disk drives, drive arrays, optical storage devices, solid-state storage devices such as RAM and / or ROM, which may be programmable, flash-updatable, etc. Such storage devices may be configured to implement any suitable data storage, including, but not limited to, various file systems, database structures, etc.

[0081] In various embodiments, the functionality may be stored as one or more computer program products (e.g., instructions or code) in one or more memory devices 486 and executed by one or more processors 484 and / or one or more DSPs 482. The computing system 470 may also include software elements (e.g., located within one or more memory devices 486) including, for example, an operating system, device drivers, executable libraries, and / or other code, such as one or more application programs, which may include computer programs that implement the functionality provided by various embodiments, and / or may be designed to implement methods and / or configure systems, as described herein.

[0082] Figure 5An example architecture of a neural network 500 that may be used according to some aspects of the present disclosure is illustrated. The example architecture of the neural network 500 may be defined by an example neural network description 502 in a neural controller 501. The neural network 500 is an example of a machine learning model that may be deployed and implemented at a base station, a central unit (CU) or one or more CUs 310, a distributed unit (DU) or one or more DUs 330, a radio unit (RU) or one or more RUs 340 in a base station 102, and / or a UE in a UE 104. The neural network 500 may be a feed-forward neural network or any other known or to be developed neural network or machine learning model.

[0083] Neural network description 502 may include a complete specification of neural network 500, including Figure 5 For example, neural network description 502 may include: a description or specification of the architecture of neural network 500 (e.g., layers, layer interconnections, number of nodes in each layer, etc.); input and output descriptions indicating how inputs and outputs are formed or processed; indications of activation functions in the neural network, operations or filters in the neural network, etc.; neural network parameters such as weights, biases, etc., etc.

[0084] Neural network 500 may reflect the neural architecture defined in neural network description 502. Neural network 500 may include any suitable neural or deep learning type of network. In some cases, neural network 500 may include a feedforward neural network. In other cases, neural network 500 may include a recursive neural network, which may have a loop that allows information to be carried across nodes when reading input. Neural network 500 may include any other suitable neural network or machine learning model. An example includes a convolutional neural network (CNN), which includes an input layer and an output layer, with multiple hidden layers between the input layer and the output layer. The hidden layers of the CNN include a series of hidden layers as described below, such as convolutional layers, nonlinear layers, pooling layers (for downsampling), and fully connected layers. In other examples, neural network 500 may represent any other neural network or deep learning network, such as an autoencoder, a deep belief network (DBN), a recursive neural network (RNN), etc.

[0085] exist Figure 5In a non-limiting example, the neural network 500 includes an input layer 503 that can receive one or more sets of input data. The input data can be any type of data (e.g., image data, video data, network parameter data, user data, etc.). The neural network 500 can include a hidden layer 504, which includes a first hidden layer 504A to a last hidden layer 504N. The hidden layer 504 can include n hidden layers, where n is an integer greater than or equal to 1. The n hidden layers can include as many layers as required for the desired processing results and / or rendering intent. In an illustrative example, any one of the hidden layers 504 can include data representing one or more of the data provided at the input layer 503. The neural network 500 also includes an output layer 506 that provides output resulting from the processing performed by the hidden layer 504. The output layer 506 can provide output data based on the input data.

[0086] exist Figure 5 In the example of , the neural network 500 is a multi-layer neural network of interconnected nodes. Each node can represent a piece of information. The information associated with these nodes is shared between different layers, and each layer retains the information when processing the information. Information can be exchanged between the nodes through node-to-node interconnections between the layers. The nodes of the input layer 503 can activate a group of nodes in the first hidden layer 504A. For example, as shown in the figure, each input node of the input layer 503 is connected to each node of the first hidden layer 504A. The nodes of the first hidden layer 504A can transform the information by applying an activation function to the information of each input node. Then, the information derived from the transformation can be passed to the nodes of the next hidden layer (e.g., the next hidden layer 504B) and these nodes can be activated, and these nodes can perform their own specified functions. Example functions include convolution, upsampling, data transformation, pooling and / or any other suitable function. The output of the hidden layer (e.g., the next hidden layer 504B) can then activate the nodes of the next hidden layer (e.g., the last hidden layer 504N), and so on. The output of the last hidden layer may activate one or more nodes of the output layer 506, which may provide an output at that point. In some cases, although nodes in the neural network 500 (e.g., nodes 508A, 508B, 508C) are shown as having multiple output lines, the nodes may have a single output, and all lines shown as outputs from the node may represent the same output value.

[0087] In some cases, each node or interconnection between nodes may have a weight that is a set of parameters derived from training neural network 500. For example, an interconnection between nodes may represent a piece of information learned about the interconnected nodes. The interconnections may have numerical weights that may be tuned (e.g., based on a training data set), thereby allowing neural network 500 to adapt to inputs and learn as more data is processed.

[0088] The neural network 500 may be pre-trained to process features of the data from the input layer 503 using different hidden layers 504 in order to provide an output through the output layer 506. For example, in some cases, the neural network 500 may use a training process known as back propagation to adjust the weights of the nodes. Back propagation may include a forward pass, a loss function, a backward pass, and a weight update. The forward pass, loss function, backward pass, and parameter update may be performed for one training iteration. This process may be repeated for each training data set for a certain number of iterations until the weights of the layers are accurately tuned (e.g., to meet a configurable threshold determined based on experiments and / or empirical studies).

[0089] Increasingly, ML (e.g., AI) algorithms (e.g., models or engines) are incorporated into a variety of technologies including wireless telecommunication standards. According to aspects described herein, one or more ML models may be trained using site-specific data to estimate or predict at least one characteristic associated with wireless communications between a UE and one or more network entities (e.g., one or more base stations), such as beam management predictions. Figure 6is a block diagram illustrating an ML engine 600 that can be trained using site-specific data to estimate or predict at least one characteristic associated with wireless communications between a UE and one or more network entities. As an example, one or more devices in a wireless system (e.g., UE 104) can include the ML engine 600. In some cases, the ML engine 600 can be similar to the neural network 500. In one example, the ML engine 600 includes three parts: an input 602 to the ML engine 600, the ML engine, and an output 604 from the ML engine 600. The input 602 to the ML engine 600 can be data that the ML engine 600 can use to make predictions or otherwise operate on it, such as site-specific data received from a base station (e.g., a gNB) or obtained locally by a device (e.g., a UE) on which the ML engine 600 is deployed. As an example, the ML engine 600 configured to make beam management predictions for selecting RF beams can take as input 602 data about current RF conditions, location information, network load, etc. As another example, data related to packets transmitted to a UE and historical packet data may be input 602 to an ML engine 600 configured to predict a channel condition of the UE (e.g., for CSI or CSF purposes). In some cases, an output 604 may be a prediction or other information generated by the ML engine 600, and the output 604 may be used to configure the wireless device, adjust settings, parameters, operating modes, etc. Continuing with the previous example, an ML engine 600 configured to select an RF beam may output 604 an RF beam or set of RF beams that may be used. Similarly, an ML engine 600 configured to predict a channel condition of a UE may output CSI or CSF for transmission to a base station.

[0090] While the principles disclosed herein relate to AI / ML models and the use cases generally include beam management for wireless communications, these principles may also be applied to any AI / ML model application in which estimates or predictions are to be made in conjunction with wireless communications between one or more UEs and / or one or more base stations.

[0091] With respect to beam management, a 4G / LTE UE may periodically monitor a radio link between the UE 104 and a network entity (e.g., an eNodeB (eNB)) to obtain the channel quality of its serving eNB. Based on measurements of the radio link (e.g., power measurements, such as RSSI, RSRP, etc.), the UE 104 may determine whether the network is able to transmit communications to and receive communications from the UE 104 with acceptable link quality. If the link quality is found to be too low based on a threshold (e.g., by comparing the power measurement to a minimum power threshold), the UE 104 may report a radio link failure (RLF) and trigger a higher layer reconnection procedure. The reconnection procedure may include initiating a new cell reselection procedure, which is more time consuming and thus results in a decrease in the overall data rate.

[0092] With the move to mmWave spectrum with 5G / New Radio (NR), where hybrid beamforming may be used at both the base station and the UE, managing the network may become more complex. On the other hand, highly directional beamforming architectures with a larger number of antenna elements may be advantageous for achieving higher data rates. Certain procedures may be useful for the UE to establish a connection with a network entity and maintain the link even in mobility scenarios.

[0093] The use of mmWaves enables directional communications with a larger number of antenna elements and provides additional beamforming gain that compensates for propagation losses. However, directional links may require precise alignment of beams at the base station 102 (e.g., gNB) and UE 104. The alignment requirement introduces the need for efficient management of beams, where the UE 104 and gNB 102 periodically identify the best beam for communication.

[0094] 5G / NR use cases, such as enhanced mobile broadband (eMBB), ultra-reliable and low-latency communications (URLLC), and massive machine type communications (mMTC), will require technology innovations, and 5G beam management may be an advantageous means for such use cases. 3GPP has defined a set of beam management procedures for 5G / NR that apply to two modes of operation: (1) idle mode; and (2) connected mode. Idle mode refers to when the UE has no active data to send. The idle mode procedures may be used when the UE attempts to connect to the network for the first time when it is turned on or when re-initiating a connection after waking up. Beam management in idle mode may help establish directional initial access. Connected mode refers to when active data exchange is occurring between the UE 104 and the base station 102 (e.g., gNB) and the UE 104 is moving within the cell. In connected mode, due to the characteristics of mmWave, there may be a high chance of rapid signal deterioration, so real-time management of the beam may help maintain a healthy link.

[0095] Beam management may use several components and is a set of layer 1 (PHY) and layer 2 (MAC) procedures to establish and maintain an optimal beam pair for a good connection. A beam pair includes a transmit beam and a corresponding receive beam in one link direction between a UE 104 and a network (e.g., gNB 102).

[0096] In some cases, before the UE 104 can communicate with the network, the UE 104 can perform a cell search and selection process and obtain initial cell synchronization and system information. For example, the UE 104 can acquire frame synchronization, determine the cell identity, and decode the master information block (MIB) and the system information block (SIB1).

[0097] In the case of a multi-antenna system that transmits multiple beams, detecting a beam from a network entity (e.g., gNB 102) may be part of an initialization process where UE 104 typically detects beams in a search space. The UE attach process may include the gNB transmitting a beam burst to UE 104 and the UE performing measurements on a "set B" of beams, and based on the scanning and measurements of set B, UE 104 may determine the best beam as part of a beam management process. Once the best beam is determined, UE 104 may receive a random access channel (RACH) assignment to communicate with gNB 102.

[0098] Beam scanning may be used during initial access of the UE 104 to determine the best beam. For example, the gNB 102 may transmit beams in multiple directions, such as in bursts at defined fixed intervals. Whenever the UE 104 synchronizes with the network, the UE 104 may analyze the synchronization signal block (SSB) and extract one or more of the following: (1) Primary Synchronization Signal (PSS): which may include one of three possible sequences and provide a timing estimate; (2) Secondary Synchronization Signal (SSS): which may include one of 336 possible sequences and provide a cell ID (one of 3*336=1008); and / or (3) Physical Broadcast Channel (PBCH) and Demodulation Reference Signal (DMRS): which may include the MIB and include basic information for taking the next step, which is to decode SIB-1.

[0099] A single SS block may span multiple OFDM symbols (e.g., four OFDM) in the time domain and multiple subcarriers (e.g., 240 subcarriers) in the frequency domain (e.g., 20 resource blocks). Each SS block corresponds to a specific beam beamformed in different directions. A group of SS blocks forms a SS burst set that spans a time window, such as a 5 ms window. The SS burst is repeated periodically with a period such as a 20 ms period.

[0100] The UE 104 may measure the beam strength by measuring received signal power such as RSRP, RSSI, etc. For example, in idle mode, the power may be based on synchronization signals, and in connected mode, the power may be based on a channel state information reference signal (CSI-RS) in the downlink and a sounding reference signal (SRS) in the uplink. The UE may periodically search for the best beam using a predefined threshold criterion (e.g., as defined or configured by the gNB) and identify the beam with the highest power (e.g., RSRP) relative to the threshold.

[0101] The UE 104 may send data or indicate the best beam to the gNB 102, which may be referred to as beam reporting. There are several ways or use cases related to how the UE 104 determines the best beam. For example, a spatial domain downlink (DL) beam prediction method may be performed, where a first set of beams (referred to as set A of beams) is determined from measurements of a second set of beams (referred to as set B of beams) via application of an AI / ML model. Set A is used for beam prediction, where the trained AI / ML model predicts which beam in set A will be the best beam for reporting. The wireless communication system 100 may measure a given set of beams (set B or a broad set of beams), and then the wireless communication system 100 may predict the best beam from set A. Set A may be established or identified based on measurements in set B. Such a process may be referred to as wide to narrow beam prediction. The best channel state information-reference signal (CSI-RS) is indexed by the wide beam measurement. On the other hand, there may be, for example, 64 beams, and the system may measure 16 of these beams and infer the best of the 64 beams from a selected set of 16 beams. In one example, 16 beams (or any subset number) from a larger set (or other set number) of 64 beams may be randomly selected or may be selected to represent a spatially broad spectrum of the 64 beams (such as every 4th beam, or a beam focused on an area of ​​the spectrum with expected better performance). Other selection protocols may be applicable, including AI / ML estimating or predicting where in the spectrum of 64 beams the best possible beam may be selected.

[0102] There may be alternatives to the spatial domain downlink (DL) beam prediction method. One alternative is where set B is a subset of set A. Here, the wireless communication system 100 attempts to determine set B from the beams in set A via a fixed pattern or a random pattern. In another alternative, set A and set B are different, where, for example, set A consists of narrow beams and set B consists of wide beams. In this case, the wireless communication system 100 can try and determine the QCL (quasi co-location) relationship between the set A beams and the set B beams. The goal is to reduce the number of measurements. For both alternatives, the system attempts to measure a limited set of beams and predict a larger set of beams.

[0103] In another case, temporal DL beam prediction for set A may be used based on historical measurements of set B beams. The wireless communication system 100 attempts to predict the best beam in the next beam management instance, or in another aspect, the wireless communication system 100 attempts to predict future beam measurements.

[0104] Time DL prediction may also have alternatives. One alternative is that set A and set B are different, where, for example, set A consists of narrow beams and set B consists of wide beams. In one alternative, prediction is being performed in both the spatial domain and the time domain. Spatial domain and time domain prediction may be referred to as "spatial-plus" prediction. In another alternative, set B may be a subset of set A, and determining how to determine set B from the beams in set A may be problematic. The wireless communication system 100 may not have the opportunity to use the spatial domain to determine the best CSI-RS index. The wireless communication system 100 may use the previous two or the previous five SSB (synchronization signal block) bursts (or some other number) and then try to determine the best narrow beam index. The system may only provide a time index, where set A and set B are the same. In one case as another alternative to time DL prediction, only in the time domain, the wireless communication system 100 sees a beam set in the past, and then the wireless communication system 100 tries to predict the best beam from the same beam set in the future.

[0105] A random access channel (RACH) is an uplink channel used during initial access or when a mobile station is not synchronized with the network and synchronization needs to be established. For example, in idle mode, after the UE selects a beam, there may be one or more RACH intervals with specific time and frequency offsets for which the UE may send a RACH preamble. The UE may send a physical RACH (PRACH) preamble corresponding to the SS block for which the best beam is identified. There may be a one-to-one mapping between the received SS block and the transmitted RACH preamble. Using such techniques, the UE may report the best beam to the gNB. The network entity 102 (e.g., gNB) may configure the UE 104 to perform certain measurements and report the results of the measurements, such as at preconfigured intervals. This process may be referred to as measurement reporting. In connected mode, when the UE 104 is already connected to the gNB 102 and active data transfer is ongoing, the UE 104 may report the selected beam to the gNB 102 via a measurement report.

[0106] In the event of a beam failure due to poor channel conditions, a beam recovery process is triggered to determine a new beam. In such cases, the UE 104 can monitor the reference signal and identify the beam failure once the failure trigger condition is met. When a beam failure occurs on a particular beam, the UE 104 can select the next best beam for transmission in a random access (RA) preamble. For example, if the first attempt at the RA fails, the UE can scan to another beam for another RA process. The RA preamble can be transmitted in the PRACH. The UE 104 can then receive downlink resource allocations and uplink grants on the physical downlink control channel (PDCCH). AI / ML model data can be used for beam recovery because predictions or outputs from the AI / ML model can include the best beam, the next best beam, and so on. Therefore, the AI / ML model can also be used for beam recovery purposes.

[0107] Switching from one beam to another beam may also be referred to as intra-cell mobility or beam-level mobility. Beam switching is based on the triggering conditions of the beam and the configured beam switching algorithm. When the UE 104 is in connected mode, beam switching is applicable and can be performed through L1 / L2 procedures. On the other hand, handover is used for inter-cell mobility and is a L3 procedure. Again, AI / ML models can be used to apply or implement switching from one beam to another.

[0108] The AI / ML model is typically trained using a large amount of data for a specific environment, such as an indoor or urban environment. In various beam prediction implementations (e.g., spatial domain DL beam prediction, temporal DL beam prediction, etc.), data for a specific environment, site, or geographic location is used to train the AI / ML model. Physical, timing, or other characteristics of the environment are provided to the AI / ML model as input, and the output of the model may be a selected beam (e.g., best beam, second-best beam, etc.) for wireless communication between the UE 104 and the gNB 102. The UE 104 then receives the AI / ML model and may use the model to make predictions for beam management (or other characteristics, such as channel measurements for CSI or CSF purposes) based on the trained environment. The UE 104 may then move to another site or another geographic location with different physical characteristics, or the characteristics of the existing site where the UE 104 is located may change over time (e.g., at night versus during the day). However, the AI / ML model will not be trained for the characteristics of the new site or geographic location. Then, in one scenario, the wireless communication system 100 may need to monitor poor performance of the AI / ML model. Monitoring may be performed on any device such as gNB 102 and / or UE 104. Performance may change based on environmental changes caused by new sites or changes to existing sites, which may affect channel characteristics between UE 104 and gNB 102 (or another gNB). For example, the environment may change based on the time of day and other entities or UEs around the UE 104 being monitored.

[0109] The wireless communication system 100 may deploy model monitoring to monitor the UE AI / ML model (e.g., from a gNB). In a prediction instance, the UE 104 will estimate or determine a prediction, and then there are actual measurements that the UE 104 can make, and a comparison can be made between the actual measurements and the predictions from the AI / ML model. There is an inferred error between the measurement and the prediction of the appropriate beam from the AI / ML model. If a threshold is met with respect to the error calculation, the gNB 102 can determine that the model is performing poorly. If the model monitoring determines that the performance of the ML model does not meet a threshold, a number of different actions can be taken. For example, the model can be deactivated or disabled for use, and another model or standard (non-ML) means can be used to determine the best beam. However, such approaches have disadvantages, such as the need to train multiple ML models or requiring more computing resources.

[0110] As described above, another method disclosed herein involves the UE 104 obtaining a site-specific data set that can provide data to allow the UE (or a server associated with the UE) to fine-tune (e.g., via online adaptation) an existing ML model of the UE 104. For example, the site-specific data can be obtained from the base station 102 (e.g., gNB) and / or can be measured locally by the UE 104. The amount of site-specific data sent to fine-tune the model is much smaller relative to the original training data, and therefore the burden on the wireless interface is smaller. Therefore, the wireless communication system 100 can initiate a retraining (e.g., fine-tuning or online adaptation) process for the ML model so that the UE 104 can adapt without the model running. As described above, when the UE 104 moves to a new geographical location, based on the time of day or other circumstances (where the same location where the UE 104 is located has different physical characteristics that cause the performance of the model to degrade), or for other reasons, the UE 104 may need to perform such adaptation.

[0111] A UE-side ML model for estimating or predicting characteristics associated with wireless communications with a gNB 102 may be needed in various scenarios. For example, a gNB 102 may transmit a reference signal (RS) at a certain time frame or frequency, such as every 10 seconds or every 20 seconds. The RS may be used by the UE 104 to determine or select the best beam for wireless communications. However, transmitting the signal requires a certain amount of bandwidth. Therefore, if the UE 104 has an ML model for predicting the appropriate or best beam to use, the gNB 102 may extend the frequency or timing at which the RS needs to be transmitted, such as every 40 seconds or every 60 seconds. Therefore, the systems and techniques described herein may increase the bandwidth of the system 100. The UE 104 may then rely on predictions based on ML model training between receptions of the RS. Power savings may also be achieved by using an ML model where it is costly from a power perspective for the UE 104 to perform or collect its own measurements for selecting the best beam. In one scenario, the UE 104 may be able to perform measurements every 40ms or 60ms instead of every 20ms.

[0112] Other use cases besides the above include positioning assisted beam management. In such cases, the input to the ML model may be the positioning information of the UE (e.g., location coordinates, orientation, or other location or positioning information indicating the location of the UE), and the output of the ML model is the best beam (e.g., the best downlink (DL) beam). When the UE 104 moves in or around the environment (e.g., around the gNB), such as in a circular pattern, the best beam available for the UE 104 is related to the positioning of the UE 104.

[0113] ML-assisted CSI or CSF is another example use case where the systems and techniques described herein for ML model adaptation based on site-specific data may be applied. For example, a first ML model (e.g., an ML-based encoder) at the UE 104 may perform compression of CSI feedback (or CSF) (e.g., to generate a latent representation of the CSI / CSF), and a second ML model (e.g., an ML-based decoder) at the gNB 102 may perform reconstruction of the compressed CSI-RS feedback. The UE 104 may update the first ML model based on the site-specific data, as described herein.

[0114] Site-specific adaptation or fine-tuning may generally be applied to a trained neural network or ML model that has been trained offline and deployed on a UE 104. The UE 104 may be in a first environment corresponding to the original offline training of the ML model. The first environment may be a geographic location, such as an indoor environment or an outdoor urban environment. The UE 104 may then move to a new site (corresponding to a new geographic location), and based on a trigger condition, the UE 104 may request the gNB 102 to transmit a “site-specific” dataset to the UE 104, or the UE 104 may locally collect information or data constituting the site-specific dataset. The UE 104 may use the site-specific dataset to fine-tune the ML model or adapt the ML model to the new environment.

[0115] In some cases, the UE 104 may perform performance monitoring to detect if the ML model is not operating correctly or reaching a certain threshold performance level, which may trigger the UE 104 to request a site-specific data set from the gNB 102 or to determine the site-specific data locally. For example, upon determining that the performance of the ML model has fallen below a threshold performance level (e.g., the probability output by the ML model is below a threshold probability representing the threshold performance level), the UE 104 may transmit to the gNB 102 a request for the site-specific data set to be transmitted to the UE 104. In one illustrative example of a metric, in a prediction instance (which refers to an instance where the UE 104 is scheduled or assumes a predicted beam measurement), the gNB 102 may transmit some auxiliary reference signals to enable the UE 104 to compare the actual beam measurement with the predicted value. The difference between the "predicted parameters" and the "measured parameters" is referred to as the "inference error". If the number of times the inference error is greater than a threshold (configurable by the gNB 102) exceeds a threshold during the time window, the AI / ML model may be performing poorly and should be deactivated or retrained.

[0116] The site-specific dataset may relate to the input of the ML model and the output or labeling of the ML model. The site-specific dataset may be collected at the gNB from a plurality of different UEs 104 that have historically been present in the geographic location corresponding to the site where the UE is located. The gNB 102 may record the data of the UEs 104 that are already in its cell, or may generate different sets for different use cases (e.g., spatial domain prediction, temporal prediction, etc.). The UE 104 may then request the site-specific dataset, and may then perform online adaptation or fine-tuning of the ML model. For example, the site-specific dataset may be smaller relative to a larger dataset used for initial offline training of the ML model. The smaller dataset may be downloaded or sent to the UE 104 and then used to adapt the ML model on the UE 104. The request may include details of the requested dataset, including at least one of the ML model, the label, the dataset size the UE wants, and the like. For example, if the degradation level of the ML model may meet a threshold but may not be large, then only a small amount of possible data in the dataset may need to be fine-tuned. For beam management use case, the site specific data set may include at least one of temporal, spatial and positioning aided beam prediction data. For CSI / CSF based use case, the site specific data may include channel conditions as input data and correctly predicted beams as labeled output data for training purposes. Based on the adaptation of the ML model, the performance of the ML model may be improved for that specific environment.

[0117] A "site" may be a geographical location covered by a serving cell served by a gNB 102, where a UE 104 is active in that cell. The wireless communication system 100 may also include a portion of intra-cell or intra-site or inter-site variations. It may be a hotspot deployment or other types of deployments. In some cases, there may be UMi (urban micro) or uMA (urban macro) deployments. In some cases, there may be variations within the same "site", such as different seasons or different times of the day, which may result in an impact on the performance of the ML model. However, typically, a "site" is a geographical location of a UE 104. An example of intra-site generalization of this concept is that the performance of a UE model may change from time to time even if the UE 104 is not moving or is generally in the same geographical location. For example, an ML model may be trained for a location, but only for a certain season, such as summer. The physical characteristics of the site may change in the winter and result in a degradation in the performance of the ML model, thus requiring adaptation. The ML model may be trained for daytime use, but the UE 104 may be used at night when the physical characteristics of the location are different. These are examples of intra-site variations where site-specific datasets may be received to fine-tune the model for that site.

[0118] With respect to positioning assisted prediction, the gNB 102 may have marked the positioning of the UE 104 with the best DL beam for the UE 104 at that positioning. The gNB 102 may continue to collect data from various UEs 104. The data may also include different orientations of the UE 104 at different times. The best gNB beam may change based on the orientation of the UE 104. Therefore, other auxiliary inputs to the ML model may include information other than the positioning of the UE. However, in one aspect, when the UE 104 determines that the ML model should be adapted or fine-tuned, the UE 104 may request a site-specific dataset (which may be of a specific size). Once the UE 104 receives the site-specific dataset, the UE 104 may perform online adaptation or fine-tuning of the ML model. The positioning in this case may be the input, and the selected beam may be the label or output. For example, the UE 104 may receive the input and the label or output, and the UE 104 may perform a supervised learning problem in which the input and label may be used to fine-tune the ML model. In one example, the label or output may be compared to the predicted output generated by the ML model based on the input, and a loss may be determined. The results of the loss can be used to perform backpropagation to tune the parameters of the ML model (e.g., weights, biases, etc.).

[0119] Typically, the site-specific datasets are the same across the cell served by the gNB 102. However, there may be scenarios where different datasets may apply to different areas within the cell covered by the gNB 102 and the specific location of the UE 104 may be used to select a positioning-based site-specific dataset from a set of site-specific datasets.

[0120] Fig. 7A is a flow chart of an example method 700. The example method 700 for wireless communication at a first network entity includes one or more of: obtaining site-specific data associated with a geographic location (702), and adapting a machine learning model at the first network entity based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communication between the first network entity and one or more network entities (704). The first network entity may be located in the geographic location. The method may also include sending an indication associated with adapting the machine learning model based on the site-specific data (706). In one example, the indication may identify that fine-tuning of the machine learning model is complete and that the updated machine learning model is being used for wireless communication.

[0121] Method 700 may also include determining, at the first network entity, one or more estimates or predictions of at least one characteristic associated with wireless communications between the first network entity and other network entities using an updated machine learning model based on data received by the first network entity at the geographic location.

[0122] In another aspect, method 700 may further include sending a request for site-specific data from the first network entity to the second network entity. Sending the request for site-specific data may be triggered based on at least one of a location of the first network entity in the geographic location or movement of the first network entity into the geographic location. Sending the request for site-specific data may also be triggered based on a change in performance of the machine learning model.

[0123] The method 700 may also include monitoring the performance of the machine learning model at the first network entity. In one case, sending a request for site-specific data may be triggered based on performance falling below a threshold level. Changes in model performance may be based on any number of factors, including changes in geographic location or changes in physical environment or location characteristics.

[0124] The estimate or prediction may be associated with wireless communications between the first network entity and the second network entity. In one aspect, the site-specific data may be obtained by the second network entity from a plurality of user equipments (UEs) in communication with the second network entity. The site-specific data may be aggregated data from the plurality of UEs 104, or may be processed in some manner to prepare data for transmission to the respective UEs 104.

[0125] The request may include at least one of: a request for input to a machine learning model, a request for labels for training the machine learning model using supervised learning, or a request for a size of site-specific data. The request may also include positioning information associated with the first network entity, and wherein the site-specific data is based on the positioning information.

[0126] The first network entity may include a user equipment (UE) 104, and the second network entity may include a base station 102. The site-specific data may include at least one of temporal beam prediction data, spatial beam prediction data, or positioning assistance beam prediction data. The site-specific data may be based on data from a plurality of UEs 104 associated with a geographic location. In a specific example, a machine learning model is trained for beam prediction. The site-specific data may be associated with a physical characteristic of the geographic location, which may be spatial and / or temporal, such as a changing characteristic of the location.

[0127] The site-specific data may include at least one of: positioning data as one or more inputs for adapting the machine learning model, beam data as one or more labeled outputs for adapting the machine learning model, or orientation data for adapting the machine learning model. In one aspect, prior to adapting the machine learning model, the machine learning model is trained offline using a training data set, which is typically larger than the amount of site-specific data that will be sent to the UE 104 for fine-tuning its model.

[0128] An apparatus for wireless communication may include: at least one memory; and at least one processor, the at least one processor coupled to the memory and configured to: obtain site-specific data associated with a geographic location; adapt a machine learning model based on the site-specific data at a first network entity to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communication between the apparatus and one or more network entities, and send an indication associated with adapting the machine learning model based on the site-specific data.

[0129] Figure 7B 7 is a flowchart illustrating a method 710 for wireless communication. The example method 710 for wireless communication may include one or more of the following: sending a message by a UE (e.g., Figure 1 104) to a network entity (eg, Figure 1 The base station or gNB 102 shown in FIG. 10A indicates that a trained AI / ML model (e.g., Figure 5 500 shown in ), in response to receiving the indication, sending site-specific data associated with the trained AI / ML model (714), and sending an indication (716) associated with adapting the AI / ML model based on the site-specific data from the UE 104 to the network entity 104. The ability to update the trained AI / ML model may include fine-tuning the AI / ML model. The site-specific data may include inputs and / or outputs (or tags) of the AI / ML model. The AI / ML model may be fine-tuned by the UE 104 using a data set of site-specific data. Note that additional training or fine-tuning of the AI / ML model does not have to be performed on any particular device. The UE 104 may update the AI / ML model via a server associated with the UE / chipset / OEM vendor. The site-specific data may be transmitted, for example, via an RRC / MAC-CE (e.g., Radio Resource Control / Medium Access Control - Control Element). RRC / MAC-CE represents an example MAC (Medium Access Control) structure that may be used to carry control information.

[0130] Indications associated with adapting the AI / ML model based on site-specific data may include, for example, an indication that fine-tuning is complete and the updated model is now being used for wireless communications.

[0131] In one example, the transmission of site-specific data may be from a network entity such as gNB 102 to UE 104. UE 104 may use the site-specific data to update its AI / ML model on UE 104, or UE 104 may update the AI / ML model via a separate server, wherein the site-specific data is sent on a communication channel used to transmit control data. In this regard, the defined apparatus may include both a network entity such as gNB 102 and UE 104. In one aspect, the method may be defined as being performed by a user equipment or a network entity. The steps of the method may be performed from the perspective of UE 104 or a network entity 203. For example, if the method is performed only from the perspective of UE 104, the method may include being performed by a UE (e.g., Figure 1 104) to a network entity (eg, Figure 1 The base station or gNB 102 shown in FIG. 10A indicates that a trained AI / ML model (e.g., Figure 5 5 ) and, in response to the indication, receiving, at UE 104, site-specific data associated with the trained AI / ML model from network entity 102, and sending, from UE 104 to network entity 102, an indication associated with adapting the AI / ML model based on the site-specific data.

[0132] An apparatus for wireless communication may include: at least one memory; and at least one processor, the at least one processor coupled to the memory and configured to: Figure 1 ) to a network entity (e.g., Figure 1 ) indicates that a trained AI / ML model (e.g., Figure 5 ) the ability to update the trained AI / ML model, in response to the indication, send site-specific data associated with the trained AI / ML model, and send an indication associated with adapting the AI / ML model based on the site-specific data from the UE 104 to the network entity 102. The ability to update the trained AI / ML model may include fine-tuning the AI / ML model. The site-specific data may include inputs and / or outputs (or markings) of the AI / ML model. The AI / ML model may be fine-tuned by the UE 104 using a data set of site-specific data. Note that additional training or fine-tuning of the AI / ML model does not have to be performed on any particular device. The UE 104 may update the AI / ML model via a server associated with the UE / chipset / OEM vendor. The site-specific data may be transmitted, for example, via RRC / MAC-CE (e.g., Radio Resource Control / Medium Access Control-Control Element). RRC / MAC-CE represents an example MAC (Medium Access Control) structure that may be used to carry control information.

[0133] Indications associated with adapting the AI / ML model based on site-specific data may include, for example, an indication that fine-tuning is complete and the updated model is now being used for wireless communications.

[0134] In one example, the transmission of site-specific data may be from a network entity such as gNB 102 to UE 104. UE 104 may use the site-specific data to update its AI / ML model on UE 104, or UE 104 may update the AI / ML model via a separate server, where the site-specific data is sent on a communication channel used to transmit control data. In this regard, the defined apparatus may include both a network entity such as gNB 102 and UE 104. On the other hand, the apparatus may include only one of a user equipment or a network entity, and the operations performed are all from the perspective of the user equipment or the network entity. For example, if the apparatus is UE 104, UE 104 may be configured to: be communicated to a user equipment (e.g., a network entity) by the UE (e.g., a user equipment). Figure 1 104) to a network entity (eg, Figure 1 The base station or gNB 102 shown in FIG. 10A indicates that a trained AI / ML model (e.g., Figure 5 5 ) and, in response to the indication, receiving, at UE 104, site-specific data associated with the trained AI / ML model from network entity 102, and sending, from UE 104 to network entity 102, an indication associated with adapting the AI / ML model based on the site-specific data.

[0135] Fig. 8A is a flow chart illustrating a method 800 for performing wireless communications at a network entity. In one aspect, the method 800 is performed from the perspective of a gNB 102. The method 800 includes obtaining site-specific data associated with a geographic location (802) and sending the site-specific data to a user equipment (UE) 104 or a mobile device (804), and Received from UE 104 and at UE 104 Adapting a machine learning model based on site-specific data to estimate or predict At least one characteristic associated with wireless communication between the network entity and the UE 104 The UE 104 may adapt a machine learning model based on the site-specific data for estimating or predicting at least one characteristic associated with wireless communications between a network entity and the UE 104.

[0136] An apparatus for wireless communication may include at least one memory and at least one processor coupled to the memory and configured to obtain site-specific data associated with a geographic location, transmit the site-specific data to a user equipment (UE) 104 or a mobile device, and Receiving from UE 104 and adapting the machine at the UE based on the site-specific data An indication of a machine learning model associated with estimating or predicting wireless communications between a network entity and a UE At least one attribute associated with .

[0137] In some examples, the processes described herein (e.g., method 800 and / or other processes herein) may be performed by a computing device or apparatus (e.g., UE 104 or base station 102). In another example, process 800 may be performed by Figure 1 In another example, process 800 may be performed by a UE in UE 104. Figure 1 The base station in base station 102 is executed.

[0138] Figure 8B 8 is a flow chart illustrating a method 810 for performing wireless communications. In one aspect, the method 810 is performed from the perspective of a UE 104. The method 810 includes obtaining, at a user equipment (UE) 104, site-specific data associated with a geographic location from a network entity (812) and adapting, at the UE 104, a machine learning model based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the UE 104 and the network entity (814). In one aspect, the network entity may be a gNB 102.

[0139] Figure 8C An example communication exchange 820 between a UE 822 having an AI / ML model and a gNB 824 having site-specific data is illustrated. A process flow for wireless communication may include communicating between the first network entity and a second network entity, such as a gNB 824, utilizing a machine learning model operating on the first network entity, such as the UE 822 (826). Based on a trigger condition, a request is sent from the first network entity for the second network entity to provide the first network entity with site-specific data (828), the site-specific data is received from the second network entity based on the request (830), the machine learning model is adapted at the first network entity based on the site-specific data to generate a tuned machine learning model (832), an indication associated with adapting the AI / ML model based on the site-specific data (i.e., adaptation of the machine learning model is complete and the first network entity is using the tuned machine learning model to resume communication) (834), and communicating between the first network entity and the second network entity utilizing the tuned machine learning model operating on the first network entity (836).

[0140] The sending of the indication may be performed via a MAC control element / DCT signal. The trigger condition may be, for example, a result of model performance monitoring.

[0141] Fig. 9 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. Specifically, Fig. 9An example of a computing system 900 is illustrated, which may be any computing device, for example, constituting an internal computing system, a remote computing system, a camera, or any components thereof, wherein the components of the system communicate with each other using a connection 905. The connection 905 may be a physical connection using a bus, or a direct connection to at least one processing unit 910 (which may also be referred to as a processor), such as in a chipset architecture. The connection 905 may also be a virtual connection, a networked connection, or a logical connection.

[0142] In some embodiments, computing system 900 is a distributed system, wherein the functionality described in the present disclosure may be distributed within a data center, multiple data centers, a peer-to-peer network, etc. In some embodiments, one or more of the described system components represent a number of such components, each of which performs some or all of the functionality described for that component. In some embodiments, a component may be a physical device or a virtual device.

[0143] The example computing system 900 includes at least one processing unit (CPU or processor) 910 and connections 905 that communicatively couple various system components including system memory 915, such as read-only memory (ROM) 920 and random access memory (RAM) 925, to the at least one processing unit 910. The computing system 900 may include a cache 912 of high-speed memory directly connected to the at least one processing unit 910, close to the processor, or integrated as part of the processor.

[0144] At least one processing unit 910 may include any general purpose processor and hardware services or software services (such as services 932, 934, and 936 stored in storage device 930 configured to control at least one processing unit 910), as well as a dedicated processor where software instructions are incorporated into the actual processor design. At least one processing unit 910 may be essentially a completely independent computing system that includes multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0145] To enable user interaction, the computing system 900 includes an input device 945 that can represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, voice, etc. The computing system 900 may also include an output device 935, which may be one or more of a plurality of output mechanisms. In some cases, a multimodal system may enable a user to provide multiple types of input / output to communicate with the computing system 900.

[0146] The computing system 900 may include a communication interface 940, which may generally govern and manage user input and system output. The communication interface may perform or facilitate receiving and / or sending wired or wireless communications using wired and / or wireless transceivers, including utilizing an audio jack / plug, a microphone jack / plug, a universal serial bus (USB) port / plug, an Apple™ Lightning™ port / plug, an Ethernet port / plug, a fiber optic port / plug, a dedicated wired port / plug, 3G, 4G, 5G and / or other cellular data network wireless signaling, Bluetooth™ wireless signaling, Bluetooth™ low energy (BLE) wireless signaling, IBEACON™ wireless signaling, radio frequency identification (RFID) wireless signaling, near field communication, or other wireless communications. The communication interface 940 may include wireless communication systems such as near field communication (NFC) wireless signal transmission, dedicated short range communication (DSRC) wireless signal transmission, 802.11 Wi-Fi wireless signal transmission, wireless local area network (WLAN) signal transmission, visible light communication (VLC), worldwide interoperability for microwave access (WiMAX), infrared (IR) communication wireless signal transmission, public switched telephone network (PSTN) signal transmission, integrated services digital network (ISDN) signal transmission, ad hoc network signal transmission, radio wave signal transmission, microwave signal transmission, infrared signal transmission, visible light signal transmission, ultraviolet light signal transmission, wireless signal transmission along the electromagnetic spectrum, or some combination thereof. The communication interface 940 may also include one or more global navigation satellite system (GNSS) receivers or transceivers, which are used to determine the location of the computing system 900 based on one or more signals received from one or more satellites associated with one or more GNSS systems. GNSS systems include, but are not limited to, the United States' Global Positioning System (GPS), Russia's Global Navigation Satellite System (GLONASS), China's Beidou Navigation Satellite System (BDS), and Europe's Galileo GNSS. There is no restriction to operating on any particular hardware arrangement, and thus the underlying features herein may be easily substituted for improved hardware or firmware arrangements as they are developed.

[0147] The storage device 930 may be a non-volatile and / or non-transitory and / or computer-readable memory device and may be a hard disk or other type of computer-readable medium that can store data accessible by a computer, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cassette, a floppy disk, a floppy disk, a hard disk, a magnetic tape, a magnetic stripe / magnetic stripe, any other magnetic storage medium, flash memory, a memristor memory, any other solid-state memory, a compact disk-read only memory (CD-ROM) optical disk, a rewritable compact disk (CD) optical disk, a digital video disk (DVD) optical disk, a Blu-ray disc (BDD) optical disk, a holographic optical disk, another optical medium, a secure digital (SD) card, a micro secure digital (microSD) card, a Memory Card, or a memory card. card, a smart card chip, an EMV chip, a subscriber identity module (SIM) card, a mini / micro / nano / pico SIM card, another integrated circuit (IC) chip / card, a random access memory (RAM), a static RAM (SRAM), a dynamic RAM (DRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash EPROM (FLASH EPROM), a cache memory (e.g., a layer 1 (L1) cache, a layer 2 (L2) cache, a layer 3 (L3) cache, a layer 4 (L4) cache, a layer 5 (L5) cache, other (L#) cache), a resistive random access memory (RRAM / ReRAM), a phase change memory (PCM), a spin transfer torque RAM (STT-RAM), another memory chip or box, and / or a combination thereof.

[0148] The storage device 930 may include software services, servers, services, etc., which, when the code defining such software is executed by at least one processing unit 910, causes the system to perform functions. In some embodiments, hardware services that perform specific functions may include software components for performing functions stored in a computer-readable medium connected to necessary hardware components such as at least one processing unit 910, connection 905, output device 935, etc. The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing or carrying instructions and / or data. Computer-readable media may include non-transient media in which data may be stored and does not include carrier waves and / or transient electronic signals propagated wirelessly or through wired connections. Examples of non-transient media may include, but are not limited to, disks or tapes, optical storage media such as compact discs (CDs) or digital versatile discs (DVDs)), flash memory, memory, or memory devices. Computer readable media may store thereon code and / or machine executable instructions, which may represent a process, function, subprogram, program, routine, subroutine, module, software package, category, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by transmitting and / or receiving information, data, independent variables, parameters, or memory contents. Information, independent variables, parameters, data, etc. may be transmitted, forwarded, or sent via any suitable means, including memory sharing, message passing, token passing, network sending, etc.

[0149] Specific details are provided in the above description to provide a thorough understanding of each embodiment and each example provided herein, but those skilled in the art will recognize that the application is not limited thereto. Thus, although the exemplary embodiments of the present application have been described in detail herein, it is to be understood that the inventive concept can be embodied and adopted in various other ways, and the appended claims are intended to be interpreted as including such variations, unless limited by the prior art. Various features and aspects of the above-mentioned applications can be used individually or in combination. In addition, without departing from the broader scope of this specification, the embodiments can be used in any number of environments and applications beyond the environment and application described herein. Therefore, the description and the accompanying drawings should be considered as illustrative rather than restrictive. For the purpose of illustration, each method is described in a specific order. It should be understood that in an alternative embodiment, each method can be performed in a different order than described.

[0150] For clarity of explanation, in some cases, the present technology may be presented as including separate functional blocks, which include devices, device components, steps or routines in the method embodied in software or a combination of hardware and software. Additional components other than those components shown in the drawings and / or described herein may be used. For example, circuits, systems, networks, processes and other components may be shown as components in block diagram form to avoid these embodiments becoming obscure in unnecessary details. In other cases, known circuits, processes, algorithms, structures and techniques may be shown without necessary details to avoid making each embodiment obscure.

[0151] Note that there are cases where the AI / ML model may not be on the UE 104 but may be configured on the gNB 102 and the AI / ML model may rely on reports for input data from the UE 104. The measurements may be transmitted to the gNB 102 which makes the predictions. Such scenarios are covered in this disclosure.

[0152] In addition, it will be appreciated by those skilled in the art that the various exemplary logic blocks, modules, circuits and algorithmic steps described in conjunction with the aspects disclosed herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, various exemplary components, blocks, modules, circuits and steps have been generally described in terms of their functionality. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints proposed to the entire system. Those skilled in the art can implement the described functionality in different ways for each specific application, but such specific implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0153] Individual embodiments may be described above as processes or methods depicted as flow charts, flow diagrams, data flow diagrams, structure diagrams, or block diagrams. Although a flow chart may describe an operation as a sequential process, many of the operations may be performed in parallel or concurrently. In addition, the order of the operations may be rearranged. The process is terminated when the operations of the process are completed, but the process may have additional steps not included in the accompanying drawings. The process may correspond to a method, function, process, subroutine, subprogram, etc. When the process corresponds to a function, the termination of the process may correspond to the function returning to the calling function or main function.

[0154] The processes and methods according to the above examples can be implemented using stored computer executable instructions or otherwise available computer executable instructions from a computer readable medium. Such instructions may include, for example, instructions and data that enable a general-purpose computer, a special-purpose computer, or a processing device or otherwise configure a general-purpose computer, a special-purpose computer, or a processing device to perform a certain function or group of functions. The portion of the computer resources used can be accessed through a network. The computer executable instructions can be, for example, binary, intermediate format instructions such as assembly language, firmware, source code. Examples of computer readable media that can be used to store instructions, information used, and / or information created during the method according to the examples include disks or optical disks, flash memory, USB devices with non-volatile memory, networked storage devices, etc.

[0155] In some embodiments, computer readable storage devices, media, and memories may include wired or wireless signals containing bit streams, etc. However, when referred to, non-transitory computer readable storage media explicitly excludes media such as power consumption, carrier signals, electromagnetic waves, and signals themselves.

[0156] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned in the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof, depending in part on the specific application, in part on the desired design, in part on the corresponding technology, etc.

[0157] Various illustrative logic blocks, modules, and circuits described in conjunction with the various aspects disclosed herein may be implemented or executed using hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof, and may be implemented in any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, program code or code segments (e.g., computer program products) for performing necessary tasks may be stored in a computer-readable or machine-readable medium. The processor may perform the necessary tasks. Examples of form factors include: laptops, smartphones, mobile phones, tablet devices, or other small form factor personal computers, personal digital assistants, rack-mounted devices, stand-alone devices, etc. The functions described herein may also be embodied in peripheral devices or add-in cards. By way of further example, such functionality may also be implemented on circuit boards in different chips or different processes executed on a single device.

[0158] Instructions, media for conveying such instructions, computing resources for executing them, and other structures for supporting such computing resources are example means for providing the functionality described in this disclosure.

[0159] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as general-purpose computers, wireless communication device mobile phones, or integrated circuit devices with multiple uses, including applications in wireless communication device mobile phones and other devices. Any features described as modules or components may be implemented together in an integrated logic device or individually as a discrete but interoperable logic device. If implemented in software, the technique may be implemented at least in part by a computer-readable data storage medium including a program code, which includes instructions for executing one or more of the above-mentioned methods, algorithms, and / or operations when executed. A computer-readable data storage medium may form part of a computer program product, which may include packaging materials. A computer-readable medium may include a memory or data storage medium, such as a random access memory (RAM) (such as a synchronous dynamic random access memory (SDRAM)), a read-only memory (ROM), a non-volatile random access memory (NVRAM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic or optical data storage medium, and the like. Additionally or alternatively, the techniques may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0160] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such processors may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; however, in an alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. Therefore, the term "processor" as used herein may refer to any of the aforementioned structures, any combination of the aforementioned structures, or any other structure or device suitable for implementing the techniques described herein.

[0161] It should be understood by those of ordinary skill in the art that the less than ("<") symbol and greater than (">") symbol or terminology used herein may be replaced by the less than or equal to ("≤") symbol and greater than or equal to ("≥") symbol, respectively, without departing from the scope of the present specification.

[0162] Where a component is described as being “configured to” perform certain operations, such configuration may be achieved, for example, by designing electronic circuits or other hardware to perform the operations, by programming programmable electronic circuits (e.g., a microprocessor or other suitable electronic circuits) to perform the operations, or any combination thereof.

[0163] The phrases “coupled to” or “communicatively coupled to” refer to any component being physically connected directly or indirectly to another component, and / or any component being in communication directly or indirectly with another component (e.g., connected to the other component via a wired or wireless connection and / or other suitable communication interface).

[0164] Claim language or other language stating "at least one of" a set and / or "one or more of" a set indicates that one member of the set or multiple members of the set (in any combination) satisfies the claim. For example, claim language stating "at least one of A and B" or "at least one of A or B" means A, B, or A and B. In another example, claim language stating "at least one of A, B, and C" or "at least one of A, B, or C" means A, B, C, or A and B, or A and C, or B and C, A and B and C, or any repetition is information or data (e.g., A and A, B and B, C and C, A and A and B, etc.), or any other ordering, repetition, or combination of A, B, and C. The language "at least one of" a set and / or "one or more of" a set does not limit the set to the items listed in the set. For example, claim language stating "at least one of A and B" or "at least one of A or B" may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0165] Exemplary aspects of the present disclosure include:

[0166] Aspect 1. A method for performing wireless communications at a first network entity, the method comprising: obtaining site-specific data associated with a geographic location; adapting a machine learning model at the first network entity based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the first network entity and one or more network entities, and sending an indication associated with adapting the machine learning model based on the site-specific data.

[0167] Aspect 2. The method according to aspect 1, wherein the first network entity is located in the geographical location.

[0168] Aspect 3. According to any one of Aspects 1 or 2, the method also includes: based on data received by the first network entity at the geographic location, using the updated machine learning model to determine at the first network entity one or more estimates or predictions of the at least one characteristic associated with wireless communication between the first network entity and one or more network entities.

[0169] Aspect 4. The method according to any one of aspects 1 to 3, further comprising: sending a request for the site-specific data from the first network entity to a second network entity.

[0170] Aspect 5. A method according to any one of Aspects 1 to 4, wherein sending the request for the site-specific data is triggered based on at least one of the location of the first network entity in the geographic location or the movement of the first network entity to the geographic location.

[0171] Aspect 6. A method according to any one of Aspects 1 to 5, wherein sending the request for the site-specific data is triggered based on a change in performance of the machine learning model.

[0172] Aspect 7. According to any one of Aspects 1 to 6, the method further includes: monitoring the performance of the machine learning model at the first network entity, wherein sending the request for the site-specific data is triggered based on the performance being below a threshold level.

[0173] Aspect 8. The method according to any one of aspects 1 to 7, wherein the estimating or the predicting is associated with wireless communication between the first network entity and the second network entity.

[0174] Aspect 9. The method according to any one of aspects 1 to 8, wherein the site-specific data is obtained by the second network entity from a plurality of user equipments (UEs) communicating with the second network entity.

[0175] Aspect 10. A method according to any one of Aspects 1 to 9, wherein the request comprises at least one of: a request for input to the machine learning model, a request for labels for training the machine learning model using supervised learning, or a request for the size of the site-specific data.

[0176] Aspect 11. The method according to any one of aspects 1 to 10, wherein the request further comprises positioning information associated with the first network entity, and wherein the site-specific data is based on the positioning information.

[0177] Aspect 12. The method according to any one of aspects 1 to 11, wherein the first network entity comprises a user equipment (UE).

[0178] Aspect 13. A method according to any one of aspects 1 to 12, wherein the second network entity comprises a base station.

[0179] Aspect 14. A method according to any one of aspects 1 to 13, wherein the site-specific data comprises at least one of time beam prediction data, spatial beam prediction data or positioning assistance beam prediction data.

[0180] Aspect 15. The method according to any one of aspects 1 to 14, wherein the site-specific data is based on data from a plurality of user equipments (UEs) associated with the geographical location.

[0181] Aspect 16. A method according to any one of Aspects 1 to 15, wherein the machine learning model is trained for beam prediction.

[0182] Aspect 17. A method according to any one of aspects 1 to 16, wherein the site-specific data is associated with physical characteristics of the geographic location.

[0183] Aspect 18. A method according to any one of Aspects 1 to 17, wherein the site-specific data includes at least one of the following: positioning data as one or more inputs for adapting the machine learning model, beam data as one or more labeled outputs for adapting the machine learning model, or orientation data for adapting the machine learning model.

[0184] Aspect 19. A method according to any one of Aspects 1 to 18, wherein before adapting the machine learning model, the machine learning model is trained offline using a training dataset.

[0185] Aspect 20. A method according to any one of aspects 1 to 19, wherein the indication indicates that the adaptation is complete and the updated machine learning model is being used for the wireless communication

[0186] Aspect 21. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to perform the operations according to any one of aspects 1 to 20.

[0187] Aspect 22. A method for performing wireless communications, the method comprising: obtaining site-specific data associated with a geographic location via a first network entity; and sending the site-specific data from the first network entity to a second network entity, wherein a machine learning model is adapted based on the site-specific data for estimating or predicting at least one characteristic associated with wireless communications between the first network entity and one or more network entities.

[0188] Aspect 23. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the memory and configured to: obtain site-specific data associated with a geographic location via a first network entity such as a gNB; send the site-specific data from the first network entity to a second network entity such as a UE or a mobile device, wherein a machine learning model is adapted based on the site-specific data for estimating or predicting at least one characteristic associated with wireless communication between the first network entity and one or more network entities; and send an indication associated with adapting the machine learning model based on the site-specific data.

[0189] Aspect 24. A wireless communication method, the method comprising one or more of the following: indicating by a UE to a network entity the ability to update a trained AI / ML model, sending or receiving site-specific data associated with the trained AI / ML model in response to the indication, and sending from the UE to the network entity an indication associated with adapting the AI / ML model based on the site-specific data.

[0190] Aspect 25. A device for wireless communication, the device comprising: at least one memory; and at least one processor, the at least one processor being coupled to the memory and configured to: indicate to a network entity by a UE the ability to update a trained AI / ML model, send or receive site-specific data associated with the trained AI / ML model in response to the indication, and send from the UE to the network entity an indication associated with adapting the AI / ML model based on the site-specific data.

[0191] Aspect 26. A method for performing wireless communications at a network entity, the method comprising: obtaining site-specific data associated with a geographic location; sending the site-specific data to a user equipment (UE); and receiving an indication from the UE associated with adapting a machine learning model at the UE based on the site-specific data, the machine learning model being used to estimate or predict at least one characteristic associated with wireless communications between the network entity and the UE.

[0192] Aspect 27. A device for wireless communication, the device comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: obtain site-specific data associated with a geographic location; send the site-specific data to a user equipment (UE); and receive from the UE an indication associated with adapting a machine learning model at the UE based on the site-specific data, the machine learning model being used to estimate or predict at least one characteristic associated with wireless communication between the device and the UE.

[0193] Aspect 28. A non-transitory computer-readable storage medium, comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to any one of Aspects 1 to 20, 22, 24 and / or Aspect 26.

[0194] Aspect 29. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations according to any one of aspects 1 to 20, 22, 24 and / or aspect 26.

Claims

1. A method for wireless communication at a first network entity, the method comprising: obtaining site-specific data associated with a geographic location; adapting, at the first network entity, a machine learning model based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the first network entity and one or more network entities; as well as Sending instructions associated with adapting the machine learning model based on the site-specific data. The method of claim 1 , wherein the first network entity is located in the geographic location.

3. The method according to claim 1, further comprising: Based on data received by the first network entity at the geographic location, one or more estimates or predictions of the at least one characteristic associated with wireless communications between the first network entity and one or more network entities are determined at the first network entity using the updated machine learning model.

4. The method according to claim 1, further comprising: A request for the site-specific data is sent from the first network entity to a second network entity.

5. The method of claim 4, wherein sending the request for the site-specific data is triggered based on at least one of a location of the first network entity in the geographic location or movement of the first network entity to the geographic location.

6. The method of claim 4, wherein sending the request for the site-specific data is triggered based on a change in performance of the machine learning model.

7. The method according to claim 4, further comprising: Performance of the machine learning model is monitored at the first network entity, wherein sending the request for the site-specific data is triggered based on the performance being below a threshold level.

8. The method of claim 4, wherein the estimating or the predicting is associated with wireless communications between the first network entity and the second network entity.

9. The method of claim 4, wherein the site-specific data is obtained by the second network entity from a plurality of user equipments (UEs) in communication with the second network entity.

10. The method of claim 4, wherein the request comprises at least one of: a request for input to the machine learning model, a request for labels for training the machine learning model using supervised learning, or a request for a size of the site-specific data.

11. The method of claim 4, wherein the request further comprises positioning information associated with the first network entity, and wherein the site-specific data is based on the positioning information.

12. The method of claim 4, wherein the first network entity comprises a user equipment (UE). The method of claim 12 , wherein the second network entity comprises a base station.

14. The method of claim 1, wherein the site-specific data comprises at least one of temporal beam prediction data, spatial beam prediction data, or positioning assistance beam prediction data.

15. The method of claim 1, wherein the site-specific data is based on data from a plurality of user equipments (UEs) associated with the geographic location.

16. The method of claim 1, wherein the machine learning model is trained for beam prediction.

17. The method of claim 1, wherein the site-specific data is associated with a physical characteristic of the geographic location.

18. A method according to claim 1, wherein the site-specific data includes at least one of the following: positioning data as one or more inputs for adapting the machine learning model, beam data as one or more labeled outputs for adapting the machine learning model, or orientation data for adapting the machine learning model.

19. The method of claim 1, wherein the machine learning model is trained offline using a training dataset before adapting the machine learning model.

20. The method of claim 1, wherein the indication identifies that the adaptation is complete and the updated machine learning model is being used for the wireless communication.

21. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: obtaining site-specific data associated with a geographic location; adapting a machine learning model based on the site-specific data to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the apparatus and one or more network entities; as well as Sending instructions associated with adapting the machine learning model based on the site-specific data.

22. The apparatus of claim 21, wherein the apparatus is located in the geographic location.

23. The apparatus of claim 21, wherein the at least one processor is configured to: Based on data received by the device at the geographic location, the updated machine learning model is used to determine one or more estimates or predictions of the at least one characteristic associated with wireless communications between the device and one or more network entities.

24. The apparatus of claim 21, wherein the at least one processor is configured to: A request for the site-specific data is sent to a network entity.

25. The apparatus of claim 24, wherein the at least one processor is configured to send the request for the site-specific data based on at least one of a location of the apparatus in the geographic location or movement of the apparatus to the geographic location.

26. An apparatus according to claim 24, wherein the at least one processor is configured to send the request for the site-specific data based on a change in performance of the machine learning model.

27. The apparatus of claim 24, wherein the at least one processor is configured to: Monitoring performance of the machine learning model, wherein sending the request for the site-specific data is triggered based on the performance being below a threshold level.

28. The apparatus of claim 24, wherein the estimating or the predicting is associated with wireless communications between the apparatus and the network entity.

29. A method for performing wireless communications at a network entity, the method comprising: obtaining site-specific data associated with a geographic location; sending the site-specific data to a user equipment (UE); as well as An indication is received from the UE associated with adapting a machine learning model at the UE based on the site-specific data, the machine learning model being used to estimate or predict at least one characteristic associated with wireless communication between the network entity and the UE.

30. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: obtaining site-specific data associated with a geographic location; sending the site-specific data to a user equipment (UE); as well as An indication is received from the UE associated with adapting a machine learning model at the UE based on the site-specific data, the machine learning model being used to estimate or predict at least one characteristic associated with wireless communication between the device and the UE.

Images