Machine learning feedback between network entities

Abstract

In general, various aspects of the present disclosure relate to wireless communications. In some aspects, a source network entity may send a message to a recipient network entity, the message including a request for machine learning feedback associated with an artificial intelligence / machine learning action triggered by the source network entity. Thus, the source network entity may receive machine learning feedback in response to the request. In some aspects, the machine learning feedback is included in a category 2 message that is data type agnostic from a recipient network entity. Numerous other aspects are described.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims the benefit of Indian Provisional Patent Application No. 202321007830, filed on February 7, 2023, and entitled “MACHINE LEARNING FEEDBACK BETWEEN NETWORK ENTITIES,” which is assigned to the assignee of this application. The disclosure of the prior application is considered a part of and incorporated by reference into this patent application. Technical Field

[0003] Generally speaking, aspects of the present disclosure relate to wireless communications, and to techniques and apparatus for sending and receiving machine learning feedback between network entities. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcasts. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies 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, single-carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and long term evolution (LTE). LTE / LTE-Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0005] A wireless network may include one or more network nodes that support communications for wireless communication devices, such as user equipment (UE) or multiple UEs. A UE may communicate with a network node via downlink and uplink communications. A "downlink" (or "DL") refers to the communication link from a network node to a UE, while an "uplink" (or "UL") refers to the communication link from a UE to a network node. Some wireless networks may support device-to-device communications, such as via a local link (e.g., a sidelink (SL), a wireless local area network (WLAN) link, and / or a wireless personal area network (WPAN) link, etc.).

[0006] The above multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different UEs to communicate at a city, country, region and / or global level. New Radio (NR) (which may be referred to as 5G) is a set of enhancements to the LTE mobile standard released by 3GPP. NR is designed to better integrate with other open standards by improving spectrum efficiency, reducing costs, improving services, utilizing new spectrum, and using orthogonal frequency division multiplexing (OFDM) (CP-OFDM) with a cyclic prefix (CP) on the downlink, and using CP-OFDM and / or single carrier frequency division multiplexing (SC-FDM) (also known as discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink, as well as supporting beamforming, multiple input multiple output (MIMO) antenna technology and carrier aggregation to better support mobile broadband Internet access. As the demand for mobile broadband access continues to grow, further improvements to LTE, NR and other radio access technologies remain useful. Summary of the Invention

[0007] Some aspects described herein relate to an apparatus for communication at a source network entity. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be individually or collectively configured to send a message to a recipient network entity, the message including a request for machine learning feedback associated with an artificial intelligence / machine learning (AI / ML) action triggered by the source network entity. The one or more processors may be individually or collectively configured to receive machine learning feedback in response to the request.

[0008] Some aspects described herein relate to an apparatus for communication at a receiving network entity. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be individually or collectively configured to receive a message from a source network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. The one or more processors may be individually or collectively configured to send the machine learning feedback in response to the request.

[0009] Some aspects described herein relate to an apparatus for communication at a source network entity. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be individually or collectively configured to send a request for machine learning feedback to a recipient network entity. The one or more processors may be individually or collectively configured to receive, in response to the request, a Category 2 message from the recipient network entity that is data type agnostic and includes machine learning feedback.

[0010] Some aspects described herein relate to an apparatus for communication at a receiving network entity. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be individually or collectively configured to receive a request for machine learning feedback from a source network entity. The one or more processors may be individually or collectively configured to respond to the request and send a Category 2 message to the source network entity that is data type agnostic and includes machine learning feedback.

[0011] Some aspects described herein relate to a method of communication performed by a source network entity. The method may include sending a message to a recipient network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. The method may include receiving the machine learning feedback in response to the request.

[0012] Some aspects described herein relate to a method of communication performed by a receiving network entity. The method may include receiving a message from a source network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. The method may include sending the machine learning feedback in response to the request.

[0013] Some aspects described herein relate to a method of communication performed by a source network entity. The method may include sending a request for machine learning feedback to a recipient network entity. The method may include responding to the request and receiving a Category 2 message from the recipient network entity that is data type agnostic and includes the machine learning feedback.

[0014] Some aspects described herein relate to a method of communication performed by a receiving network entity. The method may include receiving a request for machine learning feedback from a source network entity. The method may include responding to the request and sending a Category 2 message to the source network entity that is data type agnostic and includes the machine learning feedback.

[0015] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for communication by a source network entity. When executed by one or more processors of the source network entity, the instruction set may cause the source network entity to send a message to a recipient network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. When executed by one or more processors of the source network entity, the instruction set may cause the source network entity to receive machine learning feedback in response to the request.

[0016] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for communication by a receiving network entity. When executed by one or more processors of the receiving network entity, the set of instructions may cause the receiving network entity to receive a message from a source network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. When executed by one or more processors of the receiving network entity, the set of instructions may cause the receiving network entity to send the machine learning feedback in response to the request.

[0017] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for communication by a source network entity. When executed by one or more processors of the source network entity, the set of instructions may cause the source network entity to send a request for machine learning feedback to a recipient network entity. When executed by one or more processors of the source network entity, the set of instructions may cause the source network entity to respond to the request and receive a Category 2 message from the recipient network entity that is data type agnostic and includes machine learning feedback.

[0018] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for communication by a receiving network entity. When executed by one or more processors of the receiving network entity, the set of instructions may cause the receiving network entity to receive a request for machine learning feedback from a source network entity. When executed by one or more processors of the receiving network entity, the set of instructions may cause the receiving network entity to respond to the request and send a Category 2 message to the source network entity that is data type agnostic and includes machine learning feedback.

[0019] Some aspects described herein relate to an apparatus for communication. The apparatus may include means for sending a message to a recipient network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the apparatus. The apparatus may include means for receiving the machine learning feedback in response to the request.

[0020] Some aspects described herein relate to an apparatus for communication. The apparatus may include means for receiving a message from a source network entity, the message including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity. The apparatus may include means for sending the machine learning feedback in response to the request.

[0021] Some aspects described herein relate to an apparatus for communication. The apparatus may include means for sending a request for machine learning feedback to a recipient network entity. The apparatus may include means for responding to the request and receiving a Category 2 message from the recipient network entity that is data type agnostic and includes machine learning feedback.

[0022] Some aspects described herein relate to an apparatus for communication. The apparatus may include means for receiving a request for machine learning feedback from a source network entity. The apparatus may include means for responding to the request and sending a Category 2 message to the source network entity that is data type agnostic and includes machine learning feedback.

[0023] The various aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, network entities, network nodes, wireless communication devices, and / or processing systems as fully described herein with reference to and as illustrated by the accompanying figures and description.

[0024] The features and technical advantages of the examples according to the present disclosure have been outlined quite broadly above so that the detailed description below may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be readily 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. The characteristics of the concepts disclosed herein (both their organization and method of operation) and the associated advantages will be better understood from the description below when considered in conjunction with the accompanying drawings. Each of the figures in the accompanying drawings is provided for the purpose of illustration and description and not as a definition of limitations to the claims.

[0025] Although various aspects are described in this disclosure by the explanation of some examples, it will be understood by those skilled in the art that such aspects can be realized in many different arrangements and scenarios. Different platform types, devices, systems, shapes, sizes and / or packaging arrangements can be used to realize the technology described herein. For example, some aspects can be realized via integrated chip embodiments and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment and / or artificial intelligence equipment). Various aspects can be realized 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 described aspects and features may include additional components and features for the realization and practice of the claimed and described aspects. 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). It is intended that the various aspects described herein can be practiced in various devices, components, systems, distributed arrangements, and / or end-user devices having different sizes, shapes, and configurations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order that the above-mentioned features of the present disclosure may be fully understood, a more detailed description of the content briefly summarized above may be obtained by reference to various aspects (some of which are shown in the accompanying drawings). However, it should be noted that the accompanying drawings illustrate only certain typical aspects of the present disclosure and are therefore not to be considered as limiting the scope thereof, as the description may allow other equally effective aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0027] Figure 1 is a schematic diagram illustrating an example of a wireless network according to the present disclosure.

[0028] Figure 2 is a schematic diagram illustrating an example of communication between a network node and a user equipment in a wireless network according to the present disclosure.

[0029] Figure 3 is a schematic diagram illustrating an example decomposed base station architecture according to the present disclosure.

[0030] Figure 4 is a diagram illustrating an example of requesting and sending artificial intelligence / machine learning information according to the present disclosure.

[0031] Figure 5 is a diagram illustrating an example associated with requesting machine learning feedback according to the present disclosure.

[0032] Figure 6 is a diagram illustrating an example associated with requesting machine learning feedback according to the present disclosure.

[0033] Figure 7 is a diagram illustrating an example associated with sending machine learning feedback according to the present disclosure.

[0034] Figure 8 、 Figure 9 、 Figure 10 and Figure 11 is a diagram illustrating example processes associated with sending and receiving machine learning feedback in accordance with the present disclosure.

[0035] Figure 12 is a schematic diagram of an example apparatus for wireless communication according to the present disclosure. DETAILED DESCRIPTION

[0036] Various aspects relate generally to wireless communications and, more particularly, to artificial intelligence / machine learning (AI / ML) actions. Some aspects relate more particularly to including a request for machine learning feedback in an AI / ML action execution message. For example, a source network entity may send an AI / ML action execution message based on output from a computer algorithm that triggered the AI / ML action. Thus, the source network entity may request machine learning feedback to validate the AI / ML action. Additionally, some aspects relate more particularly to providing machine learning feedback using a data type-agnostic Category 2 message. For example, a receiving network entity may send a Category 2 message in response to a request for machine learning feedback.

[0037] Certain aspects of the subject matter described in this disclosure can be implemented to achieve one or more of the following potential advantages. For example, a source network entity can improve a computer algorithm based on machine learning feedback (e.g., via retraining) to optimize future decisions. As a result, the improved computer algorithm can trigger future AI / ML actions that save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications.

[0038] Various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure can be embodied in many different forms and should not be construed as being limited to any specific structure or function presented throughout the present disclosure. On the contrary, these aspects are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. It should be understood by those skilled in the art that the scope of the present disclosure is intended to cover any aspect of the disclosure disclosed herein, whether it is implemented independently of any other aspect of the disclosure or implemented in combination with any other aspect of the disclosure. For example, a device can be implemented or a method can be practiced using any number of aspects set forth herein. In addition, the scope of the present disclosure is intended to cover such devices or methods that are practiced using other structures, functionality, or structure and functionality in addition to or different from the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein can be embodied by one or more elements of the claims.

[0039] Several aspects of telecommunications systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0040] Although various aspects may be described herein using terminology generally associated with 5G or New Radio (NR) radio access technology (RAT), various aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or post-5G RATs (e.g., 6G).

[0041] Figure 11 is a schematic diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, etc., or may include elements of a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, etc. The wireless network 100 may include one or more network nodes 110 (illustrated as network node 110a, network node 110b, network node 110c, and network node 110d), user equipment (UE) 120 or multiple UEs 120 (illustrated as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other entities. The network node 110 is a network node that communicates with the UE 120. As shown in the figure, the network node 110 may include one or more network nodes. For example, the network node 110 may be a converged network node, meaning that the converged network node is configured to utilize a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node (e.g., within a single device or unit). As another example, the network node 110 may be a disaggregated network node (sometimes referred to as a disaggregated base station), meaning that the network node 110 is configured to utilize a protocol stack that is physically or logically distributed between two or more nodes, such as one or more central units (CUs), one or more distributed units (DUs), or one or more radio units (RUs).

[0042] In some examples, the network node 110 is or includes a network node that communicates with the UE 120 via a radio access link (such as an RU). In some examples, the network node 110 is or includes a network node that communicates with other network nodes 110 via a fronthaul link or a midhaul link (such as a DU). In some examples, the network node 110 is or includes a network node that communicates with other network nodes 110 via a midhaul link or communicates with the core network via a backhaul link (such as a CU). In some examples, the network node 110 (such as an aggregated network node 110 or a decomposed network node 110) may include multiple network nodes, such as one or more RUs, one or more CUs, and / or one or more DUs. The network node 110 may include, for example, an NR base station, an LTE base station, a Node B, an eNB (e.g., in 4G), a gNB (e.g., in 5G), an access point, a transmit receive point (TRP), a DU, an RU, a CU, a mobility element of the network, a core network node, a network element, a network device, a RAN node, or a combination thereof. In some examples, network nodes 110 may be interconnected to each other or to one or more other network nodes 110 in wireless network 100 over various types of fronthaul, midhaul, and / or backhaul interfaces (such as direct physical connections, air interfaces, or virtual networks) using any suitable transport network.

[0043] In some examples, network node 110 can provide communication coverage for a particular geographic area. In the Third Generation Partnership Project (3GPP), the term "cell" can refer to the coverage area of ​​a network node 110 and / or a network node subsystem serving that coverage area, depending on the context in which the term is used. Network node 110 can provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell can cover a relatively large geographic area (e.g., a radius of several kilometers) and can allow unrestricted access by UEs 120 with service subscriptions. A pico cell can cover a relatively small geographic area and can allow unrestricted access by UEs 120 with service subscriptions. A femto cell can cover a relatively small geographic area (e.g., a residence) and can allow restricted access by UEs 120 associated with the femto cell (e.g., UEs 120 in a closed subscriber group (CSG)). A network node 110 for a macro cell can be referred to as a macro network node. A network node 110 for a pico cell can be referred to as a pico network node. The network node 110 for a femto cell may be referred to as a femto network node or an in-home network node. Figure 1 In the example shown, network node 110a may be a macro network node for macro cell 102a, network node 110b may be a pico network node for pico cell 102b, and network node 110c may be a femto network node for femto cell 102c. A network node may support one or more (e.g., three) cells. In some examples, a cell may not necessarily be stationary, and the geographic area of ​​a cell may move depending on the location of a mobile network node 110 (e.g., a mobile network node).

[0044] In some aspects, the term "base station" or "network node" may refer to a converged base station, a decomposed base station, an integrated access and backhaul (IAB) node, a relay node, or one or more components thereof. For example, in some aspects, a "base station" or "network node" may refer to a CU, a DU, a RU, a near real-time (near-RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC, or a combination thereof. In some aspects, the term "base station" or "network node" may refer to a device configured to perform one or more functions (such as those described herein in conjunction with network node 110). In some aspects, the term "base station" or "network node" may refer to multiple devices configured to perform one or more functions. For example, in some distributed systems, each of a number of different devices (which may be located in the same geographic location or in different geographic locations) may be configured to perform at least a portion of a function or replicate the execution of at least a portion of a function, and the term "base station" or "network node" may refer to any one or more of those different devices. In some aspects, the term "base station" or "network node" may refer to one or more virtual base stations or one or more virtual base station functions. For example, in some aspects, two or more base station functions may be instantiated on a single device. In some aspects, the term "base station" or "network node" may refer to one of the base station functions but not the other. In this manner, a single device may include more than one base station.

[0045] The wireless network 100 may include one or more relay stations. A relay station is a network node that can receive transmissions of data from an upstream node (e.g., a network node 110 or a UE 120) and send transmissions of data to a downstream node (e.g., a UE 120 or a network node 110). A relay station may be a UE 120 that can relay transmissions for other UEs 120. Figure 1 In the example shown, a network node 110d (e.g., a relay network node) may communicate with a network node 110a (e.g., a macro network node) and a UE 120d to facilitate communications between the network node 110a and the UE 120d. A network node 110 that relays communications may be referred to as a relay station, a relay base station, a relay network node, a relay node, a relay, etc.

[0046] The wireless network 100 may be a heterogeneous network including different types of network nodes 110 (such as macro network nodes, pico network nodes, femto network nodes, and relay network nodes). These different types of network nodes 110 may have different transmit power levels, different coverage areas, and / or different impacts on interference in the wireless network 100. For example, a macro network node may have a high transmit power level (e.g., 5 to 40 watts), while a pico network node, a femto network node, and a relay network node may have a lower transmit power level (e.g., 0.1 to 2 watts).

[0047] The network controller 130 may be coupled to or in communication with a group of network nodes 110 and may provide coordination and control for these network nodes 110. The network controller 130 may communicate with the network nodes 110 via a backhaul communication link or a mid-range communication link. The network nodes 110 may communicate with each other directly or indirectly via a wireless or wired backhaul communication link. In some aspects, the network controller 130 may be or include a CU or a core network device.

[0048] UEs 120 may be dispersed throughout wireless network 100, and each UE 120 may be stationary or mobile. UEs 120 may include, for example, access terminals, terminals, mobile stations, and / or subscriber units. UEs 120 may be cellular phones (e.g., smartphones), personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, laptop computers, cordless phones, wireless local loop (WLL) stations, tablet computers, cameras, gaming devices, netbooks, smartbooks, ultrabooks, medical devices, biometric devices, wearable devices (e.g., smart watches, smart clothing, smart glasses, smart wristbands, smart jewelry (e.g., smart rings or smart bracelets)), entertainment devices (e.g., music devices, video devices, and / or satellite radio units), vehicle components or sensors, smart meters / sensors, industrial manufacturing equipment, global positioning system devices, UE functionality of a network node, and / or any other suitable device configured to communicate via a wireless or wired medium.

[0049] Some UEs 120 may be considered machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags that can communicate with a network node, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered Internet of Things (IoT) devices and / or may be implemented as NB-IoT (narrowband IoT) devices. Some UEs 120 may be considered customer premises equipment. UE 120 may be included within a housing that houses components of UE 120 (such as a processor component and / or a memory component). In some examples, the processor component and the memory component may be coupled together. For example, the processor component (e.g., one or more processors) and the memory component (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0050] In general, any number of wireless networks 100 may be deployed in a given geographic area. Each wireless network 100 may support a specific RAT and may operate on one or more frequencies. A RAT may be referred to as a radio technology, air interface, etc. A frequency may be referred to as a carrier, frequency channel, etc. Each frequency may support a single RAT in a given geographic area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks may be deployed.

[0051] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) can communicate directly using one or more sidelink channels (e.g., without using network node 110 as an intermediary for communicating with each other). For example, UE 120 can communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks. In such examples, UE 120 can perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by network node 110.

[0052] Devices of the wireless network 100 may communicate using an electromagnetic spectrum, which may be subdivided into various categories, bands, channels, etc., by frequency or wavelength. For example, devices of the wireless network 100 may communicate using one or more operating bands. In 5G NR, two initial operating bands have been identified with the frequency range names FR1 (410 MHz–7.125 GHz) and FR2 (24.25 GHz–52.6 GHz). It should be understood that although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the “Sub-6 GHz” band in various documents and articles. Similar naming issues sometimes arise with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz–300 GHz), which is identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0053] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands of these mid-band frequencies as the frequency range designation FR3 (7.125 GHz–24.25 GHz). Frequency bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operation to above 52.6 GHz. For example, three higher operating bands have been identified as the frequency range designations FR4a or FR4-1 (52.6 GHz–71 GHz), FR4 (52.6 GHz–114.25 GHz), and FR5 (114.25 GHz–300 GHz). Each of these higher frequency bands falls within the EHF band.

[0054] With the foregoing in mind, unless otherwise specifically stated, it will be understood that the terms "sub-6 GHz," etc., if used herein, may broadly refer to frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. Furthermore, unless otherwise explicitly stated, it will be understood that the terms "millimeter wave," etc., if used herein, may broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR4-a, FR4-1, and / or FR5, or may be within the EHF band. It is contemplated that the frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) may be modified, and that the techniques described herein are applicable to those modified frequency ranges.

[0055] In some aspects, network controller 130 may include communication manager 140. As described in more detail elsewhere herein, communication manager 140 may send a message (e.g., to a recipient network entity) including a request for machine learning feedback associated with an AI / ML action triggered by network controller 130 and may receive machine learning feedback in response to the request. The machine learning feedback may be included in a data type-agnostic Category 2 message (e.g., from the recipient network entity). Alternatively, as described in more detail elsewhere herein, communication manager 140 may receive a message (e.g., from a source network entity) including a request for machine learning feedback associated with an AI / ML action (e.g., triggered by a source network entity) and may send machine learning feedback in response to the request. The machine learning feedback may be included in a data type-agnostic Category 2 message (e.g., to the source network entity). Additionally or alternatively, communication manager 140 may perform one or more other operations described herein.

[0056] In some aspects, network node 110 may include a communications manager 150. As described in greater detail elsewhere herein, communications manager 150 may send a message (e.g., to a recipient network entity) including a request for machine learning feedback associated with an AI / ML action triggered by network node 110 and may receive machine learning feedback in response to the request. The machine learning feedback may be included in a data type-agnostic Category 2 message (e.g., from the recipient network entity). Alternatively, as described in greater detail elsewhere herein, communications manager 150 may receive a message (e.g., from a source network entity) including a request for machine learning feedback associated with an AI / ML action (e.g., triggered by a source network entity) and may send machine learning feedback in response to the request. The machine learning feedback may be included in a data type-agnostic Category 2 message (e.g., to the source network entity). Additionally or alternatively, communications manager 150 may perform one or more other operations described herein.

[0057] As pointed out above, Figure 1 is provided as an example. Other examples may be Figure 1 The examples described are different.

[0058] Figure 22 is a diagram illustrating an example 200 of a network node 110 communicating with a UE 120 in a wireless network 100 according to the present disclosure. The network node 110 may be equipped with a set of antennas 234a through 234t, such as T antennas (T ≥ 1). The UE 120 may be equipped with a set of antennas 252a through 252r, such as R antennas (R ≥ 1). The network node 110 of example 200 includes one or more radio frequency components, such as antennas 234 and a modem 232. In some examples, the network node 110 may include an interface, a communication component, or another component that facilitates communication with the UE 120 or another network node. Some network nodes 110 may not include radio frequency components, such as one or more CUs or one or more DUs, that facilitate direct communication with the UE 120.

[0059] At network node 110, transmit processor 220 may receive data intended for UE 120 (or a set of UEs 120) from data source 212. Transmit processor 220 may select one or more modulation and coding schemes (MCS) for UE 120 based at least in part on one or more channel quality indicators (CQIs) received from UE 120. Network node 110 may process (e.g., encode and modulate) the data for UE 120 based at least in part on the MCS selected for UE 120 and may provide data symbols for UE 120. Transmit processor 220 may process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling), and provide overhead symbols and control symbols. The transmit processor 220 may generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) 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., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, if applicable, and may provide a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modems) (shown as modems 232a through 232t). For example, each output symbol stream may be provided to a modulator component (shown as MOD) of the modem 232. Each modem 232 may process a corresponding output symbol stream (e.g., for OFDM) using a corresponding modulator component to obtain an output sample stream. Each modem 232 may further process (e.g., convert to analog, amplify, filter, and / or upconvert) the output sample stream using a corresponding modulator component to obtain a downlink signal. The modems 232a through 232t may transmit a set of downlink signals (eg, T downlink signals) via a corresponding set of antennas 234 (eg, T antennas) (shown as antennas 234a through 234t).

[0060] At the UE 120, a set of antennas 252 (shown as antennas 252a through 252r) may receive downlink signals from the network node 110 and / or other network nodes 110 and may provide a set of received signals (e.g., R received signals) to a set of modems 254 (e.g., R modems) (shown as modems 254a through 254r). For example, each received signal may be provided to a demodulator component (shown as DEMOD) of the modem 254. Each modem 254 may use a corresponding demodulator component to condition (e.g., filter, amplify, downconvert, and / or digitize) the received signal to obtain input samples. Each modem 254 may further process the input samples (e.g., for OFDM) using the demodulator component to obtain received symbols. A MIMO detector 256 may obtain received symbols from the modem 254, perform MIMO detection on the received symbols (if applicable), and provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, may provide decoded data for the UE 120 to a data sink 260, and may provide decoded control information and system information to the controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine, among other things, a reference signal received power (RSRP) parameter, a received signal strength indicator (RSSI) parameter, a reference signal received quality (RSRQ) parameter, and / or a CQI parameter. In some examples, one or more components of the UE 120 may be included in a housing 284.

[0061] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. For example, the network controller 130 may include one or more devices in a core network. The network controller 130 may communicate with the network node 110 via the communication unit 294.

[0062] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include or be included within one or more antenna panels, one or more antenna groups, one or more sets of antenna elements, and / or one or more antenna arrays, etc. The antenna panels, antenna groups, sets of antenna elements, and / or antenna arrays may include one or more antenna elements (within a single housing or multiple housings), sets of coplanar antenna elements, sets of non-coplanar antenna elements, and / or be coupled to one or more transmit and / or receive components (such as antennas). Figure 2 One or more antenna elements of one or more components in.

[0063] On the uplink, at the UE 120, 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, and / or CQI) from the controller / processor 280. The transmit processor 264 may generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be precoded by the TX MIMO processor 266 (if applicable), further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to the network node 110. In some examples, the modem 254 of the UE 120 may include a modulator and a demodulator. In some examples, the UE 120 includes a transceiver. The transceiver may include any combination of an antenna 252, a modem 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, and / or a TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and memory 282 to perform aspects of any of the methods described herein (e.g., with reference to Figure 5-Figure 12 ).

[0064] At the network node 110, uplink signals from the UE 120 and / or other UEs may be received by an antenna 234, processed by a modem 232 (e.g., a demodulator component (shown as DEMOD) of the modem 232), detected by a MIMO detector 236 (if applicable), and further processed by a receive processor 238 to obtain decoded data and control information sent by the UE 120. The receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to a controller / processor 240. The network node 110 may include a communication unit 244 and may communicate with the network controller 130 via the communication unit 244. The network node 110 may include a scheduler 246 to schedule one or more UEs 120 for downlink and / or uplink communications. In some examples, the modem 232 of the network node 110 may include a modulator and a demodulator. In some examples, the network node 110 includes a transceiver. The transceiver may include any combination of antenna 234, modem 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein (e.g., with reference to FIG. Figure 5-Figure 12 ).

[0065] The controller / processor 240 of the network node 110, the controller / controller 280 of the UE 120, and / or Figure 2 Any other component of may perform one or more techniques associated with sending and receiving machine learning feedback between network entities, as described in more detail elsewhere herein. For example, the controller / processor 240 of the network node 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other component of the Figure 8 The process of 800 Figure 9 The process of 900 Figure 10 The process of 1000 Figure 11 110 and / or other processes as described herein. Memory 242 and memory 282 may store data and program codes for network node 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, the one or more instructions, when executed (e.g., directly or after compilation, conversion, and / or interpretation) by one or more processors of network node 110 and / or UE 120, may cause the one or more processors, UE 120, and / or network node 110 to perform or direct, for example, Figure 8 The process of 800 Figure 9 The process of 900 Figure 10 The process of 1000 Figure 11 In some aspects, the source network entity described herein is a network node 110, included in the network node 110, including Figure 2 One or more components of the network node 110 shown in FIG. 1 are a network controller 130, are included in a network controller 130, or include Figure 2 Similarly, the receiving network entity described herein is the network node 110, included in the network node 110, including one or more components of the network controller 130 shown in FIG. Figure 2 One or more components of the network node 110 shown in FIG. 1 are a network controller 130, are included in the network controller 130, or include Figure 2 One or more components of the network controller 130 shown in .

[0066] In some aspects, a source network entity (e.g., Figure 12The network node 110, network controller 130, and / or apparatus 1200 of the source network entity may include: means for sending a message (e.g., to a receiving network entity) including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity; and / or means for receiving machine learning feedback in response to the request. Additionally or alternatively, the source network entity may include means for sending (e.g., to a receiving network entity) a request for machine learning feedback and / or means for receiving a category 2 message (e.g., from the receiving network entity) that is data type agnostic and includes machine learning feedback in response to the request. In some aspects, means for the source network entity to perform the operations described herein may include, for example, one or more of the communications manager 150, the transmit processor 220, the TX MIMO processor 230, the modem 232, the antenna 234, the MIMO detector 236, the receive processor 238, the controller / processor 240, the memory 242, or the scheduler 246. Alternatively, means for the source network entity to perform the operations described herein may include, for example, one or more of the communication manager 140 , the controller / processor 290 , the memory 292 , or the communication unit 294 .

[0067] In some aspects, a receiving network entity (e.g., network node 110, network controller 130, and / or Figure 12 The apparatus 1200 of the embodiment of the present invention may include means for receiving a message (e.g., from the source network entity) including a request for machine learning feedback associated with an AI / ML action triggered by the source network entity and / or means for sending the machine learning feedback in response to the request. Additionally or alternatively, the receiving network entity may include means for receiving (e.g., from the source network entity) a request for machine learning feedback and / or means for sending (e.g., to the source network entity) a Category 2 message that is data type agnostic and includes the machine learning feedback in response to the request. In some aspects, the means for the receiving network entity to perform the operations described herein may include, for example, one or more of the communications manager 150, the transmit processor 220, the TX MIMO processor 230, the modem 232, the antenna 234, the MIMO detector 236, the receive processor 238, the controller / processor 240, the memory 242, or the scheduler 246. Alternatively, means for the recipient network entity to perform the operations described herein may include, for example, one or more of the communication manager 140 , the controller / processor 290 , the memory 292 , or the communication unit 294 .

[0068] In some aspects, an individual processor may perform all of the functions described as being performed by one or more processors. In some aspects, one or more processors may collectively perform a set of functions. For example, a first set of (one or more) processors of the one or more processors may perform a first function described as being performed by the one or more processors, and a second set of (one or more) processors of the one or more processors may perform a second function described as being performed by the one or more processors. The first set of processors and the second set of processors may be the same set of processors, or may be different sets of processors. References to "one or more processors" should be understood to refer to the combination of Figure 2 Any one or more processors in the processors described. References to "one or more memories" should be understood to refer to any one or more memories of the corresponding device, such as in conjunction with Figure 2 For example, functions described as being performed by one or more memories may be performed by the same subset of the one or more memories or by a different subset of the one or more memories.

[0069] Although Figure 2 The blocks in FIG. 2 are shown as distinct components, but the functionality described above with respect to these blocks may be implemented in a single hardware, software, or combined component, or in various combinations of components. For example, the functionality described with respect to the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 may be performed by or under the control of the controller / processor 280.

[0070] As pointed out above, Figure 2 is provided as an example. Other examples may be Figure 2 The examples described are different.

[0071] The deployment of a communication system (such as a 5G NR system) can be arranged in a variety of ways with various components or parts. In a 5G NR system or network, a network node, a network entity, a mobility element of the network, a RAN node, a core network node, a network element, a base station or a network device can be implemented in an aggregated or decomposed architecture. For example, a base station (such as a node B (NB), an evolved NB (eNB), an NR base station, a 5G NB, an access point (AP), a TRP or a cell, etc.) or one or more units (or one or more components) that perform base station functionality can be implemented as an aggregated base station (also known as an independent base station or a monolithic base station) or a decomposed base station. "Network entity" or "network node" may refer to a decomposed base station, or to one or more units of a decomposed base station (such as one or more CUs, one or more DUs, one or more RUs, or a combination thereof).

[0072] A converged base station (e.g., a converged network node) can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node (e.g., within a single device or unit). A decomposed base station (e.g., a decomposed network node) can be configured to utilize a protocol stack that is physically or logically distributed between two or more units (such as one or more CUs, one or more DUs, or one or more RUs). In some examples, the CU can be implemented within a network node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually distributed in one or more other network nodes. The DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual unit, such as a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0073] Base station type operation or network design can take into account the aggregated nature of base station functionality. For example, a disaggregated base station can be utilized in an IAB network, an open radio access network (O-RAN (such as a network configuration sponsored by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)) to facilitate scaling of the communication system by separating base station functionality into one or more units that can be deployed individually. A disaggregated base station can include functionality implemented on two or more units at various physical locations, as well as functionality implemented virtually for at least one unit, which can enable flexibility in network design. Various units of the disaggregated base station can be configured for wired or wireless communication with at least one other unit of the disaggregated base station.

[0074] Figure 3 is a diagram illustrating an example decomposed base station architecture 300 according to the present disclosure. The decomposed base station architecture 300 may include a CU 310, which may communicate directly with a core network 320 via a backhaul link or indirectly with the core network 320 through one or more decomposed control units (such as a near-RT RIC 325 via an E2 link, or a non-RT RIC 315 associated with a service management and orchestration (SMO) framework 305, or both). The CU 310 may communicate with one or more DUs 330 via corresponding mid-haul links (such as via an F1 interface). Each of the DUs 330 may communicate with one or more RUs 340 via a respective fronthaul link. Each of the RUs 340 may communicate with one or more UEs 120 via a corresponding radio frequency (RF) access link. In some implementations, a UE 120 may be served simultaneously by multiple RUs 340.

[0075] Each of the units (including the CU 310, DU 330, RU 340, and near-RT RIC 325, non-RT RIC 315, and SMO framework 305) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of the units, or an associated processor or controller that provides instructions to one or more communication interfaces of the corresponding unit, may be configured to communicate with one or more of the other units via a transmission medium. In some examples, each of the units may include a wired interface and a wireless interface (which may include a receiver, transmitter, or transceiver (such as an RF transceiver)), the wired interface being configured to receive or send signals to one or more of the other units via a wired transmission medium, and the wireless interface being configured to receive or send signals to one or more of the other units via a wireless transmission medium.

[0076] In some aspects, the CU 310 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC) functions, packet data convergence protocol (PDCP) functions, or service data adaptation protocol (SDAP) functions, among others. Each control function may be implemented using an interface configured to transmit signals to other control functions hosted by the CU 310. The CU 310 may be configured to handle user plane functionality (e.g., central unit-user plane (CU-UP) functionality), control plane functionality (e.g., central unit-control plane (CU-CP) functionality), or a combination thereof. In some implementations, the CU 310 may be logically divided 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. The CU 310 may be implemented to communicate with the DU 330 as needed for network control and signaling.

[0077] Each DU 330 may correspond to a logical unit that includes one or more base station functions to control the operation of one or more RUs 340. In some aspects, depending at least in part on a functional partition (such as that defined by 3GPP), the DU 330 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more higher physical (PHY) layers. In some aspects, the one or more higher PHY layers may be implemented by one or more modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc. In some aspects, the DU 330 may also host one or more lower PHY layers (such as by one or more modules for fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, or physical random access channel (PRACH) extraction and filtering). Each layer (which may also be referred to as a module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by the DU 330 or with control functions hosted by the CU 310.

[0078] Each RU 340 may implement lower layer functionality. In some deployments, a RU 340 controlled by a DU 330 may correspond to a logical node that hosts RF processing functions or low PHY layer functions, such as performing FFT, performing iFFT, digital beamforming, or PRACH extraction and filtering, etc., based on a functional partition (e.g., a functional partition defined by 3GPP) (such as a lower layer functional partition). In such an architecture, each RU 340 may be operated to handle over-the-air (OTA) communications with one or more UEs 120. In some implementations, real-time and non-real-time aspects of control and user plane communications with the RU 340 may be controlled by the corresponding DU 330. In some scenarios, this configuration may enable each DU 330 and CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0079] The SMO framework 305 can be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO framework 305 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via an operations and maintenance interface (such as the O1 interface). For virtualized network elements, the SMO framework 305 can be configured to interact with a cloud computing platform (such as the Open Cloud (O-Cloud) platform 390) via a cloud computing platform interface (such as the O2 interface) to perform network element lifecycle management (such as instantiating virtualized network elements). Such virtualized network elements can include, but are not limited to, CU 310, DU 330, RU 340, non-RT RIC 315, and near-RT RIC 325. In some implementations, the SMO framework 305 can communicate with hardware aspects of the 4G RAN (such as open eNB (O-eNB) 311) via the O1 interface. Additionally, in some implementations, the SMO framework 305 can communicate directly with each of the one or more RUs 340 via a corresponding O1 interface. The SMO framework 305 can also include a non-RT RIC 315 configured to support the functionality of the SMO framework.

[0080] The non-RT RIC 315 may be configured to include logic functions that implement non-real-time control and optimization of RAN elements and resources, 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 in communication 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 implement near-real-time control and optimization of RAN elements and resources via data collection and actions over an interface connecting one or more CUs 310, one or more DUs 330, or both, and an O-eNB with the near-RT RIC 325 (such as via an E2 interface).

[0081] In some implementations, the non-RT RIC 315 can receive parameters or external enrichment information from an external server to generate an AI / ML model to be deployed in the near-RT RIC 325. Such information can be utilized by the near-RT RIC 325 and can 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 can be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 can monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions through the SMO framework 305 (such as via reconfiguration of the O1 interface) or through the creation of RAN management policies (such as A1 interface policies).

[0082] As pointed out above, Figure 3 is provided as an example. Other examples may be Figure 3 The examples described are different.

[0083] Figure 4 is a diagram illustrating an example 400 of requesting and sending AI / ML information according to the present disclosure. Figure 4 As shown, source network entity 401 and recipient network entity 403 can communicate with each other (e.g., over a wireless or wired backhaul). Source network entity 401 may include a network node (e.g., a next generation (NG) RAN (NG-RAN) node), a RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320). Similarly, recipient network entity 403 may include a network node (e.g., an NG-RAN node), a RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320).

[0084] As shown in reference numeral 405, the source network entity 401 may send an AI / ML information request (e.g., a data collection request, as defined in the 3GPP specification), and the receiving network entity 403 may receive the AI / ML information request. As used herein, "artificial intelligence / machine learning" or "AI / ML" refers to automated decision-making techniques and includes computer algorithms configured to automatically improve performance without explicit programming, such as supervised learning algorithms, unsupervised learning algorithms, and reinforcement learning algorithms. The AI / ML information request may indicate one or more types of measurements being requested (e.g., CQI, precoding matrix indicator (PMI), layer indicator (LI), rank indicator (RI), RSRP, RSSI, and / or another type of measurement). The source network entity 401 may send the AI / ML information request based on the type of measurement used as input to the computer algorithm (e.g., during training of the algorithm or during deployment of the algorithm).

[0085] The AI / ML information request may be a Category 1 message. As used herein, "Category 1" refers to a message that has a corresponding response (e.g., an acknowledgment indicating success or failure) during the process. On the other hand, "Category 2" refers to a message that does not have a corresponding response during the process.

[0086] As shown by reference numeral 410, the receiving network entity 403 may send an AI / ML information response (e.g., a data collection response, as defined in the 3GPP specification), and the source network entity 401 may receive the AI / ML information response. For example, the AI / ML information response may include one or more measurement values ​​for the type of measurement requested in the AI / ML information request. Thus, the source network entity 401 may use the measurement values ​​to train a computer algorithm and / or apply the computer algorithm to make a decision.

[0087] In some aspects, the source network entity 401 may send an AI / ML information request to receive the measurement values ​​once. Alternatively, the source network entity 401 may send an AI / ML information request to receive the measurement values ​​in response to an event (e.g., event A1, event A2, event A3, event A4, event A5, event A6, event B1, or event B2, etc., as defined in the 3GPP specification). Additionally or alternatively, the source network entity 401 may send an AI / ML information request to receive the measurement values ​​periodically. Thus, as indicated by reference numeral 415, the receiving network entity 403 may send an AI / ML information update (e.g., a data collection update, as defined in the 3GPP specification) based on the triggering event and / or periodicity indicated in the AI / ML information request, and the source network entity 401 may receive the AI / ML information update. The receiving network entity 403 may continue to send additional AI / ML information updates (eg, based on a triggering event and / or periodically) until the source network entity 401 sends an additional AI / ML information request that triggers the receiving network entity 403 to stop sending AI / ML information updates.

[0088] As mentioned above, an AI / ML Information Response may be a Category 1 message. On the other hand, an AI / ML Information Update may be a Category 2 message.

[0089] After training and / or deploying the computer algorithm, the source network entity may determine to verify the output from the computer algorithm (e.g., the action triggered by the computer algorithm). For example, the computer algorithm may make a decision to perform a handover (e.g., a handover of a UE), perform an RRC release (e.g., an RRC release of the UE), shut down or deactivate a cell, add or activate a cell, adjust the steering of a radio beam, add or remove a carrier (e.g., when using carrier aggregation (CA)), add or remove a secondary node, and / or modify mobility parameters, etc. Without verifying the actions triggered by the computer algorithm, the source network entity cannot improve the computer algorithm (e.g., via retraining). As a result, the source network entity may continue to make suboptimal decisions using the computer algorithm, which wastes power, wastes processing resources, increases latency, reduces throughput, and / or reduces the quality and reliability of wireless communications.

[0090] Some of the techniques and apparatus described herein enable a source network entity (e.g., a network node 110 (such as an NG-RAN node)) to include a request for machine learning feedback in an AI / ML action execution message. Thus, the source network entity can validate actions triggered by a computer algorithm based on the machine learning feedback. As a result, the source network entity can improve the computer algorithm (e.g., via retraining) to optimize future decisions and thereby save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications. Additionally, some of the techniques and apparatus described herein enable a recipient network entity (e.g., a network node 110 (such as an NG-RAN node)) to send a data type-agnostic Category 2 message with machine learning feedback. As a result, the source network entity can use the machine learning feedback to improve the computer algorithm (e.g., via retraining) to optimize future decisions and thereby save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications.

[0091] As pointed out above, Figure 4 is provided as an example. Other examples may be Figure 4 The examples described are different.

[0092] Figure 5 is a diagram illustrating an example 500 associated with requesting machine learning feedback according to the present disclosure. Figure 5 As shown, source network entity 401 and recipient network entity 403 can communicate with each other (e.g., over a wireless or wired backhaul). Source network entity 401 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320). Similarly, recipient network entity 403 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320).

[0093] As shown by reference numeral 505, the source network entity 401 may send an AI / ML action execution message and the recipient network entity 403 may receive the AI / ML action execution message. For example, the source network entity 401 may receive output from a computer algorithm that triggers an AI / ML action. The AI / ML action may include handover of a UE (e.g., UE 120), RRC release of a UE (e.g., UE 120), deactivation or deactivation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or activation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), adjustment of a beam (e.g., transmitted by the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or removal of a carrier (e.g., when CA is being used), addition or removal of a secondary node (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), and / or modification of mobility parameters (e.g., associated with the UE), etc.

[0094] In some implementations, the AI / ML action execution message may include a cause value (e.g., an integer associated with a cause category). Thus, the AI / ML action execution message may include a cause value indicating that the AI / ML action was triggered by machine learning. For example, the source network entity 401 may select a codepoint for the cause value based on a computer algorithm that triggers the AI / ML action. The source network entity 401 may select the codepoint based on a data structure stored in a memory of the source network entity 401 that associates cause value codepoints with cause categories (e.g., according to a 3GPP specification and / or another standard).

[0095] Additionally or alternatively, the AI / ML action execution message may include a request for machine learning feedback associated with the AI / ML action. For example, the machine learning feedback may include at least one UE-related metric (e.g., average packet delay, average downlink (DL) throughput, average uplink (UL) throughput, and / or average packet error rate, etc.) and / or at least one cell-related metric (e.g., resource status of a neighboring NG-RAN node (such as the receiving network entity 403 or an entity communicating with the receiving network entity 403), cell performance data, and / or energy efficiency data, etc.). The request may be an information element (IE) in the AI / ML action execution message (e.g., an AI / ML measurement ID IE, as defined in the 3GPP specification). The IE may indicate which metrics are requested. Additionally, the IE may indicate whether the machine learning feedback should be one-time, periodic, or event-driven.

[0096] As shown at 510, the receiving network entity 403 may send an acknowledgment of the AI / ML action execution message, and the source network entity 401 may receive the acknowledgment of the AI / ML action execution message. The AI / ML action execution message may include an Xn (or X2) message, such that the acknowledgment is an Xn (or X2) acknowledgment signal. Based on the AI / ML action execution message, as shown at 515, the source network entity 401 and the receiving network entity 403 may execute the AI / ML action. For example, the source network entity 401 and the receiving network entity 403 may exchange one or more messages to execute the AI / ML action, as described above.

[0097] As indicated by reference numeral 520, the receiving network entity 403 may send machine learning feedback and the source network entity 401 may receive the machine learning feedback. For example, the receiving network entity 403 may send the machine learning feedback after the AI / ML action and based on the request in the AI / ML action execution message. The machine learning feedback may be included in a Category 2 message (e.g., a data collection response or a data collection update, as defined in the 3GPP specification). In some aspects, the Category 2 message may be data agnostic. Thus, the receiving network entity 403 may encode the machine learning feedback into the message regardless of which UE-related metrics and / or cell-related metrics were requested by the source network entity 401.

[0098] Although example 500 depicts one-time feedback, other examples may include the receiving network entity 403 sending the machine learning feedback based on a triggering event and / or periodicity indicated in the request, and the source network entity 401 receiving the machine learning feedback. For example, the receiving network entity 403 may continue to send the machine learning feedback (e.g., based on the triggering event and / or periodicity) until the source network entity 401 sends an indication that triggers the receiving network entity 403 to stop sending the machine learning feedback.

[0099] By using a combination of Figure 5 Using the techniques described above, the source network entity 401 can improve the computer algorithm based on machine learning feedback (e.g., via retraining) to optimize future decisions. As a result, the source network entity 401 can use the improved computer algorithm to save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications.

[0100] As pointed out above, Figure 5 is provided as an example. Other examples may be Figure 5 The examples described are different.

[0101] Figure 66 is a diagram illustrating an example 600 associated with requesting machine learning feedback according to the present disclosure. Figure 6 As shown, source network entity 401 and recipient network entity 403 can communicate with each other (e.g., over a wireless or wired backhaul). Source network entity 401 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320). Similarly, recipient network entity 403 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320).

[0102] As shown by reference numeral 605, the source network entity 401 may send an AI / ML information request, and the recipient network entity 403 may receive the AI / ML information request. Figure 4 As shown in reference numeral 405, the AI / ML information request may be a Category 1 message. The AI / ML information request may include one or more measurement identifications (IDs) associated with one or more types of measurements being requested. The measurement ID may be an alphanumeric identifier associated with the corresponding type of measurement.

[0103] In some aspects, the AI / ML information request may also include an indication that the measurement configuration is associated with the AI / ML action. For example, the AI / ML information request may include an explicit indication, such as an IE that associates a measurement ID with a deactivated state (e.g., as defined in a 3GPP specification and / or another standard). Alternatively, the AI / ML information request may include an implicit indication (e.g., because some measurement IDs are associated with AI / ML actions while other measurement IDs are not associated with AI / ML actions). Thus, when a measurement ID is associated with a deactivated state (e.g., because the measurement ID is associated with feedback for an AI / ML action), the receiving network entity 403 refrains from sending one or more measurement values ​​based on the measurement ID. Additionally, the receiving network entity 403 may send machine learning feedback in response to the AI / ML action execution message, as described below (e.g., following the AI / ML information request).

[0104] As shown at reference numeral 610, the receiving network entity 403 may send an AI / ML information response (e.g., a data collection response, as defined in the 3GPP specification), and the source network entity 401 may receive the AI / ML information response. In some aspects, the AI / ML information response may include one or more measurement values ​​for the type of measurement requested in the AI / ML information request. Thus, the source network entity 401 may use the measurement values ​​to train a computer algorithm and / or apply the computer algorithm to make a decision.

[0105] When the measurement type corresponding to the measurement ID is associated with a deactivated state, the AI / ML information response may acknowledge the AI / ML information request without including any measurement values. The AI / ML information request may include an Xn (or X2) message, such that the acknowledgement is an Xn (or X2) acknowledgement signal. In some aspects, the AI / ML information request may indicate that one or more first measurement types are associated with a deactivated state, while now requesting one or more second measurement types. Thus, the AI / ML information response may include one or more measurement values ​​for the second measurement type but not for the first measurement type.

[0106] In some aspects, as shown by reference numeral 615, the receiving network entity 403 may send an AI / ML information update (e.g., a data collection update, as defined in the 3GPP specification), and the source network entity 401 may receive the AI / ML information update. The AI / ML information update may be sent based on a triggering event and / or periodically (e.g., as indicated in an AI / ML information request). In some aspects, the receiving network entity 403 may continue to send additional AI / ML information updates (e.g., based on a triggering event and / or periodically) until the source network entity 401 sends an additional AI / ML information request that triggers the receiving network entity 403 to stop sending AI / ML information updates.

[0107] As shown at reference numeral 620, source network entity 401 may send an AI / ML action execution message and recipient network entity 403 may receive the AI / ML action execution message. For example, source network entity 401 may receive output from a computer algorithm that triggers an AI / ML action. The AI / ML action may include handover of a UE (e.g., UE 120), RRC release of a UE (e.g., UE 120), deactivation or deactivation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or activation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), adjustment of a beam (e.g., transmitted by the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or removal of a carrier (e.g., when CA is being used), addition or removal of a secondary node (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), and / or modification of mobility parameters (e.g., associated with the UE). In some implementations, and as in combination with Figure 5 As described in reference numeral 505 , the AI / ML action execution message may include a reason value (e.g., an integer associated with a reason category) indicating that the AI / ML action was triggered by machine learning.

[0108] Additionally or alternatively, the AI / ML action execution message may include a request for machine learning feedback associated with the AI / ML action. The request may be an IE in the AI / ML action execution message (e.g., an AI / ML measurement ID IE, as defined in the 3GPP specification). The IE may include one or more measurement IDs previously indicated by the source network entity 401 (e.g., in the AI / ML information request, as described in conjunction with reference numeral 605). Additionally, in some aspects, the AI / ML action execution message may associate the measurement ID with an activation state. Thus, the receiving network entity 403 may initiate one or more measurements corresponding to the measurement ID based on the association of the measurement ID with the activation state.

[0109] As shown at 625, the receiving network entity 403 may send an acknowledgment of the AI / ML action execution message, and the source network entity 401 may receive the acknowledgment of the AI / ML action execution message. The AI / ML action execution message may include an Xn (or X2) message, such that the acknowledgment is an Xn (or X2) acknowledgment signal. Based on the AI / ML action execution message, as shown at 630, the source network entity 401 and the receiving network entity 403 may execute the AI / ML action. For example, the source network entity 401 and the receiving network entity 403 may exchange one or more messages to execute the AI / ML action, as described above.

[0110] As indicated by reference numeral 635, the receiving network entity 403 may send machine learning feedback and the source network entity 401 may receive the machine learning feedback. For example, the receiving network entity 403 may send the machine learning feedback after the AI / ML action and based on the request in the AI / ML action execution message. The machine learning feedback may be included in a Category 2 message (e.g., a data collection response or a data collection update, as defined in the 3GPP specification). In some aspects, the Category 2 message may be data agnostic. Thus, the receiving network entity 403 may encode the machine learning feedback into the message regardless of which UE-related metrics and / or cell-related metrics were requested by the source network entity 401.

[0111] Although example 600 describes one-time feedback, other examples may include the receiving network entity 403 sending the machine learning feedback based on a triggering event and / or periodicity indicated in the request, and the source network entity 401 receiving the machine learning feedback. For example, the receiving network entity 403 may continue to send the machine learning feedback (e.g., based on a triggering event and / or periodicity) until the source network entity 401 sends an indication that triggers the receiving network entity 403 to stop sending the machine learning feedback.

[0112] By using a combination of Figure 6 Using the techniques described above, the source network entity 401 can improve the computer algorithm based on machine learning feedback (e.g., via retraining) to optimize future decisions. As a result, the source network entity 401 can use the improved computer algorithm to save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications.

[0113] As pointed out above, Figure 6 is provided as an example. Other examples may be Figure 6 The examples described are different.

[0114] Figure 7 is a diagram illustrating an example 700 associated with sending machine learning feedback according to the present disclosure. Figure 7As shown, source network entity 401 and recipient network entity 403 can communicate with each other (e.g., over a wireless or wired backhaul). Source network entity 401 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320). Similarly, recipient network entity 403 can include a network node (e.g., an NG-RAN node), an RU (e.g., RU 340), a DU (e.g., DU 330), a CU (e.g., CU 310), and / or a portion of a core network (e.g., core network 320).

[0115] As shown at reference numeral 705, source network entity 401 may send an AI / ML action execution message and recipient network entity 403 may receive the AI / ML action execution message. For example, source network entity 401 may receive output from a computer algorithm that triggers an AI / ML action. The AI / ML action may include handover of a UE (e.g., UE 120), RRC release of a UE (e.g., UE 120), deactivation or deactivation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or activation of a cell (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), adjustment of a beam (e.g., transmitted by the receiving network entity 403 and / or controlled by the receiving network entity 403), addition or removal of a carrier (e.g., when CA is being used), addition or removal of a secondary node (e.g., including the receiving network entity 403 and / or controlled by the receiving network entity 403), and / or modification of mobility parameters (e.g., associated with the UE), etc.

[0116] As shown at 710, the receiving network entity 403 may send an acknowledgment of the AI / ML action execution message, and the source network entity 401 may receive the acknowledgment of the AI / ML action execution message. The AI / ML action execution message may include an Xn (or X2) message, such that the acknowledgment is an Xn (or X2) acknowledgment signal. Based on the AI / ML action execution message, as shown at 715, the source network entity 401 and the receiving network entity 403 may execute the AI / ML action. For example, the source network entity 401 and the receiving network entity 403 may exchange one or more messages to execute the AI / ML action, as described above.

[0117] As shown by reference numeral 720, the source network entity 401 may send an AI / ML information request, and the recipient network entity 403 may receive the AI / ML request. Figure 4As described in reference numeral 405 of the AI / ML information request, the AI / ML information request may be a category 1 message. The AI / ML information request may further include a request for machine learning feedback associated with the AI / ML action. For example, the machine learning feedback may include at least one UE-related metric (e.g., average packet delay, average DL throughput, average UL throughput, and / or average packet error rate, etc.) and / or at least one cell-related metric (e.g., resource status of a neighboring NG-RAN node (such as the receiving network entity 403 or an entity communicating with the receiving network entity 403), cell performance data, and / or energy efficiency data, etc.). The request may be an IE in the AI / ML information request (e.g., an AI / ML feedback IE to be defined in a 3GPP specification and / or another standard). The IE may indicate which metrics are requested. Additionally, the IE may indicate whether the machine learning feedback should be one-time, periodic, or event-driven.

[0118] Alternatively, the request for machine learning feedback may be sent in a separate message. For example, the source network entity 401 may send a Category 1 message (e.g., as defined in a 3GPP specification and / or another standard) and the recipient network entity 403 may receive the Category 1 message to request machine learning feedback.

[0119] As indicated by reference numeral 725, the receiving network entity 403 may send an AI / ML information response (e.g., a data collection response or a data collection update, as defined in the 3GPP specification), and the source network entity 401 may receive the AI / ML information response. In some aspects, the AI / ML information response may include one or more measurement values ​​for the type of measurement requested in the AI / ML information request. Thus, the source network entity 401 may use the measurement values ​​to train a computer algorithm and / or apply the computer algorithm to make a decision.

[0120] As indicated by reference numeral 730, the receiving network entity 403 may send machine learning feedback, and the source network entity 401 may receive the machine learning feedback. For example, the receiving network entity 403 may send the machine learning feedback based on the request in the AI / ML information request. The machine learning feedback may be included in a Category 2 message (e.g., a data collection response or a data collection update, as defined in the 3GPP specification). In some aspects, the Category 2 message may be data agnostic. Thus, the receiving network entity 403 may encode the machine learning feedback into the message regardless of which UE-related metrics and / or cell-related metrics were requested by the source network entity 401.

[0121] Although example 700 depicts one-time feedback, other examples may include the receiving network entity 403 sending the machine learning feedback based on a triggering event and / or periodicity indicated in the request, and the source network entity 401 receiving the machine learning feedback. For example, the receiving network entity 403 may continue to send the machine learning feedback (e.g., based on a triggering event and / or periodicity) until the source network entity 401 sends an indication that triggers the receiving network entity 403 to stop sending the machine learning feedback.

[0122] By using a combination of Figure 7 Using the techniques described above, the source network entity 401 can improve the computer algorithm based on machine learning feedback (e.g., via retraining) to optimize future decisions. As a result, the source network entity 401 can use the improved computer algorithm to save power, save processing resources, reduce latency, increase throughput, and / or improve the quality and reliability of wireless communications.

[0123] As pointed out above, Figure 7 is provided as an example. Other examples may be Figure 7 The examples described are different.

[0124] Figure 8 8 is a diagram illustrating an example process 800 performed, for example, by a source network entity according to the present disclosure. The example process 800 is a diagram illustrating an example process 800 performed by a source network entity (eg, source network entity 401 and / or Figure 12 An example of a device 1200) performing operations associated with sending and receiving machine learning feedback.

[0125] like Figure 8 As shown, in some aspects, process 800 may include sending a message (e.g., to a recipient network entity 403) that includes a request for machine learning feedback associated with an AI / ML action triggered by a source network entity (block 810). For example, the source network entity (e.g., using sending component 1204 and / or communication manager 1206, as shown in FIG. Figure 12 ) can send a message that includes a request for machine learning feedback associated with an AI / ML action triggered by a source network entity, as described herein.

[0126] like Figure 8 As further shown, in some aspects, process 800 may include receiving machine learning feedback in response to the request (block 820). For example, the source network entity (e.g., using receiving component 1202 and / or communication manager 1206, such as Figure 12 ) can receive machine learning feedback in response to the request, as described herein.

[0127] Process 800 may include additional aspects, such as any single aspect or any combination of the aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0128] In a first aspect, the source network entity comprises a RAN node.

[0129] In a second aspect, alone or in combination with the first aspect, the source network entity comprises a CU.

[0130] In a third aspect, alone or in combination with one or more of the first and second aspects, the source network entity comprises a DU.

[0131] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the message comprises an AI / ML action execution message for the AI / ML action.

[0132] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the request includes an IE within the AI / ML action execution message indicating the type of machine learning feedback being requested.

[0133] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the request comprises an indication of a measurement ID previously indicated by the source network entity.

[0134] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, the process 800 includes sending (e.g., using the sending component 1204 and / or the communication manager 1206) an AI / ML information request including an explicit or implicit indication that a measurement configuration is associated with an AI / ML action, wherein the AI / ML action execution message activates reporting, and the machine learning feedback is received in response to the AI / ML action execution message.

[0135] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the AI / ML action execution message includes a cause value indicating that the AI / ML action is triggered by machine learning.

[0136] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the AI / ML action includes handover of the UE or activation of a cell.

[0137] although Figure 8 Example blocks of process 800 are shown, but in some aspects process 800 may include Figure 8The blocks depicted in the process 800 may include additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner than those depicted in the process 800. Additionally or alternatively, two or more blocks of the blocks in the process 800 may be executed in parallel.

[0138] Figure 9 9 is a diagram illustrating an example process 900 performed, for example, by a receiving network entity according to the present disclosure. The example process 900 is a diagram illustrating an example process 900 performed by a receiving network entity (e.g., receiving network entity 403 and / or Figure 12 An example of a device 1200) performing operations associated with sending and receiving machine learning feedback.

[0139] like Figure 9 As shown, in some aspects, process 900 may include receiving a message (e.g., from source network entity 401) that includes a request for machine learning feedback associated with an AI / ML action triggered by the source network entity (block 910). For example, the receiving network entity (e.g., using receiving component 1202 and / or communication manager 1206, as shown) may include receiving a message (e.g., from source network entity 401) that includes a request for machine learning feedback associated with an AI / ML action triggered by the source network entity (block 910). Figure 12 ) can receive a message that includes a request for machine learning feedback associated with an AI / ML action triggered by a source network entity, as described herein.

[0140] like Figure 9 As further shown, in some aspects, process 900 may include sending machine learning feedback in response to the request (block 920). For example, the receiving network entity (e.g., using sending component 1204 and / or communication manager 1206, such as Figure 12 ) can send machine learning feedback in response to the request, as described herein.

[0141] Process 900 may include additional aspects, such as any single aspect or any combination of the aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0142] In a first aspect, the recipient network entity comprises a RAN node.

[0143] In a second aspect, alone or in combination with the first aspect, the receiving network entity comprises a CU.

[0144] In a third aspect, alone or in combination with one or more of the first and second aspects, the receiving network entity comprises a DU.

[0145] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the message comprises an AI / ML action execution message for the AI / ML action.

[0146] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the request includes an IE within the AI / ML action execution message indicating the type of machine learning feedback being requested.

[0147] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the request includes an indication of a measurement IE previously indicated to the recipient network entity.

[0148] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 900 includes receiving (e.g., using receiving component 1202 and / or communication manager 1206) an AI / ML information request including an explicit or implicit indication that a measurement configuration is associated with an AI / ML action, wherein the AI / ML action execution message activates reporting and the machine learning feedback is sent in response to the AI / ML action execution message.

[0149] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the AI / ML action execution message includes a cause value indicating that the AI / ML action is triggered by machine learning.

[0150] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the AI / ML action includes handover of the UE or activation of a cell.

[0151] In a tenth aspect, alone or in combination with one or more of aspects 1 to 9, the machine learning feedback is sent according to a periodicity.

[0152] In an eleventh aspect, alone or in combination with one or more of aspects one to ten, the machine learning feedback is sent in response to an event.

[0153] although Figure 9 Example blocks of process 900 are shown, but in some aspects process 900 may include Figure 9 The blocks depicted in process 900 may include additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner than those depicted in process 900. Additionally or alternatively, two or more blocks of the blocks in process 900 may be executed in parallel.

[0154] Figure 10 1 is a diagram illustrating an example process 1000 performed, for example, by a source network entity according to the present disclosure. The example process 1000 is a process performed by a source network entity (eg, source network entity 401 and / or Figure 12 An example of a device 1200) performing operations associated with sending and receiving machine learning feedback.

[0155] like Figure 10 As shown, in some aspects, process 1000 may include sending (e.g., to a recipient network entity 403) a request for machine learning feedback (block 1010). For example, a source network entity (e.g., using sending component 1204 and / or communication manager 1206, such as Figure 12 ) can send a request for machine learning feedback, as described herein.

[0156] like Figure 10 As further shown, in some aspects, process 1000 may include receiving a category 2 message (e.g., from a recipient network entity 403) that is data type agnostic and includes machine learning feedback in response to the request (block 1020). For example, the source network entity (e.g., using receiving component 1202 and / or communication manager 1206, such as Figure 12 ) can receive a category 2 message in response to the request that is data type agnostic and includes machine learning feedback, as described herein.

[0157] Process 1000 may include additional aspects, such as any single aspect or any combination of the aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0158] In a first aspect, the request for machine learning feedback is included in a Category 1 message requesting measurements for training.

[0159] In a second aspect, alone or in combination with the first aspect, the request is included in an AI / ML action execution message associated with an AI / ML action triggered by the source network entity.

[0160] In a third aspect, alone or in combination with one or more of the first and second aspects, the category 2 messages are sent according to a periodicity.

[0161] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the category 2 message is sent in response to an event.

[0162] although Figure 10 Example blocks of process 1000 are shown, but in some aspects process 1000 may include blocks related to Figure 10 The blocks depicted in the process 1000 may include additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner. Additionally or alternatively, two or more blocks of the blocks in process 1000 may be executed in parallel.

[0163] Figure 11is a diagram illustrating an example process 1100 performed, for example, by a receiving network entity according to the present disclosure. The example process 1100 is a diagram illustrating an example process 1100 performed by a receiving network entity (e.g., receiving network entity 403 and / or Figure 12 An example of a device 1200) performing operations associated with sending and receiving machine learning feedback.

[0164] like Figure 11 As shown, in some aspects, process 1100 may include receiving (e.g., from source network entity 401) a request for machine learning feedback (block 1110). For example, a receiving network entity (e.g., using receiving component 1202 and / or communication manager 1206, such as Figure 12 ) can receive requests for machine learning feedback, as described herein.

[0165] like Figure 11 As further shown, in some aspects, process 1100 may include sending a category 2 message (e.g., to source network entity 401) that is data type agnostic and includes machine learning feedback in response to the request (block 1120). For example, a receiving network entity (e.g., using sending component 1204 and / or communication manager 1206, such as Figure 12 ) can send a category 2 message in response to the request that is data type agnostic and includes machine learning feedback, as described herein.

[0166] Process 1100 may include additional aspects, such as any single aspect or any combination of the aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0167] In a first aspect, the request for machine learning feedback is included in a Category 1 message requesting measurements for training.

[0168] In a second aspect, alone or in combination with the first aspect, the request is included in an AI / ML action execution message associated with an AI / ML action triggered by the source network entity.

[0169] In a third aspect, alone or in combination with one or more of the first and second aspects, the category 2 messages are sent according to a periodicity.

[0170] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the category 2 message is sent in response to an event.

[0171] although Figure 11 Example blocks of process 1100 are shown, but in some aspects process 1100 may include Figure 11The blocks depicted in the process 1100 may include additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner. Additionally or alternatively, two or more blocks in the process 1100 may be executed in parallel.

[0172] Figure 12 1 is a diagram of an example apparatus 1200 for wireless communication according to the present disclosure. Apparatus 1200 may be a network entity, or a network entity may include apparatus 1200. In some aspects, apparatus 1200 includes a receiving component 1202, a sending component 1204, and / or a communication manager 1206, which may communicate with each other (e.g., via one or more buses and / or one or more other components). In some aspects, communication manager 1206 is a communication manager that is configured to communicate with one another. Figure 1 The communication manager 140 or the communication manager 150 is depicted. As shown, the apparatus 1200 can communicate with another apparatus 1208, such as a UE or a network node, such as a CU, DU, RU, or base station, using a receiving component 1202 and a sending component 1204.

[0173] In some aspects, the apparatus 1200 may be configured to perform the Figure 5-Figure 7 Additionally or alternatively, the apparatus 1200 may be configured to perform one or more of the processes described herein, such as Figure 8 The process of 800 Figure 9 The process of 900 Figure 10 The process of 1000 Figure 11 In some aspects, Figure 12 The apparatus 1200 and / or one or more components shown in FIG. 1 may include a combination of Figure 2 Additionally or alternatively, Figure 12 One or more of the components shown in the Figure 2 In addition or alternatively, one or more components in the component set may be implemented at least in part as software stored in a memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0174] The receiving component 1202 may receive communications, such as reference signals, control information, data communications, or a combination thereof, from the apparatus 1208. The receiving component 1202 may provide the received communications to one or more other components of the apparatus 1200. In some aspects, the receiving component 1202 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications and may provide the processed signals to one or more other components of the apparatus 1200. In some aspects, the receiving component 1202 may include a combination of Figure 2 One or more antennas, modems, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described network entities.

[0175] The transmitting component 1204 may transmit communications, such as reference signals, control information, data communications, or a combination thereof, to the apparatus 1208. In some aspects, one or more other components of the apparatus 1200 may generate communications and may provide the generated communications to the transmitting component 1204 for transmission to the apparatus 1208. In some aspects, the transmitting component 1204 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding) on ​​the generated communications and may transmit the processed signals to the apparatus 1208. In some aspects, the transmitting component 1204 may include a combination of Figure 2 One or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the described network entities. In some aspects, the transmitting component 1204 can be co-located with the receiving component 1202 in a transceiver.

[0176] The communication manager 1206 can support the operation of the receiving component 1202 and / or the sending component 1204. For example, the communication manager 1206 can receive information associated with configuring the reception of communications by the receiving component 1202 and / or the sending of communications by the sending component 1204. Additionally or alternatively, the communication manager 1206 can generate and / or provide control information to the receiving component 1202 and / or the sending component 1204 to control the receipt and / or sending of communications.

[0177] In some aspects, apparatus 1200 can include, or be included in, a source network entity. Thus, sending component 1204 can send (e.g., to apparatus 1208) a message including a request for machine learning feedback associated with an AI / ML action triggered by apparatus 1200. Receiving component 1202 can receive (e.g., from apparatus 1208) machine learning feedback in response to the request. In some aspects, the machine learning feedback can be included in a data type-agnostic Category 2 message.

[0178] In some aspects, the sending component 1204 can further send an AI / ML information request including an explicit or implicit indication that the measurement configuration is associated with the AI / ML action. Thus, the AI / ML action performed message can activate reporting, and the receiving component 1202 can receive machine learning feedback in response to the AI / ML action performed message.

[0179] In some aspects, apparatus 1200 can include, or be included in, a receiving network entity. Thus, receiving component 1202 can receive a message (e.g., from apparatus 1208) comprising a request for machine learning feedback associated with an AI / ML action triggered by apparatus 1208. Sending component 1204 can send (e.g., to apparatus 1208) the machine learning feedback in response to the request. In some aspects, the machine learning feedback can be included in a data type-agnostic Category 2 message.

[0180] In some aspects, receiving component 1202 can further receive an AI / ML information request including an explicit or implicit indication that a measurement configuration is associated with an AI / ML action. Accordingly, the AI / ML action performed message can activate reporting, and sending component 1204 can send machine learning feedback in response to the AI / ML action performed message.

[0181] exist Figure 12 The number and arrangement of components shown in the FIG are provided as examples. In practice, there may be Figure 12 Components may be additional, fewer, different, or arranged differently than those shown in FIG. Figure 12 Two or more components shown in may be implemented in a single component, or in Figure 12 A single component shown in can be implemented as multiple distributed components. Additionally or alternatively, Figure 12 The assembly of (one or more) components shown in the FIGURES may perform the operations described by Figure 12 Another collection of components shown in FIG.

[0182] The following provides a summary of some aspects of the disclosure:

[0183] Aspect 1: A method of communication performed by a source network entity, comprising: sending a message to a recipient network entity, the message including a request for machine learning feedback associated with an artificial intelligence / machine learning (AI / ML) action triggered by the source network entity; and receiving machine learning feedback in response to the request.

[0184] Aspect 2: The method according to aspect 1, wherein the source network entity comprises a radio access network node.

[0185] Aspect 3: The method according to aspect 1, wherein the source network entity comprises a central unit.

[0186] Aspect 4: The method according to aspect 1, wherein the source network entity comprises a distributed unit.

[0187] Aspect 5: The method according to any one of aspects 1 to 4, wherein the message comprises an AI / ML action execution message for the AI / ML action.

[0188] Aspect 6: The method of aspect 5, wherein the request includes an information element within the AI / ML action execution message indicating the type of machine learning feedback being requested.

[0189] Aspect 7: The method according to aspect 5, wherein the request includes an indication of a measurement identity (ID) previously indicated by the source network entity.

[0190] Aspect 8: The method according to Aspect 7 further includes: sending an AI / ML information request, the AI / ML information request including an explicit or implicit indication that the measurement configuration is associated with the AI / ML action, wherein the AI / ML action execution message further activates the reporting, and the machine learning feedback is received in response to the AI / ML action execution message.

[0191] Aspect 9: The method according to any one of aspects 5 to 8, wherein the AI / ML action execution message includes a cause value indicating that the AI / ML action is triggered by machine learning.

[0192] Aspect 10: The method according to any one of aspects 1-9, wherein the AI / ML action comprises handover of the user equipment or activation of a cell including the receiving network entity.

[0193] Aspect 11: A method of communication performed by a receiving network entity, comprising: receiving a message from a source network entity, the message comprising a request for machine learning feedback associated with an artificial intelligence / machine learning (AI / ML) action triggered by the source network entity; and sending the machine learning feedback in response to the request.

[0194] Aspect 12: The method according to aspect 11, wherein the receiving network entity comprises a radio access network node.

[0195] Aspect 13: The method according to aspect 11, wherein the receiving network entity comprises a central unit.

[0196] Aspect 14: The method according to aspect 11, wherein the receiving network entity comprises a distributed unit.

[0197] Aspect 15: The method according to any one of aspects 11-14, wherein the message comprises an AI / ML action execution message for the AI / ML action.

[0198] Aspect 16: The method of aspect 15, wherein the request includes an information element within the AI / ML action execution message indicating the type of machine learning feedback being requested.

[0199] Aspect 17: The method according to aspect 15, wherein the request includes an indication of a measurement identity (ID) previously indicated to the receiving network entity.

[0200] Aspect 18: The method according to Aspect 17 further includes: receiving an AI / ML information request that associates the measurement ID with a deactivated state, wherein the AI / ML action execution message further associates the measurement ID with an activated state, and the machine learning feedback is sent based on the activated state.

[0201] Aspect 19: The method according to any one of aspects 15 to 18, wherein the AI / ML action execution message includes a cause value indicating that the AI / ML action is triggered by machine learning.

[0202] Aspect 20: The method according to any one of aspects 11-19, wherein the AI / ML action comprises handover of the user equipment or activation of a cell comprising the receiving network entity.

[0203] Aspect 21: The method according to any one of aspects 11-20, wherein the machine learning feedback is sent on a periodic basis.

[0204] Aspect 22: The method according to any one of aspects 11-20, wherein the machine learning feedback is sent in response to an event.

[0205] Aspect 23: A method of communication performed by a source network entity, comprising: sending a request for machine learning feedback to a recipient network entity; and responding to the request and receiving a Category 2 message from the recipient network entity that is data type agnostic and includes machine learning feedback.

[0206] Aspect 24: The method of aspect 23, wherein the request for machine learning feedback is included in a category 1 message for requesting measurements for training.

[0207] Aspect 25: The method according to Aspect 23, wherein the request is included in an artificial intelligence / machine learning (AI / ML) action execution message associated with an AI / ML action triggered by the source network entity.

[0208] Aspect 26: The method according to any one of aspects 23-25, wherein the category 2 message is sent according to a periodicity.

[0209] Aspect 27: The method according to any one of aspects 23-25, wherein the category 2 message is sent in response to an event.

[0210] Aspect 28: A method of communication performed by a receiving network entity, comprising: receiving a request for machine learning feedback from a source network entity; and responding to the request and sending a Category 2 message to the source network entity that is data type agnostic and includes machine learning feedback.

[0211] Aspect 29: The method of aspect 28, wherein the request for machine learning feedback is included in a category 1 message for requesting measurements for training.

[0212] Aspect 30: The method according to Aspect 28, wherein the request is included in an artificial intelligence / machine learning (AI / ML) action execution message associated with an AI / ML action triggered by the source network entity.

[0213] Aspect 31: The method according to any one of aspects 28-30, wherein the category 2 message is sent according to a periodicity.

[0214] Aspect 32: The method according to any one of aspects 28-30, wherein the category 2 message is sent in response to an event.

[0215] Aspect 33. An apparatus for communication at a device, comprising a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform the method according to one or more of aspects 1-32.

[0216] Aspect 34: A device for communication, comprising: one or more memories; and one or more processors coupled to the one or more memories, the one or more processors being individually or collectively configured to perform the method according to one or more of aspects 1-32.

[0217] Aspect 35: An apparatus for communication, comprising at least one means for performing the method according to one or more of aspects 1-32.

[0218] Aspect 36: A non-transitory computer-readable medium storing code for communication, the code comprising instructions executable by a processor to perform the method according to one or more of aspects 1-32.

[0219] Aspect 37: A non-transitory computer-readable medium storing an instruction set for communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method according to one or more of aspects 1-32.

[0220] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practice of the various aspects.

[0221] As used herein, the term "component" is intended to be broadly interpreted as a combination of hardware and / or hardware and software. Regardless of being referred to as software, firmware, middleware, microcode, hardware description language or other names, "software" should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes and / or functions, etc. As used herein, a "processor" is implemented in a combination of hardware and / or hardware and software. It will be apparent that the system and / or method described herein can be implemented with a combination of hardware and / or hardware and software in different forms. The actual specialized control hardware or software code for implementing these systems and / or methods is not intended to limit various aspects. Therefore, the operation and behavior of the system and / or method are described herein without citing specific software code, because it will be understood by those skilled in the art that software and hardware can be designed to implement the system and / or method at least in part based on the description herein.

[0222] As used herein, "satisfying a threshold" may refer to a value being greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0223] Even if the specific combination of feature is recorded in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. Many features in these features can be combined in a manner not specifically recorded in the claims and / or not specifically disclosed in the specification. The disclosure of various aspects includes the combination of each dependent claim and each other claim in the claim set. As used herein, the phrase of "at least one of" the item list refers to any combination of these items, including single members. For example, "at least one of a, b or c" is intended to cover a, b, c, a+b, a+c, b+c and a+b+c, and any combination with the multiple of the same element (for example, a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c and c+c+c or any other sorting of a, b and c).

[0224] Any element, action or instruction used herein should not be interpreted as critical or necessary, unless clearly described as such. In addition, as used herein, the article "a" and "an" are intended to include one or more projects, and can be used interchangeably with "one or more". In addition, as used herein, the article "the" is intended to include one or more projects quoted in conjunction with the article "the", and can be used interchangeably with "one or more". In addition, as used herein, the terms "set" and "group" are intended to include one or more projects, and can be used interchangeably with "one or more". In the case of only intending a project, phrase "only one" or similar terms are used. In addition, as used herein, the term "has", "have", "having" etc. are intended to be open terms (for example, "an element having" A can also have B) that are not limited to the elements of its modification. In addition, the phrase "based on" is intended to mean "at least partially based on", unless otherwise explicitly stated. Furthermore, as used herein, the term "or" when used in a series is intended to be inclusive and can be used interchangeably with "and / or" unless expressly stated otherwise (e.g., if used in conjunction with "either" or "only one of").

Claims

1. An apparatus for communication at a source network entity, comprising: one or more memories; as well as One or more processors coupled to the one or more memories, the one or more processors being individually or collectively configured to: sending a message to a recipient network entity, the message comprising a request for machine learning feedback associated with an artificial intelligence / machine learning (AI / ML) action triggered by the source network entity; and The machine learning feedback is received in response to the request.

2. The device according to claim 1, wherein The source network entity comprises a radio access network node.

3. The device according to claim 1, wherein The source network entity comprises a central unit.

4. The device according to claim 1, wherein The source network entity includes a distributed unit.

5. The device according to claim 1, wherein The message includes an AI / ML action execution message for the AI / ML action.

6. The device according to claim 5, wherein The request includes an information element within the AI / ML action execution message that indicates the type of machine learning feedback being requested.

7. The device according to claim 5, wherein The request includes an indication of a measurement identity (ID) previously indicated by the source network entity.

8. The device according to claim 7, wherein The one or more processors are individually or collectively configured to: sending an AI / ML information request including an explicit or implicit indication that a measurement configuration is associated with said AI / ML action, Wherein the AI / ML action performed message further activates reporting, and the machine learning feedback is received in response to the AI / ML action performed message.

9. The device according to claim 5, wherein The AI / ML action execution message includes a cause value indicating that the AI / ML action is triggered by machine learning.

10. The device according to claim 1, wherein The AI / ML action includes handover of a user equipment or activation of a cell including the receiving network entity.

11. An apparatus for communication at a receiving network entity, comprising: one or more memories; as well as One or more processors coupled to the one or more memories, the one or more processors being individually or collectively configured to: receiving a message from a source network entity, the message comprising a request for machine learning feedback associated with an artificial intelligence / machine learning (AI / ML) action triggered by the source network entity; and In response to the request, the machine learning feedback is sent.

12. The device according to claim 11, wherein The receiving network entity comprises a radio access network node.

13. The device according to claim 11, wherein The receiving network entity comprises a central unit.

14. The device according to claim 11, wherein The receiving network entity includes a distributed unit.

15. The device according to claim 11, wherein The message includes an AI / ML action execution message for the AI / ML action.

16. The device according to claim 15, wherein The request includes an information element within the AI / ML action execution message that indicates the type of machine learning feedback being requested.

17. The device according to claim 15, wherein The request includes an indication of a measurement identity (ID) previously indicated to the receiving network entity.

18. The device according to claim 11, wherein The AI / ML action includes handover of a user equipment or activation of a cell including the receiving network entity.

19. The device according to claim 11, wherein The machine learning feedback is sent on a periodic basis.

20. The device according to claim 11, wherein The machine learning feedback is sent in response to an event.

21. An apparatus for communication at a source network entity, comprising: one or more memories; as well as One or more processors coupled to the one or more memories, the one or more processors being individually or collectively configured to: sending a request for machine learning feedback to a recipient network entity; and In response to the request and from the recipient network entity, a category 2 message is received that is data type agnostic and includes the machine learning feedback.

22. The device according to claim 21, wherein The request for machine learning feedback is included in a Category 1 message requesting measurements for training.

23. The device according to claim 21, wherein The request is included in an artificial intelligence / machine learning (AI / ML) action execution message associated with an AI / ML action triggered by the source network entity.

24. The apparatus according to claim 21, wherein The category 2 messages are sent on a periodic basis.

25. The apparatus according to claim 21, wherein The Category 2 messages are sent in response to events.

26. An apparatus for communication at a receiving network entity, comprising: one or more memories; as well as One or more processors coupled to the one or more memories, the one or more processors being individually or collectively configured to: receiving a request for machine learning feedback from a source network entity; and In response to the request and to the source network entity, a category 2 message is sent that is data type agnostic and includes the machine learning feedback.

27. The device according to claim 26, wherein The request for machine learning feedback is included in a Category 1 message requesting measurements for training.

28. The apparatus according to claim 26, wherein The request is included in an artificial intelligence / machine learning (AI / ML) action execution message associated with an AI / ML action triggered by the source network entity.

29. The apparatus according to claim 26, wherein The category 2 messages are sent on a periodic basis.

30. The apparatus of claim 26, wherein: The Category 2 messages are sent in response to events.

Images