Artificial intelligence model delivery via radio data plane
By establishing data radio bearers directly with user equipment through radio access network nodes and bypassing user plane functions, the problem of low transmission efficiency of artificial intelligence models is solved, and efficient and reliable model transmission is achieved in URLLC and eMBB applications.
Patent Information
- Application Number
- CN202380098816.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-04-06
- Filing Date
- 2023-10-28
- Publication Date
- 2025-12-26
AI Technical Summary
In existing technologies, when artificial intelligence models are transmitted in mobile wireless communication systems, they need to go through user plane functions, which results in low transmission efficiency and an inability to meet strict latency and reliability requirements, especially in application scenarios such as URLLC and eMBB.
By establishing a data radio bearer directly with user equipment through radio access network nodes, bypassing user plane functions, artificial intelligence model information is transmitted directly. The transmission process is optimized through data volume reports and signal strength analysis to ensure the integrity and timeliness of model information.
It enables efficient transmission of artificial intelligence models while meeting strict latency and reliability requirements, thereby improving the performance and efficiency of mobile communication systems, especially in URLLC and eMBB applications.
Smart Images

Figure CN121220176A_ABST
Abstract
Description
Cross-references to related applications
[0001] This application claims priority to U.S. nonprovisional patent application No. 18 / 296,974, filed April 6, 2023, entitled “ARTIFICIAL INTELLIGENCE MODELDELIVERY VIA RADIO DATA PLANE,” the entire contents of which are incorporated herein by reference. Background Technology
[0002] The term 'New Radio' (NR) associated with fifth-generation mobile wireless communication systems (5G) refers to aspects of technology used in the radio access network (RAN), encompassing several Quality of Service (QoS) levels, including Ultra-Reliable Low Latency Communication (URLLC), Enhanced Mobile Broadband (eMBB), and Massive Machine-Type Communication (mMTC). URLLC QoS levels are associated with stringent latency requirements (e.g., low latency or low signal / message delay) and high reliability of radio performance, while traditional eMBB use cases can be associated with high-capacity wireless communication, allowing for less stringent latency requirements (e.g., higher latency than URLLC) and lower radio performance than URLLC. mMTC performance requirements can be lower than those of eMBB use cases. Some use cases involving mobile devices or mobile user equipment (such as smartphones, wireless tablets, smartwatches, etc.) may impose varying loads or demands on a given RAN resource. Summary of the Invention
[0003] The following is a simplified overview of the disclosed subject matter to provide a basic understanding of some embodiments across the various examples. This overview is not a comprehensive summary of the various embodiments. It is neither intended to identify key or essential elements of the various embodiments nor to define the scope of the various embodiments. Its sole purpose is to present some concepts of this disclosure in a simplified form as a prelude to the more detailed description that follows.
[0004] In one embodiment, an example method includes a radio access network node including a processor determining artificial intelligence model information or updated artificial intelligence model information to be sent to a user equipment. The method may further include the radio access network node sending a data radio bearer establishment request to a control entity (e.g., a core network entity) to request a data radio bearer capable of bypassing user plane functions when sending the artificial intelligence model information. The method may also include the radio access network node receiving a data radio bearer configuration from the control entity, wherein the control entity sends the data radio bearer configuration to the radio access network node in response to the data radio bearer establishment request. The method may further include the radio access network node sending the artificial intelligence model information or updated artificial intelligence model information to the user equipment via a data radio bearer established according to the data radio bearer configuration; and the radio access network node sending a data volume report corresponding to the artificial intelligence model information or updated artificial intelligence model information to the user plane functions, and sending a data volume report corresponding to the artificial intelligence model signal or updated artificial intelligence model information to the user plane functions, the information having been sent to the user equipment but not sent to the user plane functions, not transmitted via, through, by, or otherwise combined with the user plane functions.
[0005] The data radio bearer configuration may include at least one of the following: a quality of service indicator indicating the quality of service corresponding to the updated artificial intelligence model information; a data volume reporting period indicator indicating a reporting period, wherein the radio access network node will send a data volume report according to the reporting period; or a data forwarding coverage delivery standard to be transmitted to another radio access network node other than the radio access network node, for example, when the user equipment can be switched.
[0006] Data volume reports may include at least one of the following: a data radio bearer identifier corresponding to a data radio bearer; or one or more user equipment identifiers corresponding to one or more user equipments including user equipment, wherein the radio access network node sends updated artificial intelligence model information to one or more user equipments.
[0007] In one embodiment, a data radio bearer can be established between a radio access network node and a user equipment. Data transmission via the data radio bearer can deliver data directly from the radio access network node to the user equipment without first sending the data to and receiving it back from a user plane function.
[0008] Control entities or user plane functions can be implemented by computing components in the core network that are communicatively coupled to the radio access network nodes. The transmission of artificial intelligence model information, or updated artificial intelligence model information, can be via the wireless link between the radio access network nodes and the user equipment.
[0009] The transmission of updated AI model information may include: transmitting at least one protocol data unit including the updated AI model information, wherein the transmission of the updated AI model information excludes: transmitting at least one protocol data unit that may include the updated AI model information to user plane functions. The protocol data unit may be a packet, segment, datagram, etc.
[0010] The data volume report may include a quantity indication indicating the number of units in at least one protocol data unit that includes updated AI model information. The data volume report may also include a quantity indication indicating the size of at least one protocol data unit that includes updated AI model information. The data volume report may indicate the number of bytes used to transmit AI model information or updated AI model information, or the number of packets, segments, datagrams, etc.
[0011] The example method may further include sending a coverage request from a radio access network node to a user equipment (UE), the coverage request including a request for the signal strength at the UE corresponding to the radio access network node. The method may include receiving a coverage indication from the UE by the radio access network node, the coverage indication indicating a determined signal strength corresponding to the radio access network node as determined by the UE. (It should be understood that the UE may determine and send a coverage indication indicating the determined signal strength corresponding to the radio access network node even without receiving a coverage request from the radio access network node.) The method may further include the radio access network node analyzing the determined signal strength according to a transmission criterion to obtain an analyzed determined signal strength, and the radio access network node determining the remaining portion of updated artificial intelligence model information that has not yet been sent to the UE to obtain a determined unsent portion. Based on the analyzed determined signal strength being determined to satisfy the transmission criterion, the method may further include sending the determined unsent portion to the user plane function by the radio access network node. The determined unsent portion may be sent by the radio access network node to the user plane function via a backhaul communication link. Therefore, the user plane function can be able to transmit the remaining, determined untransmitted portion of AI model information or updated AI model information to different radio access network nodes, so as to facilitate the transmission of the remaining, determined untransmitted portion to the user equipment when different radio access network nodes switch to different radio access network nodes.
[0012] In one embodiment, the method may further include the radio access network node determining a portion of the artificial intelligence model information, or updated artificial intelligence model information, that has been transmitted by the radio access network node to the user equipment, to generate a determined transmitted portion. The data volume report may include a volume indication indicating the number of at least one protocol data unit (such as a packet) that includes the determined transmitted portion.
[0013] The method may further include the radio access network node determining the portion of artificial intelligence model information or updated artificial intelligence model information that has been sent by the radio access network node to the user equipment, to generate a determined portion of the transmitted information, and the data volume report may include a volume indication indicating one or more protocol data units including the updated artificial intelligence model information.
[0014] In one embodiment, a radio access node may include a processor configured to determine data to be transmitted to a user equipment. The processor may be configured to send a data radio bearer establishment request to a control entity. In response to the data radio bearer establishment request, the processor may also be configured to receive a data radio bearer configuration from the control entity. The processor may also be configured to transmit data to the user equipment via a data radio bearer established between the radio access network node and the user equipment according to the data radio bearer configuration. The control entity may include at least one of session management functions or access and mobility functions.
[0015] The data radio bearer configuration may include a reporting period indication that instructs the radio access node to send data volume reports to the user plane function at a frequency corresponding to data transmissions from the radio access network node to the user equipment. The method may also include the radio access network node sending data volume reports to the user plane function according to the reporting period indication, corresponding to data transmissions from the radio access network node to the user equipment.
[0016] Data transmission may include: transmission of protocol data units containing data, and data transmission may exclude the following: transmission of protocol data units containing data to user plane functions.
[0017] The processor can also be configured to receive a coverage indication from the user equipment, which indicates a determined signal strength corresponding to a radio access network node. The processor can also be configured to analyze the determined signal strength according to transmission criteria (such as a signal strength threshold) to obtain the analyzed determined signal strength. The processor can be configured to determine a portion of data that has not yet been transmitted to the user equipment, to obtain the determined untransmitted data portion, and, based on the analyzed determined signal strength being determined to satisfy the transmission criteria, to transmit the determined untransmitted data portion from the radio access network node to the user plane function.
[0018] In another embodiment, a non-transitory machine-readable medium may include executable instructions that, when executed by a processor of a radio access network node, facilitate the execution of operations including receiving radio performance metrics corresponding to radio functions from a user equipment implementing radio functions based on an artificial intelligence model. The operations may include determining, based on the radio performance metrics, updated artificial intelligence model information to be sent to the user equipment for updating the artificial intelligence model, and establishing a data radio bearer between the radio access network node and the user equipment for sending the updated artificial intelligence model information to the user equipment. The operations may include sending the updated artificial intelligence model information to the user equipment via the data radio bearer without sending the updated artificial intelligence model information to user plane functions, and the radio access network node sending a data volume report corresponding to the transmission of the updated artificial intelligence model information to the user plane functions.
[0019] The operation may further include identifying untransmitted portions of the updated AI model information. The operation may also include receiving a coverage indication from the user equipment (UE) corresponding to a determined signal strength corresponding to the UE's operation with respect to a radio access network node, and analyzing the determined signal strength according to transmission criteria to obtain an analyzed determined signal strength. Based on the analyzed determined signal strength being determined to satisfy the transmission criteria, the operation may further include transmitting the untransmitted portions of the updated AI model information to the user plane function to be transmitted to another radio access node, wherein the other radio access node may then transmit the untransmitted portions of the updated AI model information to the UE. Attached Figure Description
[0020] Figure 1 The diagram illustrates the environment of a wireless communication system.
[0021] Figure 2 The illustration shows an example environment where radio functionality is implemented in conjunction with a corresponding learning model.
[0022] Figure 3AThe diagram illustrates a network environment where data is directed to user equipment via user plane functions.
[0023] Figure 3B The diagram illustrates a network environment in which data is transmitted from radio access network nodes to user equipment via user plane functions.
[0024] Figure 3C The diagram illustrates a network environment where data is transmitted from radio access network nodes to user equipment without passing through user plane functions.
[0025] Figure 4 The illustration shows a specific data radio bearer request from an example artificial intelligence model.
[0026] Figure 5 The illustration shows an example AI machine learning model data volume information report sent from a radio access network node to a user plane function.
[0027] Figure 6 The illustration shows an example environment where a user equipment receives a learning model update as it moves from the coverage of one radio access network to the coverage of another.
[0028] Figure 7 The illustration shows a timing diagram of an example method used by radio access network nodes to update the learned model at the user equipment.
[0029] Figure 8 The illustration shows a timing diagram of an example method used by a radio access network node to update a learning model at a user equipment that has moved to the coverage of another radio access network node.
[0030] Figure 9 The diagram illustrates a flowchart of an example method for updating an artificial intelligence learning model via data plane resources.
[0031] Figure 10 The diagram illustrates the example method.
[0032] Figure 11 The diagram illustrates a block diagram of an example radio access network node.
[0033] Figure 12 The diagram illustrates a block diagram of an example non-transitory machine-readable medium.
[0034] Figure 13 The illustration shows an example computer environment.
[0035] Figure 14 The diagram illustrates a block diagram of an example wireless UE. Detailed Implementation
[0036] First, those skilled in the art will readily understand that this embodiment has broad applicability and utility. In addition to those described herein, many methods, embodiments, and adaptations of this application, as well as many variations, modifications, and equivalent arrangements, will be clearly or reasonably suggested from the spirit or scope of the various embodiments of this application.
[0037] Therefore, although this application has been described in detail herein with reference to various embodiments, it should be understood that this disclosure is an illustration of one or more concepts expressed in various exemplary embodiments and is made solely to provide a complete and feasible disclosure. The following disclosure is not intended and should not be construed as limiting this application or otherwise excluding any such other embodiments, adaptations, variations, modifications, and equivalent arrangements, and the embodiments described herein are limited only by the appended claims and their equivalents.
[0038] As used in this disclosure, in some embodiments, the terms "component," "system," etc., are intended to refer to or include computer-related entities or entities associated with operating means having one or more specific functions, wherein the entity may be hardware, a combination of hardware and software, software, or executing software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, a thread of execution, computer-executable instructions, a program, and / or a computer. By way of illustration and not limitation, both an application running on a server and the server itself can be components.
[0039] One or more components may reside in a process and / or execution thread, and components may be located on a single computer and / or distributed across two or more computers. Furthermore, these components may be executed from various computer-readable media on which various data structures are stored. Components may communicate via local and / or remote processes, such as according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system, a distributed system, and / or interacting with other systems via such signals through a network such as the Internet). As another example, a component may be a device having specific functions provided by mechanical parts operated by an electrical or electronic circuit system, operated by a software or firmware application executed by a processor, wherein the processor may be internal or external to the device and executes at least a portion of the software or firmware application. As yet another example, a component may be a device providing specific functions through an electronic component without mechanical parts, the electronic component including a processor therein to execute software or firmware that at least partially endows the electronic component with the functions. While various components have been shown as separate components, it should be understood that multiple components may be implemented as a single component, or a single component may be implemented as multiple components, without departing from the exemplary embodiments.
[0040] As used herein, the term "facilitation" means that a system, device, or component "facilitates" one or more actions or operations, relating to the nature of a complex computing environment in which multiple components and / or devices may participate in some computational operations. Non-limiting examples of actions that may or may not involve multiple components and / or devices include transmitting or receiving data, establishing connections between devices, determining intermediate results for obtaining results, and so on. In this regard, a computing device or component may facilitate an operation by playing any role in accomplishing the operation. When the operation of a component is described herein, it should therefore be understood that, where an operation is described as being facilitated by a component, the operation may optionally be accomplished in cooperation with one or more other computing devices or components, such as, but not limited to, sensors, antennas, audio and / or visual output devices, other devices, etc.
[0041] Furthermore, various embodiments can be implemented as methods, apparatus, or articles of art using standard programming and / or engineering techniques to produce software, firmware, hardware, or any combination thereof, thereby controlling a computer to implement the disclosed subject matter. The term "article of art" as used herein is intended to cover a computer program accessible from any computer-readable (or machine-readable) device or computer-readable (or machine-readable) storage / communication media. For example, computer-readable storage media may include, but is not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic stripes), optical discs (e.g., compact discs (CDs), digital versatile discs (DVDs)), smart cards, and flash memory devices (e.g., cards, sticks, key drives). Of course, those skilled in the art will recognize that many modifications can be made to this configuration without departing from the scope or spirit of the various embodiments.
[0042] Artificial intelligence (AI) and machine learning (ML) models can enhance performance and operational capabilities and improve 5G implementations, such as network automation, optimized signaling overhead, energy efficiency, and maximized service capacity. AI / ML model functionality can be implemented and built in many different forms and with proprietary designs from various providers. User equipment (UEs) can be connected to or registered to the 5G radio access network (RAN) node, which can manage or control the real-time AI / ML model performance for various radio functions at different UE devices.
[0043] As disclosed herein, several embodiments facilitate the dynamic management and updating of various AI / ML models deployed at different UE devices. The network RAN can dynamically control the activation, deactivation, triggering, or updating of the learning model (which may be radio function-specific) based on the monitoring and analysis of real-time performance metrics defined corresponding to the learning model executed at the user equipment. It should be understood that even if the learning model is implementing a specific radio function, the metric being monitored or analyzed may be a learning model metric, and not necessarily a radio function metric (e.g., a mathematical / statistical metric is not necessarily a radio function metric such as signal strength).
[0044] Now turn to the attached image. Figure 1 An example of a wireless communication system 100 supporting blind decoding of the PDCCH candidate or search space according to various aspects of this disclosure is illustrated. The wireless communication system 100 may include one or more base stations 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a Long Term Evolution (LTE) network, an Advanced LTE (LTE-A) network, an LTE-A Pro network, or a New Radio (NR) network. In some examples, the wireless communication system 100 may support enhanced broadband communication, ultra-reliable (e.g., mission-critical) communication, low-latency communication, communication with low-cost and low-complexity devices, or any combination thereof. As shown, examples of UE 115 may include smartphones, cars or other vehicles, or drones or other aircraft. Another example of a UE may be a virtual reality device 117, such as smart glasses, virtual reality headsets, augmented reality headsets, and other similar devices that can provide the wearer with images, video, audio, touch, taste, or smell. The UE (such as VR device 117) can transmit or receive wireless signals with the RAN base station 105 via a long-range wireless link 125, or the UE / VR device can receive or transmit wireless signals via a short-range wireless link 137, which may include a wireless link with the UE device 115, such as a Bluetooth link, a Wi-Fi link, etc. The UE (such as device 117) can communicate simultaneously via multiple wireless links, such as via link 125 with the base station 105 and via the short-range wireless link. The VR device 117 can also communicate with the wireless UE via a cable or other wired connection. The RAN or its components may be referenced. Figure 12 It is implemented by one or more computer components as described.
[0045] Continue the discussion Figure 1Base stations 105 can be distributed throughout a geographical area to form a wireless communication system 100, and can be devices of different forms or with different capabilities. Base stations 105 and UE 115 can communicate wirelessly via one or more communication links 125. Each base station 105 can provide a coverage area 110, on which UE 115 and base station 105 can establish one or more communication links 125. Coverage area 110 can be an example of a geographical area over which base station 105 and UE 115 can support signal communication according to one or more radio access technologies.
[0046] UE 115 can be distributed throughout the coverage area 110 of the wireless communication system 100, and each UE 115 can be stationary or mobile or both at different times. UE 115 can be devices of different forms or with different capabilities. Figure 1 The diagram illustrates some example UE 115s. The UE 115 described herein can communicate with various types of devices, such as other UE 115s, base station 105, or network devices (e.g., core network nodes, relay devices, integrated access and backhaul (IAB) nodes, or other network devices). Figure 1 As shown.
[0047] Base station 105 may communicate with core network 130, or communicate with each other, or both. For example, base station 105 may interface with core network 130 via one or more backhaul links 120 (e.g., via S1, N2, N3, or other interfaces). Base station 105 may communicate with each other directly (e.g., directly between base stations 105) or indirectly (e.g., via core network 130) or both via backhaul links 120 (e.g., via X2, Xn, or other interfaces). In some examples, backhaul link 120 may include one or more radio links.
[0048] One or more base stations 105 described herein may include, or may be referred to by those skilled in the art as, base station, radio base station, access point, radio transceiver, NodeB, eNodeB (eNB), next-generation NodeB or gigabit NodeB (any of which may be referred to as bNodeB or gNB), home NodeB, home eNodeB or other suitable terms.
[0049] UE 115 may include or be referred to as a mobile device, wireless device, remote device, handheld device, or subscriber device, or some other suitable term, wherein "device" may also be referred to as a cell, station, terminal, or client, etc. UE 115 may also include or be referred to as a personal electronic device, such as a cellular phone, personal digital assistant (PDA), tablet computer, laptop computer, personal computer, or router. In some examples, UE 115 may include or be referred to as a wireless local loop (WLL) station, Internet of Things (IoT) device, Internet of Everything (IoE) device, or machine-type communication (MTC) device, etc., which can be implemented in various objects, such as appliances, vehicles, or smart meters, etc.
[0050] UE 115 can communicate with various types of devices, such as other UE 115s that can sometimes act as relays, as well as base station 105 and network devices, including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, etc. Figure 1 As shown in the image.
[0051] UE 115 and base station 105 can wirelessly communicate with each other via one or more communication links 125 on one or more carriers. The term "carrier" can refer to a set of radio frequency spectrum resources having a defined physical layer structure for supporting communication link 125. For example, a carrier for communication link 125 may include a portion of the radio frequency spectrum band (e.g., a bandwidth portion (BWP)) operating according to one or more physical layer channels of a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling coordinating carrier operation, user data, or other signaling. Wireless communication system 100 can use carrier aggregation or multi-carrier operation to support communication with UE 115. Depending on the carrier aggregation configuration, UE 115 can be configured with multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation can be used in conjunction with frequency division duplex (FDD) and time division duplex (TDD) component carriers.
[0052] In some examples (e.g., in a carrier aggregation configuration), a carrier may also have acquisition or control signaling to coordinate the operation of other carriers. A carrier may be associated with a frequency channel (e.g., an Evolved Universal Mobile Telecommunications System Terrestrial Radio Access (E-UTRA) Absolute Radio Frequency Channel Number (EARFCN)) and can be located according to a channel grating for discovery by UE 115. A carrier can operate in standalone mode, where UE 115 can initially acquire and connect via the carrier, or the carrier can operate in non-standalone mode, where different carriers (e.g., the same or different radio access technologies) are used for anchoring connections.
[0053] The communication link 125 shown in the wireless communication system 100 may include uplink transmission from UE 115 to base station 105 or downlink transmission from base station 105 to UE 115. The carrier may carry downlink or uplink communication (e.g., in FDD mode), or may be configured to carry both downlink and uplink communication (e.g., in TDD mode).
[0054] A carrier can be associated with a specific bandwidth of the radio frequency spectrum, and in some examples, the carrier bandwidth can be referred to as the carrier or the “system bandwidth” of the wireless communication system 100. For example, the carrier bandwidth can be one of several defined bandwidths of a carrier for a particular radio access technology (e.g., 1.4, 3, 5, 10, 15, 20, 40, or 80 MHz). Devices of the wireless communication system 100 (e.g., base station 105, UE 115, or both) can have a hardware configuration that supports communication on a specific carrier bandwidth, or can be configured to support communication on one of a set of carrier bandwidths. In some examples, the wireless communication system 100 may include a base station 105 or UE 115 that supports simultaneous communication via carriers associated with multiple carrier bandwidths. In some examples, each served UE 115 can be configured to operate on a portion of the carrier bandwidth (e.g., subband, BWP) or the entire carrier bandwidth.
[0055] The signal waveform transmitted on a carrier can consist of multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread spectrum OFDM (DFT-S-OFDM)). In a system employing MCM, a resource element can consist of one symbol period (e.g., the duration of a modulation symbol) and one subcarrier, where the symbol period and subcarrier spacing are inversely proportional. The number of bits carried by each resource element can depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both). Therefore, the more resource elements the UE 115 receives and the higher the order of the modulation scheme, the higher the data rate of the UE. Wireless communication resources can refer to a combination of radio frequency spectrum resources, temporal resources (e.g., search space), or spatial resources (e.g., spatial layers or beams), and using multiple spatial layers can also improve the data rate or data integrity of communication with the UE 115.
[0056] One or more digital technologies can be supported for a carrier, where the digital technologies may include subcarrier spacing (Δf) and a cyclic prefix. A carrier can be divided into one or more BWPs with the same or different digital technologies. In some examples, the UE 115 can be configured with multiple BWPs. In some examples, a single BWP of a carrier can be active at a given time, and the communication of the UE 115 can be limited to one or more active BWPs.
[0057] The time interval of base station 105 or UE 115 can be expressed as a multiple of a basic time unit. For example, the basic time unit could be T. s =1 / (Δf max ·N f The sampling period is ) seconds, where Δf max This can represent the maximum supported subcarrier spacing, N. f This can represent the maximum supported Discrete Fourier Transform (DFT) size. The time interval of the communication resources can be organized according to each radio frame having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame can be identified by a System Frame Number (SFN) (e.g., ranging from 0 to 1023).
[0058] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, a frame may be divided into subframes (e.g., in the time domain), and each subframe may also be divided into multiple time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include multiple symbol periods, for example, depending on the length of the cyclic prefix appended to each symbol period. In some wireless communication systems 100, time slots may also be divided into multiple mini-time slots containing one or more symbols. In addition to the cyclic prefix, each symbol period may contain one or more (e.g., N) symbols. f (Number) sampling periods. The duration of a symbol period can depend on the subcarrier spacing or the operating frequency band.
[0059] A subframe, time slot, mini-time slot, or symbol can be the smallest scheduling unit of the wireless communication system 100 (e.g., in the time domain) and can be referred to as a transmission time interval (TTI). In some examples, the duration of the TTI (e.g., the number of symbol periods in the TTI) can be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 can be dynamically selected (e.g., in a burst of shortened TTIs (sTTIs)).
[0060] Physical channels can be multiplexed on carriers using various techniques. Physical control channels and physical data channels can be multiplexed on downlink carriers, for example, using one or more of Time Division Multiplexing (TDM), Frequency Division Multiplexing (FDM), or hybrid TDM-FDM techniques. The control region (e.g., a control resource set (CORESET)) of a physical control channel can be defined by multiple symbol periods and can extend to the system bandwidth or a subset of the system bandwidth of the carrier. One or more control regions (e.g., CORESETs) can be configured for a group of UEs 115. For example, one or more UEs 115 can monitor or search control regions or spaces to obtain control information based on one or more search space sets, and each search space set can include one or more control channel candidates in one or more aggregation levels arranged in a cascaded manner. The aggregation level of control channel candidates can refer to multiple control channel resources (e.g., control channel elements (CCEs)) associated with coded information in a control information format having a given payload size. The search space set can include a common search space set configured to send control information to multiple UEs 115 and a UE-specific search space set for sending control information to a specific UE 115. This paper discloses novel, rather than conventional, additional search spaces and configurations for monitoring and decoding them.
[0061] Base station 105 may provide communication coverage via one or more cells, such as macro cells, small cells, hotspots, or other types of cells, or any combination thereof. The term "cell" may refer to a logical communication entity used for communication with base station 105 (e.g., via a carrier) and may be associated with an identifier used to distinguish neighboring cells (e.g., Physical Cell Identifier (PCID), Virtual Cell Identifier (VCID), or other identifiers). In some examples, a cell may also refer to a geographic coverage area 110 or a portion of geographic coverage area 110 (e.g., a sector) on which a logical communication entity operates. The extent of such a cell can range from a smaller area (e.g., a structure, a subset of structures) to a larger area, depending on various factors such as the capabilities of base station 105. For example, a cell may be or include buildings, subsets of buildings, or external space between or overlapping with geographic coverage areas 110.
[0062] Macro cells typically cover a relatively large geographical area (e.g., a radius of several kilometers) and allow UE 115 to have unrestricted access via a service subscription with a network provider supporting the macro cell. In contrast, small cells can be associated with a lower-power base station 105 and can operate in the same or different (e.g., licensed, unlicensed) frequency bands as macro cells. Small cells can provide unrestricted access to UE 115 with a service subscription with a network provider, or restricted access to UE 115 associated with a small cell (e.g., UE 115 in a Closed Subscriber Group (CSG), or UE 115 associated with a user in a home or office). Base station 105 can support one or more cells and can also use one or more component carriers to support communication on one or more cells.
[0063] In some examples, a carrier can support multiple cells, and different cells can be configured according to different protocol types (e.g., MTC, Narrowband Internet of Things (NB-IoT), Enhanced Mobile Broadband (eMBB)), which can provide access for different types of devices.
[0064] In some examples, base station 105 may be mobile, and thus provide communication coverage for mobile geographic coverage areas 110. In some examples, different geographic coverage areas 110 associated with different technologies may overlap, but the different geographic coverage areas 110 may be supported by the same base station 105. In other examples, overlapping geographic coverage areas 110 associated with different technologies may be supported by different base stations 105. Wireless communication system 100 may include, for example, a heterogeneous network, in which different types of base stations 105 use the same or different radio access technologies to provide coverage for various geographic coverage areas 110.
[0065] The wireless communication system 100 can support synchronous or asynchronous operation. For synchronous operation, base stations 105 can have similar frame timing, and transmissions from different base stations 105 can be approximately time-aligned. For asynchronous operation, base stations 105 can have different frame timing, and in some examples, transmissions from different base stations 105 can be time-disaligned. The techniques described herein can be used for both synchronous and asynchronous operation.
[0066] Some UE 115 devices (such as MTC or IoT devices) can be low-cost or low-complexity devices and can provide automated communication between machines (e.g., via machine-to-machine (M2M) communication). M2M communication or MTC can refer to data communication technologies that allow devices to communicate with each other or with base station 105 without human intervention. In some examples, M2M communication or MTC can include communication from devices that integrate sensors or meters to measure or capture information and relay such information to a central server or application that uses the information or presents it to people interacting with the application. Some UE 115 devices can be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, medical monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based service charging.
[0067] Some UE 115s can be configured to operate in a power-saving mode, such as half-duplex communication (e.g., a mode that supports unidirectional communication via transmission or reception but not both transmission and reception simultaneously). In some examples, half-duplex communication can be performed at a reduced peak rate. Other power-saving techniques for UE 115s include entering a power-efficient deep sleep mode when not engaged in active communication, operating on limited bandwidth (e.g., according to narrowband communication), or a combination of these techniques. For example, some UE 115s can be configured to operate using a narrowband protocol type associated with a defined portion or range (e.g., a subcarrier set or resource block (RB) set) within a carrier, within a carrier's guard band, or outside the carrier.
[0068] Wireless communication system 100 can be configured to support ultra-reliable communication or low-latency communication, or various combinations thereof. For example, wireless communication system 100 can be configured to support ultra-reliable low-latency communication (URLLC) or mission-critical communication. UE 115 can be designed to support ultra-reliable, low-latency, or mission-critical functions (e.g., mission-critical functions). Ultra-reliable communication may include dedicated communication or group communication and may be supported by one or more mission-critical services, such as Mission-Critical Push-to-Talk (MCPTT), Mission-Critical Video (MCVideo), or Mission-Critical Data (MCData). Support for mission-critical functions may include service prioritization, and mission-critical services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, mission-critical, and ultra-reliable low-latency are used interchangeably herein.
[0069] In some examples, UE 115 may also be able to communicate directly with other UE 115 via device-to-device (D2D) communication link 135 (e.g., using peer-to-peer (P2P) or D2D protocols). Communication link 135 may include sidechain communication links. One or more UE 115s utilizing D2D communication may be within the geographic coverage area 110 of base station 105. Other UE 115s in such a group may be located outside the geographic coverage area 110 of base station 105 or unable to receive transmissions from base station 105. In some examples, the group of UE 115s communicating via D2D communication may utilize a one-to-many (1:M) system, where a UE transmits to each other UE in the group. In some examples, base station 105 facilitates resource scheduling for D2D communication. In other cases, D2D communication is performed between UE 115s without involving base station 105.
[0070] In some systems, the D2D communication link 135 may be an example of a communication channel between vehicles (e.g., UE 115), such as a sidechain communication channel. In some examples, vehicles may communicate using vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination thereof. Vehicles may signal information related to traffic conditions, signal control, weather, safety, emergencies, or any other information related to the V2X system. In some examples, vehicles in a V2X system may communicate with roadside infrastructure (such as roadside units) using vehicle-to-network (V2N) communication, or with the network via one or more RAN network nodes (e.g., base station 105), or both.
[0071] Core network 130 can provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. Core network 130 can be an evolved packet core (EPC) or a 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), access and mobility management function (AMF)) managing access and mobility, and at least one user plane entity (e.g., a serving gateway (S-GW), packet data network (PDN) gateway (P-GW), or user plane function (UPF)) routing packets or interconnects to external networks. The control plane entity can manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by base station 105 associated with core network 130. User IP packets can be delivered through the user plane entity, which can provide IP address allocation and other functions. The user plane entity can connect to one or more network operator IP services 150. IP services 150 may include access to the Internet, intranet(s), IP Multimedia Subsystem (IMS), or packet-switched streaming services.
[0072] Some network devices (such as base station 105) may include sub-components, such as access network entity 140, which may be an example of an access node controller (ANC). Each access network entity 140 may communicate with UE 115 through one or more other access network transport entities 145, which may be referred to as a radio headend, smart radio headend, or transmit / receive point (TRP). Each access network transport entity 145 may include one or more antenna panels. In some configurations, the various functions of each access network entity 140 or base station 105 may be distributed across various network devices (e.g., radio headends and ANCs) or combined into a single network device (e.g., base station 105).
[0073] Wireless communication system 100 can operate using one or more frequency bands, typically in the range of 300 MHz to 300 GHz. The region from 300 MHz to 3 GHz is generally referred to as the Ultra High Frequency (UHF) region or decimeter band because the wavelength range is from approximately one decimeter to one meter. UHF waves can be blocked or redirected by buildings and environmental features, but these waves can penetrate structures sufficiently to allow macrocells to serve UE 115 located indoors. Compared to transmissions using smaller frequencies and longer waves in the lower frequencies (HF) or very high frequencies (VHF) portions of the spectrum below 300 MHz, UHF wave transmission can be associated with smaller antennas and shorter distances (e.g., less than 100 km).
[0074] The wireless communication system 100 can also operate in the ultra-high frequency (SHF) region using a frequency band from 3 GHz to 30 GHz (also known as the centimeter band), or in the extremely high frequency (EHF) region of the spectrum (e.g., from 30 GHz to 300 GHz) (also known as the millimeter band). In some examples, the wireless communication system 100 can support millimeter-wave (mmW) communication between the UE 115 and the base station 105, and the EHF antennas of the corresponding devices can be smaller and more closely spaced than UHF antennas. In some examples, this can facilitate the use of antenna arrays within the device. However, the propagation of EHF transmissions may be subject to greater atmospheric attenuation and shorter distances than SHF or UHF transmissions. The techniques disclosed herein can be used in transmissions using one or more different frequency regions, and the designated use of frequency bands in these frequency regions may vary by country or regulatory body.
[0075] Wireless communication system 100 can utilize both licensed and unlicensed radio spectrum bands. For example, wireless communication system 100 can employ Licensed Assisted Access (LAA), LTE Unlicensed (LTE-U) radio access technology, or NR technology in unlicensed bands such as the 5 GHz Industrial, Scientific, and Medical (ISM) band. When operating in unlicensed radio spectrum bands, devices such as base station 105 and UE 115 can employ carrier sensing for collision detection and avoidance. In some examples, operation in unlicensed bands can be based on carrier aggregation configuration and combined with component carriers operating in licensed bands (e.g., LAA). Operation in unlicensed spectrum can include downlink transmission, uplink transmission, P2P transmission, or D2D transmission, etc.
[0076] Base station 105 or UE 115 may be equipped with multiple antennas that can be used to employ technologies such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communication, or beamforming. The antennas of base station 105 or UE 115 may be located within one or more antenna arrays or antenna panels that can support MIMO operation or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be juxtaposed at an antenna assembly, such as an antenna tower. In some examples, the antennas or antenna arrays associated with base station 105 may be located in different geographical locations. Base station 105 may have an antenna array with multiple rows and columns of antenna ports that base station 105 can use to support beamforming for communication with UE 115. Similarly, UE 115 may have one or more antenna arrays that can support various MIMO or beamforming operations. Additionally or alternatively, antenna panels may support radio frequency beamforming of signals transmitted via antenna ports.
[0077] Base station 105 or UE 115 can use MIMO communication to utilize multipath signal propagation and improve spectral efficiency by transmitting or receiving multiple signals via different spatial layers. This technique can be called spatial multiplexing. For example, multiple signals can be transmitted by a transmitting device via different antennas or different combinations of antennas. Similarly, multiple signals can be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals can be referred to as a separate spatial stream and can carry bits associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers can be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include single-user MIMO (SU-MIMO) (where multiple spatial layers are transmitted to the same receiving device) and multi-user MIMO (MU-MIMO) (where multiple spatial layers are transmitted to multiple devices).
[0078] Beamforming (also known as spatial filtering, directional transmission, or directional reception) is a signal processing technique that can be used at transmitting or receiving devices (e.g., base station 105, UE 115) to shape or control antenna beams (e.g., transmit beam, receive beam) along a spatial path between the transmitting and receiving devices. Beamforming can be achieved by combining signals transmitted via antenna elements of an antenna array such that some signals propagating relative to a particular orientation of the antenna array experience constructive interference, while other signals experience destructive interference. The conditioning of signals transmitted via antenna elements can include the transmitting or receiving device applying amplitude offset, phase offset, or both to the signals carried via the antenna elements associated with that device. The conditioning associated with each antenna element can be defined by a beamforming weight set associated with a particular orientation (e.g., the antenna array relative to the transmitting or receiving device, or relative to some other orientation).
[0079] Base station 105 or UE 115 may use beam scanning technology as part of beamforming operations. For example, base station 105 may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted multiple times by base station 105 in different directions. For example, base station 105 may transmit signals according to different beamforming weight sets associated with different transmission directions. Transmissions in different beam directions may be used to identify (e.g., by a transmitting device such as base station 105, or by a receiving device such as UE 115) the beam direction for later transmission or reception by base station 105.
[0080] Some signals (such as data signals associated with a specific receiving device) may be transmitted by base station 105 in a single beam direction (e.g., the direction associated with a receiving device such as UE 115). In some examples, the beam direction associated with transmission along a single beam direction may be determined based on signals transmitted in one or more beam directions. For example, UE 115 may receive one or more signals transmitted by base station 105 in different directions and may report to the base station an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.
[0081] In some examples, a transmission performed by a device (e.g., base station 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or radio frequency beamforming to generate a combined beam for the transmission (e.g., from base station 105 to UE 115). UE 115 may report feedback indicating precoding weights for one or more beam directions, and this feedback may correspond to a configuration number of beams across the system bandwidth or one or more subbands. Base station 105 may transmit reference signals (e.g., cell-specific reference signals (CRS), channel state information reference signals (CSI-RS)), which may or may not be precoded. UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-panel codebook, a linearly combined codebook, or a port-selective codebook). While these techniques are described with reference to signals transmitted by base station 105 in one or more directions, UE 115 may employ similar techniques to transmit signals multiple times in different directions (e.g., to identify the beam direction of subsequent transmissions or receptions by UE 115) or to transmit signals in a single direction (e.g., to transmit data to a receiving device).
[0082] When receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from base station 105, the receiving device (e.g., UE 115) can attempt multiple receiving configurations (e.g., directional listening). For example, the receiving device can attempt multiple receiving directions by: receiving via different antenna subarrays; processing the received signal according to different antenna subarrays; receiving according to different sets of receiving beamforming weights applied to signals received at multiple antenna elements of the antenna array (e.g., different sets of directional listening weights); or processing the received signal according to different sets of receiving beamforming weights applied to signals received at different antenna elements of the antenna array, any of which can be referred to as "listening" based on different receiving configurations or receiving directions. In some examples, the receiving device can use a single receiving configuration to receive along a single beam direction (e.g., when receiving data signals). The single receiving configuration can be aligned based on beam directions determined according to listening in different receiving configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or other acceptable signal quality based on listening in multiple beam directions).
[0083] The wireless communication system 100 can be a packet-based network operating according to a layered protocol stack. In the user plane, communication at the bearer or Packet Data Convergence Protocol (PDCP) layer can be IP-based. The Radio Link Control (RLC) layer can perform packet segmentation and reassembly for communication over logical channels. The Media Access Control (MAC) layer can perform priority processing and multiplexing logical channels into transport channels. The MAC layer can also use error detection techniques, error correction techniques, or both to support MAC layer retransmissions to improve link efficiency. In the control plane, the Radio Resource Control (RRC) protocol layer can provide the establishment, configuration, and maintenance of RRC connections between the UE 115 and the base station 105 or core network 130 supporting user plane data radio bearers. At the physical layer, transport channels can be mapped to physical channels.
[0084] UE 115 and base station 105 can support data retransmission to increase the likelihood of data being successfully received. Hybrid Automatic Repeat Request (HARQ) feedback is a technique used to increase the likelihood of data being correctly received through communication link 125. HARQ can include a combination of error detection (e.g., using Cyclic Redundancy Check (CRC)), forward error correction (FEC), and retransmission (e.g., Automatic Repeat Request (ARQ)). HARQ can improve MAC layer throughput under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, the device can support same-slot HARQ feedback, where the device can provide HARQ feedback in a specific time slot for data received in a previous symbol within that time slot. In other cases, the device can provide HARQ feedback in subsequent time slots or according to some other time interval.
[0085] Traditional rule-based models can be implemented in user equipment to perform various radio frequency (RF) functions or signal processing functions, such as beamforming, channel estimation, demodulation, and decoding, and can be based on well-developed system models. These models can produce satisfactory performance as long as they closely follow the actual behavior of the radio network system in which the user equipment operates. However, the performance of traditional models may not be optimal. AI / ML-based models generally outperform traditional models; unlike traditional rule-based models, AI / ML-based models can be based on data rather than the pre-determined rules of traditional models. Therefore, the output or result of a traditional rule-based model can be considered "deterministic" because the input is applied to static rules, producing a "deterministic" output, while the output or result of an AI / ML model can be considered probabilistic because the learned model typically infers possible outputs based on coefficients, factors, functions, or other variables that can be derived from the model's previous inputs.
[0086] Using AI / ML models can improve user equipment performance compared to traditional rule-based models. Several AI / ML-driven use cases can include AI / ML channel state information (CSI) acquisition / prediction, AI / ML radio localization, and AI / ML beam management. While AI / ML-based models trained using data from real-world operations can outperform traditional rule-based models, their robustness can be poor in situations where the radio system / environment may experience changes during training that it may not have experienced or 'saw,' resulting in less than ideal results. In such cases, the learning model may infer undesirable outputs when the learning model is 'unknown,' compared to static rule-based models. This problematic situation may arise from, for example, specific network / user equipment conditions or configurations, the architecture of the AI / ML learning model, or a combination thereof. Therefore, it is desirable to implement a process that allows the network RAN to be updated.
[0087] For AI / ML learning model implementations of radio functions at user equipment (UE), the UE or gNB / RAN can predict the modulation and coding scheme (MCS), and a given amount of channel state information reporting time can be used. The modulation and coding scheme can be referred to as a format. A format or scheme can be associated with quality of service (QoS). Channel conditions or interference conditions absent during model training may systematically lead to suboptimal MCS selections, potentially resulting in violations of minimum equipment performance objectives.
[0088] Training AI / ML models at radio access network nodes and transmitting models or trained / updated models from the RAN to the user equipment are anticipated (because the processing power at the RAN is superior to that at the UE) to train or otherwise refine the learning model. Therefore, it is expected that AI / ML models will be transferred and delivered from the RAN to the UE via the radio link to leverage the AI / ML processing-intensive model training performed separately by the RAN and the UE actively running such models, in order to perform radio functions based on inference from the AI / ML models. For example, the AI / ML model can be trained at the RAN node and transferred or delivered to the UE as an off-the-shelf training model via the downlink radio interface to perform AI / ML-driven beam fault detection and recovery operations. Depending on the model complexity and purpose, the size of the AI / ML model can range from small (e.g., 1 kilobyte or less) to large (e.g., hundreds of megabytes or more).
[0089] Artificial intelligence machine learning models can be delivered to user equipment via data channels or data channel resources (which can be scheduled data channel resources). Unlike AI / ML model transmission via control channels, sending larger AI / ML model data can leverage the dynamic flexibility associated with data channels, including dynamic Quality of Service (QoS) adaptation and dynamic resource scheduling. However, conventional data plane implementations (e.g., the network path taken by data services to reach the UE) require that data always pass through or traverse the User Plane Function (UPF) entity in the core network. This requirement for data to pass through or traverse the UPF is to facilitate QoS regulations in the core network and radio network, subscription-dependent performance adaptation, and tracking of data transmission volumes from various devices for customer billing purposes. Therefore, conventional data plane operation requires data plane termination at the UPF (not at the RAN node). UPF termination in data plane operations poses no problem for traditional data plane data exchange (whether in the downlink or uplink direction) because, for example, for downlink data transmission, the data either originates from an external server (outside the cellular core network) or from a network edge server; traffic from either of these sources is typically routed to the UPF as a waypoint along the traffic route to the RAN node for radio transmission to user equipment.
[0090] However, AI / ML model data can be initiated by the RAN node itself, via AI / ML models deployed from the RAN node. Therefore, according to current data plane technology, if AI / ML model data is sent on the data plane, the source RAN node (e.g., the RAN that initiated or updated the AI / ML model information) sends the AI / ML model information, which can include a large amount of data, to the UPF entity via the N3 backhaul link. The UPF then retransmits the large payload back to the source RAN node for radio transmission to the user equipment. For many AI-capable UE devices, each device may require multiple model passes to perform various radio functions. This ping-pong exchange of model data can consume significant backhaul link resources and potentially overwhelm the interface link between the RAN node and the UPF, potentially leading to data transmission rejection or increased interface latency corresponding to other non-AI data exchanges.
[0091] In some embodiments disclosed herein, novel data plane implementations specific to AI / ML model delivery or other use cases where data originates from the RAN node itself terminate at the RAN node rather than the UPF. For UPF QoS specifications and data volume billing tracking, the novel reporting embodiments disclosed herein facilitate RAN-to-UPF reporting signaling to facilitate UPF implementation of QoS for AI model data traffic flows sent over the radio interface for various devices, and accordingly determine the amount of AI data sent by each device without requiring large amounts of ping-pong exchange between the RAN node and the UPF. The embodiments disclosed herein can facilitate the implementation of vendor-specific differentiations. Vendor-specific configurations can facilitate cross-vendor interoperability (e.g., RAN nodes and UPFs from different vendors).
[0092] Now go to Figure 2 The figure illustrates a system 200 including a RAN node 105 communicating with a user equipment 115 via a radio link 125. The UE 115 can perform various radio functions 205A-205n, each facilitated by a corresponding machine learning model 215A-215n. During UE 115 radio operation and communication with the RAN 105, the UE can send parameter measurement reports 220A-220n, which may include one or more learning model parameter measurements corresponding to 215A-215n respectively. Reports 220A-220n may include one or more control action requests, such as requests to deactivate or retrain one or more of models 215A-215n. The RAN 105 may send learning model information 215 to the UE 115 in one or more learning model information data messages 225.
[0093] AI / ML learning models (such as those deployed at UE device 115) Figure 2 Model 215 shown can be implementation-specific (e.g., a supplier-proprietary learning model). (Examples of suppliers that can provide proprietary learning models may include user equipment manufacturers, or user equipment application providers, network equipment providers, or network equipment application providers, or mobile network operators, or mobile network operator application providers.) The network RAN can determine the overall performance of the learning model deployed at the UE to facilitate minimum device performance requirements. User equipment can compile and report indications that can be configured or pre-configured to reflect or indicate the model performance of the corresponding learning model.
[0094] A specific UE device can employ several different AI / ML learning models to run, execute, or otherwise facilitate different radio functions. Different learning model parameter metrics can indicate the performance of different learning models. The UE can compile and report one or more different learning model performance indicator parameter metrics or indications for each learning model. Different learning model metrics can be associated with different corresponding filtering or time resolution configurations. Therefore, as... Figure 1 or Figure 2 As shown, this customized metric reporting for a given learning model can facilitate optimized tracking and reporting of each active learning model for each UE device 115 that can be served by RAN 105. Therefore, network RAN 105 can acquire and use the real-time performance of each learning model active at UE 115 to promote optimal performance of the learning model and the inference it can generate. Furthermore, several reporting variants can be customized to suit various AI / ML learning model implementations or purposes, such as exact absolute, exact relative, quantized, or time-based (e.g., historical) metric reporting.
[0095] For AI / ML learning model performance, various parameters and their corresponding metrics can be considered, analyzed, or evaluated, depending on the nature of the problem being solved and the corresponding learning model function (e.g., regression or classification), or the radio function performed or facilitated by the learning model. For example, for radio functions such as channel estimation or channel state information (CSI) compression, regression functions can be used in the learning model, where the following parameters or their corresponding metrics can be evaluated: mean squared error (MSE); root mean square error (RMSE); normalized mean squared error (NMSE); mean absolute error (MAE); R-squared; generalized cosine similarity (GCS); or squared generalized cosine similarity (SGCS). Table 1 illustrates example functions defining corresponding learning model parameters, and as described above, the corresponding metrics can be monitored and evaluated. Table 1
[0096] For classification problems such as beam index prediction, precision metrics can be analyzed to determine the performance of the learning model that facilitates beam index prediction. Other example learning model parameter metrics that can indicate the performance of a learning model solving a classification problem may include, but are not limited to: the absolute number of true negatives, true positives, false negatives, and false positives; precision and recall; or F1 score. The F1 score can include an evaluation metric used to represent the performance of a machine learning model or classifier and provides combined information about the precision and recall of the learning model. A high F1 score typically indicates high values for both recall and precision metrics.
[0097] As mentioned above, AI / ML learning model implementations at different devices can be vendor-proprietary and transparent to network nodes (e.g., the RAN serving a UE may not have access to the specific features and programming of a given learning model that facilitates radio functions deployed in the UE). To manage and facilitate UE devices achieving performance targets, RAN nodes can be made aware of the UE device's capabilities and the overall performance of the AI / ML learning model. Therefore, upon initial connection to the serving network RAN, an active UE device can send device-specific AI / ML capability information, including the following information elements (IEs): the type of AI / ML algorithm supported, including supervised learning, unsupervised learning, and reinforcement learning; a list of radio functions supporting AI / ML; a list of model-specific metrics for estimating and reporting AI / ML support; the model library size for each radio function, e.g., the number of models that can be stored per radio function; or an indication of model classification (small / medium / large), which can facilitate the network RAN in defining or determining the dataset to be used by the learning model. For example, for a large number of neurons (e.g., nodes in a neural network of a learning model), determining the appropriate number of information samples can help avoid overfitting of the learning model. AI / ML capability information elements can be part of device capability signaling transmitted based on subsequent Radio Resource Control (RRC) signaling or Dynamically Scheduled Uplink Control Information (UCI) transmissions. Therefore, the network RAN can determine updates to one or more learned models and deliver the updated model, or its corresponding coefficients, to the user equipment.
[0098] Dynamic AI / ML model delivery over data channels.
[0099] The term 'bearer' can refer to an Internet Protocol (IP) service flow, which includes one or more protocol data units, such as packets corresponding to Quality of Service (QoS). A bearer can include or correspond to routing packets to a User Equipment (UE). Existing Data Radio Bearers (DRBs) terminate at the User Plane Function (UPF) (core network entity), through which all data must be delivered to the UE. Through the embodiments disclosed herein, the new DRB can be terminated at the RAN node to facilitate the delivery and transmission of AI / ML model information to UE devices with AI / ML capabilities without overwhelming the backhaul link. The embodiments disclosed herein can include new reporting and signaling via the backhaul interface between the RAN node and the UPF. The new signaling and reporting can facilitate interoperability between the RAN node and UPFs from different providers while efficiently delivering AI / ML model payloads over data channels.
[0100] Therefore, unlike traditional network implementations where the UPF is aware of the amount of data sent from the RAN to the UE because data must first be forwarded through the UPF itself, the forced forwarding of data via the UPF is eliminated or minimized for RAN-initiated data (such as AI / ML model information) to the UE. For AI / ML model data sent from the RAN to the UE and generated or updated within the RAN, eliminating or minimizing the forced delivery of AI / ML model information via the UPF is desirable. This paper discloses novel routing and reporting techniques that, instead of sending AI / ML generated at the RAN to the UPF and then back to the RAN for transmission to the UE, facilitate the UPF in determining the amount of data used to send AI / ML information. Dynamic reporting techniques can indicate to the UPF the amount of data used to send AI / ML model information via a novel AI-specific DRB, facilitating the UPF's understanding of the data volume. This enables the UPF to perform accounting functions corresponding to the delivery of AI / ML models from the RAN to the UE without requiring the data stream used to transmit AI / ML models to the UPF and then back to the RAN.
[0101] Now go to Figure 3A The environment 300A diagram illustrates a data message 305 sent from a data source 307 (e.g., a web server, enterprise server, etc.) to user equipment 115. (Reference) Figure 1 The described Internet service 150 may include Internet 301 or data source 307. Continue Figure 3A As described, data 305 may follow a path from server 307 via Internet 301 through core network 130 through user plane function 310 via interface N3 to RAN 105 and finally from RAN 105 via radio communication link 125 to user equipment 115. Although the multi-entity, multi-link path from data source 307 to user equipment 115 includes multiple interfaces and links, it is indicated in bold as a single flow path 315 to illustrate the movement of data portions (such as packets) used to transmit data from source 307 to UE 115.
[0102] Now go to Figure 3BContext 300B illustrates a scenario where an AI machine learning model 215 can be generated or updated at RAN node 105. The AI machine learning model 215 may include information data 225, which can be sent to user plane function 310 via flow path 345 and returned to RAN 105, the source of the AI machine learning model data. After traversing user plane function 310 and returning to RAN 105 via path 345, the data 225 including model 215 can then be sent from RAN 105 to user equipment 115 via radio communication link 125. Therefore, even if the information data 225 to be sent to user equipment 115 is not received by RAN 105 via an entity in core network 130, but is generated by the RAN node itself, the information data 225 generated at RAN 105 is still sent from RAN 105 to core network 130 (e.g., UPF 310) and returned to RAN 105. The transmission of data 225 from RAN 105 to UPF 310 and back to RAN 105 before it is sent to UE 115 can be called 'ping-pong' communication because the same information sent from RAN 105 to UPF 310 is sent back to RAN. Figure 3B As shown in bold path 345, this ping-pong communication consumes resources of the backhaul interface N3 and increases the delivery latency of AI / ML model 215 from RAN 105 to UE 115.
[0103] Now go to Figure 3CIn environment 300C, RAN 105 can send the AI / ML model information payload to UE 115 via radio interface link 125 without prior 'ping-pong' data exchange between RAN and UPF 310 via a backhaul link. RAN node 105 can send a new Data Radio Bearer (DRB) establishment request 340 to entities in core network 130 via the backhaul link. DRB request 340 can be sent to the Access and Mobility Function (AMF) or Session Management Function (SMF) via the N2 interface, first to the AMF via the N2 interface and then from the AMF to the SMF via the N11 interface. DRB establishment request 340 can instruct RAN node 105 to request entities in core network 130 to establish a new, on-demand data plane to deliver AI / ML model information 225 from RAN 105 to UE 115 without protocol data elements (e.g., packets) passing through UPF 310. Request 340 can facilitate core network 130 configuring QoS implementation and data volume reporting instructions for RAN node 105 corresponding to the new AI / ML data radio bearer 355. Data volume reporting 360 can facilitate reporting volume information to UPF 310 corresponding to the payload service used to deliver AI / ML model 225 to user equipment 115. Therefore, when AI / ML model information to be delivered to UE 115 (e.g., information corresponding to a new AI model or updated information corresponding to an AI model already used at UE 115) is available, RAN node 105 can schedule and transmit AI / ML model payload data on radio interface 125 via DRB 355 without ping-pong data exchange with UPF. AI / ML model information can be transmitted from RAN 105 to UE 115 via AI-specific DRB 355 according to QoS objectives associated with the DRB configured by entities of core network 130. (See reference...) Figure 6 In more detail, when UE 115 switches from RAN 105A to RAN 105B while receiving a large AI / ML model, RAN node 105A can forward AI / ML information data that RAN 105A has not yet sent or that UE 115 has not yet received to UE 115. Therefore, when a handover event occurs and there is no direct connection (e.g., IP connection) between the source RAN 105A and the destination RAN 105B, UPF 310 may only be involved in processing data packets for sending AI / ML information data 225 from RAN 105 to UE 115. (For various reasons, network operators may choose not to configure a direct connection between RAN 105A and RAN 105B; in this case, the RAN typically exchanges control and data information through core entities such as UPF 310.)
[0104] Furthermore, since RAN node 105 is configured to periodically report the amount of AI data as part of the AI-specific DRB configuration received from entities in core network 130, RAN 105 can track and periodically report to the UPF the amount of AI / ML model information transmitted via AI-specific DRB 355 for AI-capable UE 115. This reporting facilitates UPF 310 in maintaining accurate information about the amount of data used by UE 115 for accounting or billing purposes—if one or more AI / ML model data instances are transmitted directly via the radio interface without UPF involvement, report 360 can provide a report, for example, in bytes, on the amount of data used to transfer AI / ML model information 225 from RAN 105 to UE 115 via AI-specific DRB 355. Therefore, it is possible to avoid Figure 3B The 'ping-pong' AI / ML model data exchange 345 between RAN node 105 and UPF 310, as shown, still facilitates the implementation of QoS and charging tracking of AI data sent on AI-specific and RAN node-terminated DRB 355 by core network 130 / UPF.
[0105] For reference Figure 3C The RAN node 105, capable of AI / ML model training and direct dynamic model delivery to the AI-capable UE 115 via a data channel, can send a new AI-specific data radio bearer request 340 to the core network access and mobility function 320 or session management function 330 via a backhaul link. In response to request 340, the RAN node 105 can receive an AI-specific DRB configuration 345. Figure 4 As shown, the DRB configuration 345 can be sent from the AMF 320 or SMF 330 to the RAN node 105 via the backhaul interface and link. The AI-specific DRB configuration 345 may include a Quality of Service Flow Identifier (QFI) 410. The QFI 410 may indicate a QoS profile, which includes information via a radio interface (such as via...). Figure 3C The performance parameters of the link 125 shown are an indication of the target. Figure 4 The performance parameters indicated by AFI 410 may include latency, buffer delay, reliability level, etc., and these parameters will be compared with those obtained via... Figure 3CThe AI-specific DRB 355 shown is associated with sending AI / ML information services. QFI 410 can facilitate semi-static changes to the processing of AI / ML model payloads on the core network 130 or radio interface (e.g., link 125). QFI can refer to a numbering or sequencing indication corresponding to a flow. Therefore, a QFI associated with, for example, a packet can indicate the flow corresponding to that packet. QCI can refer to a QoS profile associated with the QFI (e.g., certain delay targets, certain tolerance targets, etc.).
[0106] continue Figure 4 The description states that configuration 365 may include an AI / ML data volume reporting cycle indicator 415. Cycle indicator 415 can indicate a cycle, based on which... Figure 3C The AI-capable RAN 105 shown should send an AI / ML data volume report 360 to the UPF 310. The data volume report 360 may include an explicit report stating the exact size of the AI / ML data volume sent to the user equipment. In one embodiment, the data volume report may include an implicit indication of the amount of data sent, such as an index mapped to a predetermined range of AI data sent (e.g., index '0' may include fewer bits than the explicitly reported amount and may indicate, for example, a data volume between 1 megabyte and 5 megabytes).
[0107] continue Figure 4 The description states that configuration 365 may include an AI / ML data forwarding coverage threshold 420. The data forwarding coverage threshold 420 may include a configured radio coverage threshold used to determine when to forward AI / ML data 225 to... Figure 3CThe UPF 310 is shown. When the user equipment is located in a position experiencing poor RF conditions, the data coverage threshold 420 can be beneficial, and inter-RAN node handover may be involved during the delivery of a large AI / ML model payload. Therefore, in the event of a violation of the configured coverage threshold 420 corresponding to the UE device during AI / ML model transmission on an AI-specific DRB 355, RAN node 105 may forward the AI / ML model payload, or a portion thereof that has not yet been successfully sent to or received by the UE, to the UPF 310. Thus, when a handover is invoked, the UPF 310 can directly forward the buffered AI / ML model payload to the destination RAN node that has become or is becoming the serving RAN of the user equipment. This 'advance' buffering, based on the determination that the user equipment handover may be due to meeting the coverage threshold 420 (e.g., the coverage level reported by the UE has fallen below the threshold 420), can reduce or eliminate the delay in sending a large AI / ML model payload from the current serving source RAN node to the UPF, since the delivery of AI / ML model information may have already begun or may have already been completed before the handover is invoked.
[0108] Now go to Figure 5 The diagram illustrates Figure 3C The example shown is AI / ML data volume information report 360. A RAN node 105 with AI capabilities can send report 360 to UPF 310 for billing / data usage tracking at the UPF. Back Figure 5 The report 360 may include one or more AI-specific DRB identifiers 510. Different AI-specific DRB identifiers 510 may be used to accommodate one or more AI-specific DRBs 355 (such as...). Figure 3C As shown), these DRBs are configured and built to carry AI / ML model payloads to AI-capable devices, where different AI-specific DRBs can be used to facilitate different corresponding QFI profiles (e.g., different QFI profiles can be determined based on, for example, user device criticality or (multiple) corresponding service subscriptions).
[0109] For each DRB identifier 510, report 360 may include a device identifier 515 with AI capabilities corresponding to a UE device, which corresponds to a DRB 355 with the corresponding DRB identifier 510. Report 360 may include a delivered AI / ML model data size indication 520, indicating the amount of AI / ML data to be delivered via the DRB 355 corresponding to the corresponding DRB identifier 510, for example, given in bytes, megabytes, or gigabytes. The AI / ML data size indicated by indication 520 may be determined by… Figure 3CThe RAN 105 shown is determined to account for AI / ML model payloads that are not forwarded to UPF 310 and can indicate the amount of data related to AI / ML model services delivered to UE 115 without involving UPF.
[0110] Figure 6 The illustration shows environment 600, where UE 115, while receiving updated AI / ML information data 225, moves in direction 605 out of coverage area 610 corresponding to RAN 105A and into coverage area 615 corresponding to RAN 105B. The first portion 225-1 of the AI / ML model information 225 (shown as a shaded block of AI / ML model information 225) has been delivered to UE 115 via data radio bearer 355 before the UE moves out of coverage area 610. RAN 105A can send portion 225-2 of the AI / ML model information 225 to UPF 310, which may not yet have been sent to or received by UE 115. RAN 105A can send report 360-1 indicating that data corresponding to portion 225-1 has been sent to UE 115. Therefore, UPF 310 can send the remaining portion 225-2 of the AI / ML model to RAN 105B via the backhaul link. After UE115 switches from being served by RAN 105A to being served by RAN 105B, RAN 105B can then transmit part 225-2 to UE115 via radio link 125, indicating that the UE is better served by RAN 105B than by RAN 105A (e.g., the signal received from RAN 105B is stronger than the signal received from RAN 105A).
[0111] Now go to Figure 7 The figure illustrates a timing diagram of method 700 in an example embodiment. At action 705, the AI-capable RAN node 105 sends a RAN node termination AI Data Radio Bearer (DRB) establishment request to the User Plane Function (UPF), such as reference Figure 3C Request 340 is described. Request 340 can be sent on the backhaul interface N2 or N3 via access and mobility functions and / or session management functions. At action 710, the AI-capable RAN 105 can receive the AI DRB setup configuration terminated by the RAN node from the UPF, AMF, or SMF, such as reference... Figure 3C The configuration described is 345. (See reference...) Figure 4The configuration 345 may include an indication 410 for indicating a default quality of service profile, an explicit information or data volume reporting period for RAN 105 to generate and send reports of traffic volume sent according to configuration 345 to UPF and / or AMF, or a radio coverage standard (such as threshold 420) for determining whether or when to forward AI payload data to UPF.
[0112] At action 715, if AI / ML model information is available to be passed to UE 115 (this AI / ML model information may have already been generated or initiated by RAN node 105), the RAN node may pass an allocation of AI / ML-specific DRBs to the AI model (e.g., reference...). Figure 3C The described DRB 355 can employ a quality profile corresponding to the quality level indication (QCI) profile indication associated with the QFI received in the configuration at action 710.
[0113] RAN 105 can determine that AI / ML model data information is available for transmission to UE 115 without the UE needing to switch to another RAN, and the last coverage report received from the UE indicates that the signal strength / coverage at the UE corresponding to RAN 105 suggests that the UE is unlikely to switch during the transmission of RAN-initiated AI / ML information. At action 720, RAN node 105, based on the configuration information received at action 710 and the AI DRB configured at action 715, transmits the RAN-initiated AI / ML model payload via the radio interface, without forwarding the AI / ML model payload to UPF 310 via the backhaul link. RAN 105 can periodically (e.g., referencing...) Figure 4 The described instruction 415 indicates the period to which a quantity data report is sent to the UPF 310, and a quantity data report can be sent to the UPF at action 725.
[0114] Now go to Figure 8 The figure illustrates a timing diagram of method 800 in an example embodiment. At action 805, the AI-capable RAN node 105A sends a RAN node termination AI Data Radio Bearer (DRB) establishment request to the User Plane Function (UPF), such as reference... Figure 3C Request 340 is described. Request 340 can be sent on the backhaul interface N2 or N3 via access and mobility functions and / or session management functions. At action 810, the AI-capable RAN 105A can receive the AI DRB setup configuration terminated by the RAN node from the UPF, AMF, or SMF, such as reference... Figure 3C The configuration described is 345. (See reference...) Figure 4The configuration 345 may include an indication of a default quality of service profile, an indication 415 for RAN 105A to generate and report information and data volume reporting periods for traffic volume sent according to configuration 345 to UPF 310 and / or AMF, or a radio coverage standard (such as threshold 420) for determining whether or when to forward AI payload data to UPF.
[0115] Back Figure 8 The description states that at action 815, under the condition that AI / ML model information is available to be passed to UE 115 (the AI / ML model message may have already been generated or initiated by RAN node 105A), RAN node 105A may assign AI / ML-specific DRBs to the AI model (e.g., reference...). Figure 3C The described DRB 355 transmits and employs a quality profile corresponding to the Quality Level Indicator (QCI) associated with the QFI received in the configuration at action 810.
[0116] At action 820, RAN 105A can determine, based on a coverage report received from the UE, that AI / ML model data information is available to be passed to UE 115 and that the UE can switch to another RAN 105B. The coverage report indicates that, based on an analysis of the signal strength / coverage at the UE corresponding to RAN 105A that meets handover criterion 420, the UE may be better served by RAN 105B in the present or future, and therefore the UE can switch during the RAN-initiated AI / ML information being passed from RAN 105A to the UE.
[0117] At action 825, RAN node 105A can send the RAN-initiated AI / ML model information payload to UE 115 via the radio interface according to the configuration information received at action 810 and the AI DRB configured at action 815, without forwarding the AI / ML model payload to UPF 310 via the backhaul link.
[0118] However, at action 830, RAN node 105A can transmit packets of AI / ML model information generated by RAN 105A to UPF 310 via the backhaul link to facilitate a potential handover of UE 115 from service provided by RAN 105A to service provided by RAN 105B. The packets transmitted at action 830 can be packets of AI / ML model information generated by RAN 105A that have not yet been transmitted to UE 115 via the radio / radio interface link at action 825. Therefore, packets of AI / ML model information generated by RAN 105A that UE 115 has already transmitted and received via the radio interface link will not be transmitted to UPF 310 via the backhaul link, but packets that have not yet been transmitted to the UE or received by the UE can be transmitted to UPF 310, which can buffer packets transmitted at action 830 until UE 115 has switched to RAN 105B. At action 835, RAN105A can enable UE 115 to switch over, allowing RAN 105B to start providing services to the UE.
[0119] At action 840, UPF 310 can pass the DRB configuration information and packets sent by RAN 105A and received by UPF at action 830 to RAN 105B. RAN can then send packets of AI / ML model information generated by RAN 105A at action 845. These packets may not have been sent at action 825 before the handover is implemented at action 835.
[0120] Therefore, when the UE connects to RAN 105A, RAN 105A can send packets containing AI / ML model information generated by RAN 105A to UE 115 using a specially configured AI-specific DRB, without going through UPF 310. Due to handover, packets sent from RAN 105A to UE 115 without the configured special DRB can be passed to UPF 310 via the backhaul link, and then from UPF to RAN 105B via the backhaul link. RAN 105B can then forward the packets to UE 115 via the radio interface link. RAN 105B can forward packets at action 845 according to the DRB, which can be established between RAN 105B and UE 115 based on the configuration information received by RAN 105A at action 810, and passed from UPF 310 to RAN 105B at action 840.
[0121] When the configuration data volume reporting period corresponding to AI DRB expires, RAN 105A can, based on the period (e.g., reference...), Figure 4The described instruction 415 (indicated by the period) determines the quantity data report to be sent to UPF 310. At action 850, RAN 105A can send a quantity data report to UPF 310 to indicate the quantity of AI model information sent at action 825 via the configured AI DRB.
[0122] Now go to Figure 9 The diagram illustrates a flowchart of example method 900. Method 900 begins at action 905. At action 910, the radio access network node can determine the data to be transmitted to the user equipment. For example, the radio access network node can determine an artificial intelligence machine learning model, or an update to an artificial intelligence machine learning model. Besides artificial intelligence machine learning model information data, the data can originate from or be determined by the radio access network node.
[0123] At Action 915, a radio access network node can request the use of a special data radio bearer to transmit data originating from that radio access network node to a user equipment (UE) without sending and receiving data back from the user plane function before the radio access network node can transmit data to the UE. The request sent at Action 915 can be sent via a backhaul interface link to the user plane function, access and mobility function, or session management function. At Action 920, the radio access network node receives special data radio bearer configuration information for configuring the special data radio bearer to transmit data originating from the radio access network node to the UE, thereby avoiding data transmission via the user plane function. The special data radio bearer configuration can be received via a backhaul interface link from the user plane function, access and mobility function, or session management function. The configuration information received at Action 920 may include a Quality of Service (QoS) flow identifier, an AI / ML data volume reporting cycle indication, or an AI / ML data forwarding coverage threshold.
[0124] At action 925, the radio access network node transmits data initiated by the radio access network node to the user equipment. At action 930, the user equipment receives packets transmitted by the radio access network marked at 925. At action 935, the user equipment may transmit a coverage indication or a signal strength indication, which indicates the signal strength of the signal received by the user equipment from the radio access network node.
[0125] At action 940, the radio access network node can determine whether the handover criteria are met. The handover criteria can be received in the configuration received at action 920. If the determination at action 940 is that the handover criteria are not met, method 900 proceeds to action 945. At action 945, it can be determined whether the transmission or delivery of data originating from the radio access network node has been completely sent to the user equipment. If the determination at action 945 is that the data originating from the radio access network node (e.g., artificial intelligence machine learning model information) has been completely sent to the user equipment, method 900 proceeds to action 975 and ends. If the determination at action 945 is that the data originating from the radio access network node has not been completely sent to the user equipment, method 900 returns to action 925, and the radio access network node continues to send data originating from the radio access network node to the user equipment.
[0126] Returning to the description of action 940, if the radio access network node determines, as determined by the user equipment, that the coverage level or signal strength corresponding to the radio access network node meets the handover criteria (e.g., the signal strength is below a threshold configured according to the configuration information received at action 920), then method 900 proceeds to action 950. At action 950, the radio access network node can continue to send packets of data originating from that node to the user equipment. At action 955, the radio access network node can send packets of data determined at action 910 that have not yet been sent to the user equipment to the user plane function. At action 960, a radio access network node, which may be referred to as the original radio access network node or source radio access network node (e.g., the data being transmitted was initiated by the original / source radio access network node), can initiate a handover for the user equipment, connecting the user equipment to a different / target radio access network node that can provide the user equipment with a stronger signal than the original radio access network node, and allowing the different / target radio access network node to begin providing service to the user equipment. At action 965, the user plane function can forward data packets sent by the original radio access network node to the target radio access network node at action 955. The packets sent at action 965 may not have yet been sent to the user equipment by the original user equipment. At action 970, the original radio access network node may send a data volume report to the user plane function to inform it of the amount of data sent by the original radio access network node to the user equipment that was not sent through the user plane function. At action 970, the original radio access network node may determine to send the data volume report based on the expiration of a timer or reporting period, which may have been configured by the configuration information received at action 920. Method 900 proceeds to action 975 and ends.
[0127] Now go to Figure 10The figure illustrates an example embodiment of method 1000, which includes: at block 1005, a radio access network node including a processor determines updated artificial intelligence model information to be sent to a user equipment; at block 1010, the radio access network node sends a data radio bearer establishment request to a control entity; at block 1015, the radio access network node receives a data radio bearer configuration from the control entity, wherein the control entity sends the data radio bearer configuration to the radio access network node in response to the data radio bearer establishment request; at block 1020, the radio access network node sends the updated artificial intelligence model information to the user equipment via the data radio bearer established according to the data radio bearer configuration; and at block 1025, the radio access network node sends a data volume report corresponding to the updated artificial intelligence model information to a user plane function.
[0128] Now go to Figure 11 The figure illustrates a radio access network node 1100, which includes: at block 1105, a processor configured to: determine data to be transmitted to a user equipment; at block 1110, send a data radio bearer establishment request to a control entity; at block 1115, receive a data radio bearer configuration from the control entity in response to the data radio bearer establishment request; at block 1120, transmit data to the user equipment via a data radio bearer established between the radio access network node and the user equipment according to the data radio bearer configuration; and at block 1125, wherein the data transmission includes: the transmission of protocol data elements including the data, and wherein the data transmission excludes: the transmission of protocol data elements including the data to user plane functions.
[0129] Now go to Figure 12The figure illustrates a non-transitory machine-readable medium 1200, which includes: at block 1205, executable instructions, when executed by a processor of a radio access network node, facilitating the execution of operations including: receiving radio performance metrics corresponding to radio functions from a user equipment implementing radio functions based on an artificial intelligence model; at block 1210, determining, based on the radio performance metrics, updated artificial intelligence model information to be transmitted to the user equipment for the user equipment to update the artificial intelligence model; at block 1215, establishing a data radio bearer between the radio access network node and the user equipment for transmitting the updated artificial intelligence model information to the user equipment; and at block 1220, transmitting the updated artificial intelligence model information to the user equipment via the data radio bearer. The system prepares to send updated AI model information; at box 1225, the radio access network node sends a data volume report corresponding to the transmission of the updated AI model information to the user plane function; at box 1230, it identifies the untransmitted portion of the updated AI model information; at box 1235, it receives a coverage indication from the user equipment, which indicates a determined signal strength corresponding to the user equipment's operation with respect to the radio access network node; at box 1240, it analyzes the determined signal strength according to the transmission criteria to obtain the analyzed determined signal strength; at box 1245, based on the analyzed determined signal strength being determined to meet the transmission criteria, it sends the untransmitted portion of the updated AI model information to the user plane function.
[0130] To provide additional context for the various embodiments described herein, Figure 13 The following discussion is intended to provide a brief, general description of a suitable computing environment 1300 in which various embodiments of the embodiments described herein may be implemented. While the embodiments have been described above in the general context of computer-executable instructions that can run on one or more computers, those skilled in the art will recognize that the embodiments may also be implemented in combination with other program modules and / or as a combination of hardware and software.
[0131] Typically, program modules include routines, programs, components, data structures, etc., that perform specific tasks or implement specific abstract data types. Furthermore, those skilled in the art will recognize that these methods can be practiced using other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframes, IoT devices, distributed computing systems, and personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, each of which can be operatively coupled to one or more associated devices.
[0132] The embodiments shown herein can also be practiced in a distributed computing environment, where certain tasks are performed by remote processing devices linked via a communication network. In a distributed computing environment, program modules can reside on both local and remote memory storage devices.
[0133] Computing devices typically include various media, which may include computer-readable storage media, machine-readable storage media, and / or communication media, these two terms being used herein in ways distinct from each other. A computer-readable storage medium or a machine-readable storage medium can be any available storage medium accessible by a computer, and includes both volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, a computer-readable storage medium or a machine-readable storage medium can be implemented in conjunction with any method or technique for storing information such as computer-readable or machine-readable instructions, program modules, structured data, or unstructured data.
[0134] Computer-readable storage media may include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CDROM), digital versatile disc (DVD), Blu-ray disc (BD) or other optical disc storage, cassette tape, magnetic tape, disk storage or other magnetic storage devices, solid-state drives or other solid-state storage devices, or other tangible and / or non-transitory media that can be used to store desired information. In this regard, the terms “tangible” or “non-transitory” used herein to describe storage, memory, or computer-readable media should be understood to exclude only the propagation of transient signals as a modifier, and do not waive the rights to all standard storage, memory, or computer-readable media that (in themselves propagate not only transient signals).
[0135] Computer-readable storage media can be accessed by one or more local or remote computing devices, for example via access requests, queries or other data retrieval protocols, to perform various operations on the information stored on the media.
[0136] Communication media typically embody computer-readable instructions, data structures, program modules, or other structured or unstructured data in data signals such as modulated data signals, such as carrier waves or other transmission mechanisms, and include any medium for delivering or transmitting information. The term "modulated data signal" refers to a signal whose characteristics are set or altered in a manner that encodes information in one or more signals. As an example, and not a limitation, communication media include wired media (such as wired networks or direct wired connections) and wireless media (such as acoustic, RF, infrared, and other wireless media).
[0137] Refer again Figure 13An example environment 1300 for implementing various embodiments of the aspects described herein includes a computer 1302, which includes a processing unit 1304, system memory 1306, and a system bus 1308. The system bus 1308 couples system components (including, but not limited to, system memory 1306) to the processing unit 1304. The processing unit 1304 can be any of a variety of commercial processors and may include cache memory. Dual microprocessors and other multiprocessor architectures may also be used as the processing unit 1304.
[0138] System bus 1308 can be any of several types of bus architectures, which can be further interconnected to memory buses (with or without memory controllers), peripheral buses, and local buses using any of the various commercial bus architectures. System memory 1306 includes ROM 1310 and RAM 1312. The Basic Input / Output System (BIOS) can be stored in non-volatile memory, such as ROM, erasable programmable read-only memory (EPROM), or EEPROM, containing basic routines that facilitate the transfer of information between components within computer 1302, such as during startup. RAM 1312 may also include high-speed RAM, such as static RAM for caching data.
[0139] Computer 1302 also includes an internal hard disk drive (HDD) 1314 (e.g., EIDE, SATA), one or more external storage devices 1316 (e.g., floppy disk drive (FDD) 1316, memory stick or flash drive reader, memory card reader, etc.), and an optical disc drive 1320 (e.g., capable of reading from or writing to CD-ROMs, DVDs, BDs, etc.). While the internal HDD 1314 is shown as residing within computer 1302, it can also be configured for external use in a suitable chassis (not shown). Furthermore, although not shown in environment 1300, a solid-state drive (SSD) may be used in addition to or in place of the HDD 1314. The HDD 1314, the multiple external storage devices 1316, and the optical disc drive 1320 can be connected to system bus 1308 via HDD interface 1324, external storage interface 1326, and optical disc drive interface 1328, respectively. The interface 1324 for external driver implementation may include at least one or both of Universal Serial Bus (USB) and Institute of Electrical and Electronics Engineers (IEEE) 1394 interface technologies. Other external driver connectivity technologies are within the scope of the embodiments described herein.
[0140] The drive and its associated computer-readable storage medium provide non-volatile storage of data, data structures, computer-executable instructions, etc. For computer 1302, the drive and storage medium are adapted to store any data in a suitable digital format. Although the above description of computer-readable storage media refers to a corresponding type of storage device, those skilled in the art will understand that other types of computer-readable storage media (whether currently existing or developed in the future) may also be used in the example operating environment, and further, any such storage medium may contain computer-executable instructions for performing the methods described herein.
[0141] Multiple program modules can be stored in the drive and RAM 1312, including an operating system 1330, one or more application programs 1332, other program modules 1334, and program data 1336. All or part of the operating system, applications, modules, and / or data can also be cached in RAM 1312. The systems and methods described herein can be implemented using various commercial operating systems or combinations of operating systems.
[0142] Computer 1302 may optionally include emulation technology. For example, a hypervisor (not shown) or other intermediary may emulate the hardware environment of operating system 1330, and the emulated hardware may optionally be different from that of computer 1330. Figure 13 The hardware is shown. In such an embodiment, the operating system 1330 may include one of a plurality of virtual machines (VMs) hosted at the computer 1302. Furthermore, the operating system 1330 may provide a runtime environment for the application 1332, such as the Java Runtime Environment or the .NET Framework. A runtime environment is a consistent execution environment that allows the application 1332 to run on any operating system that includes a runtime environment. Similarly, the operating system 1330 may support containers, and the application 1332 may be in the form of a container, which is a lightweight, standalone, executable software package that includes, for example, code, runtime, system tools, system libraries, and application settings.
[0143] Furthermore, computer 1302 may include a security module, such as a Trusted Processing Module (TPM). For example, with a TPM, the boot component hashes the next live boot component and waits for the result to match a security value before loading the next boot component. This process can occur at any layer of the computer 1302's code execution stack, for example, it can be applied at the application execution level or the operating system (OS) kernel level, thereby achieving security at any level of code execution.
[0144] Users can input commands and information into computer 1302 through one or more wired / wireless input devices, such as keyboard 1338, touchscreen 1340, and pointing devices, such as mouse 1342. Other input devices (not shown) may include microphones, infrared (IR) remote controls, radio frequency (RF) remote controls, or other remote controls, joysticks, virtual reality controllers and / or virtual reality headsets, gamepads, styluses, image input devices (e.g., cameras), gesture sensor input devices, visual motion sensor input devices, emotion or face detection devices, biometric input devices (e.g., fingerprint or iris scanners), etc. These and other input devices are typically connected to processing unit 1304 via input device interface 1344 (which may be coupled to system bus 1308), but may be connected via other interfaces, such as parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, Bluetooth® interfaces, etc.
[0145] The monitor 1346 or other types of display devices, such as the video adapter 1348, can also be connected to the system bus 1308 via an interface. In addition to the monitor 1346, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, etc.
[0146] Computer 1302 can operate in a networked environment using logical connections to one or more remote computers (such as (multiple) remote computers 1350) via wired and / or wireless communications. The (multiple) remote computers 1350 can be workstations, server computers, routers, personal computers, laptops, microprocessor-based entertainment devices, peer-to-peer devices, or other public network nodes, and typically include many or all of the elements described relative to computer 1302, although for simplicity, only memory / storage device 1352 is illustrated. The depicted logical connections include wired / wireless connections to a local area network (LAN) 1354 and / or a larger network (e.g., a wide area network (WAN) 1356). Such LAN and WAN network environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can connect to global communication networks, such as the Internet.
[0147] When used in a LAN network environment, computer 1302 can connect to local network 1354 via a wired and / or wireless communication network interface or adapter 1358. Adapter 1358 can facilitate wired or wireless communication with LAN 1354, which may also include a wireless access point (AP) configured thereon for communicating with adapter 1358 in wireless mode.
[0148] When used in a WAN networking environment, computer 1302 may include modem 1360, or may otherwise be connected to a communication server on WAN 1356 to establish communication via WAN 1356, such as via the Internet. Modem 1360 (which may be internal or external, wired or wireless) may be connected to system bus 1308 via input device interface 1344. In a networking environment, program modules depicted relative to computer 1302 or parts thereof may be stored in remote memory / storage device 1352. It should be understood that the network connection shown is an example, and other methods of establishing communication links between computers may be used.
[0149] When used in a LAN or WAN network environment, computer 1302 can access cloud storage systems or other network-based storage systems to supplement or replace external storage device 1316 as described above. Typically, the connection between computer 1302 and the cloud storage system can be established via LAN 1354 or WAN 1356, for example, via adapter 1358 or modem 1360, respectively. When computer 1302 is connected to the associated cloud storage system, external storage interface 1326 can manage the storage devices provided by the cloud storage system with the help of adapter 1358 and / or modem 1360, just as it would manage other types of external storage devices. For example, external storage interface 1326 can be configured to provide access to cloud storage sources as if these sources were physically connected to computer 1302.
[0150] Computer 1302 can be operable to communicate with any wireless device or entity operatively configured in wireless communication, such as printers, scanners, desktop and / or laptop computers, portable data assistants, communication satellites, any device or location associated with a wirelessly detectable tag (e.g., a kiosk, newsstand, shelf, etc.), and telephones. This can include Wi-Fi and Bluetooth® wireless technologies. Therefore, communication can be a predefined structure like a traditional network, or simply self-organizing communication between at least two devices.
[0151] Go to Figure 14The figure illustrates a block diagram of example UE 1460. UE 1460 may include a smartphone, wireless tablet, wirelessly-enabled laptop, wearable device, machine equipment that can facilitate vehicle telematics, tracking device, remote sensing device, etc. UE 1460 includes a first processor 1430, a second processor 1432, and shared memory 1434. UE 1460 includes a radio front-end circuitry system 1462, which may be referred to herein as a transceiver, but should be understood to generally include a transceiver circuitry system, separate filters, and a separate antenna for facilitating communication via wireless links (such as…). Figure 1 The transceiver 1462 may include multiple sets of circuitry, or may be tunable to accommodate different frequency ranges, different modulation schemes, or different communication protocols to facilitate long-range wireless links (such as link 125, 135, and 137), device-to-device links (such as link 135), and short-range wireless links (such as link 137).
[0152] continue Figure 14 As described above, UE 1460 may also include SIM 1464 or SIM profile, which may include information stored in memory (memory 1434 or a separate memory portion) for facilitating communication with... Figure 1 The wireless communication of RAN 105 or core network 130 shown. Figure 14 The SIM 1464 is shown as a single component in the form of a traditional SIM card; however, it should be understood that the SIM 1464 can represent multiple SIM cards, multiple SIM profiles, or multiple eSIMs, some or all of which can be implemented in hardware or software. It should be understood that a SIM profile may include security certificates (e.g., encryption keys, values that can be used to generate encryption keys, or shared values shared between the SIM 1464 and another device, which could be...) Figure 1 Information such as the components of RAN 105 or core network 130 shown. The SIM profile 1464 may also include SIM or SIM profile-specific identification information, such as International Mobile Subscriber Identity (IMSI) or information that may constitute an IMSI.
[0153] SIM 1464 is shown as being coupled to both the first processor portion 1430 and the second processor portion 1432. This implementation provides the advantage that the first processor portion 1430 does not need to request or receive information or data that the second processor 1432 may request from SIM 1464, thereby eliminating the use of the first processor as a "man-in-the-middle" when the second processor uses information from the SIM in performing its functions and executing applications. The first processor 1430 (which may be a modem processor or a baseband processor) is shown as smaller than processor 1432, which may be a more complex application processor, to visually indicate the relative complexity (i.e., processing power and performance) and corresponding relative operating power consumption levels between the two processor portions. Keeping the UE 1460 in a sleep / inactive / low-power state when the second processor section 1432 is not required to execute applications and process application-related data provides an advantage. Specifically, power consumption can be reduced when the UE only needs to use the first processor section 1430 in listening mode to monitor the routine configuration of bearer management and mobility management / maintenance processes, or when the second processor section is kept inactive / sleep to monitor the search space that the UE is configured to monitor.
[0154] UE 1460 may also include sensors 1466 that can provide signals to the first processor 1430 or the second processor 1432, such as, for example, a temperature sensor, accelerometer, gyroscope, barometer, humidity sensor, etc. Output devices 1468 may include, for example, one or more visual displays (e.g., computer monitors, VR devices, etc.), acoustic transducers (such as speakers or microphones), vibration components, etc. Output devices 1468 may include software that interfaces with output devices (e.g., visual displays, speakers, microphones, haptic devices, olfactory or gustatory devices, etc.) external to UE 1460.
[0155] The following glossary of terms given in Table 2 may be applied to one or more descriptions of the embodiments disclosed herein. Table 2
[0156] The above description includes non-limiting examples of various embodiments. It is certainly not possible to describe every conceivable combination of components or methods in order to describe the disclosed subject matter, and those skilled in the art will recognize that other combinations and arrangements of various embodiments are possible. The disclosed subject matter is intended to cover all such changes, modifications, and variations that fall within the spirit and scope of the appended claims.
[0157] Regarding the various functions performed by the aforementioned components, devices, circuits, systems, etc., unless otherwise stated, the terminology used to describe such components (including references to "means") should also include any (or more) structures (e.g., functional equivalents) that perform the specified functions of the aforementioned components, even if they are not structurally equivalent to the disclosed structures. Furthermore, while specific features of the disclosed subject matter may be disclosed only for one of several implementations, such features may be combined with one or more other features of other implementations that are desirable and advantageous for any given or particular application.
[0158] The terms “exemplary” and / or “illustrator” or variations thereof, as used herein, are intended to mean as an example, instance, or illustration. To avoid ambiguity, the subject matter disclosed herein is not limited to these examples. Furthermore, any aspect or design described herein as “exemplary” and / or “illustrator” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor does it exclude equivalent structures and techniques known to those skilled in the art. Moreover, within the scope of the terms “includes,” “has,” “contains,” and other similar words used in the detailed descriptions or claims, these terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word, without excluding any additional or other elements.
[0159] The term “or” as used herein is intended to mean an inclusive “or” rather than an exclusive “or.” For example, the phrase “A or B” is intended to include A, B, and instances of A and B. Furthermore, the articles “a” and “an” as used in this application and the appended claims should generally be interpreted as “one or more” unless the context otherwise specifies or explicitly points to the singular form.
[0160] The term "set" as used herein does not include the empty set, i.e., a set containing no elements. Therefore, a "set" in the subject matter disclosure includes one or more elements or entities. Similarly, the term "group" as used herein refers to a collection of one or more entities.
[0161] Unless the context clearly specifies otherwise, the terms “first,” “second,” and “third,” etc., used in the claims are for clarity only and do not otherwise indicate or imply any order of time. For example, “first determination,” “second determination,” and “third determination” do not mean or imply that the first determination will be made before the second determination, or vice versa, etc.
[0162] The description of the illustrated embodiments of the subject matter disclosed herein (including those described in the abstract) is not intended to be exhaustive or to limit the disclosed embodiments to the precise forms disclosed. While specific embodiments and examples have been described herein for illustrative purposes, various modifications are possible within the scope of these embodiments and examples, as will be appreciated by those skilled in the art. In this regard, although the subject matter has been described herein in conjunction with various embodiments and corresponding drawings, it should be understood where applicable that other similar embodiments may be used, or modifications and additions may be made to the described embodiments to perform the same, similar, alternative, or replacement functions of the disclosed subject matter without departing from the disclosure. Therefore, the disclosed subject matter should not be limited to any single embodiment described herein, but should be interpreted broadly and broadly in accordance with the following appended claims.
Claims
1. A method comprising: determining, by a radio access network node comprising a processor, updated artificial intelligence model information to be transmitted to a user equipment; transmitting, by the radio access network node, a data radio bearer setup request to a control entity; receiving, by the radio access network node, a data radio bearer configuration from the control entity, wherein the control entity transmitted the data radio bearer configuration to the radio access network node in response to the data radio bearer setup request; transmitting, by the radio access network node, the updated artificial intelligence model information to the user equipment via a data radio bearer established in accordance with the data radio bearer configuration; and transmitting, by the radio access network node, a data volume report corresponding to the updated artificial intelligence model information to a user plane function.
2. The method of claim 1, wherein the data radio bearer configuration comprises at least one of a quality of service indication indicating a quality of service corresponding to the updated artificial intelligence model information, a data volume reporting period indication indicating a reporting period in accordance with which the data volume report is to be transmitted by the radio access network node, or a data forwarding delivery standard to be used for the transmission of the updated artificial intelligence model information by the radio access network node to be relayed to another radio access network node other than the radio access network node.
3. The method of claim 1, wherein the data volume report comprises at least one of a data radio bearer identifier corresponding to the data radio bearer or one or more user equipment identifiers corresponding to one or more user equipment comprising the user equipment to which the updated artificial intelligence model information was transmitted by the radio access network node.
4. The method of claim 1, wherein the data radio bearer is established between the radio access network node and the user equipment.
5. The method of claim 1, wherein the control entity or the user plane function is implemented by a computing component of a core network communicatively coupled to the radio access network node.
6. The method of claim 1, wherein the transmission of the updated artificial intelligence model information is via a wireless link between the radio access network node and the user equipment. transmitting at least one protocol data unit comprising the updated artificial intelligence model information, and wherein the transmission of the updated artificial intelligence model information excludes transmitting the at least one protocol data unit comprising the updated artificial intelligence model information to the user plane function.
7. The method of claim 1, wherein the sending of the updated artificial intelligence model information comprises:
8. The method of claim 7, wherein the data volume report comprises a quantity indication indicating a number of units of the at least one protocol data unit comprising the updated artificial intelligence model information. 9. The method of claim 7, wherein the data volume report comprises a volume indication indicating a size of the at least one protocol data unit comprising the updated artificial intelligence model information.
10. The method of claim 1, further comprising: sending, by the radio access network node to the user equipment, a coverage request comprising a request for a signal strength at the user equipment corresponding to the radio access network node; receiving, by the radio access network node from the user equipment, a coverage indication indicating a determined signal strength corresponding to the radio access network node determined by the user equipment; analyzing, by the radio access network node, the determined signal strength according to a delivery criterion to obtain an analyzed determined signal strength, determining, by the radio access network node, a portion of the updated artificial intelligence model information that has not been sent to the user equipment to obtain a determined not sent portion; and based on the analyzed determined signal strength being determined to satisfy the delivery criterion, sending, by the radio access network node to the user plane function, the determined not sent portion.
11. The method of claim 10, wherein the determined not sent portion is sent, by the radio access network node, to the user plane function via a backhaul communication link.
12. The method of claim 10, further comprising: determining, by the radio access network node, a portion of the updated artificial intelligence model information that has been sent to the user equipment by the radio access network node to produce a determined sent portion, wherein the data volume report comprises a volume indication indicating a number of protocol data units comprising the determined sent portion.
13. The method of claim 10, further comprising: determining, by the radio access network node, a portion of the updated artificial intelligence model information that has been sent to the user equipment by the radio access network node to produce a determined sent portion, wherein the data volume report comprises a volume indication indicating one or more protocol data units comprising the updated artificial intelligence model information.
14. A radio access node, comprising: a processor configured to: determine data to be sent to a user equipment; send a data radio bearer setup request to a control entity; receive, from the control entity in response to the data radio bearer setup request, a data radio bearer configuration; and send the data to the user equipment via a data radio bearer established between the radio access network node and the user equipment according to the data radio bearer configuration. 15. The radio access network node of claim 14, wherein the data radio bearer configuration comprises a reporting period indication that indicates a frequency at which the radio access node is to send a data volume report to a user plane function, the data volume report corresponding to a transmission of the data by the radio access network node to the user equipment, and the method further comprising: sending, by the radio access network node, a data volume report to the user plane function corresponding to the transmission of the data by the radio access network node to the user equipment in accordance with the reporting period indication.
16. The radio access network node of claim 14, wherein the transmission of the data comprises: the transmission of the protocol data unit comprising the data, and wherein the transmission of the data excludes a transmission of the protocol data unit comprising the data to the user plane function.
17. The radio access network node of claim 14, wherein the processor is further configured to: receive, from the user equipment, a coverage indication that indicates a determined signal strength corresponding to the radio access network node; analyze the determined signal strength in accordance with a delivery criterion to obtain an analyzed determined signal strength; determine a portion of the data that has not been sent to the user equipment to obtain a determined unsent data portion; and based on the analyzed determined signal strength being determined to satisfy the delivery criterion, send, by the radio access network node, the determined unsent data portion to the user plane function.
18. The radio access network node of claim 14, wherein the control entity comprises at least one of a session management function, or an access and mobility function.
19. A non-transitory machine-readable medium comprising executable instructions that, when executed by a processor of a radio access network node, facilitate performance of operations comprising: receiving, from a user equipment that implements a radio function in accordance with an artificial intelligence model, a radio performance metric corresponding to the radio function; determining, based on the radio performance metric, updated artificial intelligence model information to be sent to the user equipment for use by the user equipment to update the artificial intelligence model; establishing a data radio bearer between the radio access network node and the user equipment for sending the updated artificial intelligence model information to the user equipment; sending, via the data radio bearer, the updated artificial intelligence model information to the user equipment; and sending, by the radio access network node, a data volume report to a user plane function corresponding to the sending of the updated artificial intelligence model information.
20. The non-transitory machine-readable medium of claim 19, the operations further comprising: determining an unsent portion of the updated artificial intelligence model information; receiving, from the user equipment, a coverage indication that indicates a determined signal strength corresponding to operation of the user equipment with respect to the radio access network node; analyzing the determined signal strength in accordance with a delivery criterion to obtain an analyzed determined signal strength; and based on the analyzed determined signal strength being determined to satisfy the delivery criterion, sending, by the radio access network node, the determined unsent data portion to the user plane function. based on the analyzed determined signal strength being determined to satisfy the transfer criteria, sending the unsent portion of the updated artificial intelligence model information to the user plane function.