Indications for artificial intelligence performance phases in wireless communications
Patent Information
- Application Number
- PCT/CN2024/085797
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-04-03
- Publication Date
- 2025-07-31
Smart Images

Figure CN2024085797_31072025_PF_FP_ABST
Abstract
Description
INDICATIONS FOR ARTIFICIAL INTELLIGENCE PERFORMANCE PHASES IN WIRELESS COMMUNICATIONSTECHNICAL FIELD
[0001] This document is directed generally to communicating indications for artificial intelligence performance phases in wireless communication.BACKGROUND
[0002] In wireless communication systems, artificial intelligence (AI) may be implemented to improve the accuracy of predicted information. The communication nodes or entities of a wireless communication system in which AI models may be implemented may vary. As such, ways to optimally and efficiently determine how to communicate information related to various AI performance phases in view of the various types of AI model implementations may be desirable.SUMMARY
[0003] This document relates to methods, systems, apparatuses and devices for wireless communication. In some implementations, a method for wireless communication includes: receiving, by a first communication node, an indication from a second communication node, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; and transmitting, by the first communication node to the second communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.
[0004] In some other implementations, a method for wireless communication includes: transmitting, by a second communication node to a first communication node, an indication, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; and receiving, by the second communication node from the first communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.
[0005] In some other implementations, a device, such as a network device, is disclosed. The device may include one or more processors and one or more memories, wherein the one or more processors are configured to read computer code from the one or more memories to implement any of the methods above.
[0006] In yet some other implementations, a computer program product is disclosed. The computer program product may include a non-transitory computer-readable program medium with computer code stored thereupon, the computer code, when executed by one or more processors, causing the one or more processors to implement any of the methods above.
[0007] The above and other aspects and their implementations are described in greater detail in the drawings, the descriptions, and the claims.BRIEF DESCRIPTION OF THE DRAWINGS
[0008] FIG. 1 shows a block diagram of an example of a wireless communication system.
[0009] FIG. 2A shows a block diagram of an example configuration of a wireless access node of the wireless communication system of Fig. 1.
[0010] FIG. 2B shows an example configuration of a radio access network (RAN) node of the wireless communication system of FIG. 1 and / or the wireless access node of FIG. 2A.
[0011] FIG. 3 shows a flow chart of an example method for wireless communication.
[0012] FIG. 4 shows a flow chart of another example method for wireless communication.
[0013] FIG. 5 shows an example signaling framework between a centralized unit (CU) , a distributed unit (DU) , and a location management function (LMF) , where an artificial intelligence (AI) model is implemented in the CU.
[0014] FIG. 6 shows an example signaling framework between a CU, a DU, and a LMF, where an AI model is implemented in the DU.
[0015] FIG. 7 shows an example signaling framework between a CU, a DU, and a LMF, where an AI model is implemented in the LMF.
[0016] FIG. 8 shows a diagram of example signaling utilized by a core network element and radio access network (RAN) nodes to communicate AI measurements, requests for measurements, and error causes.DETAILED DESCRIPTION
[0017] The present description describes various embodiments of systems, apparatuses, devices, and methods for wireless communications that relate to indications for artificial intelligence performance phases. As described in further detail below, the present descriptions describes various implementations related to at least one of AI model training, AI model inference or AI performance monitoring performed at a radio access network (RAN) node side, including implementations where the NG-RAN node has a centralized unit (CU) -distributed unit (DU) split structure. Additionally, the present description describes implementations of signaling between the RAN node (s) and a core network element and signaling between the CU (s) and the DU (s) with respect to measurement requests and measurement reports. Additionally, the present description describes solutions to situations where only some of the RAN nodes have AI capability. Additionally, the present description describes solutions to situations where the AI performance monitoring is performed at the RAN node side with the assistance of the core network element.
[0018] Fig. 1 shows a diagram of an example wireless communication system 100 including a plurality of communication nodes (or just nodes) that are configured to wirelessly communicate with each other. In general, the communication nodes include at least one user device 102 and at least one wireless access node 104. The example wireless communication system 100 in Fig. 1 is shown as including two user devices 102, including a first user device 102 (1) and a second user device 102 (2) , and one wireless access node 104. However, various other examples of the wireless communication system 100 that include any of various combinations of one or more user devices 102 and / or one or more wireless access nodes 104 may be possible.
[0019] In general, a user device as described herein, such as the user device 102, may include a single electronic device or apparatus, or multiple (e.g., a network of) electronic devices or apparatuses, capable of communicating wirelessly over a network. A user device may comprise or otherwise be referred to as a user terminal, a user terminal device, or a user equipment (UE) . Additionally, a user device may be or include, but not limited to, a mobile device (such as a mobile phone, a smart phone, a smart watch, a tablet, a laptop computer, vehicle or other vessel (human, motor, or engine-powered, such as an automobile, a plane, a train, a ship, a bicycle, a drone, an unmanned aerial vehicle (UAV) , as non-limiting examples) or a fixed or stationary device, (such as a desktop computer or other computing device that is not ordinarily moved for long periods of time, such as appliances, other relatively heavy devices including Internet of things (IoT) , or computing devices used in commercial or industrial environments, as non-limiting examples) . In addition or alternatively, in any of various embodiments, a user device 102 may include an ambient IoT device, a normal user device, a reduced capacity (RedCap) user device, a low power high-accuracy positioning (LPHAP) user device, a sidelink user device, or a V2X user device.
[0020] In various embodiments, a user device 102 may include transceiver circuitry 106 coupled to an antenna 108 to effect wireless communication with the wireless access node 104. The transceiver circuitry 106 may also be coupled to a processor 110, which may also be coupled to a memory 112 or other storage device. The memory 112 may store therein instructions or code that, when read and executed by the processor 110, cause the processor 110 to implement various ones of the methods described herein.
[0021] Additionally, in general, a wireless access node as described herein, such as the wireless access node 104, may include at least one device, electronic and / or network device or apparatus, and may comprise one or more base stations or other wireless network access points capable of communicating wirelessly over a network with one or more user devices and / or with one or more other wireless access nodes 104. For example, the wireless access node 104 may comprise at least one of: a 4G LTE base station, a 5G NR base station, a 5G central-unit base station, a 5G distributed-unit base station, a next generation Node B (gNB) , an enhanced Node B (eNB) , or other similar or next-generation (e.g., 6G) base stations, or a location management function (LMF) , in various embodiments. A wireless access node 104 may include transceiver circuitry 114 coupled to an antenna 116, which may include an antenna tower 118 in various approaches, to effect wireless communication with the user device 102 or another wireless access node 104. The transceiver circuitry 114 may also be coupled to one or more processors 120, which may also be coupled to a memory 122 or other storage device. The memory 122 may store therein instructions or code that, when read and executed by the processor 120, cause the processor 120 to implement one or more of the methods described herein.
[0022] Fig. 2 shows a block diagram of an example configuration of a wireless access node 104. In the example configuration, the wireless access node (or network) 104 may include a core network element 202 and one or more radio access network (RAN) nodes 204. Some embodiments may include only one RAN node 204. Other embodiments, such as shown in Fig. 2, may include a plurality, or an n-number, of RAN nodes 204 (1) to 204 (n) , where n is two or more. In any of various embodiments, a RAN node 204 may be or include a Next Generation (NG) -RAN node, a gNB, a ng-eNB, a transmission reception point (TRP) , a transmission point (TP) , a reception point (RP) , a base station, and / or an integrated access and backhaul (IAB) node, an example of which is shown in FIG. 2. Also, in any of various embodiments, the core network element 202 may include at least one of: a location management function (LMF) 210, an access and mobility management function (AMF) 212, a user plane function (UPF) 214, and / or a sensing function (SF) 216. The core newtork element 202 may include alternative, other, or additional components in any of various other embodiments, such as a network data analytics function (NWDAF) for example. Additionally, each component of the wireless access node 104, such as the core network element 202 and each RAN node 204, may include at least one network device, and / or may be configured in hardware or a combination of hardware and software, such as by having a processor 120, a memory 122, transceiver circuitry 114, an antenna 116, and / or an antenna tower 118, such as shown in Fig. 1 for the wireless access node 104.
[0023] Additionally, as shown in Fig. 2A, the core network element 202 and each of the RAN nodes 204 may be configured to communicate (transmit and receive) with each other, such as signals or messages, and may be configured to communicate (transmit and receive) with one or more user device 102, either directly or indirectly via another component of the wireless access node (network) 104. For example, the core network element 202 (e.g., the LMF 210) may directly communicate with a user device 10, such as according to a Long-Term Evolution (LTE) positioning protocol (LPP) (i.e., via LPP signaling) , sidelink positioning protocol (SLPP) (i.e., via SLPP signaling) , and / or non-access-stratus (NAS) messaging, as non-limiting examples. In addition or alternatively, the signaling may be UE-associated signaling or non-UE-associated signaling. Also, a RAN node 204 may directly communicate with a user device 102. In particular embodiments, a RAN node 204 may directly communicate with a user device 102 at least via radio resource control (RRC) signaling. In addition, the core network element 202 may directly communicate with each RAN node 204, such as according to dedicated messaging for sensing, New Radio Positioning Protocol A (NRPPa) (i.e., via NRPPa signaling) , and / or Next Generation Application Protocol (NGAP) (i.e., via NGAP messaging) . In addition, RAN nodes 204 may directly communicate with each other, such as according to Xn application protocol (XnAP) (i.e., via XnAP messaging) . Additionally, although not shown in Fig. 2, two user devices 102 may directly communicate with each other, such as via dedicating messaging for sensing, SLPP signaling, PC5-RRC messaging, SL medium access control (MAC) control element (CE) , and / or sidelink control information (SCI) .
[0024] Also, for at least some embodiments, such as shown in Fig. 2, each RAN node 204 may include one or more sub-components. For example, a RAN node 204 may include a gNB and / or at least one transmission / reception point (TRP) 208. Additionally, as used herein unless specified otherwise, the terms “network” or “network device” may include at least one gNB 206, at least one ng-eNB, at least one TRP 208, at least one base station, at least one RAN node 204 (e.g., at least one NG-RAN node) and / or at least one core network element 202. Further functionality of the core network element 202 and the RAN nodes 204 is described in further detail below.
[0025] Fig. 2B shows an example configuration of a RAN node 204, which may be an alternative or additional configuration to one or more of the RAN nodes 204 in Fig. 2A. As shown in Fig. 2B, the RAN node 204 may include one or more TRPs 208, similar to the configuration shown in Fig. 2A. Additionally, the RAN node 204 may include a centralized unit 252 and one or more distributed units (DU) 254. Fig. 2B shows the RAN node 204 including two DUs 254 (1) , 254 (2) , although other numbers including only one or three or more DUs for any of various other configurations are possible. In addition, each TRP 208 may be associated with a respective one of the DUs 254, and / or each DU 254 may be associated with one or more TRPs 208. For example, in the configuration shown in Fig. 2B, TRP1 and TRP2 are associated with the first DU1 254 (1) and TRP3 and TRP4 are associated with the second DU2 254 (2) . In addition, the CU 252 may communicate with the DUs 254 and the DUs 254 may communicate with each other, such as via F1AP signaling. Further, the CU 252 may communicate with other RAN nodes, such as other CUs of other RAN nodes via XnAP signaling. Also, the CU 252 may communicate with the core network element 202, including one or more components of the core network element 202, such as the LMF 210, such as via NGAP signaling for example. In some implementations, the CU 252 and DUs 254 may effectively replace the structure and / or functionality of the gNB 206 of a RAN node 204. In other implementations, a gNB 206 of a given RAN node 204 may be configured in the form of a CU 252 and DUs 254. Various ways of implementing a RAN node 204 with a gNB 206, a CU 252, one or more DUs 254 or any of various combinations thereof are possible.
[0026] Accordingly, in the configuration in Fig. 2B, one RAN node 204 may be split into a CU 252 and one or more associated DUs 254. Additionally, in some implementations, one TRP 208 may be associated with one or more antenna reference points (ARPs) . In particularly of these implementations, each TRP 208 and each ARP may have different geographic locations. One RAN node 204 may serve a plurality of cells, such as up to 16, 384 cells in some implementations. In addition or alternatively, one RAN node 204 may serve a plurality of TRPs 208, such as up to 65,535 TRPs in some implementations. In addition or alternatively, in some implementations, a CU 252 may be directly linked with and / or be able to directly communicate with the core network element 202. For at least some of these implementations, signaling to enable to the direct communication is embedded in the NGAP or NRPPa protocol. Also, for at least some implementations such as shown in Fig. 2B, the CU 252 of the RAN node 250 is directly linked and / or is able to directly communicate with the DUs 254 of the RAN node 250. Signaling to enable the direct communication may be embedded in the F1AP protocol. Additionally, the CU 252 of a RAN node 250 is directly linked and / or is able to directly communicate with one or more CUs 252 of one or more other RAN nodes. Signaling to enable the direct communication may be embedded in the XnAP protocol. Implementations where one or more DUs 254 are directly linked and / or are able to directly communicate with the core network element 202 are possible.
[0027] In addition, referring back to Fig. 1, in various embodiments, two communication nodes in the wireless system 100-such as a user device 102 and a wireless access node 104, two user devices 102 without a wireless access node 104, or two wireless access nodes 104 without a user device 102-may be configured to wirelessly communicate with each other in or over a mobile network and / or a wireless access network according to one or more standards and / or specifications. In general, the standards and / or specifications may define the rules or procedures under which the communication nodes can wirelessly communicate, which, in various embodiments, may include those for communicating in millimeter (mm) -Wave bands, and / or with multi-antenna schemes and beamforming functions. In addition or alternatively, the standards and / or specifications are those that define a radio access technology and / or a cellular technology, such as Fourth Generation (4G) Long Term Evolution (LTE) , Fifth Generation (5G) New Radio (NR) , or New Radio Unlicensed (NR-U) , as non-limiting examples.
[0028] Additionally, in the wireless system 100, the communication nodes are configured to wirelessly communicate signals between each other. In general, a communication in the wireless system 100 between two communication nodes can be or include a transmission or a reception, and is generally both simultaneously, depending on the perspective of a particular node in the communication. For example, for a given communication between a first node and a second node where the first node is transmitting a signal to the second node and the second node is receiving the signal from the first node, the first node may be referred to as a source or transmitting node or device, the second node may be referred to as a destination or receiving node or device, and the communication may be considered a transmission for the first node and a reception for the second node. Of course, since communication nodes in a wireless system 100 can both send and receive signals, a single communication node may be both a transmitting / source node and a receiving / destination node simultaneously or switch between being a source / transmitting node and a destination / receiving node.
[0029] Also, particular signals can be characterized or defined as either an uplink (UL) signal, a downlink (DL) signal, or a sidelink (SL) signal. An uplink signal is a signal transmitted from a user device 102 to a wireless access node 104. A downlink signal is a signal transmitted from a wireless access node 104 to a user device 102. A sidelink signal is a signal transmitted from a one user device 102 to another user device 102, or a signal transmitted from one wireless access node 104 to a another wireless access node 104. Also, for sidelink transmissions, a first / source user device 102 directly transmits a sidelink signal to a second / destination user device 102 without any forwarding of the sidelink signal to a wireless access node 104.
[0030] Additionally, signals communicated between communication nodes in the system 100 may be characterized or defined as a data signal or a control signal. In general, a data signal is a signal that includes or carries data, such multimedia data (e.g., voice and / or image data) , and a control signal is a signal that carries control information that configures the communication nodes in certain ways in order to communicate with each other, or otherwise controls how the communication nodes communicate data signals with each other. Also, certain signals may be defined or characterized by combinations of data / control and uplink / downlink / sidelink, including uplink control signals, uplink data signals, downlink control signals, downlink data signals, sidelink control signals, and sidelink data signals.
[0031] For at least some specifications, such as 5G NR, data and control signals are transmitted and / or carried on physical channels. Generally, a physical channel corresponds to a set of time-frequency resources used for transmission of a signal. Different types of physical channels may be used to transmit different types of signals. For example, physical data channels (or just data channels) are used to transmit data signals, and physical control channels (or just control channels) are used to transmit control signals. Example types of physical data channels include, but are not limited to, a physical downlink shared channel (PDSCH) used to communicate downlink data signals, a physical uplink shared channel (PUSCH) used to communicate uplink data signals, and a physical sidelink shared channel (PSSCH) used to communicate sidelink data signals. In addition, example types of physical control channels include, but are not limited to, a physical downlink control channel (PDCCH) used to communicate downlink control signals, a physical uplink control channel (PUCCH) used to communicate uplink control signals, and a physical sidelink control channel (PSCCH) used to communicate sidelink control signals. As used herein for simplicity, unless specified otherwise, a particular type of physical channel is also used to refer to a signal that is transmitted on that particular type of physical channel, and / or a transmission on that particular type of transmission. As an example illustration, a PDSCH refers to the physical downlink shared channel itself, a downlink data signal transmitted on the PDSCH, or a downlink data transmission. Accordingly, a communication node transmitting or receiving a PDSCH means that the communication node is transmitting or receiving a signal on a PDSCH.
[0032] Additionally, for at least some specifications, such as 5G NR, and / or for at least some types of control signals, a control signal that a communication node transmits may include control information comprising the information necessary to enable transmission of one or more data signals between communication nodes, and / or to schedule one or more data channels (or one or more transmissions on data channels) . For example, such control information may include the information necessary for proper reception, decoding, and demodulation of a data signals received on physical data channels during a data transmission, and / or for uplink scheduling grants that inform the user device about the resources and transport format to use for uplink data transmissions. In some embodiments, the control information includes downlink control information (DCI) that is transmitted in the downlink direction from a wireless access node 104 to a user device 102. In other embodiments, the control information includes uplink control information (UCI) that is transmitted in the uplink direction from a user device 102 to a wireless access node 104, or sidelink control information (SCI) that is transmitted in the sidelink direction from one user device 102 (1) to another user device 102 (2) .
[0033] In addition, in some embodiments, a transmitting node may transmit a reference signal for positioning, such via an interface. For example, a gNB 206 may transmit a downlink positioning reference signal (DL-PRS) to a user device 102 via a Uu interface. As another example, a user device 102 may transmit a sounding reference signal (SRS) to a gNB 206, such as via a Uu interface. As another example, a user device 102 may transmit a sidelink positioning reference signal (SL-PRS) to another user device 102.
[0034] Fig. 3 is a flow chart of an example method 300 of wireless communication related to artificial intelligence (AI) indication information. At block 302, a first communication node receives an indication from a second communication node. The indication includes at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter. At block 304, the first communication node transmits to the second communication node a report according to the indication. The report including at least one of: an AI measurement result or an AI performance monitoring result.
[0035] Fig. 4 is a flow chart of another example method 400 of wireless communication related to AI indication information. At block 402, a second communication node transmits to a first communication node an indication. The indication includes at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter. At block 404, the second communication node receives from the first communication node a report according to the indication. The report includes at least one of: an AI measurement result or an AI performance monitoring result.
[0036] In some implementations of the method 300 and / or the method 400, the indication includes the AI measurement report request, the AI measurement report request includes at least one of: a number of transmission reception points (TRPs) per first communication node to be reported; a TRP identification (ID) list to be measured; an Antenna Reference Point (ARP) ID list to be measured; a number of ARPs per TRP to be reported; a number of ARPs per first communication node to be reported; a port ID list or a port pair ID list to be measured; a number of ports or a number of port pairs to be reported; a number of reference signals to be measured; a required one or more AI measurement types to be reported; an indication on whether to report a path timing or a sample index for an AI measurement; a required reporting sample number; a required reporting path number; a maximum and / or a minimum required reporting sample number; a maximum and / or a minimum required reporting path number; a request to report whether one or more intermediate features is generated by an AI model; or an AI model ID or an AI model ID list.
[0037] In some implementations of the method 300 and / or the method 400, the maximum and / or a minimum required reporting sample number is associated with each AI measurement type or each requested measurement quantity.
[0038] In some implementations of the method 300 and / or the method 400, the maximum and / or the minimum required reporting path number is associated with each AI measurement type or each requested measurement quantity.
[0039] In some implementations of the method 300 and / or the method 400, the first communication node transfers a set of AI measurements to a third communication node of a same type as the first communication node.
[0040] In some implementations of the method 300 and / or the method 400, the first communication node receives from the second communication node a transfer indication in the AI measurement transfer request.
[0041] In some implementations of the method 300 and / or the method 400, the transfer indication includes an identification (ID) of the third communication node to which the first communication node is to transfer the set of AI measurements.
[0042] In some implementations of the method 300 and / or the method 400, the third communication node receives from the second communication node, a transfer indication in the AI measurement transfer request.
[0043] In some implementations of the method 300 and / or the method 400, the transfer indication includes an identification of the first communication node from which the third communication node is to gather the set of AI measurements.
[0044] In some implementations of the method 300 and / or the method 400, the first communication node transfers the set of AI measurements to the third communication node based on a transfer indication sent by the third communication node.
[0045] In some implementations of the method 300 and / or the method 400, the set of AI measurements includes at least one of: channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .
[0046] In some implementations of the method 300 and / or the method 400, the set of AI measurements is associated with at least one of: one or more positioning reference unit (PRU) identifications (IDs) or one or more PRU locations.
[0047] In some implementations of the method 300 and / or the method 400, the third communication node reports a set of AI intermediate features to the second communication node, wherein the set of AI intermediate is associated with one or more identifications (IDs) of the first communication node which provides the set of AI measurements.
[0048] In some implementations of the method 300 and / or the method 400, the first communication node reports a set of AI intermediate features to the second communication node. The set of AI intermediate features is associated with one or more identifications (IDs) of the third communication node which provides the set of AI intermediate features.
[0049] In some implementations of the method 300 and / or the method 400, the AI measurement result includes a cause of error in response to the first communication node being required to perform AI measurements and / or determine AI intermediate features using an AI model but the first communication node is not available to perform the AI measurements and / or to determine the intermediate features using the AI model.
[0050] In some implementations of the method 300 and / or the method 400, the cause of error is reported together with a transmission reception point (TRP) list.
[0051] In some implementations of the method 300 and / or the method 400, the AI model training parameter includes whether to train an AI model and / or to download the AI model from an external network element.
[0052] In some implementations of the method 300 and / or the method 400, the AI model training parameter includes a training quality of service (QoS) requirement, the training QoS requirement including at least one of: a timing accuracy requirement, an angle accuracy requirement, a power class accuracy requirement, a phase accuracy requirement, a location or distance accuracy requirement, a latency requirement, a minimum accuracy rate of line of sight (LOS) and / or non-line of sight (NLOS) determination, or a generalization requirement.
[0053] In some implementations of the method 300 and / or the method 400, the second communication node provides a positioning reference unit (PRU) list to the first communication node.
[0054] In some implementations of the method 300 and / or the method 400, the PRU list includes PRU information, the PRU information including at least one of: a PRU identification (ID) , a PRU location, a cell ID or a cell list that is associated with a PRU, a transmission reception point (TRP) ID or a TRP ID list that is associated with the PRU, an antenna reference point (ARP) ID or a ARP ID list that is associated with the PRU, beam information that is associated with the PRU, or a radio access network (RAN) node ID or a RAN node list that is associated with the PRU.
[0055] In some implementations of the method 300 and / or the method 400, the second communication node provides one or more expected intermediate features of at least one positioning reference unit (PRU) to the first communication node.
[0056] In some implementations of the method 300 and / or the method 400The method of claim 22, wherein the one or more expected intermediate features comprises at least one of: one or more expected relative time of arrival (RTOA) values or one or more expected time of arrival (TOA) values; one or more expected angle of arrival (AoA) values; one or more expected receive (Rx) -transmit (Tx) time difference values; one or more expected sounding reference signal (SRS) reference signal received power (RSRP) values or one or more expected SRS reference signal received power per path (RSRPP) values; or one or more expected SRS reference signal carrier phase (RSCP) values or one or more expected SRS reference signal carrier phase difference (RSCPD) values; or one or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.
[0057] In some implementations of the method 300 and / or the method 400, the second communication node is a location management function (LMF) 210 and the first communication is a user device 102, and the one or more expected intermediate features includes at least one of: one or more expected reference signal time difference (RSTD) values or one or more expected time of arrival (TOA) values; one or more expected angle of arrival (AoA) values; one or more expected angle of departure (AoD) values; one or more expected receive (Rx) -transmit (Tx) time difference values; one or more expected positioning reference signal (PRS) reference signal received power (RSRP) values or one or more expected PRS reference signal received power per path (RSRPP) values; one or more expected PRS reference signal carrier phase (RSCP) values or one or more expected PRS reference signal carrier phase difference (RSCPD) values; or one or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.
[0058] In some implementations of the method 300 and / or the method 400, one or more PRU identifications (IDs) and / or one or more PRU locations are indicated together with the one or more expected intermediate features.
[0059] In some implementations of the method 300 and / or the method 400, one or more TRP IDs and / or one or more RAN node IDs are indicated together with the one or more expected intermediate features.
[0060] In some implementations of the method 300 and / or the method 400, the second communication node provides a recommended sounding reference signal (SRS) configuration for a positioning reference unit (PRU) to the first communication node to do performance monitoring.
[0061] In some implementations of the method 300 and / or the method 400, the recommended SRS configuration or a requested SRS characteristic message is provided together with at least one of a PRU identification (ID) or a PRU ID list, a PRU location, or a PRU location list.
[0062] In some implementations of the method 300 and / or the method 400, the recommended SRS configuration is provided with an indication on whether or not the recommended SRS configuration is used for AI performance monitoring.
[0063] In some implementations of the method 300 and / or the method 400, the second communication node sends the AI measurement report request message to the first communication node. The first communication node includes a serving and / or a neighboring communication node of a positioning reference unit (PRU) , and the AI measurement report request message includes at least one of a type of user device or a user device identification (ID) .
[0064] In some implementations of the method 300 and / or the method 400, the second communication node sends the AI measurement report request to the first communication node. The first communication node includes a serving and / or a neighboring communication node of a positioning reference unit (PRU) for measurement requests, and the AI measurement report request message is sent according to a user device associated signaling.
[0065] In some implementations of the method 300 and / or the method 400, the AI performance monitoring parameter includes one or more monitoring control parameters or criteria for the first communication node. The one or more monitoring control parameters or criteria include at least one of: a threshold, a time duration, or a number of times.
[0066] In some implementations of the method 300 and / or the method 400, the threshold includes at least one of: a value representing a timing, a value representing a distance, a value representing an angle, a value representing a power class, or a value representing a phase.
[0067] In some implementations of the method 300 and / or the method 400, the AI performance monitoring result includes an indication of AI model performance loss.
[0068] In some implementations of the method 300 and / or the method 400, the first communication node includes a user device and the second communication node includes a core network element.
[0069] In some implementations of the method 300 and / or the method 400, the report includes the AI measurement result, and the AI measurement result includes one or more AI measurements.
[0070] In some implementations of the method 300 and / or the method 400, the report further comprises an indication of whether each of the one or more AI measurements includes a channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .
[0071] In some implementations of the method 300 and / or the method 400, each of the one or more AI measurements is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; one or more port pair IDs; or one or more user device IDs.
[0072] In some implementations of the method 300 and / or the method 400, the report includes one or more intermediate features. Each of the one or more intermediate features is associated with an indication to indicate whether or not the intermediate feature is generated by an AI model.
[0073] In some implementations of the method 300 and / or the method 400, each of the one or more AI intermediate features is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; one or more port pair IDs; or one or more user device IDs.
[0074] In some implementations of the method 300 and / or the method 400, the first communication node includes a radio access network (RAN) node and the second communication node includes a core network element.
[0075] In some implementations of the method 300 and / or the method 400, the first communication node includes a distributed unit (DU) and the second communication node includes a centralized unit (CU) .
[0076] Further details of actions performed by one or more communication nodes in the wireless communication system 100, any of which may be incorporated into any of various implementations of the method 300, the method 400 or other methods, are now described.
[0077] In some implementations positioning utilizing AI (or AI positioning) may include and / or be performed in at least one of three phase, including: an AI training phase, an AI inference phase, and an AI performance monitoring phase. Uplink (UL) positioning and a combination of UL and downlink (DL) positioning may be performed with a RAN node 204 using an AI model.
[0078] In further detail, in some implementations of the AI inference phase, AI inference is performed by an AI model in the CU 252, or inference is performed with an AI model in one or more DUs 254. In other implementations, inference is performed by an external network element (e.g., operation administration and maintenance (OAM) or over-the-top (OTT) server, or an external server, as non-limiting examples) . In still other implementations, AI inference may be performed in the core network element 202.
[0079] Also, in some implementations of the AI training phase, AI training may be performed in the CU 252 of a RAN node 204 and / or in one or more DUs 254 of a RAN node 204. In other implementations, AI training is performed with the core network element 202 (e.g., the LMF 210) . In still other implementations, AI training is performed with an external network element.
[0080] Additionally, in some implementations of the AI performance monitoring phase, AI performance monitoring may be performed with the CU 252 of a RAN node 204 and / or with one or more DUs 254 of a RAN node 204. In other implementations, AI performance monitoring may be performed with an external network element. In still other implementations, AI performance monitoring may be performed with the core network element 210.
[0081] Additionally, in any of various implementations, an external network element may include at least one of an OAM, an OTT server, or any entity or network element configured to perform an AI function and can be linked to and / or communicate with one or more NG-RAN nodes 204. In addition or alternatively, an external network element may be directly linked with a CU 252 and / or DUs 254 of a RAN node 204. In addition or alternatively, an external network element may be directly linked with the core network element 210.
[0082] Additionally, as used herein, the term UL positioning means or includes a positioning method in which a user device 102 sends a sounding reference signal (SRS) , and / or one or more RAN nodes 204 to receive the SRS and make one or more SRS measurements. In turn, the the one or more RAN nodes 204 may report the SRS measurement to the core network element 202 for positioning calculation. For example, an uplink (UL) -time difference of arrival (TDOA) or UL-angle of arrival (AoA) positioning method.
[0083] In addition, a combination of UL and DL positioning, also called herein “UL+DL positioning” , means or includes a positioning method in which a RAN node 204 send a positioning reference signal (PRS) and the RAN node 204 receives a SRS from a user device 102. In turn, the NG-RAN node 204 reports a reference signal measurement for positioning to the core network element 202 for a positioning calculation. One type of UL+DL positioning may include multi-round-trip time (RTT) positioning.
[0084] Additionally, in some implementations, an AI measurement made by a user device 102 may include at least one of the following: a channel impulse response (CIR) for a PRS measurement, a power delay profile (PDP) for a PRS measurement, or a delay profile (DP) for a PRS measurement.
[0085] Additionally, in some implementations, an AI measurement made by a RAN node 204 may include at least one of the following: a CIR for a SRS measurement, a PDP for a SRS measurement, or DP for a SRS measurement.
[0086] Additionally, in some implementations, a CIR includes a timing, a phase and an amplitude value; a PDP includes a timing and an amplitude value; and / or a DP includes a timing value. The timing value may indicate a path delay of the measurement, the phase value may indicate the phase measurement, and the amplitude value may indicate a power, e.g., RSRP or RSRPP measurement.
[0087] Additionally, in some implementations, an AI intermediate feature generated by a user device 102 may include at least one of the following: a PRS reference signal received power (RSRP) , a PRS reference signal received power per path (RSRPP) , a PRS reference signal carrier phase (RSRPP) , a PRS reference signal carrier phase difference (RSCPD) , a PRS reference signal time difference (RSTD) , a user device (or UE) receive (Rx) -transmit (Tx) time difference, a PRS angle of arrival (AoA) , a SRS angle of departure (AoD) , a PRS Rx beam index, a PRS Rx timing error group (TEG) , a PRS Tx TEG, a user device (or UE) RxTx TEG, a line of sight (LOS) indicator, or a non-line of sight (NLOS) indicator. Additionally, each AI intermediate feature may be measured by a user device 102 from a TRP 208 or several TRPs 208 of one or more RAN nodes 204.
[0088] Additionally, in some implementations, an AI intermediate feature generated by a RAN node 204 may include at least one of the following: a SRS AoA, a PRS AoD, a SRS Zenith Angle of Arrival (Z-AoA) , a SRS Rx beam index or SRS Rx beam information, an ARP ID, a SRS RSRP, a SRS RSRPP, a SRS RSCP, a SRS RSCPD, a SRS reference time of arrival (RTOA) , a gNB Rx-Tx time difference, a LOS / NLOS indicator, a SRS Rx TEG, a SRS Tx TEG, or a gNB RxTx TEG.
[0089] In addition, as used herein, the term AI measurement is or refers to the input of an AI model. Also, in any of various implementations, the output of an AI model may be or include a location of a user device 102 and / or at least one AI intermediate feature.
[0090] Additionally, in some implementations for a life cycle management (LCM) procedure, the core network element 202 (e.g., the LMF 210) may schedule or request the user device 102 to use an AI model to output an estimated user device 102 location. In other implementations, the core network element 202 (e.g., the LMF 210) may schedule or request the user device 102 to use an AI model to output AI intermediate features. In other implementations, the core network element 202 (e.g., the LMF 210) may schedule or request the user device 102 to measure PRS and report PRS AI measurement. The signaling can be embedded in LTE positioning protocol (LPP) , RequestLocationInformation, or ProvideAssistanceData messages.
[0091] Additionally, in some implementations, the core network element 202 (e.g., the LMF 210) may schedule or request a RAN node 204 to use an AI model to output AI intermediate features, or the core network element 202 (e.g., the LMF 210) may schedule or request a RAN node 204 to measure a sounding reference signal (SRS) and report a SRS AI measurement. In any of various of these implementations, the RAN node 204 may be a serving RAN node or one or more neighbor RAN nodes of a user device 102.
[0092] Embodiment 1
[0093] In further detail in some embodiments, a CU 252 may indicate an AI measurement request to a DU 254. In at least some of these embodiments, the AI measurement request may include at least one of the following:
[0094] a number of TRPs per DU, indicating that how many TRPs 208 are associated with a particular DU 254 are required to make and report an AI measurement (this number may be indicated as a value range, such as one that includes or indicates a minimum allowed number and / or a maximum allowed number) ;
[0095] a TRP ID list, indicating the TRP (s) 208 of a DU 254 that are to make an AI measurement;
[0096] an ARP ID list, indicating the ARPs of an associated TRP 208 that are required to make and report an AI measurement;
[0097] a number of ARPs per TRP 208, indicating how many ARPs of a TRP 208 are required to make and report an AI measurement (this number may be indicated as a value range, such as one indicating a minimum allowed number and / or a maximum allowed number) ;
[0098] a number of ARPs per DU 254, indicating that how many ARPs of a particular DU 254 are required to make and report an AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0099] a port ID list or a port pair ID list, indicating a receiving port or a port pair that is required to make and report an AI measurement (the port ID list or port pair ID list may be associated with at least one of each DU 254, each TRP 208 or each ARP) ;
[0100] a number of ports or port pairs, indicating how many receiving ports or port pairs that are required to make and report AI measurement (the number may be associated with at least one of each DU 254, each TRP 208, or each ARP; this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0101] a number of RS, indicating how many RS the DU 254 is to measure to make an AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number; and / or the number of RS may also be a number of RS instances or samples per RS, or a repetition number of a RS; and / or the RS may be a SRS resource or a SRS resource set) ;
[0102] a required one or more AI measurement types (e.g., CIR, PDP, and / or DP) (this indication may be associated with at least one of each DU 254, each TRP 208, each ARP, each port, or each port pair;
[0103] an indication on whether to report path timing or sample index for an AI measurement (this indication can be associated with at least one of each DU 254, each TRP 208, each ARP, each port, or each port pair) ;
[0104] a required reporting sample number, indicating the required reporting sample number of a symbol (the required reporting sample number may be associated with at least one of each AI measurement type, or may be associated with at least one of each DU 254, each TRP 208, each ARP, each port, or each port pair;
[0105] a required reporting path number, indicating the required reporting path number or additional path number of a symbol (the required reporting path number may be associated with at least one of each AI measurement type, or may be associated with at least one of each DU 254, each TRP 208, each ARP, each port, or each port pair) ;
[0106] a maximum and / or a minimum required reporting sample number, indicating that the DU 254 is to report no larger than the maximum required reporting sample number in a symbol, and / or that the DU 254 is to report no smaller than the minimum required reporting sample number in a symbol (the maximum and / or the minimum required reporting sample number can be associated with each AI measurement type or each requested measurement quantities, or can be associated with at least one of each NG-RAN node, each TRP, each ARP, each port or each port pair) ;
[0107] a maximum and / or a minimum required reporting path number, indicating that the DU 154 is to report no larger than the maximum required reporting path number in a symbol, and / or that the DU 254 is to report no smaller than the minimum required reporting path number in a symbol (the maximum and / or the minimum required reporting path number may be associated with each AI measurement type or each requested measurement quantities, or may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair) ;
[0108] a request from a CU 252 to a DU 254 to report whether or not the intermediate features are generated by an AI model (this request message may be associated with each requested measurement quantity, with each requested TRP 208, or with each DU 254) ; or
[0109] an AI model ID or an AI model ID list to be used by a DU 254 for positioning.
[0110] Additionally, in some implementations, the core network element 202 may indicate an AI measurement request to a RAN node 204. The AI measurement request may include at least one of the following:
[0111] a number of TRPs 208 per RAN node 204, indicating how many TRPs 208 of the RAN node 204 are to make and report an AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0112] a TRP ID list per RAN node 204, indicating the TRPs 208 of a RAN node 204 that are to make an AI measurement;
[0113] an ARP ID list, indicating the ARPs of an associated TRP 208 of a RAN node 204 that are to make and report an AI measurement;
[0114] a number of ARPs per TRP 208, indicating how many ARPs of a TRP 208 are to make and report AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0115] a number of ARPs per RAN node, indicating how many ARPs of a RAN node 204 are to make and report an AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0116] a port ID list or a port pair ID list, indicating the receiving port or the port pair that is to make and report an AI measurement (the port ID list or port pair ID list may be associated with at least one of each RAN node 204, each TRP 208, or each ARP;
[0117] a number of ports or port pairs, indicating that how many receiving ports or port pairs are to make and report an AI measurement (the indicated number may be associated with at least one of each RAN node 204, each TRP 208, or each ARP; this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0118] a number of RS, indicating that how many RS the RAN node 204 is to measure to make an AI measurement (this number may be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number; and / or the number of RS may also be a number of RS instances or samples per RS, or a repetition number of a RS; and / or the RS may be SRS resource or SRS resource set) ;
[0119] a required one or more AI measurement types (e.g., CIR, PDP, DP) (this indication may be associated with at least one of each NG-RAN node 204, each TRP 208, each ARP, each port, or each port pair;
[0120] an indication on whether a RAN node 204 is to report path timing or sample index for an AI measurement (this indication may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair) ; a required reporting sample number, indicating the required reporting sample number of a symbol (the required reporting sample number may be associated with at least one of each AI measurement type, or may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair;
[0121] a required reporting path number, indicating the required reporting path number or additional path number of a symbol (the required reporting path number may be associated with at least one of each AI measurement type, or may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair;
[0122] a maximum and / or a minimum required reporting sample number, indicating that a RAN node 204 is to report no larger than the maximum required reporting sample number in a symbol, and / or the RAN node 204 is to report no smaller than the minimum required reporting sample number in a symbol (the maximum and / or the minimum required reporting sample number may be associated with each AI measurement type or each requested measurement quantity, or may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair) ;
[0123] a maximum and / or a minimum required reporting path number, indicating the RAN node 204 is to report no larger than the maximum required reporting path number in a symbol, and / or that the RAN node 204 is to report no smaller than the minimum required reporting path number in a symbol (the maximum and / or the minimum required reporting path number may be associated with each AI measurement type or each requested measurement quantity, or may be associated with at least one of each RAN node 204, each TRP 208, each ARP, each port, or each port pair) ;
[0124] a request from the core network element 202 to a RAN node 204 to report whether the intermediate features are generated by an AI model (this request message may be associated with each AI measurement type or each requested measurement quantity, or with each requested TRP 208, or with each RAN node 204) ;
[0125] an AI model ID or an AI model ID list that is to be used by a RAN node 204 for positioning.
[0126] Additionally, in some implementations, the core network element 202 or a RAN node 204 may indicate an AI measurement request to a user device 102. The AI measurement request may include at least one of the following:
[0127] a number of TRPs 208 per user device 102, indicating how many TRPs 208 that the user device 102 is to measure to make and report an AI measurement (this number may also be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0128] a number of ports or port pairs, indicating how many receiving ports or port pairs are to make and report an AI measurement (the indicated number may be associated with at least one of each RAN node 204, each TRP 208, or each RAN node’s ARP; this number may also be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number) ;
[0129] a number of PRS resources, indicating how many PRS resources a user device 102 is to measure to make and report an AI measurement (the number of PRS resources may be indicated via at least one of per TRP 208, per frequency layer, or per user device 102; the number of PRS resources may also be the number of PRS instances / samples per PRS resource, or the number of repetitions per PRS resource that a user device 102 it to measure for a AI measurement; this number may also be indicated as a value range, such as one including or indicating a minimum allowed number and / or a maximum allowed number; and / or the PRS resource can also be replaced by PRS resource set) ;
[0130] a required one or more AI measurement types (e.g., CIR, PDP, or DP) (this indication may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource) ;
[0131] an indication of whether a user device 102 is to report a path timing or a sample index for the AI measurement (this indication may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource) ;
[0132] a required reporting sample number, indicating the required reporting sample number in a symbol (the required reporting sample number may be associated with at least one of each AI measurement type, or may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource) ;
[0133] a required reporting path number, indicating the required reporting path number or additional path number of a symbol (the required reporting path number may be associated with at least one of each AI measurement type, or may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource) ;
[0134] a maximum and / or a minimum required reporting sample number, indicating that the user device 102 is to report no larger than the maximum required reporting sample number in a symbol, and / or that the user device 102 is to report no smaller than the minimum required reporting sample number in a symbol (the maximum and / or the minimum required reporting sample number may be associated with each AI measurement type, or may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource;
[0135] a maximum and / or a minimum required reporting path number, indicating that the user device 102 is to report no larger than the maximum required reporting path number in a symbol, and / or that the user device is to report no smaller than the minimum required reporting path number in a symbol (the maximum and / or the minimum required reporting path number may be associated with each AI measurement type, or may be associated with at least one of each positioning frequency layer, each TRP 208, each PRS resource set, or each PRS resource) ;
[0136] an AI model ID or an AI model ID list that is to be used by the user device 102 for positioning.
[0137] Embodiment 2
[0138] Additionally, in some implementations for UL positioning or UL+DL positioning with AI, if AI training or inference is performed using an AI model within or inside a CU 252 of a RAN node 204, or AI training or inference is performed using an AI model within or inside the core network element 202, a DU 254 may report one or more AI measurements to the CU 252, and the one or more AI measurements is used as the AI model input. Further details of implementations of a report of one or more AI measurements is as follows.
[0139] In some implementations, a DU 254 may report one or more AI measurements to the CU 252. The type (s) of the one or more AI measurements may include at least one of: a CIR, a PDP, or a DP.
[0140] Additionally, in some implementations, a DU 254 may report an indication that indicates a type of each of the one or more AI measurements, such as whether each AI measurement is a CIR, a PDP, or a DP to the CU 252. In some of these implementations, the indication may be associated with each TRP 208, with each ARP, with each port, or with each port pair.
[0141] Additionally, in some implementations, a DU 254 may report one or more AI measurements to the CU 252, in conjunction with one or more of the following associations: each AI measurement may be associated with one or more TRP IDs; each AI measurement may be associated with one or more ARP IDs, each AI measurement may be associated with one or more port IDs, or each AI measurement may be associated with one or more port pair IDs. In some of these implementations, the port ID or the port pair ID may be associated with each ARP or each TRP 208. That is to say, one TRP 208 or one ARP may have one or more receiving ports or port pairs; or one port or one port pair may be associated with multiple ARPs or multiple TRPs 208. Each AI measurement may be associated with one or more time stamps. In addition or alternatively, each AI measurement may be associated with one or more measurement qualities, where each measurement quality may be associated with at least one of the time stamps.
[0142] To further illustrate, in an example implementation (Example 1) , a DU 254 may report multiple AI measurements to a CU 252. Each AI measurement may include up to X time sample measurements or up to X path measurements. In addition or alternatively, each AI measurement may be associated with a TRP ID, a ARP ID, a port ID, and / or a port pair ID.
[0143] As another example implementation (Example 2) , a DU 254 may report multiple AI measurements to a CU 252. Each AI measurement may include up to A×B time sample measurements or up to A×B path measurements, where A represents the maximum number of time samples or the maximum number of paths, and B represents the maximum number of receiving ports of a TRP 208 or of an ARP, or B represents the maximum number of port pairs between a user device 102 and the TRP 208 or the ARP. In addition or alternatively, each AI measurement may be associated with a TRP ID and / or an ARP ID list that includes one or more ARP IDs.
[0144] As another example implementation (Example 3) , a DU 254 may report one AI measurement to the CU 252. The AI measurement may include up to C×A×B time sample measurements or up to C×A×B path measurements, where A represents the maximum number of time samples or the maximum number of paths; B represents the maximum number of receiving ports of a TRP 208 or of an ARP, or B represents the maximum number of port pairs between a user device 102 and the TRP 208 or the ARP; and C represents the maximum number of TRPs 208 that the DU 254 measured. In addition or alternatively, each AI measurement may be associated with a TRP ID list that includes one or more TRP IDs. In addition or alternatively, each AI measurement may be further associated with an ARP ID list that includes one or more ARP IDs.
[0145] Additionally, in some implementations, a DU 254 may report intermediate features to CU.Each intermediate feature may be associated with an AI indication to indicate whether or not the intermediate feature is generated by an AI model. Some of these implementations may include one or more of the following signaling scheme. In a first signaling scheme, separate intermediate features in one measurement quantity may have separate AI indications. In a second signaling scheme, multiple measurement quantities of one TRP 208 may have a same AI indication. In a third signaling scheme, the measured intermediate features from one DU’s TRP 208 may have a same AI indication. In a fourth signaling scheme, the measurement quantities that are associated with a same ARP may have a same AI indication. Examples of the signaling schemes are as follows.
[0146] In a first example: a DU 254 may reports two measurement of a TRP1 208. For each measurement quantity, an associated DU 254 reports one SRS RTOA value and an AI indication value corresponding to ‘true’ , which indicates that the SRS RTOA is generated by an AI model. Also for this measurement quantity, a DU 254 may report a LOS indicator and / or a NLOS indicator as ‘false’ , or the DU 254 may not report an AI a LOS indicator and / or a NLOS indicator, which may indicate that the LOS / NLOS indicator is not generated by the AI model.
[0147] In a second example, a DU 254 may report AI measurements of two associated TRPs 208. For both TRPs 208, the DU 254 may report all possible AI measurement quantities. In turn, the DU 254 may report an AI indication of ‘true’ , which may indicate that all measured intermediate features from all measurement quantities of the two TRPs 208 associated with the DU 254 are generated using an AI model.
[0148] In a third example, a DU 254 may reports AI measurement of two TRPs 208. For each TRP 208, the DU 254 may report multiple measurement quantities, and an AI indication of ‘true’ , which may indicate that all of the measurement quantities that is associated with the two TRPs is generated using an AI model.
[0149] In other implementations, a RAN node 204 may report the above information to the core network element 202. In such implementations, the AI model is in core network element side 202, including in situations when at least one of the AI model training, the AI model inference, or the AI model performance monitoring is performed at core network element side. In such implementations, the DU 254 mentioned above may instead be a RAN node 204, and the CU 252 mentioned above may instead by the core network element 202, but the actions may otherwise be the same as described.
[0150] Additionally, in some implementations, a receiving port of a TRP 208 or an ARP or a RAN node 204 may have a relationship (or correspondence or association) with a receiving beam of the TRP 208 or ARP. For example, in some implementations, one receiving port may correspond to one receiving beam. In other implementations, one receiving port may correspond to multiple receiving beams. In still other implementations, multiple receiving ports may correspond to one receiving beam.
[0151] Additionally, in some implementations, the receiving port of the TRP 208, the ARP, or the RAN node 204 may have a relationship (or correspondence or association) with a cell of the TRP 208, the ARP, or the NG-RAN node 204.
[0152] Additionally, in some implementations, the measurement report may be reported based on a measurement request, or may be reported without a measurement request.
[0153] In accordance with the above description, Fig. 5 shows an example signaling framework between a CU 252, a DU 254, and the LMF 210, where an artificial intelligence (AI) model is implemented in the CU 252. Fig. 6 shows another example signaling framework between a CU 252, a DU 254, and the LMF 210, where an AI model is implemented in the DU 254.
[0154] Fig. 7 shows an example signaling framework between a CU 252, a DU 254, and the LMF 210, where an AI model is implemented in the LMF 210.
[0155] Embodiment 3
[0156] Additionally, in some implementations for UL positioning and / or UL+DL positioning, at least one of AI training, AI inference, AI performance monitoring may be performed at the RAN-node side. However, in some of these implementations, not all of the RAN nodes 204 involved in one positioning session may have AI capability. As used herein, an AI capability of a RAN node 204 may include at least one of: the RAN node 204 has the capability of training an AI model; the RAN node 204 has the capability to perform inference measurements using an AI model; the RAN node 204 has the capability to do performance monitoring to adjust an AI model’s performance; or an AI model is implemented in a RAN node 204 for data collection, inference, and / or performance monitoring. In one example scenario, one or more micro nodes and are all requested to report an AI measurement and / or at least one of: AI training, AI inference, or AI performance monitoring for AI positioning. However, the micro nodes may not have the AI capability to implement or use an AI model. Another example scenario is that AI model training is performed in some of the NG-RAN nodes, but one of the RAN nodes 204 is only able to obtain the AI training data from itself. However, if this RAN node 204 can gather AI measurements from other RAN nodes 204, the RAN node 204 will have more training data to facilitate its AI model training. In such a scenario, or other scenarios irrespective of whether a RAN node 204 can obtain AI measurements from other RAN nodes 204, and / or irrespective of whether or which RAN nodes 204 do and do not have AI capability, one RAN node 204 may transfer one or more AI measurements to another NG-RAN node 204. In particular of these implementations, the RAN node 204 transmitting the AI measurements does not have AI capability, and the RAN node 204 receiving the AI measurements has AI capability. Also, in any of various implementations, the RAN nodes 204 may use signaling in the form of XnAP messages.
[0157] Such implementation involving transfer of AI measurement information may be advantageous in that in general, high costs are involved to implement AI capability in RAN node 204, including for AI positioning. That is, the more RAN nodes 204 in which to implement AI capability for positioning, the higher the cost. Moreover, AI positioning requires multiple NG-RAN nodes 204 to receive SRSs and make SRS measurements together. As such, utilizing AI models in less than all of RAN nodes 204 while still effectively performing AI positioning using the implementations described herein may be cost effective without significantly diminishing AI positioning performance. In addition, such implementations may reduce complexity, including where AI performance monitoring is performed at the core network element side 202. In addition or alternatively, for implementations where AI training is performed at the NG-RAN node side 204, a NG-RAN node 204 may advantageously have a large AI training data set based on AI measurements from multiple NG-RAN nodes 204.
[0158] Additionally, in some implementations, to facilitate a transfer or other communication of AI measurement information, one or more signaling of the following signaling schemes may be implemented, and as illustrated in Fig. 8.
[0159] In some implementations, the core network element 202 may indicate to a RAN node 204 that the RAN node 204 is to provide AI measurements. In addition or alternatively, the core network element 202 may transmit a message to a first RAN node 204, where the message includes a second NG-RAN node ID of a second NG-RAN node 204 that is to receive an AI measurement from the first NG-RAN node 204. For example, the LMF 210 may send a NRPPa message to a NG-RAN node 2 and to a NG-RAN node 3. The NRPPa message may include a NG-RAN node ID of a NG-RAN node 1, which indicates that the LMF 210 requires or recommends that the NG-RAN node 2 and the NG-RAN node 3 to transfer their respective SRS AI measurements (e.g., CIR, PDP, DP) to NG-RAN node 1 for AI output. As previously described, such AI output may include intermediate features output from an AI model, such as UL AoA, SRS RSRP, RTOA, Rx-Tx time difference, RSRPP, and / or LOS / NLOS indicator, as non-limited examples, which in turn may be used for AI data collection.
[0160] Additionally, in some implementations, one RAN node 204 may send the AI measurement to another RAN node 204, such as CIR, PDP, or DP. Each AI measurement may be associated with one or more TRP IDs, one or more ARP IDs, one or more port IDs, or one or more port pair IDs. In some of these implementations, the AI measurement may also be associated with the user device ID, the PRU ID, or the PRU location, to indicate which user device 102 or PRU the AI measurement is used for. In some of these implementations, the one RAN node 204 may receive a request from another RAN node 204 before sending the AI measurement.
[0161] Additionally, in some implementations, a RAN node 204 may report to the core network element 202 that the intermediate features are an output of an AI model, e.g., UL AoA, SRS RSRP, RTOA, Rx-Tx time difference, RSRPP, LOS / NLOS indicator, as previously described. In some of these implementations, the RAN node 204 may indicate to the core network element 202 a NG-RAN node ID that is associated with the intermediate features. For example, a NG-RAN node 1 may report a measurement list to the core network element 202, where each measurement element in the measurement list includes one or more intermediate feature measurements. Additionally, each measurement element in the measurement list is associated with a TRP ID of a TRP 208 and a RAN node ID of a RAN node other than the ID of RAN node 1. That is, the RAN node ID is the TRP’s RAN node.
[0162] Additionally, in some implementations, a RAN node 204 may report a cause of error to the LMF 210 in event that the RAN node 204 is to make an AI measurement and / or determine one or more intermediate features using an AI model, but the RAN node 204 does not have AI capability and / or is not currently available to make the AI measurement and / or determine the intermediate features using an AI model. In addition or alternatively, the cause of error may indicate that a RAN node 204 does not successfully receive other NG-RAN node’s AI measurements or intermediate features that are output from an AI model. In addition or alternatively, the cause of error may indicate that a RAN node 204 does not successfully transmit AI measurements or intermediate features that are output from an AI model to one or more other RAN nodes 204. In any of various implementations, the cause of error may be embedded in a MEASUREMENT FAILURE or an ERROR INDICATION message. In addition or alternatively, the cause of error may be reported together with a TRP list that includes one or more TRPs 208, indicating which TRP cannot currently report an AI measurement and / or intermediate features using an AI model.
[0163] In other implementations, signaling may be employed according to one or more of the following schemes.
[0164] In some implementations, the core network element 202 may indicate to a RAN node 204 a RAN node list that includes one or more NG-RAN node IDs. The RAN node 204 receiving the RAN node list may gather AI measurements from one or more RAN nodes 204 indicated or identified by the RAN node list, which in turn may be used for AI inference and / or AI training.
[0165] Additionally, in some implementations, one RAN node 204 may indicate to another RAN node 204 the AI measurement, such as CIR, PDP, DP. Each AI measurement may be associated with one or more TRP IDs, one or more ARP IDs, one or more port IDs, or one or more port pair IDs.
[0166] Additionally, in some implementations, one RAN node 204 may indicate to another RAN node 204: the intermediate features of another RAN node 204, where the intermediate features are an output of an AI model.
[0167] Additionally, in some implementations, a RAN node 204 may report to the core network element 202: the intermediate features that are an output of an AI model, e.g., UL AoA, SRS RSRP, RTOA, Rx-Tx time difference, RSRPP, LOS / NLOS indicator, and indicate to the core network element 202 one or more associated RAN node IDs that indicate one or more RAN nodes 204 that actually generate the associated intermediate features using an AI model.
[0168] Additionally, in some implementations, a RAN node ID, as described above, may use and / or be in the form of: a Global gNB ID, a Global ng-eNB ID, or a Global NG-RAN Node ID, such as specified in the XnAP protocol, that are used to globally identify a gNB, a ng-eNB or a NG-RAN node, respectively.
[0169] Additionally, in some implementations where only some (i.e., less than all) of the RAN nodes 204 have AI capability, the core network element 202 may indicate to the RAN nodes 204 to perform AI model transfer between the RAN 204 nodes, or to perform model transfer between a RAN node 204 and a core network element 202. In addition or alternatively, a RAN node 204 may request the core network element 202 to deliver an AI model to the RAN node 204.
[0170] The model can be transferred between CU and DU in a RAN node. For example, at least one of the following can be supported: CU can request DU to transfer DU’s AI model to CU; DU reports the AI model parameters to CU; DU can request CU to transfer CU’s AI model to DU; CU delivers the AI model parameters to DU.
[0171] Embodiment 4
[0172] Additionally, in implementations where AI inference and / or AI training is at NG-RAN node side 204, while AI performance monitoring is at core network element side 202, for UL positioning and / or UL+DL positioning, a RAN node 204 may report one or more intermediate features that are an output of a AI model. In turn, the core network element 202 may use the one or more intermediate features to calculate a location of a user device 102. The core network element 202 may perform performance monitoring according to one or more of the following schemes.
[0173] In some implementations, the core network element may schedule UL positioning or UL+DL positioning of a positioning reference unit (PRU) . The PRU may send a SRS, and one or more RAN nodes 204 may receive the SRS and determine one or more intermediate features using an AI model of the RAN node 204. Additionally, the RAN node 204 may report the one or more intermediate features to core network element 202. In turn, the core network element 202 may calculate a PRU location using AI intermediate features reported by one or more RAN nodes 204. Additionally, in some of these implementations, the core network element 202 may know the actual PRU location. In such implementations, the core network element 202 may compare the calculated PRU location and the known accurate PRU location, and in turn, the core network element 202 may assess an accuracy of the AI model in the RAN node side 204 based on the comparison.
[0174] Additionally, in some implementations, the core network element 202 may schedule UL positioning and / or UL+DL positioning of a user device 102. In at least some of these implementations, concurrently, the core network element 202 may schedule GNSS positioning of a user device 102. The core network element 202 may schedule a RAN node 204 to make or obtain traditional (e.g., non-AI) SRS measurements and determine AI intermediate features of or from the same user device 102. For example, the core network element 202 may obtain, from the user device 102, traditional SRS measurements, AI intermediate features of the user device 102, and the location of the user device 102 generated by GNSS positioning. The core network element 202 may compare the calculated location of the user device 102 using AI intermediate features, the calculated location of the user device 102 using SRS measurements, and the location of the user device 102 generated by GNSS positioning. Based on the comparison, the core network element 202 may assess the accuracy of the AI model in the RAN node side 204.
[0175] Additionally, in some implementations, a problem may arise when AI inference and / or AI training is performed at the RAN node side 204, while AI performance monitoring is performed at the core network element side 202. Since multiple RAN nodes 204 may have their own AI model and output their own AI intermediate features, then when a user device location is calculated via AI intermediate features from all of the RAN nodes 204 is insufficiently accurate, the core network element may not be able to determine which RAN node’s AI model is creating the problems (i.e., is not sufficiently accurate) . To address this problem, the number of RAN nodes 204 that implement or utilize an AI model may be reduced; the RAN nodes 204 participating in a positioning session may all use the same AI model; and / or AI performance monitoring may be performed at the RAN node side 204, rather than at the core network element side 202.
[0176] Additionally, in some implementations where AI inference and / or AI training is at the RAN node side 204, while the AI performance monitoring is also at the RAN node side 204, the RAN node 240 / 250 may know the PRU location of a PRU. If the PRU location is known, then accurate intermediate features of a PRU and RAN node pair may be known and / or calculated by the RAN node 204. Additionally, the PRU may send a SRS. In turn, the RAN node 204 may receive the SRS, and the RAN node 204 may determine one or more intermediate feature measurements using an AI model. Then, the RAN node 204 may compare the one or more intermediate feature measurements generated using the AI model and known accurate intermediate features of the PRU and RAN node pair, in order to assess an accuracy of the AI model of the RAN node 204.
[0177] In further detail, initially, the RAN node 204 may know or determine an accurate intermediate feature of the PRU, such as in accordance with one or more of the following schemes.
[0178] In a first scheme, the core network element 202 may provide a PRU list to the RAN node 204. The PRU list may include PRU information that includes at least one of: a PRU ID, a PRU location, a cell ID or a cell list that is associated with the PRU, a TRP ID or a TRP ID list that is associated with the PRU, an ARP ID or an ARP ID list that is associated with the PRU, or beam information that is associated with the PRU, NG-RAN node ID or NG-RAN node list that is associated with the PRU. If the PRU location is known, accurate intermediate features of the PRU and RAN node pair may be known and / or calculated by the NG-RAN node 204.
[0179] In a second scheme, the core network element 202 may directly provide expected intermediate features of the PRU to RAN node 204. Additionally, the core network element 202 may indicate a PRU ID and / or a PRU location together with the expected intermediate features. Additionally, the core network element 202 may indicate a RAN node ID and / or a TRP ID together with the expected RTOA or TOA value, where the RAN node ID and / or a TRP ID is the serving RAN node 204 and / or the serving TRP 208 of the associated PRU. Additionally, the core network element 202 may indicate a SRS resource ID or a SRS resource set ID together with the expected intermediate features. In at least some of these implementations, the core network element 202 may do according to one or more of the following ways.
[0180] In a first way, the core network element 202 may provide an expected RTOA value of each PRU to the RAN node 204. In some of these implementations, the core network element 202 may provide an uncertainty of the expected RTOA or TOA value of each PRU to the RAN node 204. The expected RTOA value is a timing period of propagation delay between the PRU and the RAN node 204. Correspondingly, the uncertainty of the expected RTOA or TOA defines a positive and a negative deviation of the expected RTOA or TOA. The core network element 202 may indicate a PRU ID and / or a PRU location together with the expected RTOA or TOA value. In any of various of these implementations, the unit may be a slot, a frame, a subframe, a meter, a nanosecond, a microsecond, or a milli-second, as non-limiting examples. In addition or alternatively, the expected RTOA value and / or the uncertainty value may be represented as a integer multiple of a Ts or a Tc, such as: Ts=1 / (15000*2048) seconds, as a non-limiting example.
[0181] In addition or alternatively, in a second way, the core network element 202 may provide an expected AoA value of each PRU to NG-RAN node 204. In some of these implementations, the core network element 202 may provide an uncertainty of the expected AOA value of each PRU to the RAN node 205 / 250. The core network element 202 may indicate a PRU ID and / or a PRU location together with the expected AoA value. The expected AoA value is the estimated receiving angle of the RAN node 204 on the PRU’s SRS. The uncertainty of the expected AOA value defines a positive and a negative deviation of the expected RTOA or TOA. In any of various of these implementations, the unit is a degree.
[0182] In addition or alternatively, in a third way, the core network element 202 may provide an expected Rx-Tx time difference value of each PRU to the RAN node 204. The core network element 202 may indicate a PRU ID and / or a PRU location together with the expected Rx-Tx time difference value. In some implementations, the core network element 202 may provide an uncertainty of the expected Rx-Tx time difference value of each PRU to the NG-RAN node 204.
[0183] In addition or alternatively, in a fourth way, the core network element 202 can provide the expected SRS RSRP value or expected SRS RSRPP value of each PRU to NG-RAN node. core network element indicates PRU ID and / or PRU location together with the expected SRS RSRP or RSRPP value. Additionally, in some implementations, the core network element 202 may provide the uncertainty of the expected SRS RSRP or RSRPP value of each PRU to NG-RAN node.
[0184] In addition or alternatively, in a fifth way, the core network element 202 may provide an expected SRS RSCP value or expected SRS RSCPD value of each PRU to the RAN node 204. The core network element may indicate a PRU ID and / or a PRU location together with the expected SRS RSCP or RSCPD value. Additionally, in some implementations, the core network element 202 may provide the uncertainty of the expected SRS RSCP or RSCPD value of each PRU to the RAN node 204.
[0185] In addition or alternatively, in a sixth way, the above-described expected intermediate features may come from the serving PRU of the RAN node 204. In addition or alternatively, in some of these implementations, the core network element 202 may provide the above-described expected intermediate features of the PRU (s) belonging to other RAN node 204 to a RAN node 204. In addition or alternatively, in some implementations, each kind of the expected intermediate features may be associated with at least one of a PRU, a TRP 208, an ARP, or a RAN node 204. In this context, the signaling used to obtain or communicate the expected intermediate features may be provided together with at least one of a PRU ID, a PRU location, a TRP ID, an ARP ID or a RAN node ID.
[0186] In addition or alternatively, in a seventh way, the expected intermediate features may be associated with a corresponding time stamp. The uncertainty can also be a measurement quality, or a confidence of the measurement.
[0187] In addition or alternatively, in an eighth way, the above-described ways may also or alternatively be implemented when the RAN node 204 performs AI model training and / or data collection. In any of various of these implementations, the expected intermediate feature may be considered a label of the training data.
[0188] Additionally, in some implementations, at least one of two schemes related to scheduling PRUs may be implemented. In a first scheme, a RAN node 204 schedule its own serving PRU to send a SRS. In a second scheme, the core network element 202 schedules a PRU to perform UL positioning, and then the NG-RAN node 204 may measure the PRU’s SRS using an AI model. The following describes ways that the first scheme and the second scheme may be utilized in the AI performance monitoring phase and / or the AI model training phase when collecting training data.
[0189] Under the first scheme, the core network element 202 may recommend to a RAN node 204 a suitable SRS configuration for the PRU use to perform the performance monitoring. In some of these implementations, the recommended SRS configuration or a requested SRS characteristic message may be provided together with a PRU ID or a PRU ID list or a PRU location or a PRU location list. In addition or alternatively, the recommended SRS configuration is provided with an indication of whether or not the recommended SRS configuration is used for the AI performance monitoring. For at least some of these implementations, the recommended SRS configuration may include at least the SRS sending periodicity. In at least some of these implementations, the SRS sending periodicity may match the performance monitoring periodicity. In addition or alternatively, the performance monitoring periodicity may be determined by the core network element 202, such as via an AI positioning QoS requirement. In some of these implementations, the recommended SRS configuration for the AI performance monitoring may be the same as or different from the SRS configuration for normal (non-AI) user device UL positioning from the signaling design perspective. In such implementations, the RAN node 204 schedules its serving PRU to send a SRS based on the recommended SRS configuration.
[0190] Under the second scheme, in some implementations, the core network element 202 may send a Measurement Request message to a serving and / or a neighboring RAN node 204 of the PRU. In at least some of these implementations, the Measurement Request message may include at least one of: a user device type or a user device ID. A user device (or UE) type may refer to whether or not the user device 102 sends a corresponding SRS is a PRU. Additionally, a user device (or UE) ID may include a PRU ID. In other implementations under the second scheme, the core network element 202 may send NRPPa signaling to a serving and / or a neighboring RAN node 204 of the PRU for a measurement request. In some of these implementations, the NRPPa signaling is UE-associated signaling. In addition or alternatively, the NRPPa signaling includes at least the SRS configuration that the associated user device 102 and / or PRU sends.
[0191] Additionally, in some implementations, the core network element 202 may configure one or more monitoring control parameters or criteria for a RAN node 204, and / or provide one or more monitoring control parameters or criteria to the RAN node 204, which may guide the RAN node 204 in determining whether or not the AI model is sufficiently accurate. The one or more monitoring control parameters may include at least one of: a threshold, a time duration, or a number of times. The threshold may include at least one of: a value representing a timing, a value representing a distance, a value representing an angle, a value representing a power class, or a value representing a phase. Additionally, in some implementations, a RAN node 204 compares the accurate or known (or reference) intermediate feature with a measured intermediate feature generated using an AI model. In some implementations, in event that the RAN node 204 determines that a difference between the accurate intermediate feature and the measured intermediate feature is larger than a configured threshold, the RAN node 204 determines that the AI model is not accurate. In other implementations, in event that the RAN node 204 determines that the difference between the accurate intermediate feature and the measured intermediate feature is larger than the threshold, the RAN node 204 may further determine whether this larger-than condition has occurred over the indicated time duration, and / or may further determine whether a number times that this larger-than condition has occurred exceeds the indicated number of times. If so, then RAN node 204 may determine that the AI model is not accurate.
[0192] To illustrate as an example, the core network element 202 may provide the RAN node 204 with a threshold value as X ms, and also provide the RAN node 204 with a time period of Y ms.In event that the RAN node 204 detects that the difference between the accurate intermediate feature and the measured intermediate feature is larger than the X ms. and further determines that the difference being larger lasts longer than Y ms, then in response, the RAN node 204 / 240 may determine that the AI model of itself is not sufficiently accurate.
[0193] In addition, in some implementations, a RAN node 204 may report an AI model performance loss to the core network element 202. In some of these implementations, the RAN node 204 may report the AI model performance loss in response to a detection that the AI model is not sufficiently accurate. In some of these implementations, the reporting may be performed using at least one of the NRPPa messages.
[0194] Although the above-described implementations are described as being performed with the core network element 202 and a RAN node 204, in any of various other implementations, the actions are performed with a CU 252 and a DU 254. For example, the CU 252 may provide at least one of the above expected intermediate features of the PRU to the DU 254. In addition or alternatively, the CU 252 may provide a Measurement Request including at least one of a user device (or UE) type or a user device (or UE) ID to a DU 254. In addition or alternatively, a DU 254 may report an AI model performance loss to the CU 252, such as by using at least one of the F1AP messages.
[0195] Additionally, for implementations where a PRU is, or is implemented in a user device 102, a PRU ID and a UE ID may be communicated using the same signaling framework and / or value range.
[0196] Embodiment 4a
[0197] Additionally, in some implementations, an AI model may be implemented in a user device (or at the user device side) 102. In such implementations, the user device 102 may perform AI performance monitoring.
[0198] Additionally, in some implementations, the core network element 202 may provide at least one of the following to the user device 102 for the user device 102 to perform AI performance monitoring: a PRU ID, a PRU ID list, one or more PRU locations, one or more PRU AI measurements, one or more PRU intermediate features, one or more timestamps, or one or more measurement quality.
[0199] Additionally, in some implementations, the core network element 202 may configure one or more monitoring control parameters or criteria for the user device 102 and / or may indicate one or more monitoring control parameters or criteria to the user device 102, which may guide the user device 102 to determine whether or not the user device side AI model is sufficiently accurate. In some of these implementations, the monitoring control parameter may include at least one of: a threshold, a time duration, or a number of times. The threshold can include at least one of: a value representing a timing, a value representing a distance, a value representing an angle, a value representing a power class, or a value representing a phase. The user device 102 may compare an accurate (or known or reference) intermediate feature and a measured intermediate feature generated using an AI model to determine a difference. In some implementations, in event that the user device 102 determines that the difference between the accurate intermediate feature and the measured intermediate feature is larger than the configured threshold, the user device 102 may determine that the AI model is not sufficiently accurate. In other implementations, in event that the user device 102 determines that the difference between the accurate intermediate feature and the measured intermediate feature is larger than the threshold, the user device 102 may further determine whether this condition (the difference being larger than the threshold) has occurred over the indicated time duration, or may further determine whether a number of times the condition has occurred exceeds the indicated number of times. If so, then the user device 102 may determine that the AI model is not sufficiently accurate.
[0200] In other implementations, the user device 102 may analyze location. For example, in event that the user device determines that the difference between an accurate (or known or reference) UE or PRU location and a measured UE or PRU location generated using an AI model is larger than a configured threshold, then the user device 102 may determine that the AI model is not sufficiently accurate. In addition or alternatively, in event that the user device 102 determines that the difference between the accurate UE or PRU location and the measured UE or PRU location is larger than the threshold, the user device 102 may further determine whether this condition (i.e., the difference being larger than the configured threshold) has occurred over the indicated time duration whether a number of times this condition has occurred exceeds the indicated number of times. If so, then the user device 102 may determine that the AI model is not sufficiently accurate.
[0201] In any of various of these implementations, the accurate intermediate feature and / or the accurate UE location may be derived from user device-based positioning, such as by using at least one of: A-GNSS, Sensor, WLAN, DL-TDOA, DL-AoD positioning schemes.
[0202] Embodiment 5 model training
[0203] Additionally, in some implementations, AI model training is performed at the RAN node side 204. In some of these implementations, the RAN node 204 may obtain assistance data from the core network element 202 to facilitate its AI model training. For at least some of these implementations, the assistance data may include at least one of the following: an indication on whether to train the AI model or to download the AI model from an external network element; or positioning quality of service (QoS) or training QoS. For implementations using the latter, the QoS may include at least one of: the timing accuracy requirement, the angle accuracy requirement, the power class accuracy requirement, the phase accuracy requirement, the location or distance accuracy requirement, the latency requirement, the minimum accuracy rate of a LOS and / or aNLOS determination, or a generalization requirement. For at least some of these implementations, the accuracy requirement may be associated with a confidence value. In addition or alternatively, the QoS provision may be to let the RAN node 204 train an AI model to satisfy the QoS requirement. For example, the timing accuracy requirement can indicate a maximum timing error, and in turn, the RAN node 204 may train the AI model so that the AI model output of the trained model (e.g., RTOA measurement) does not exceed a timing accuracy requirement.
[0204] Also, while the above-described implementations of AI model training with assistance data are described with use of a RAN node 204, other implementations may instead do so with a CU 252 and a DU 254. For example, the above-described assistance data may be delivered from the CU 252 to the DU 254 to guide the DU’s model training.
[0205] Additionally, in some implementations where AI model training is performed at the user device 102, the user device 102 may receive assistance data from the core network element 202 to facilitate and / or guide the user device’s AI model training. For example, the user device 102 may receive two QoS indications from the core network element 202, where one is a positioning QoS and a second is an AI model training QoS.
[0206] Additionally, in some implementations, the core network element 202 may provide the PRU’s AI measurement to the user device 102 for the user device 102 to perform AI model training or performance monitoring. In some of these implementations, the PRU’s AI measurement may be associated with the PRU ID and / or PRU location information.
[0207] In addition or alternatively, in some implementations, the core network element 202 may provide one or more expected intermediate features of the one or more PRUs to the user device for the user device 102 to perform AI model training or performance monitoring. An expected intermediate feature may include at least one of: an expected Rx-Tx time difference measurement, an expected PRS RSRP or RSRPP measurement, an expected PRS AOD measurement, an expected PRS RSCP or RSCPD measurement, or an expected PRS RSTD measurement. In addition or alternatively, each expected intermediate feature may be associated with at least one of: a PRU ID, a PRU location, a TRP ID, a PRS resource set ID, a PRS resource ID, a frequency layer ID, a measurement quality or uncertainty, or a time stamp.
[0208] The description and accompanying drawings above provide specific example embodiments and implementations. The described subject matter may, however, be embodied in a variety of different forms and, therefore, covered or claimed subject matter is intended to be construed as not being limited to any example embodiments set forth herein. A reasonably broad scope for claimed or covered subject matter is intended. Among other things, for example, subject matter may be embodied as methods, devices, components, systems, or non-transitory computer-readable media for storing computer codes. Accordingly, embodiments may, for example, take the form of hardware, software, firmware, storage media or any combination thereof. For example, the method embodiments described above may be implemented by components, devices, or systems including memory and processors by executing computer codes stored in the memory.
[0209] Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment / implementation” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment / implementation” as used herein does not necessarily refer to a different embodiment. It is intended, for example, that claimed subject matter includes combinations of example embodiments in whole or in part.
[0210] In general, terminology may be understood at least in part from usage in context. For example, terms, such as “and” , “or” , or “and / or, ” as used herein may include a variety of meanings that may depend at least in part on the context in which such terms are used. Typically, “or” if used to associate a list, such as A, B or C, is intended to mean A, B, and C, here used in the inclusive sense, as well as A, B or C, here used in the exclusive sense. In addition, the term “one or more” as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a, ” “an, ” or “the, ” may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.
[0211] Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present solution should be or are included in any single implementation thereof. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present solution. Thus, discussions of the features and advantages, and similar language, throughout the specification may, but do not necessarily, refer to the same embodiment.
[0212] Furthermore, the described features, advantages and characteristics of the present solution may be combined in any suitable manner in one or more embodiments. One of ordinary skill in the relevant art will recognize, in light of the description herein, that the present solution can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the present solution.
[0213] The subject matter of the disclosure may also relate to or include, among others, the following aspects:
[0214] A first aspect includes a method for wireless communication that includes: receiving, by a first communication node, an indication from a second communication node, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; and transmitting, by the first communication node to the second communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.
[0215] A second aspect includes a method for wireless communication that includes: transmitting, by a second communication node to a first communication node, an indication, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; and receiving, by the second communication node from the first communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.
[0216] A third aspect includes any of the first or second aspects, and further includes wherein the indication comprises the AI measurement report request, the AI measurement report request comprises at least one of: a number of transmission reception points (TRPs) per first communication node to be reported; a TRP identification (ID) list to be measured; an Antenna Reference Point (ARP) ID list to be measured; a number of ARPs per TRP to be reported; a number of ARPs per first communication node to be reported; a port ID list or a port pair ID list to be measured; a number of ports or a number of port pairs to be reported; a number of reference signals to be measured; a required one or more AI measurement types to be reported; an indication on whether to report a path timing or a sample index for an AI measurement; a required reporting sample number; a required reporting path number; a maximum and / or a minimum required reporting sample number; a maximum and / or a minimum required reporting path number; a request to report whether one or more intermediate features is generated by an AI model; or an AI model ID or an AI model ID list.
[0217] A fourth aspect includes the third aspect, and further includes wherein the maximum and / or the minimum required reporting sample number is associated with each AI measurement type or each requested measurement quantity.
[0218] A fifth aspect includes any of the third or fourth aspects, and further includes wherein the maximum and / or the minimum required reporting path number is associated with each AI measurement type or each requested measurement quantity.
[0219] A sixth aspect includes any of the first through fifth aspects, and further includes: transferring, by the first communication node, a set of AI measurements to a third communication node of a same type as the first communication node.
[0220] A seventh aspect includes any of the first through sixth aspects, and further includes: receiving, by the first communication node from the second communication node, a transfer indication in the AI measurement transfer request.
[0221] An eighth aspect includes the seventh aspect, and further includes wherein the transfer indication comprises an identification (ID) of the third communication node to which the first communication node is to transfer the set of AI measurements.
[0222] A ninth aspect includes any of the sixth through eighth aspects, and further includes: receiving, by the third communication node from the second communication node, a transfer indication in the AI measurement transfer request.
[0223] A tenth aspect includes the ninth aspect, and further includes wherein the transfer indication comprises an identification of the first communication node from which the third communication node is to gather the set of AI measurements.
[0224] An eleventh aspect includes any of the sixth through tenth aspects, and further includes wherein the first communication node transfers the set of AI measurements to the third communication node based on a transfer indication sent by the third communication node.
[0225] A twelfth aspect includes any of the sixth through eleventh aspects, and further includes wherein the set of AI measurements comprises at least one of: channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .
[0226] A thirteenth aspect includes any of the sixth through twelfth aspects, and further includes wherein the set of AI measurements is associated with at least one of: one or more positioning reference unit (PRU) identifications (IDs) or one or more PRU locations.
[0227] A fourteenth aspect includes any of the sixth through thirteenth aspects, and further includes: reporting, by the third communication node, a set of AI intermediate features to the second communication node, wherein the set of AI intermediate features is associated with one or more identifications (IDs) of the first communication node which provides the set of AI measurements.
[0228] A fifteenth aspect includes any of the sixth through fourteenth aspects, and further includes: reporting, by the first communication node, a set of AI intermediate features to the second communication node, wherein the set of AI intermediate features is associated with one or more identification (ID) s of the third communication node which provides the set of AI intermediate features.
[0229] A sixteenth aspect includes any of the first through fifteenth aspects, and further includes wherein the AI measurement result comprises a cause of error in response to the first communication node being required to perform AI measurements and / or determine AI intermediate features using an AI model but the first communication node is not available to perform the AI measurements and / or to determine the intermediate features using the AI model.
[0230] A seventeenth aspect includes the sixteenth aspect, and further includes wherein the cause of error is reported together with a transmission reception point (TRP) list.
[0231] An eighteenth aspect includes any of the first through seventeenth aspects, and further includes wherein the AI model training parameter comprises whether to train an AI model and / or to download the AI model from an external network element.
[0232] A nineteenth aspect includes any of the first through eighteenth aspects, and further includes wherein the AI model training parameter comprises a training quality of service (QoS) requirement, the training QoS requirement comprising at least one of: a timing accuracy requirement, an angle accuracy requirement, a power class accuracy requirement, a phase accuracy requirement, a location or distance accuracy requirement, a latency requirement, a minimum accuracy rate of line of sight (LOS) and / or non-line of sight (NLOS) determination, or a generalization requirement.
[0233] A twentieth aspect includes any of the first through nineteenth aspects, and further includes wherein the second communication node provides a positioning reference unit (PRU) list to the first communication node.
[0234] A twenty-first aspect includes the twentieth aspect, and further includes wherein the PRU list comprises PRU information, the PRU information comprising at least one of: a PRU identification (ID) , a PRU location, a cell ID or a cell list that is associated with a PRU, a transmission reception point (TRP) ID or a TRP ID list that is associated with the PRU, an antenna reference point (ARP) ID or a ARP ID list that is associated with the PRU, beam information that is associated with the PRU, or a radio access network (RAN) node ID or a RAN node list that is associated with the PRU.
[0235] A twenty-second aspect includes any of the first through twenty-first aspects, and further includes wherein the second communication node provides one or more expected intermediate features of at least one positioning reference unit (PRU) to the first communication node.
[0236] A twenty-third aspect includes the twenty-second aspect, and further includes wherein the one or more expected intermediate features comprises at least one of: one or more expected relative time of arrival (RTOA) values or one or more expected time of arrival (TOA) values; one or more expected angle of arrival (AoA) values; one or more expected receive (Rx) -transmit (Tx) time difference values; one or more expected sounding reference signal (SRS) reference signal received power (RSRP) values or one or more expected SRS reference signal received power per path (RSRPP) values; or one or more expected SRS reference signal carrier phase (RSCP) values or one or more expected SRS reference signal carrier phase difference (RSCPD) values; or one or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.
[0237] A twenty-fourth aspect includes any of the twenty-second or twenty-third aspects, and further includes wherein the second communication node is a location management function (LMF) and the first communication is a user device, the one or more expected intermediate features comprises at least one of: one or more expected reference signal time difference (RSTD) values or one or more expected time of arrival (TOA) values; one or more expected angle of arrival (AoA) values; one or more expected angle of departure (AoD) values; one or more expected receive (Rx) -transmit (Tx) time difference values; one or more expected positioning reference signal (PRS) reference signal received power (RSRP) values or one or more expected PRS reference signal received power per path (RSRPP) values; or one or more expected PRS reference signal carrier phase (RSCP) values or one or more expected PRS reference signal carrier phase difference (RSCPD) values.; or one or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.
[0238] A twenty-fifth aspect includes any of the twenty-second through twenty-fourth aspects, and further includes wherein one or more PRU identifications (IDs) and / or one or more PRU locations are indicated together with the one or more expected intermediate features.
[0239] A twenty-sixth aspect includes any of the twenty-third through twenty-fifth aspects, and further includes wherein one or more transmission reception point (TRP) identifications (IDs) and / or one or more radio access network (RAN) node IDs are indicated together with the one or more expected intermediate features.
[0240] A twenty-seventh aspect includes any of the first through twenty-sixth aspects, and further includes wherein the second communication node provides a recommended sounding reference signal (SRS) configuration for a positioning reference unit (PRU) to the first communication node to do performance monitoring.
[0241] A twenty-eighth aspect includes the twenty-seventh aspect, and further includes wherein the recommended SRS configuration or a requested SRS characteristic message is provided together with at least one of a PRU identification (ID) , a PRU ID list, a PRU location or a PRU location list.
[0242] A twenty-ninth aspect includes any of the twenty-seventh aspect or the twenty-eighth aspect, and further includes wherein the recommended SRS configuration is provided with an indication on whether or not the recommended SRS configuration is used for AI performance monitoring.
[0243] A thirtieth aspect includes any of the first through twenty-ninth aspects, and further includes wherein the second communication node sends the AI measurement report request message to the first communication node, the first communication node comprising a serving and / or a neighboring communication node of a positioning reference unit (PRU) , the AI measurement report request message comprising at least one of a type of user device or a user device identification (ID) .
[0244] A thirty-first aspect includes any of the first through thirtieth aspects, and further includes wherein the second communication node sends the AI measurement report request to the first communication node, the first communication node comprising a serving and / or a neighboring communication node of a positioning reference unit (PRU) for measurement requests, and wherein the AI measurement report request message is sent according to a user device associated signaling.
[0245] A thirty-second aspect includes any of the first through thirty-first aspects, and further includes wherein the AI performance monitoring parameter comprises one or more monitoring control parameters or criteria for the first communication node, wherein the one or more monitoring control parameters or criteria comprise at least one of: a threshold, a time duration, or a number of times.
[0246] A thirty-third aspect includes any of the thirty-first or thirty-second aspects, and further includes wherein the threshold comprises at least one of: a value representing a timing, a value representing a distance, a value representing an angle, a value representing a power class, or a value representing a phase.
[0247] A thirty-fourth aspect includes any of the first through thirty-third aspects, and further includes wherein the AI performance monitoring result comprises an indication of AI model performance loss.
[0248] A thirty-fifth aspect includes any of the thirty-second through thirty-fourth aspects, and further includes wherein the first communication node comprises a user device and the second communication node comprises a core network element.
[0249] A thirty-sixth aspect includes any of the first through thirty-fifth aspects, and further includes wherein the report comprises the AI measurement result, and wherein the AI measurement result comprises one or more AI measurements.
[0250] A thirty-seventh aspect includes the thirty-sixth aspect, and further includes wherein the report further comprises an indication of whether each of the one or more AI measurements comprises a channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .
[0251] A thirty-eighth aspect includes any of the thirty-sixth or thirty-seventh aspects, and further includes wherein each of the one or more AI measurements is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; or one or more port pair IDs; or one or more user device IDs.
[0252] A thirty-ninth aspect includes any of the thirty-sixth through thirty-eighth aspects, and further includes wherein the report comprises one or more intermediate features, each of the one or more intermediate features is associated with an indication to indicate whether or not the intermediate feature is generated by an AI model.
[0253] A fortieth aspect includes the thirty-ninth aspect, and further includes wherein each of the one or more AI intermediate features is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; one or more port pair IDs; or one or more user device IDs.
[0254] A forty-first aspect includes any of the first through fortieth aspects, and further includes wherein the first communication node comprises a radio access network (RAN) node and the second communication node comprises a core network element.
[0255] A forty-second aspect includes any of the first through fortieth aspects, and further includes wherein the first communication node comprises a distributed unit (DU) and the second communication node comprises a centralized unit (CU) .
[0256] A forty-third aspect includes a wireless communications apparatus comprising a processor and a memory, wherein the processor is configured to read code from the memory to implement any of the first through forty-second aspects.
[0257] A forty-fourth aspect includes a computer program product including a computer-readable program medium comprising code stored thereupon, the code, when executed by a processor, causing the processor to implement any of the first through forty-second aspects.
[0258] In addition to the features mentioned in each of the independent aspects enumerated above, some examples may show, alone or in combination, the optional features mentioned in the dependent aspects and / or as disclosed in the description above and shown in the figures.
Claims
1.A method for wireless communication, the method comprising:receiving, by a first communication node, an indication from a second communication node, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; andtransmitting, by the first communication node to the second communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.2.A method for wireless communication, the method comprising:transmitting, by a second communication node to a first communication node, an indication, the indication comprising at least one of: an artificial intelligence (AI) measurement report request, an AI measurement transfer request, an AI model training parameter, or an AI performance monitoring parameter; andreceiving, by the second communication node from the first communication node, a report according to the indication, the report comprising at least one of: an AI measurement result or an AI performance monitoring result.3.The method of any of claims 1 or 2, wherein the indication comprises the AI measurement report request, the AI measurement report request comprises at least one of:a number of transmission reception points (TRPs) per first communication node to be reported;a TRP identification (ID) list to be measured;an Antenna Reference Point (ARP) ID list to be measured;a number of ARPs per TRP to be reported;a number of ARPs per first communication node to be reported;a port ID list or a port pair ID list to be measured;a number of ports or a number of port pairs to be reported;a number of reference signals to be measured;a required one or more AI measurement types to be reported;an indication on whether to report a path timing or a sample index for an AI measurement;a required reporting sample number;a required reporting path number;a maximum and / or a minimum required reporting sample number;a maximum and / or a minimum required reporting path number;a request to report whether one or more intermediate features is generated by an AI model; oran AI model ID or an AI model ID list.4.The method of claim 3, wherein the maximum and / or the minimum required reporting sample number is associated with each AI measurement type or each requested measurement quantity.5.The method of claim 3, wherein the maximum and / or the minimum required reporting path number is associated with each AI measurement type or each requested measurement quantity.6.The method of any of claims 1 or 2, further comprising:transferring, by the first communication node, a set of AI measurements to a third communication node of a same type as the first communication node.7.The method of claim 6, further comprising:receiving, by the first communication node from the second communication node, a transfer indication in the AI measurement transfer request.8.The method of claim 7, wherein the transfer indication comprises an identification (ID) of the third communication node to which the first communication node is to transfer the set of AI measurements.9.The method of claim 6, further comprising:receiving, by the third communication node from the second communication node, a transfer indication in the AI measurement transfer request.10.The method of claim 9, wherein the transfer indication comprises an identification of the first communication node from which the third communication node is to gather the set of AI measurements.11.The method of claim 6, wherein the first communication node transfers the set of AI measurements to the third communication node based on a transfer indication sent by the third communication node.12.The method of claim 6, wherein the set of AI measurements comprises at least one of: channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .13.The method of claim 6, wherein the set of AI measurements is associated with at least one of:one or more positioning reference unit (PRU) identifications (IDs) or one or more PRU locations.14.The method of claim 6, further comprising:reporting, by the third communication node, a set of AI intermediate features to the second communication node, wherein the set of AI intermediate features is associated with one or more identifications (IDs) of the first communication node which provides the set of AI measurements.15.The method of claim 6, further comprising:reporting, by the first communication node, a set of AI intermediate features to the second communication node, wherein the set of AI intermediate features is associated with one or more identification (ID) s of the third communication node which provides the set of AI intermediate features.16.The method of any of claims 1 or 2, wherein the AI measurement result comprises a cause of error in response to the first communication node being required to perform AI measurements and / or determine AI intermediate features using an AI model but the first communication node is not available to perform the AI measurements and / or to determine the intermediate features using the AI model.17.The method of claim 16, wherein the cause of error is reported together with a transmission reception point (TRP) list.18.The method of any of claims 1 or 2, wherein the AI model training parameter comprises whether to train an AI model and / or to download the AI model from an external network element.19.The method of any of claims 1 or 2, wherein the AI model training parameter comprises a training quality of service (QoS) requirement, the training QoS requirement comprising at least one of:a timing accuracy requirement, an angle accuracy requirement, a power class accuracy requirement, a phase accuracy requirement, a location or distance accuracy requirement, a latency requirement, a minimum accuracy rate of line of sight (LOS) and / or non-line of sight (NLOS) determination, or a generalization requirement.20.The method of any of claims 1 or 2, wherein the second communication node provides a positioning reference unit (PRU) list to the first communication node.21.The method of claim 20, wherein the PRU list comprises PRU information, the PRU information comprising at least one of: a PRU identification (ID) , a PRU location, a cell ID or a cell list that is associated with a PRU, a transmission reception point (TRP) ID or a TRP ID list that is associated with the PRU, an antenna reference point (ARP) ID or a ARP ID list that is associated with the PRU, beam information that is associated with the PRU, or a radio access network (RAN) node ID or a RAN node list that is associated with the PRU.22.The method of any of claims 1 or 2, wherein the second communication node provides one or more expected intermediate features of at least one positioning reference unit (PRU) to the first communication node.23.The method of claim 22, wherein the one or more expected intermediate features comprises at least one of:one or more expected relative time of arrival (RTOA) values or one or more expected time of arrival (TOA) values;one or more expected angle of arrival (AoA) values;one or more expected receive (Rx) -transmit (Tx) time difference values;one or more expected sounding reference signal (SRS) reference signal received power (RSRP) values or one or more expected SRS reference signal received power per path (RSRPP) values; orone or more expected SRS reference signal carrier phase (RSCP) values or one or more expected SRS reference signal carrier phase difference (RSCPD) values; orone or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.24.The method of claim 22, wherein the second communication node is a location management function (LMF) and the first communication is a user device, the one or more expected intermediate features comprises at least one of:one or more expected reference signal time difference (RSTD) values or one or more expected time of arrival (TOA) values;one or more expected angle of arrival (AoA) values;one or more expected angle of departure (AoD) values;one or more expected receive (Rx) -transmit (Tx) time difference values;one or more expected positioning reference signal (PRS) reference signal received power (RSRP) values or one or more expected PRS reference signal received power per path (RSRPP) values; orone or more expected PRS reference signal carrier phase (RSCP) values or one or more expected PRS reference signal carrier phase difference (RSCPD) values. ; orone or more expected line of sight (LOS) and / or non-line of sight (NLOS) indicators.25.The method of any of claims 22-24, wherein one or more PRU identifications (IDs) and / or one or more PRU locations are indicated together with the one or more expected intermediate features.26.The method of claim 23, wherein one or more transmission reception point (TRP) identifications (IDs) and / or one or more radio access network (RAN) node IDs are indicated together with the one or more expected intermediate features.27.The method of any of claims 1 or 2, wherein the second communication node provides a recommended sounding reference signal (SRS) configuration for a positioning reference unit (PRU) to the first communication node to do performance monitoring.28.The method of claim 27, wherein the recommended SRS configuration or a requested SRS characteristic message is provided together with at least one of a PRU identification (ID) , a PRU ID list, a PRU location or a PRU location list.29.The method of claim 27, wherein the recommended SRS configuration is provided with an indication on whether or not the recommended SRS configuration is used for AI performance monitoring.30.The method of any of claims 1 or 2, wherein the second communication node sends the AI measurement report request message to the first communication node, the first communication node comprising a serving and / or a neighboring communication node of a positioning reference unit (PRU) , the AI measurement report request message comprising at least one of a type of user device or a user device identification (ID) .31.The method of any of claims 1 or 2, wherein the second communication node sends the AI measurement report request to the first communication node, the first communication node comprising a serving and / or a neighboring communication node of a positioning reference unit (PRU) for measurement requests, and wherein the AI measurement report request message is sent according to a user device associated signaling.32.The method of any of claims 1 or 2, wherein the AI performance monitoring parameter comprises one or more monitoring control parameters or criteria for the first communication node, wherein the one or more monitoring control parameters or criteria comprise at least one of: a threshold, a time duration, or a number of times.33.The method of claim 31, wherein the threshold comprises at least one of: a value representing a timing, a value representing a distance, a value representing an angle, a value representing a power class, or a value representing a phase.34.The method of any of claims 1 or 2, wherein the AI performance monitoring result comprises an indication of AI model performance loss.35.The method of claims 32 to 34, wherein the first communication node comprises a user device and the second communication node comprises a core network element.36.The method of any of claims 1 or 2, wherein the report comprises the AI measurement result, and wherein the AI measurement result comprises one or more AI measurements.37.The method of claim 36, wherein the report further comprises an indication of whether each of the one or more AI measurements comprises a channel impulse response (CIR) , a power delay profile (PDP) , or a delay profile (DP) .38.The method of claim 36, wherein each of the one or more AI measurements is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; or one or more port pair IDs; or one or more user device IDs.39.The method of claim 36, wherein the report comprises one or more intermediate features, each of the one or more intermediate features is associated with an indication to indicate whether or not the intermediate feature is generated by an AI model.40.The method of claim 39, wherein each of the one or more AI intermediate features is associated with at least one of: one or more transmission reception point (TRP) identifications (IDs) ; one or more antenna reference point (ARP) IDs; one or more port IDs; one or more port pair IDs; or one or more user device IDs.41.The method of any of claims 1 to 40, wherein the first communication node comprises a radio access network (RAN) node and the second communication node comprises a core network element.42.The method of any of claims 1 to 40, wherein the first communication node comprises a distributed unit (DU) and the second communication node comprises a centralized unit (CU) .43.A wireless communications apparatus comprising a processor and a memory, wherein the processor is configured to read code from the memory to implement a method of any of claims 1 to 42.44.A computer program product comprising a computer-readable program medium comprising code stored thereupon, the code, when executed by a processor, causing the processor to implement a method of any of claims 1 to 42.
Citation Information
Patent Citations
Network optimization method, server, network side equipment, system and storage medium
CN112512059A
Wireless multicarrier configuration and selection
CN115004755A
Measurement and reporting for artificial intelligence based positioning
WO2023148665A1
Techniques for indicating wireless channel information related to positioning
WO2024016337A1