Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
  • H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
  • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
  • G01S5/0009—Transmission of position information to remote stations
  • G01S5/0018—Transmission from mobile station to base station
  • G01S5/0036—Transmission from mobile station to base station of measured values, i.e. measurement on mobile and position calculation on base station
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N20/00—Machine learning
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L5/00—Arrangements affording multiple use of the transmission path
  • H04L5/003—Arrangements for allocating sub-channels of the transmission path
  • H04L5/0048—Allocation of pilot signals, i.e. of signals known to the receiver
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W24/00—Supervisory, monitoring or testing arrangements
  • H04W24/02—Arrangements for optimising operational condition
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W24/00—Supervisory, monitoring or testing arrangements
  • H04W24/08—Testing, supervising or monitoring using real traffic
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W24/00—Supervisory, monitoring or testing arrangements
  • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/08—Learning methods
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04W—WIRELESS COMMUNICATION NETWORKS
  • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
  • H04W4/02—Services making use of location information
  • H04W4/025—Services making use of location information using location based information parameters

Definitions

• the present disclosure relates generally to wireless communication and more specifically to techniques for supporting location services for user equipments (UEs).
• UEs user equipments
• FIG. 1 is a diagram of an example of user equipment (UE), base stations (BS), core network, and artificial intelligence/machine learning management function ( AI/ML-MF) server, in accordance with various aspects described.
• UE user equipment
• BS base stations
• AI/ML-MF artificial intelligence/machine learning management function
• FIG. 2 is table outlining example characteristics of Al-based UE positioning, in accordance with various aspects described.
• FIG. 3 is a diagram of an example neural network (NN), in accordance with various aspects described.
• FIG. 4 is a functional block diagram of an example system for generating an AI./ML based positioning-related inference output, in accordance with various aspects described.
• FIG. 5 illustrates an example message sequence for configuring and performing collection of AI/ML model data, in accordance with various aspects described.
• FIG. 6 is a flow diagram outlining an example method for collecting measurement data for training or monitoring an AI/ML model, in accordance with various aspects described.
• FIGs. 7, 7A, 7B are flow diagrams outlining an example method for collecting measurement data for training or monitoring an AI/ML model, in accordance with various aspects described.
• FIG. 8 is a flow diagram outlining an example method for collecting measurement data for training or monitoring an AI/ML model, in accordance with various aspects described.
• FIG. 9 illustrates a simplified block diagram of a network device, in accordance with various aspects described.
• FIG. 1 illustrates an exemplary wireless communication system 100 that includes a UE 110, a positioning reference unit (PRU) 115, a Radio Access Network (RAN) having a plurality of base stations 120, and a core network (CN) having an Access and Mobility Management Function (AMF) 130 that communicates with Location Management Function (LMF) 135.
• the AMF 130 and LMF 135 may be implemented on a server(s) associated with the CN.
• the communication system may include an Access Network (AN) in which devices communicate using Wireless Local Area Network (WLAN) protocols and interfaces instead of, or in addition to, NG-RAN or LTE cellular protocols.
• WLAN Wireless Local Area Network
• the LMF 135 provides AI/ML model-enhanced UE position or position-related information to a requesting application or service (e.g., associated with the UE or a lawful external entity) during a positioning session.
• the LMF 135 provides positioning assistance data to the UE 110 including, for example, information regarding signals to be measured (e.g., expected signal timing, signal coding, signal frequencies, and so on), locations and identities of terrestrial transmitters (e.g., base stations 120) and/or signal timing or orbital information for Global Navigation Satellite System (GNSS) satellites (not shown).
• This positioning information may be used to facilitate positioning techniques such as Assisted GNSS (A-GNSS), Advanced Forward Link Trilateration (AFLT), Observed Time Difference of Arrival (OTDOA), Enhanced Cell Identity (ECID), and so on.
• A-GNSS Assisted GNSS
• AFLT Advanced Forward Link Trilateration
• OTDA Observed Time Difference of Arrival
• ECID Enhanced Cell Identity
• the CN also includes an AI/ML management function (AI/ML-MF) 140 which is implemented on a server(s) or other “smart entity” associated with the CN.
• AI/ML-MF AI/ML management function
• the AI/ML-MF is implemented as part of the functions performed by the LMF 135.
• the AI/ML-MF 140 is implemented as a separate or independent function, within the CN, with respect to the LMF 135.
• the AI/ML-MF 140 maintains and deploys positioning-related AI/ML-MF models within the network as described in more detail below.
• AI/ML-MF 140 is an arbitrary notation used herein to describe a core network side function that manages AI/ML model related aspects.
• the AI/ML-MF 140 may be any core network side function that performs the functions attributed to the AI/ML-MF herein.
• the AI/ML-MF 140 and the base stations 120 may communicate using a New Radio Positioning Protocol A (NRPPa) with NRPPa messages being transferred between the base stations 120 and the AI/ML-MF 140 via the AMF 130.
• the AI/ML-MF 140 and the UE 110 may communicate using the LTE Positioning Protocol (LPP) where LPP messages are transferred through Non-Access Stratum (NAS) messages between the UE 110 and the AI/ML- MF 140 via the AMF 130 and a serving base station 120A for the UE.
• LPP LTE Positioning Protocol
• NAS Non-Access Stratum
• the AI/ML-MF 140 and the base stations 120 and the UE 110 may communicate using one or more dedicated AI/MF protocols with messages being transferred between the base stations 120, the UE 110, and the AI/ML-MF 140 via the AMF 130.
• the wireless communication system 100 includes at least one Positioning Reference Unit (PRU) 115.
• PRU Positioning Reference Unit
• a PRU at a known location can act as a measurement entity and perform measurements of position- related reference signals (e.g., positioning reference signals (PRS) from a base station) and report these measurements for use in training or monitoring the AI/ML-MF model.
• PRS positioning reference signals
• the PRU can act as a reference signal entity and transmit sounding reference signals (SRS) to enable base stations to measure and report uplink (UL) positioning measurements for the PRU (at its known location) for use in training or monitoring the AI/ML model.
• SRS sounding reference signals
• the PRU functionality is realized by a UE (either stationary or mobile) with a known location.
• the ground truth location for a PRU may be programmed and stored in the PRU and/or provided to the AI/ML-MF at installation (for a stationary PRU) or determined during a positioning session that uses a method that does not include use of the AI/ML-MF model- enhanced techniques disclosed herein.
• Positioning techniques may be enhanced by the addition of an AI/ML model.
• an inference function may use the AI/ML model to generate an inferred position or inferred position-related data for a UE based on measurements provided by the UE.
• Use of AI/ML model based positioning techniques may be of particular benefit in scenarios where a UE may often be in a non-line-of- sight (NLOS) position with respect to transmission reception points (TRPs) or base stations that transmit positioning reference signals.
• NLOS non-line-of- sight
• TRPs transmission reception points
• an AI/ML model may be maintained for a particular building or factory in which cellular signals are attenuated and obstacles may move.
• the AI/ML model may be stored in and/or monitored by any network device, including the UE 110, a base station 120 (or other access node), or a device or server associated with the AI/ML-MF 140 or the CN more generally.
• any network device including the UE 110, a base station 120 (or other access node), or a device or server associated with the AI/ML-MF 140 or the CN more generally.
• Disclosed herein are various techniques for collecting measurement data to support AI/ML enhanced positioning services in which the associated AI/ML model is stored in and/or monitored by various alternative network entities.
• FIG. 2 is a table that outlines several possible configurations for AI/ML enhanced positioning.
• AEML-MF-based positioning and UE-based positioning will be discussed respectively.
• the suffix “-based” refers to the device or node (e.g., UE, base station, or AI/ML-MF (instantiated on a CN related device)) that is responsible for making the positioning calculation.
• the suffix “-assisted” refers to the device or node that provides measurements to another device or node that makes the positioning calculation.
• the AI/ML model output e.g., inferred position
• AI/ML Type Direct AI/ML
• the AI/ML model output e.g., inferred position or other inferred position-related information
• AI/ML Type AI/ML assisted
• the BS provides measurement data to the AEML-MF (Assistance
• AI/ML Type BS-assisted).
• FIG. 3 is a diagram of an example of a neural network (NN) 300 according to one or more implementations described herein.
• NN 300 may include nodes arranged in different layers, such as an input layer 310 of nodes, multiple hidden or intermediary layers 320 of nodes, and an output layer 330 of nodes.
• NN 300 may be an example of, or a portion of, an AI/ML model deployed (e.g., stored) on a model entity.
• NN 300 may be trained by a training function using training data received from a data collection entity.
• the NN 300 may be deployed by model configuration entity.
• the NN 300 may be used by an inference function that inputs inference input data (e.g., measurement data) to the input layer 310 and receives inference output data from the output layer 330.
• the inference function may generate an inferred position or inferred position-related information from the inference output data.
• Example NN 300 may include a number N of inputs introduced to four input nodes [N, 4] of input layer 310. This may include processing or encoding input data into a form, shape, vector, or data structure, that is receivable by the NN.
• the four input nodes may process the inputs to produce a first weight (Wi) that the four input nodes provide to the five nodes [4;5] of a first hidden layer.
• the five nodes of the first hidden layer may use a first function (fi) to process the inputs to produce a second weight (W2) that the five nodes of the first hidden layer may provide to the five nodes [5;5] of a second hidden layer.
• the five nodes of the second layer may use a second function (f2) to process the inputs to produce a third weight (W3) that the five nodes of the second hidden layer may provide to the three nodes [5 ;3] of output layer 330.
• the nodes of output layer 330 may each process the inputs received and produce an output. This may include converting or decoding output data from a form, shape, vector, or data structure, that may be used by a subsequent algorithm, process, or procedure.
• Al Artificial intelligence
• Al may involve the combination of computer science and datasets to enable problem-solving.
• Al may encompass machine learning (ML) and deep learning (DL), which are frequently mentioned in conjunction with Al.
• ML machine learning
• DL deep learning
• These disciplines are comprised of Al algorithms which seek to create expert systems which make predictions or classifications based on input data.
• ML, DL, and neural networks (NNs) are sub-fields of Al.
• NNs are actually a sub-field of ML
• DL is a sub-field of NNs. The way in which DL and ML differ is in how each algorithm learns.
• NNs may comprise logically interconnected nodes arranged in node layers. There may be an input layer, one or more hidden or intermediate layers, and an output layer. Each node, or artificial neuron, may connect to another and has an associated weight and threshold. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data may be passed along to the next layer of the network by that node.
• the “deep” in deep learning is just referring to the number of layers in a NN.
• a NN that consists of more than three layers — which would be inclusive of the input and the output — can be considered a deep learning algorithm or a deep NN.
• a neural network that only has three layers is just a basic NN.
• Feedforward NNs may include an input layer, one or more hidden layers, and an output layer. While these NNs are also referred to as MLPs, they may comprise sigmoid neurons, not perceptrons, as some real-world problems may nonlinear. Data is usually fed into these models to train them, and they may function as a foundation for computer vision, natural language processing, and other neural networks. Recurrent neural networks (RNNs) are identified by feedback loops.
• RNNs Recurrent neural networks
• Convolutional neural networks may be similar to feedforward NNs, but may be used for image recognition, pattern recognition, and/or computer vision. These NN may harness principles from linear algebra, particularly matrix multiplication, to identify patterns within an image. Linear regression analysis, for example, may be used to predict a value of a variable based on a value of another variable. This form of analysis may estimate coefficients of a linear equation, involving one or more independent variables that best predict the value of the dependent variable. Linear regression may fit a straight line or surface that minimizes discrepancies between a predicted value and an actual value. These learning algorithms may be leveraged when using time-series data to make predictions about future outcomes.
• FIG. 4 is a functional block diagram of an AI/ML model system that trains and monitors an AI/ML model that can be used to generate a position-related inference output based, at least in part, on measurements made by a UE.
• the inference output may be an inferred position of a UE or other inferred position-related data.
• the system includes a model configuration entity 445, a model entity 450, a monitoring entity 480, and a data collection entity 490.
• An entity is a network device that performs a given function.
• the model configuration entity 445 is a network device that performs a model configuration function, and so on.
• an entity includes a processor, memory, and stored instructions that cause the processor to control the network device to perform the functions associated with the entity.
• An entity may be, for example, a UE, a PRU, a base station, or a network device associated with the AI/ML-MF (e.g., a server).
• a device associated with the AI/ML-MF serves as the model configuration entity 445.
• the data collection entity 490 may be a base station (e.g., base station 120 of FIG. 1) or a network device associated with an AI/ML-MF (e.g., AI/ML-MF 140 of FIG. 1).
• the model entity 450 may be a UE (e.g., UE 110 of FIG. 1), a base station (e.g., base station 120 of FIG. 1), or a network device associated with the AI/ML-MF (e.g., AI/ML-MF 140 of FIG. 1).
• the monitoring entity 480 may be a UE (e.g., UE 110 of FIG.
• the model entity 450 and the monitoring entity 480 may be implemented on different devices.
• the model entity 450 stores a NN 300 that, during a positioning session, generates the inference output based, at least in part, on measurement data from a UE whose position is being determined.
• the input data to the input nodes of NN is measurement data.
• neural network inputs may also include data from other measurement entities as well as other sources, such as clock/calendar services, temperature/weather related sensors, and so on.
• the inference output is provided by the output nodes of the NN.
• AI/ML model is described as a NN 300, any other type of AI/ML model may be used to generate the inference results and inference output.
• the model entity 450 implements a training function 455 and an inference function 465, which may be different from one another.
• a particular entity e.g., a US, a base station, or an AI/ML-MF
• this entity stores the AI/ML neural network 300 and also includes hardware and stored instructions used to execute the training function 455 and the inference function 465.
• the training function 455 updates the weights applied by respective nodes in the neural network 300.
• This training process is performed based on training data that includes measurement values which serve as neural network inputs and, usually, an associated “ground truth”.
• the ground truth is a known value (e.g., known based on another positioning method with a desired accuracy) which, if the AI/ML neural network 300 perfectly represented reality, would be equal to the inference output.
• the training data would include respective sets of measurements made by the various measurement entities 495 and a respective ground truth for the measurement entities comprising a known location of the measurement entities (e.g., preprogrammed or determined by some other method).
• the ground truth may be unknown or may be intentionally distorted to simulate a noisy environment.
• Training data may also include data from other (nonmeasurement entity) sources, such as clock/calendar services, temperature/weather related sensors, and so on.
• the inference function 465 inputs inference data (e.g., including a UE’s measurement data and possibly other assistance data not based on measurements) to the AI/ML neural network 300 and generates the inference output based, at least in part, on an output of the AI/ML neural network 300.
• the inference output may be used as the UE’s position, may be an input to the determination of the UE’s position, and may include position-related information including whether the UE is LOS or NLOS with respect to a fixed point.
• the training function 455 receives a data training initiator message from the model configuration entity 445 to initiate training. In other examples, the training function 455 initiates training based on the occurrence of some predefined event (e.g., an initial deployment of an AI/ML model in a model entity) or a training trigger generated by another device or function (e.g., a monitoring action taken by the monitoring entity 480). To train the AI/ML neural network 300 the training function 455 transmits a model training request to the data collection entity 490 and, in response, receives training data.
• some predefined event e.g., an initial deployment of an AI/ML model in a model entity
• a training trigger generated by another device or function e.g., a monitoring action taken by the monitoring entity 480
• the training function 455 provides the training data to the inference function 465 and receives performance feedback (e.g., the inference output that is generated by the AI/ML neural network 300 in response to the training data). Based on the performance feedback, the training function 455 adapts the neural network by adding or subtracting nodes, modifying inputs summed by virtual nodes, adapting weights applied by the virtual nodes, and so on.
• performance feedback e.g., the inference output that is generated by the AI/ML neural network 300 in response to the training data.
• the training function 455 adapts the neural network by adding or subtracting nodes, modifying inputs summed by virtual nodes, adapting weights applied by the virtual nodes, and so on.
• FIG. 7A An example of a method that may be performed by the model entity’s training function is illustrated in FIG. 7A.
• the monitoring entity 480 performs a monitoring process that checks the accuracy of inference results generated by the AI/ML model.
• the monitoring process may be triggered periodically (e.g., the monitoring condition is the expiration of a timer which is configured statically or semi-persistently).
• the monitoring entity may monitor inference data being provided to the model entity during positioning sessions and when the inference data falls outside a preconfigured threshold range, the monitoring process may be triggered.
• the monitoring entity 480 transmits a monitoring request to the data collection entity 490 and a monitoring initiator message to the inference function 465.
• the monitoring initiator message informs the inference function 465 that it will be receiving reference data and causes the inference function to use this reference data to generate inference results that are provided to the monitoring entity 480.
• the monitoring entity 480 receives the reference data and a reference value (e.g., a ground truth value or other known position-related information) from the data collection entity.
• the reference value is ground truth position of the measurement entity, a position of the measurement entity determined by a non-model based technique, or a Global Navigation Satellite System (GNSS) estimate of the position of the measurement entity.
• the reference value may include an intermediate output of the AI/ML model.
• the reference data is predetermined inference input values and the reference value is an expected output of the AI/ML model based on the predetermined inference input values
• the monitoring entity 480 provides the reference data (which may also include assistance data not based on measurements) to the inference function 465 and receives the inference results.
• the monitoring entity 480 compares the reference value with the inference results and, based on the result of the comparison, may perform a monitoring action, such as triggering a model training process, triggering a model re-selection process, providing feedback to the AI/ML-MF, activating a different AI/ML model, or de-activating the AI/ML model.
• the comparison operation may be performed by another entity, with the results provided to the AI/ML-MF so that the AI/ML-MF may determine a monitoring action.
• An example of a method that may be performed by the monitoring entity is illustrated in FIG. 7B.
• the data collection entity 490 may receive data collection configuration information from the model configuration entity and provide a measurement configuration to the measurement entities 495 and an RS configuration to the RS entities 497.
• the measurement configuration and RS configuration may cause periodic or semi-persistent measurement of configured RS signals.
• the measurement configuration and RS configuration may cause measurement of configured RS signals in response to a trigger signal from the data collection entity 490.
• the measurement configuration may cause the measurement entity to measure the RS and provide the measurement data when the measurement entity is providing other position- related feedback to the network device.
• the measurement configuration may cause the measurement entity to measure the RS and provide measurement data when the measurement entity arrives at a preconfigured location.
• the measurement configuration and RS configuration (e.g. including configuring downlink position reference signals, uplink sounding reference signals, or sidelink position reference signals) may be performed by the model configuration entity 445.
• the data collection entity 490 serves as central control for measurement data collection used in training and monitoring the AI/ML model.
• the data collection entity 490 receives requests for measurement data (e.g., either training data or reference data) from various requesting entities, triggers RS, triggers measurement of the RS, and provides resulting measurement data to the requesting entities.
• the data collection entity 490 may perform preprocessing on received measurement data to align the format of the data with the inputs and other requirements of the NN 300.
• the data collection entity 490 collects training data from the measurement entities 495 and provides the training data to the model entity 450.
• the data collection entity 490 triggers the transmission of reference signals (RS) by RS entities 497 and also measurement of the RS by measurement entities 495.
• the reference signals may include downlink (position reference signals (PRS)), uplink (SRS for positioning or for MIMO), and/or sidelink (SL-PRS) signals.
• PRS position reference signals
• SRS uplink
• S-PRS sidelink
• the data collection entity 490 receives the training data and may perform some pre-processing on the training data.
• the training data is provided to the training function 455. As noted above the training data includes ground truth information.
• This ground truth information may be transmitted by a measurement entity 495 (e.g., if the data collection device is mobile and is capable of independently determining its position) or a ground truth value for the data collection device may be stored by the data collection entity 490 (e.g., for a stationary data collection device).
• a measurement entity 495 e.g., if the data collection device is mobile and is capable of independently determining its position
• a ground truth value for the data collection device may be stored by the data collection entity 490 (e.g., for a stationary data collection device).
• the data collection entity 490 collects inference data and provides the inference data to the inference function 465.
• Inference data includes data received from a UE whose inferred position-related information is being sought in the positioning session. Inference data may also include data from other measurement entities as well as other sources, such as clock/calcndar services, tcmpcraturc/wcathcr related sensors, and so on.
• the data collection entity 490 collects reference data and provides the reference data to the monitoring entity 480. In response to a monitoring request from the monitoring entity 480, the data collection entity triggers transmission of RS configured for monitoring and performance of measurements configured for monitoring.
• the data collection entity 490 receives the measurements and generates reference data, including a reference value (e.g., ground truth value) and provides the reference data to the monitoring entity 480.
• reference data may also include artificial data and data from other sources such as clock/calendar services, temperature/weather related sensors, and so on.
• the AI/ML model system relies on data from measurement entities 495 for training and monitoring of the AI/ML NN 300.
• Measurement entities include PRUs or base stations or, in some examples, UEs that have a secondary means for sufficiently accurately determining their ground truth location without relying on an inference output. Measurement entities may be static or mobile.
• the measurement entities provide an indication of their AI/ML model capability to the model configuration entity 445, including information about the accuracy of the measurement entity’s ground truth value and which types of measurements the measurement entity can make.
• capable measurement entities are configured to perform measurements to generate the types of measurement data that is collected to train and monitor the AI/ML NN 300.
• the configuration of the measurement entities for use in collecting data for an AI/ML model may be performed by the data collection entity 490 or the model configuration entity 445.
• Example measurement data includes channel impulse response (CIR), Power Delay Profile (PDP), time of arrival (TOA), angle of arrival (AOA), and so on.
• the measurement entity may also provide measurement data that is the result of additional logical functions by the measurement entity, such as measurement data that indicates whether the measurement entity is LOS or NLOS with respect to the RS entity 497.
• the measurement entities may measure signals from base stations, UEs, or PRUs. For example, a UE measurement entity may measure sidclink positioning reference signals from another UE or downlink positioning reference signals from a base station while a base station measurement entity may measure SRS from UEs or PRUs.
• the measurement entities may be configured to make measurements periodically or semi-persistently or in response to a trigger from the data collection entity 490.
• the measurement entities may be configured to measure the RS and provide measurement data when the network device is providing other position-related feedback to an AI/ML-MF server or when the measurement entity arrives at a preconfigured location.
• the RS entity 497 transmits reference signals that are measured by measurement entities 495 to generate the measurement data collected by the data collection entity.
• RS entities include base stations and PRUs/UEs.
• a base station acting as an RS entity transmits position related reference signals (PRS), which include, for example, DL-PRS.
• PRS position related reference signals
• a UE or PRU acting as an RS entity transmits sounding reference signals (SRS) which may be received by measurement entities including another UE or PRU or a base station or sidelink position related reference signals (SL-PRS) which may be received by measurement entities including another UE or PRU.
• SRS sounding reference signals
• the configuration of the RS entities for use in collecting data for an AI/ML model may be performed by the data collection entity 490 or the model configuration entity 445.
• RS parameters that may be configured include bandwidth, time duration, and so on).
• the RS entity is configured with a trigger which, when received, will cause the RS entity to transmit the RS.
• the trigger may be provided in a physical layer signal, a media access control signal, or a higher layer signal.
• Different RS may be configured for use in AI/ML model training as compared to monitoring.
• the RS entity may be configured to transmit the RS on a periodic or semi-persistent basis.
• the model configuration entity 445 may store multiple models (e.g., for different locations, conditions, and so on) and perform an initial deployment of one or more models to the model entity 450.
• the models may have an initially trained condition and a monitoring process or training process may be performed upon deployment.
• the model configuration entity may control selection of which model is deployed to the model entity 450.
• the model configuration entity 445 configures the measurement entities 495 and RS entities 497 based on a model being deployed.
• the data collection entity 490 receives the data collection configurations from the model configuration entity 445 and passes a measurement configuration to the measurement entities 495 and an RS configuration to RS entities 497.
• the model configuration entity 445 may identify the model that is associated with the measurements and a required quality (e.g., accuracy) of the measurements.
• the configuration process may also define labels to be attached to each measurement.
• the measurement configuration provides information identifying specific position- related measurements the measurement entity is to perform in response to requests for training data and requests for reference data (e.g., associated with monitoring). While training data may be a fairly comprehensive set of measurements from many or all measurement entities, the reference data may be a subset of training data selected as being sufficiently representative of the complete set of training measurements.
• the reference data may include fewer measurement types and/or measurements from fewer measurement entities or possibly predetermined data (e.g., “artificial” data) that simulates measurement data but is not the result of measurements made a measurement entity.
• the RS configuration configures RS entities 497 (e.g., UEs, PRUs or base stations) to transmit specific positioning-related reference signals (RS).
• RS entities 497 e.g., UEs, PRUs or base stations
• the model configuration entity 445 may configure different measurements and RS for use in generating training data versus reference data that is used for monitoring.
• FIG. 5 outlines an exemplary flow of messages for collecting training or reference data (referred to collectively as measurement data) for an AI/ML model.
• entities sending and receiving messages in FIG. 5 may correspond to entities of the same name that are included in the system illustrated in FIG. 4.
• a measurement entity transmits a capability message 505 to a model configuration entity.
• the capability message 505 indicates capability for providing measurement data and/or reference signals for use in AI/ML model training and/or monitoring.
• the measurement entity may be a PRU, UE, or base station.
• the model configuration entity is a network device associated with the AI/ML- MF of the core network.
• the message may indicate, for example, the measurement entity’s measurement capabilities such as measurement types (also referred to as labels), accuracies, and latencies.
• the capability message also indicates the entity’s capabilities for transmitting reference signals (e.g., to function as a reference signal (RS) entity).
• RS reference signal
• the model configuration entity transmits a data collection configuration 510 associated with a deployed AI/ML model to a data collection entity.
• the data collection entity may be a base station or a device associated with the AI/ML-MF.
• the data collection configuration identifies the AI/ML model that is deployed and includes measurement configurations for measurement entities and RS configurations for RS entities for both training and monitoring scenarios.
• Either the data collection entity or the model configuration entity transmits the measurement entity configuration 520 to measurement entities whose capability message 505 indicates sufficient capabilities to perform the measurements for the deployed AI/ML model.
• the measurement configuration includes measurement types and associated labels as well as which RS are to be measured for each measurement type.
• the measurement configuration may include separate configurations for training data and reference data.
• measurements include channel impulse response, LOS/NLOS property, time of arrival, angle of arrival, and so on.
• Either the data collection entity or the model configuration entity transmits the RS entity configuration 525 to RS entities (e.g., including measurement entities that indicated sufficient capabilities to transmit the RS for the deployed AI/ML model).
• RS entities may be PRUs, UEs, or base stations.
• the RS configuration may include separate configurations for RS used to generate training data and RS used to generate reference data.
• the RS configuration indicates a particular RS type. Examples of reference signals include DL-PRS, SL-PRS, and UL-SRS. Other RS parameters that may be configured by the RS configuration include bandwidth, time duration, and so on.
• the measurement entities transmit an acknowledgement message 530 for the measurement configuration.
• the data collection entity serves as a central receiver of requests for measurement data from various requesting entities and collector of measurement data from various measurement entities.
• measurement data is collected in response to specific requests (or configured periodic requests) from an authorized requesting entity to reduce overhead associated with the AI/ML model.
• the requesting entity may be a model entity requesting training data for use by a training function or a monitoring entity requesting reference data for use in monitoring the quality of the AI/ML model inference results.
• measurement data refers collectively to training data and reference data.
• a requesting entity transmits a measurement data request 535 to the data collection entity.
• the requesting entity may be a UE, a base station, or the AFML-MF.
• the measurement data request 535 indicates whether training or reference data is requested.
• the data collection entity transmits respective RS triggers 540 to the RS entities and respective measurement triggers 550 to the measurement entities.
• the RS trigger 540 and measurement trigger 550 may indicate whether training or reference data is being requested to determine which RS are transmitted and which measurements are performed.
• the data collection entity times the triggering of RS and measurements based on configured measurement gaps of measurement entities, muting of other reference signals, and so on to facilitate accurate measurements.
• a single trigger set 540,550 from the data collection entity may cause collection of several measurements in a periodic or semi-persistent manner.
• the measurement data request 535 may be made using LPP.
• the measurement data request 535 may be made using NRPPa.
• the RS entities transmit respective RS 560 and at 570 the respective measurement entities make measurements and process those measurements to generate respective measurement data.
• the processing may include computing or determining measurement data based on raw measurements, such as determining an LOS or NLOS property.
• the measurement entities transmit respective measurement data 580 to the data collection entity, which may perform some pre-processing on the received measurement data such as accumulating data collected over a time period and packaging the measurement data for use as training data or reference data by the AI/ML model.
• the data collection entity transmits the received measurement data 585 to the requesting entity.
• FIG. 6 is a flow diagram outlining an example method 600 for collecting measurement data for use in training or monitoring an AI/ML model.
• the method 600 may be performed, for example by the data collection entity 490 of FIG. 4.
• the method includes, at 610, receiving, from a requesting entity, a request for measurement data for use in generating artificial intelligence/machine learning (AI/ML) model input data.
• At 620 at least one measurement entity is controlled to measure a reference signal (RS).
• RS reference signal
• measurement data is received from the at least one measurement entity.
• the measurement data is provided to the requesting entity at 650.
• the requesting entity when the requesting entity is a UE and the request for measurement data is received according to a Long Term Evolution (LTE) Positioning Protocol (LPP).
• LTE Long Term Evolution
• LPP Positioning Protocol
• NRPPa New Radio (NR) Positioning Protocol A
• the method 600 includes receiving respective capability information from a plurality of measurement entities that includes the at least one measurement entity, wherein the respective capability information indicates that a respective measurement entity is capable of performing position-related measurements and providing a ground truth value.
• the method includes transmitting a configuration to the plurality of measurement entities.
• the configuration may include an indication of the RS, a measurement to be made on the RS to generate the measurement data, and a label to be applied to the measurement in the measurement data.
• the method 600 includes controlling the at least one measurement entity by configuring the measurement entity to measure the RS and provide measurement data periodically or semi-persistently. In one example, the method 600 includes controlling the at least one measurement entity to measure the RS by transmitting a trigger signal to the at least one measurement entity. In one example, the method 600 includes controlling the at least one measurement entity to measure the RS by configuring the measurement entity to measure the RS and provide the measurement data when the measurement entity is providing other position- related feedback to the network device. In one example, the method 600 includes controlling the at least one measurement entity to measure the RS by configuring the measurement entity to measure the RS and provide measurement data when the measurement entity arrives at a preconfigured location.
• the method 600 includes transmitting an RS configuration to a plurality of RS entities and, in response to the request for measurement data, triggering the plurality of RS entities to transmit the RS.
• FIG. 7 is a flow diagram outlining an example method 700 for requesting measurement data for use in training or monitoring an AI/ML model.
• the method 700 may be performed, for example by the training function of model entity 450 or monitoring entity 480 of FIG. 4.
• the method 700 includes, at 710, transmitting, to a data collection entity, a request for measurement data for use in training or monitoring an AI/ML model.
• the measurement data is received from the data collection entity.
• the method includes, at 730, providing the measurement data to an AI/ML model.
• the method includes transmitting the request for measurement to an artificial intelligence/machine learning management function (AI/ML-MF) according to LPP. In one example, the method includes transmitting the request for measurement data to an artificial intelligence/machine learning management function (AI/ML-MF) according to New Radio (NR) Positioning Protocol A (NRPPa). In one example, the method includes transmitting the request for measurement data using one or more dedicated AI/MF protocols.
• AI/ML-MF artificial intelligence/machine learning management function
• NRPPa New Radio Positioning Protocol A
• FIG. 7A is a flow diagram outlining an example data collection for training method 720 that includes method 700.
• the method 720 may be performed by the training function 455 of FIG. 4.
• Picking up at 715 the received training data is provided to the AI/ML model and at 725 feedback (e.g., inference results) are received from the AI/ML model.
• the method includes training the AI/ML model based on the feedback.
• the training may include adapting NN weights, pruning the NN, and so on.
• the method 720 includes transmitting the request for measurement data in response to a training initiation condition being met.
• the training initiation condition may be an initial deployment of a model.
• FIG. 7B is a flow diagram outlining an example data collection for monitoring method 740 that includes method 700.
• the method 740 may be performed by the monitoring entity 480 of FIG. 4.
• Picking up at 715 the received reference data is provided to the AI/ML model and at 745 inference results are received from the AI/ML model.
• the method includes comparing the inference results with a reference value and, at 755, a monitoring action is performed based on the comparison.
• the method when the measurement data is reference data the method includes transmitting the request for measurement data in response to a monitoring condition being met.
• the monitoring condition is the expiration of a periodic timer, wherein the timer is configured in a static or semi-persistent manner.
• the method includes monitoring inference data provided to the AI/ML model and transmitting the request for measurement data in response to the inference data having a value that falls outside a preconfigured threshold range.
• the reference value includes a ground truth position of a measurement entity, a position of the measurement entity determined by a non-model based technique, a Global Navigation Satellite System (GNSS) estimate of the position of the measurement entity, or an intermediate output of the AI/ML model.
• the reference data includes predetermined inference input values and the reference value includes an expected output of the AI/ML model based on the predetermined inference input values.
• the monitoring action includes triggering a model training process, triggering a model re-selection process, providing feedback to an AI/ML-MF, activating a different AI/ML model, or de-activating the AI/ML model.
• FIG. 8 is a flow diagram outlining an example method 800 for generating measurement data for use in training or monitoring an AI/ML model.
• the method 800 may be performed, for example by a measurement entity 495 of FIG. 4.
• the method 800 includes, at 810, receiving, from a data collection entity, a request for measurement data for use in training or monitoring an AI/ML model.
• the method includes performing one or more measurements on reference signals (RS) to generate measurement data.
• RS reference signals
• the method includes transmitting capability information to a model configuration entity, the capability information indicating that the apparatus is capable of performing position-related measurements and providing a ground truth value and receiving a configuration from the model configuration entity.
• the configuration includes an indication of the RS, a measurement to be made on the RS to generate the measurement data, and a label to be applied to the measurement in the measurement data.
• the method includes, in response to the request, measuring the RS and providing measurement data periodically or semi- pcrsistcntly.
• the method includes, in response to the request, measuring the RS and providing measurement data when other position-related feedback is provided to an AI/ML- MF server.
• the method includes, in response to the request, measuring the RS and providing measurement data when an entity performing the method arrives at a preconfigured location.
• the measurement data may include training data or reference data associated with a monitoring process.
• the term identify when used with reference to some entity or value of an entity is to be construed broadly as encompassing any manner of determining the entity or value of the entity.
• the term identify is to be construed to encompass, for example, receiving and parsing a communication that encodes the entity or a value of the entity.
• the term identify should be construed to encompass accessing and reading memory (e.g., device queue, lookup table, register, device memory, remote memory, and so on) that stores the entity or value for the entity.
• the term encode when used with reference to some entity or value of an entity is to be construed broadly as encompassing any manner or technique for generating a data sequence or signal that communicates the entity to another component.
• the term select when used with reference to some entity or value of an entity is to be construed broadly as encompassing any manner of determining the entity or value of the entity from amongst a plurality or range of possible choices.
• the term select is to be construed to encompass accessing and reading memory (e.g., lookup table, register, device memory, remote memory, and so on) that stores the entities or values for the entity and returning one entity or entity value from amongst those stored.
• the term select is to be construed as applying one or more constraints or rules to an input set of parameters to determine an appropriate entity or entity value.
• the term select is to be construed as broadly encompassing any manner of choosing an entity based on one or more parameters or conditions.
• the term derive when used with reference to some entity or value of an entity is to be construed broadly. “Derive” should be construed to encompass accessing and reading memory (e.g., lookup table, register, device memory, remote memory, and so on) that stores some initial value or foundational values and performing processing and/or logical/mathematical operations on the value or values to generate the derived entity or value for the entity.
• the term derive should be construed to encompass computing or calculating the entity or value of the entity based on other quantities or entities.
• the term derive should be construed to encompass any manner of deducing or identifying an entity or value of the entity.
• the term indicate when used with reference to some entity (e.g., parameter or setting) or value of an entity is to be construed broadly as encompassing any manner of communicating the entity or value of the entity either explicitly or implicitly.
• bits within a transmitted message may be used to explicitly encode an indicated value or may encode an index or other indicator that is mapped to the indicated value by prior configuration.
• the absence of a field within a message may implicitly indicate a value of an entity based on prior configuration.
• Fig. 9 is a diagram of an example of components of a network device according to one or more implementations described herein.
• the device 900 can include application circuitry 902, baseband circuitry 904, RF circuitry 906, front-end module (FEM) circuitry 908, one or more antennas 910, and power management circuitry (PMC) 912 coupled together at least as shown.
• the components of the illustrated device 900 can be included in a UE or a RAN node.
• the device 900 can include fewer elements (e.g., a RAN node may not utilize application circuitry 902, and instead include a processor/controller to process IP data received from a CN or an Evolved Packet Core (EPC)).
• EPC Evolved Packet Core
• the device 900 can include additional elements such as, for example, memory/storage, display, camera, sensor (including one or more temperature sensors, such as a single temperature sensor, a plurality of temperature sensors at different locations in device 900, etc.), or input/output (RO) interface.
• additional elements such as, for example, memory/storage, display, camera, sensor (including one or more temperature sensors, such as a single temperature sensor, a plurality of temperature sensors at different locations in device 900, etc.), or input/output (RO) interface.
• the components described below can be included in more than one device (e.g., said circuitries can be separately included in more than one device for Cloud-RAN (C-RAN) implementations).
• C-RAN Cloud-RAN
• the application circuitry 902 can include one or more application processors.
• the application circuitry 902 can include circuitry such as, but not limited to, one or more single-core or multi-core processors.
• the processor(s) can include any combination of general-purpose processors and dedicated processors (e.g., graphics processors, application processors, etc.).
• the processors can be coupled with or can include memory/storage and can be configured to execute instructions stored in the memory/storage to enable various applications or operating systems to run on the device 900.
• processors of application circuitry 902 can process IP data packets received from an EPC.
• the baseband circuitry 904 can include circuitry such as, but not limited to, one or more single-core or multi-core processors.
• the baseband circuitry 904 can include one or more baseband processors or control logic to process baseband signals received from a receive signal path of the RF circuitry 906 and to generate baseband signals for a transmit signal path of the RF circuitry 906.
• Baseband circuity 904 can interface with the application circuitry 902 for generation and processing of the baseband signals and for controlling operations of the RF circuitry 906.
• the baseband circuitry 904 can include a 3G baseband processor 904A, a 4G baseband processor 904B, a 5G baseband processor 904C, or other baseband processor(s) 904D for other existing generations, generations in development or to be developed in the future (e.g., 5G, 6G, etc.).
• the baseband circuitry 904 can handle various radio control functions that enable communication with one or more radio networks via the RF circuitry 906. In other implementations, some or all of the functionality of baseband processors 904A-D can be included in modules stored in the memory 904G and executed via a Central Processing Unit (CPU) 904E. In some implementations, the baseband circuitry 904 can include one or more audio digital signal proccssor(s) (DSP) 904F.
• DSP audio digital signal proccssor
• memory 904G may receive and/or store information and instructions for collecting measurement data for training or monitoring an AI/ML model, training an AI/ML model, monitoring an AI/ML model, and/or performing positioning related inference functions with an AI/ML model.
• the information and instructions enable the network device to function as one or more of a model entity, data collection entity, measurement entity, RS entity, or monitoring entity as illustrated in FIG. 4.
• RF circuitry 906 can enable communication with wireless networks using modulated electromagnetic radiation through a non- solid medium.
• the RF circuitry 906 can include switches, filters, amplifiers, etc. to facilitate the communication with the wireless network.
• RF circuitry 906 can include a receive signal path which can include circuitry to down-convert RF signals received from the FEM circuitry 908 and provide baseband signals to the baseband circuitry 904.
• RF circuitry 906 can also include a transmit signal path which can include circuitry to up-convert baseband signals provided by the baseband circuitry 904 and provide RF output signals to the FEM circuitry 908 for transmission.
• the receive signal path of the RF circuitry 906 can include mixer circuitry 906A, amplifier circuitry 906B and filter circuitry 906C.
• the transmit signal path of the RF circuitry 906 can include filter circuitry 906C and mixer circuitry 906A.
• RF circuitry 906 can also include synthesizer circuitry 906D for synthesizing a frequency for use by the mixer circuitry 906A of the receive signal path and the transmit signal path.
• Examples herein can include subject matter such as a method, means for performing acts or blocks of the method, at least one machine -readable medium including executable instructions that, when performed by a machine or circuitry (e.g., a processor (e.g., processor , etc.) with memory, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like) cause the machine to perform acts of the method or of an apparatus or system for concurrent communication using multiple communication technologies according to implementations and examples described.
• a machine or circuitry e.g., a processor (e.g., processor , etc.) with memory, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like
• ASIC application-specific integrated circuit
• FPGA field programmable gate array
• Example 1 is an apparatus for a network device, including a memory and a processor coupled to the memory.
• the processor is configured to, when executing instructions stored in the memory, cause the network device to receive, from a requesting entity, a request for measurement data for use in training or monitoring an artificial intelligence/machine learning (AI/ML) model; control at least one measurement entity to measure a reference signal (RS); receive measurement data from the at least one measurement entity; and provide, to the requesting entity, the measurement data.
• AI/ML artificial intelligence/machine learning
• RS reference signal
• Example 2 includes the subject matter of example 1, including or omitting optional elements, wherein the requesting entity includes a user equipment (UE); and the processor is configured to receive the request for measurement data according to a Long Term Evolution (LTE) Positioning Protocol (LPP).
• LTE Long Term Evolution
• LPP Positioning Protocol
• Example 3 includes the subject matter of example 1, including or omitting optional elements, wherein the requesting entity includes a base station (BS); and the processor is configured to receive the request for measurement data according to a New Radio (NR) Positioning Protocol A (NRPPa).
• BS base station
• NRPPa New Radio Positioning Protocol A
• Example 4 includes the subject matter of any of examples 1-3, including or omitting optional elements, wherein the processor is configured to receive the request for measurement data according to one or more dedicated AI/MF protocols from an access and mobility function (AMF).
• Example 5 includes the subject matter of any of examples 1-4, including or omitting optional elements, wherein the processor is configured to receive respective capability information from a plurality of measurement entities that includes the at least one measurement entity, wherein the respective capability information indicates that a respective measurement entity is capable of performing position-related measurements and providing a ground truth value; and transmit a configuration to the plurality of measurement entities, wherein the configuration includes an indication of the RS; a measurement to be made on the RS to generate the measurement data; and a label to be applied to the measurement in the measurement data.
• Example 6 includes the subject matter of any of examples 1-5, including or omitting optional elements, wherein the processor is configured to control the at least one measurement entity by configuring the measurement entity to measure the RS and provide measurement data periodically or semi-persistently.
• Example 7 includes the subject matter of any of examples 1-6, including or omitting optional elements, wherein the processor is configured to control the at least one measurement entity by transmitting a trigger signal to the at least one measurement entity.
• Example 8 includes the subject matter of any of examples 1-7, including or omitting optional elements, wherein the processor is configured to control the at least one measurement entity by configuring the measurement entity to measure the RS and provide the measurement data when the measurement entity is providing other position-related feedback to the network device.
• Example 9 includes the subject matter of any of examples 1-8, including or omitting optional elements, wherein the processor is configured to control the at least one measurement entity by configuring the measurement entity to measure the RS and provide measurement data when the measurement entity arrives at a preconfigured location.
• Example 10 includes the subject matter of any of examples 1-9, including or omitting optional elements, wherein the processor is configured to transmit an RS configuration to a plurality of RS entities; and in response to the request for measurement data, trigger the plurality of RS entities to transmit the RS.
• Example 11 is an apparatus for a network device, including a memory and a processor coupled to the memory. The processor is configured to, when executing instructions stored in the memory, cause the network device to transmit, to a data collection entity, a request for measurement data for use in training or monitoring an artificial intelligence/machine learning ( AI/ML) model; receive the measurement data from the data collection entity; and provide the measurement data to the Al/ML model.
• AI/ML artificial intelligence/machine learning
• Example 12 includes the subject matter of example 11, including or omitting optional elements, wherein the processor is configured to transmit the request for measurement to an artificial intelligence/machine learning management function ( AI/ML-MF) according to a Long Term Evolution (LTE) Positioning Protocol (LPP).
• AI/ML-MF artificial intelligence/machine learning management function
• LTE Long Term Evolution
• LPP Positioning Protocol
• Example 13 includes the subject matter of any of examples 11-12, including or omitting optional elements, wherein the processor is configured to transmit the request for measurement data to an artificial intelligence/machine learning management function (AI/ML- MF) according to New Radio (NR) Positioning Protocol A (NRPPa).
• AI/ML- MF artificial intelligence/machine learning management function
• NRPPa New Radio Positioning Protocol A
• Example 14 includes the subject matter of any of examples 11-13, including or omitting optional elements, wherein the processor is configured to transmit the request for measurement data to an artificial intelligence/machine learning management function (AI/ML- MF) according to one or more dedicated AI/MF protocols from an access and mobility function (AMF).
• AI/ML- MF artificial intelligence/machine learning management function
• AMF access and mobility function
• Example 15 includes the subject matter of any of examples 11-14, including or omitting optional elements, further including second memory configured to store the AI/ML model.
• Example 16 includes the subject matter of any of examples 11-15, including or omitting optional elements, wherein the measurement data includes training data and the processor is configured to transmit the request for measurement data in response to a training initiation condition being met.
• Example 17 includes the subject matter of any of examples 11-16, including or omitting optional elements, wherein the measurement data includes reference data and wherein the processor is configured to transmit the request for measurement data in response to a monitoring condition being met; receive inference results based on the measurement data from the AVML model; compare the inference results with a reference value; and based on the comparison, perform a monitoring action.
• Example 18 includes the subject matter of any of examples 11-17, including or omitting optional elements, wherein the monitoring condition includes expiration of a timer, wherein the timer is configured in a static or semi-persistent manner.
• Example 19 includes the subject matter of any of examples 11-12, including or omitting optional elements, wherein the processor is configured to monitor inference data provided to the AI/ML model; and transmit the request for measurement data in response to the inference data having a value that falls outside a preconfigured threshold range.
• Example 20 includes the subject matter of any of examples 11-19, including or omitting optional elements, wherein the reference value includes a ground truth position of a measurement entity, a position of the measurement entity determined by a non-model based technique, or a Global Navigation Satellite System (GNSS) estimate of the position of the measurement entity.
• GNSS Global Navigation Satellite System
• Example 21 includes the subject matter of any of examples 11-20, including or omitting optional elements, wherein the reference value include an intermediate output of the AI/ML model.
• Example 22 includes the subject matter of any of examples 11-21, including or omitting optional elements, wherein the measurement data includes predetermined inference input values and the reference value includes an expected output of the AVML model based on the predetermined inference input values.
• Example 23 includes the subject matter of any of examples 11-22, including or omitting optional elements, wherein the monitoring action includes triggering a model training process, triggering a model re-selection process, providing feedback to an artificial intclligcncc/machinc learning management function (AVML- MF), activating a different AVML model, or de-activating the AVML model.
• AVML- MF artificial intclligcncc/machinc learning management function
• Example 24 is an apparatus for a network device, including a memory and a processor coupled to the memory.
• the processor is configured to, when executing instructions stored in the memory, cause the network device to receive, from a data collection entity, a request for measurement data for use in training or monitoring an artificial intelligence/machine learning (AI/ML) model; perform one or more measurements on reference signals (RS) to generate measurement data; and provide the measurement data to the data collection entity.
• AI/ML artificial intelligence/machine learning
• RS reference signals
• Example 25 includes the subject matter of example 24, including or omitting optional elements, wherein the processor is configured to transmit capability information to a model configuration entity, wherein the capability information indicates that the apparatus is capable of performing position-related measurements and providing a ground truth value; and receive a configuration from the model configuration entity.
• the configuration includes an indication of the RS; a measurement to be made on the RS to generate the measurement data; and a label to be applied to the measurement in the measurement data.
• Example 26 includes the subject matter of any of examples 24-25, including or omitting optional elements, wherein the processor is configured to, in response to the request, measure the RS and provide measurement data periodically or semi-persistently.
• Example 27 includes the subject matter of any of examples 24-26, including or omitting optional elements, wherein the processor is configured to, in response to the request, measure the RS and provide measurement data when the network device is providing other position-related feedback to an AI/ML-MF server.
• Example 28 includes the subject matter of any of examples 24-27, including or omitting optional elements, wherein the processor is configured to, in response to the request, measure the RS and provide measurement data when the network device arrives at a preconfigured location.
• Example 29 includes the subject matter of any of examples 24-28, including or omitting optional elements, wherein the measurement data includes training data.
• Example 30 includes the subject matter of any of examples 24-29, including or omitting optional elements, wherein the measurement data includes reference data associated with a monitoring process.
• Example 31 is an apparatus for a network device, including a memory and a processor coupled to the memory. The processor is configured to, when executing instructions stored in the memory, cause the network device to transmit a data collection configuration to a data collection entity, the data collection configuration including an RS configuration indicating reference signals (RS) to be transmitted by RS entities and a measurement configuration indicating measurements to be made on the RS by respective measurement entities to generate measurement data and respective labels to be applied to the respective measurement data.
• RS RS configuration indicating reference signals
• Example 32 is an apparatus for a network device, including a memory and a processor coupled to the memory, cause the network device to transmit a measurement configuration to a measurement entity, the measurement configuration indicating measurements to be made on RS and respective labels to be applied to the respective measurement data; and transmit an RS configuration to a reference signal (RS) entity, the RS configuration configuring RS to be transmitted by the RS entity.
• RS reference signal
• Example 33 includes the subject matter of any of examples 31-32, including or omitting optional elements, wherein the measurement configuration configures the measurement entity to measure the RS and provide measurement data periodically or semi-persistently.
• Example 34 includes the subject matter of any of examples 31-33, including or omitting optional elements, wherein the measurement configuration configures the measurement entity to measure the RS and provide the measurement data when the measurement entity is providing other position-related feedback to the network device.
• Example 35 includes the subject matter of any of examples 31-34, including or omitting optional elements, wherein the measurement configuration configures the measurement entity to measure the RS and provide measurement data when the measurement entity arrives at a preconfigured location.
• Example 36 is a UE including the apparatus of any of examples 1-35.
• Example 37 is base station including the apparatus of any of examples 1-35.
• Example 38 is an artificial intelligence/machine learning management function (AI/ML-MF) server including the apparatus of any of examples 1-35.
• Example 38 is location management function (LMF) server including the apparatus of any of examples 1-35.
• Couple is used throughout the specification.
• the term may cover connections, communications, or signal paths that enable a functional relationship consistent with the description of the present disclosure. For example, if device A generates a signal to control device B to perform an action, in a first example device A is coupled to device B, or in a second example device A is coupled to device B through intervening component C if intervening component C does not substantially alter the functional relationship between device A and device B such that device B is controlled by device A via the control signal generated by device A.

Landscapes

• Engineering & Computer Science (AREA)
• Signal Processing (AREA)
• Computer Networks & Wireless Communication (AREA)
• Theoretical Computer Science (AREA)
• Software Systems (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Evolutionary Computation (AREA)
• Computing Systems (AREA)
• General Engineering & Computer Science (AREA)
• Medical Informatics (AREA)
• Mathematical Physics (AREA)
• Data Mining & Analysis (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Artificial Intelligence (AREA)
• Radar, Positioning & Navigation (AREA)
• Remote Sensing (AREA)
• Mobile Radio Communication Systems (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=89983733

Family Applications (1)

Country Status (4)

Families Citing this family (7)

Family Cites Families (1)

• 2024
  • 2024-01-10 CN CN202480010456.8A patent/CN120712493A/zh active Pending
  • 2024-01-10 WO PCT/US2024/010970 patent/WO2024163142A1/en not_active Ceased
  • 2024-01-10 KR KR1020257025872A patent/KR20250130663A/ko active Pending
  • 2024-01-10 EP EP24706262.3A patent/EP4643146A1/de active Pending

Also Published As

Similar Documents

Legal Events