[go: up one dir, main page]

WO2025093364A1 - Système et appareil de transfert de modèle dans un réseau et procédé associé - Google Patents

Système et appareil de transfert de modèle dans un réseau et procédé associé Download PDF

Info

Publication number
WO2025093364A1
WO2025093364A1 PCT/EP2024/079752 EP2024079752W WO2025093364A1 WO 2025093364 A1 WO2025093364 A1 WO 2025093364A1 EP 2024079752 W EP2024079752 W EP 2024079752W WO 2025093364 A1 WO2025093364 A1 WO 2025093364A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
uplink
aiml
transfer
model transfer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/EP2024/079752
Other languages
English (en)
Inventor
Rajat PUSHKARNA
Rikin SHAH
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aumovio Germany GmbH
Original Assignee
Continental Automotive Technologies GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Continental Automotive Technologies GmbH filed Critical Continental Automotive Technologies GmbH
Publication of WO2025093364A1 publication Critical patent/WO2025093364A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/34—Network arrangements or protocols for supporting network services or applications involving the movement of software or configuration parameters 
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • H04B17/3913—Predictive models, e.g. based on neural network models

Definitions

  • a communication network would be a 3rd Generation Partnership Project (3GPP) 5G (fifth generation) New Radio (NR) standard-based telecommunications network.
  • 3GPP 3rd Generation Partnership Project
  • 5G fourth generation
  • NR New Radio
  • conventional techniques for uplink (UL) model transfer do not disclose a mechanism for two-sided model training.
  • the present disclosure contemplates that conventional techniques may not facilitate efficiency and energy savings in an optimal manner.
  • RRC radio resource control
  • UAI UE Assistance Information UAI message
  • CP cyclic prefix
  • a method for model transfer in a network comprising: configuring a plurality of parameters indicative of uplink model transfer; communicating the plurality of parameters to a user device; and initiating an uplink model transfer by the user device based on the plurality of parameters.
  • the method as described herein can provide a dedicated framework for Artificial Intelligence Machine Learning (AIML) model transfer during uplink (UL) and may also allow the User Equipment (UE) to have an indication from the network on when to perform model transfer.
  • AIML Artificial Intelligence Machine Learning
  • the plurality of parameters indicative of uplink model transfer comprises at least one of: an uplink model transfer periodicity and/or a model drift threshold.
  • the method further comprises determining whether a current model performance is below the model drift threshold; and initiating the uplink model transfer if the current model performance is below the model drift threshold.
  • the uplink model transfer comprises an Artificial Intelligence Machine Learning (AIML) model transfer.
  • AIML Artificial Intelligence Machine Learning
  • initiating the uplink model transfer comprises generating a new Radio Resource Control (RRC) message and transmitting an AIML model via the new RRC message.
  • RRC Radio Resource Control
  • the new RRC message comprises an information element having a plurality of parameters related to an AIML model.
  • the plurality of parameters related to an AIML model comprises at least one of: an AIML payload, an AIML segment identification and/or an AIML model identification.
  • a computer readable storage medium having data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, to carry out the method of the first aspect.
  • an apparatus for model transfer in a network comprising a first module configured to receive at least one input signal associated with a plurality of parameters indicative of uplink model transfer; a second module configured to at least one of process and facilitate the method of the first aspect to generate at least one output signal; and a third module configured to communicate at least one output signal, wherein the output signal corresponds to a control signal for uplink model transfer by the user device.
  • the apparatus can correspond to a User Equipment (UE) which can communicate with a device corresponding to a base station.
  • the base station can, for example, correspond to a Next generation Node B (gNB) which can be configured to communicate one or more signals (e.g., input signal(s)) to the UE.
  • gNB Next generation Node B
  • a system comprising one or more apparatuses and one or more devices.
  • the apparatus(es) and the device(s) can, for example, be capable of being coupled via wired coupling and/or wireless coupling.
  • the system can allow the gNB (or base station) to have control over the UE to transfer the AIML model.
  • the RRC message can provide a dedicated framework in the CP to perform AIML model delivery to the gNB (or base station).
  • Fig. 1A shows a schematic diagram illustrating a system for model transfer in a network which can include at least one apparatus, according to an embodiment of the disclosure.
  • Fig. 1 B shows an example scenario in association with the system of Fig. 1A, according to an embodiment of the disclosure.
  • FIG. 2 shows a schematic diagram illustrating the apparatus of Fig. 1A in further detail, according to an embodiment of the disclosure.
  • the non-limiting term User Equipment (UE) or wireless device or user device may be used and may refer to any type of wireless device communicating with a network node and/or with another UE in a cellular or mobile communication system.
  • UE are target device, device-to-device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc.
  • a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a User Equipment (directly or via another node) and/or with another network node.
  • AIML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift and update feedback is then provided to re-train/update the model or select alternative model.
  • AIML model enabled wireless communication network it is then important to consider how to handle AIML model in activation with reconfiguration for wireless devices under operations such as model training, inference, updating, etc. Therefore, there is a need for specification for signaling methods and gNB-UE behaviors when a set of multiple specific AIML models are supported for RAN-based model operation and a new mechanism about gNB-UE behaviors and procedures is necessary to avoid any performance impact on model operation using multiple specific AIML models.
  • the present disclosure generally contemplates the facilitation of, for example, network (e.g., in association with 3GPP based standard/specification etc.) and/or user equipment (UE) efficiency (e.g., energy/power efficiency), in accordance with an embodiment of the disclosure.
  • network e.g., in association with 3GPP based standard/specification etc.
  • UE user equipment
  • AIML models which are to be transferred from the UE (or user device) to the gNB (or base station) may have issues if existing Radio Resource Control (RRC) messages (e.g. User Equipment Assistance Information UAI) for uplink (UL) model transfer are used.
  • RRC Radio Resource Control
  • UAI User Equipment Assistance Information
  • UL uplink
  • RRC Radio Resource Control
  • UAI User Equipment Assistance Information
  • CP cyclic prefix
  • the UE may have a single RRC state based on the main node (MN) RRC state.
  • the UE (or user device) may connect to the CN via single control plane connection and initial access (SRBO) and RRC configuration (SRB1 ) may be via the MN.
  • SRBO single control plane connection and initial access
  • SRB1 RRC configuration
  • Later reconfigurations can be from either the MN or secondary node (SN) and EN-DC may start with EUTRA Packet Data Convergence Protocol (PDCP) which can be reconfigured to use new radio (NR) PDCP.
  • PDCP EUTRA Packet Data Convergence Protocol
  • the present disclosure further contemplates that in the scenario of an UL AIML model transfer, the CP mechanism which the UE (or user device) can make use of is UE Assistance Information message (UAI).
  • UAI UE Assistance Information message
  • the functionality of UAI can be highly dependent on the UE state and the mobility of the UE (or user device) and therefore, using UAI for UL AIML model transfer may not be suitable.
  • the present disclosure therefore contemplates the possibility of a method to address the UL model transfer issue for a UE (or user device). Specifically, the present disclosure contemplates a method in which a new UL RRC message may be used to transfer the uplink AIML model.
  • the gNB (or base station) may configure the UE (or user device) to initiate the uplink AIML model transfer based one (or more) of the following criteria such as periodicity, UE AIML model drift and/or a combination of both periodicity and model drift.
  • a system 100 for model transfer in a network is shown, according to an embodiment of the disclosure.
  • the system 100 can, for example, be suitable for energy savings and facilitating energy/power efficiency in a network, in accordance with an embodiment of the disclosure.
  • the system 100 can include one or more apparatuses 102, at least one device 104 and, optionally, a communication network 106, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 can be coupled to the device(s) 104. Specifically, the apparatus(es) 102 can, for example, be coupled to the device(s) 104 via the communication network 106, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 can be coupled to the communication network 106 and the device(s) 104 can be coupled to the communication network 106. Coupling can be by manner of one or both of wired coupling and wireless coupling.
  • the apparatus(es) 102 can, in general, be configured to communicate with the device(s) 104 via the communication network 106, according to an embodiment of the disclosure.
  • the apparatus(es) 102 can, for example, be associated with/correspond to/include one or more user equipment (UE) which can carry one or more computers, in accordance with an embodiment of the disclosure.
  • UE user equipment
  • an apparatus 102 can correspond to a UE carrying at least one computer (e.g., an electronic device/module having computing capabilities such as an electronic mobile device which can be carried into a vehicle or an electronic module which can be installed in a vehicle, in accordance with an embodiment of the disclosure) which can be configured to perform one or more processing tasks in association with adaptive/dynamic/gradual control, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 can, in one embodiment, include one or more processors (not shown) which can be configured to perform one or more processing tasks in association with dynamic/adaptive/gradual control, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 can, for example, be configured to receive one or more input signals and perform at least one processing task based on the input signal(s) in a manner to generate one or more output signals.
  • the input signal(s) can, for example, be communicated from the device(s) 104 and received by the apparatus(es) 102, in accordance with an embodiment of the disclosure.
  • the output signal(s) can, for example, be communicated from the apparatus(es) 102, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 will be discussed later in further detail with reference to Fig. 2, according to an embodiment of the disclosure.
  • the device(s) 104 can, for example, be associated with/correspond to at least one base station (e.g., at least one gNB). Moreover, the device(s) 104 can, for example, be configured to carry/be associated with/include one or more computers (e.g., an electronic device/module having computing capabilities) which can, for example, be configured to perform one or more processing tasks in association with the base station. The device(s) 104 can be configured to generate one or more input signals which can be communicated to the apparatus(es) 102, in accordance with an embodiment of the disclosure. This will be discussed later in further detail in the context of an example scenario, in accordance with an embodiment of the disclosure.
  • the apparatus(es) 102 can, for example, be configured to receive at least one input signal and perform at least one processing task in association with dynamic/adaptive/gradual control on the input signal(s) in a manner so as to generate at least one output signal.
  • the device(s) 104 can, for example, be configured to generate (and communicate) the input signal(s) to the apparatus(es) 102, in accordance with an embodiment of the disclosure. This will be discussed, in accordance with an embodiment of the disclosure, in the context of an example scenario with reference to Fig. 1 B, hereinafter.
  • the present disclosure contemplates that there may be two solutions for the transfer of models, for example an AIML model, in a network.
  • One example solution is where a base station or node or gNB can transfer or deliver AIML model(s) to the User Equipment (UE) via Radio Resource Control (RRC) signaling.
  • RRC Radio Resource Control
  • Another example solution can be the base station or node or gNB can transfer or deliver AIML model(s) to the UE via UP data.
  • RRC Radio Resource Control
  • model delivery can be from the over-the-top (OTT) server to the gNB and the UE (or user device), or from the UE (or user device) to the gNB. Therefore, the present disclosure contemplates the possibility of a model delivery solution that can support both downlink and uplink.
  • OTT over-the-top
  • the present disclosure contemplates, as will be discussed further in detail in the context of an example scenario associated with the system 100 in accordance with an embodiment of the disclosure, that it may be helpful to consider some form of dynamic/adaptive/gradual configuration/determination strategy which will aid in power/energy consumption efficiency, in accordance with an embodiment of the disclosure.
  • the dynamic/adaptive/gradual control configuration/determination strategy can, for example, be in relation to dynamic/adaptive/gradual control based on model transfer by a UE (or user device) in a network, in accordance with an embodiment of the disclosure.
  • FIG. 2 an apparatus 102 is shown in further detail in the context of an example implementation 200, according to an embodiment of the disclosure.
  • the apparatus 102 can correspond to an electronic module 200a.
  • the electronic module 200a can, in one example, correspond to a mobile device which can, for example, be carried into the vehicle by a user, in accordance with an embodiment of the disclosure.
  • the electronic module 200a can correspond to an electronic device which can be installed/mounted in the vehicle, in accordance with an embodiment of the disclosure.
  • the electronic module 200a can be considered to be carried by the vehicle (e.g., either carried into the vehicle by a user or installed/mounted in the vehicle).
  • the electronic module 200a can be capable of performing one or more processing tasks in association with adaptive/dynamic/gradual control related processing, in accordance with an embodiment of the disclosure.
  • the electronic module 200a can, for example, include a casing 200b. Moreover, the electronic module 200a can, for example, carry any one of a first module 202, a second module 204, a third module 206, or any combination thereof.
  • the electronic module 200a can carry a first module 202, a second module 204 and/or a third module 206.
  • the electronic module 200a can carry a first module 202, a second module 204 and a third module 206, in accordance with an embodiment of the disclosure.
  • the casing 200b can be shaped and dimensioned to carry any one of the first module 202, the second module 204 and the third module 206, or any combination thereof.
  • the first module 202 can be coupled to one or both of the second module 204 and the third module 206.
  • the second module 204 can be coupled to one or both of the first module 202 and the third module 206.
  • the third module 206 can be coupled to one or both of the first module 202 and the second module 204.
  • the first module 202 can be coupled to the second module 204 and the second module 204 can be coupled to the third module 206, in accordance with an embodiment of the disclosure.
  • Coupling between the first module 202, the second module 204 and/or the third module 206 can, for example, be by manner of one or both of wired coupling and wireless coupling.
  • Each of the first module 202, the second module 204 and the third module 206 can correspond to one or both of a hardware-based module and a software-based module, according to an embodiment of the disclosure.
  • the first module 202 can correspond to a hardware-based receiver which can be configured to receive one or more input signals.
  • the input signal(s) can, for example, be communicated from the device(s) 104 (e.g., a gNB), in accordance with an embodiment of the disclosure.
  • the second module 204 can, for example, correspond to a hardware-based processor which can be configured to perform one or more processing tasks (e.g., in a manner so as to generate one or more output signals) as will be discussed later in further detail with reference to Fig. 3, in accordance with an embodiment of the disclosure.
  • the third module 206 can correspond to a hardware-based transmitter which can be configured to communicate one or more output signals from the electronic module 200a.
  • the output signal(s) can, for example, include/correspond to one or more instructions/commands/control signals in association with the aforementioned dynamic/adaptive/gradual control configuration/determination strategy so as to facilitate efficiency (e.g., power/energy efficiency and/or communication efficiency), in accordance with an embodiment of the disclosure.
  • FIG. 3 a method (also referable to as a processing method) in association with the system 100 is shown, according to an embodiment of the disclosure.
  • the method 300 can, for example, be suitable for/capable of facilitating energy efficiency, in accordance with an embodiment of the disclosure.
  • the processing method 300 can include any one of an input step 302, a processing step 304 and an output step 306, or any combination thereof, in accordance with an embodiment of the disclosure.
  • the processing method 300 can include the input step 302. In another embodiment, the processing method 300 can include the input step 302 and the processing step 304. In another embodiment, the processing method 300 can include the input step 302, the processing step 304 and the output step 306. In yet another embodiment, the processing method 300 can include the processing step 304 and one or both of the input step 302 and the output step 306. In yet a further embodiment, the processing method 300 can include the input step 302, the processing step 304 and the output step 306. In yet a further additional embodiment, the processing method 300 can include the processing step 304. In yet another further additional embodiment, the processing method 300 can include any one of or any combination of the input step 302, the processing step 304 and the output step 306 (i.e. , the input step 302, the processing step 304 and/or the output step 306).
  • one or more input signal(s) can be received.
  • the input signal(s) can be communicated from the device(s) 104 and can be received by an apparatus 102, in accordance with an embodiment of the disclosure.
  • the input step 302 can include receiving at least one input signal associated with a plurality of parameters indicative of uplink model transfer, where the uplink model transfer may include an Artificial Intelligence Machine Learning (AIML) model transfer.
  • AIML Artificial Intelligence Machine Learning
  • the input signal(s) may be generated by the device 104 and transmitted from the device 104 to the apparatus 102.
  • the input signal(s) may be generated and received by the apparatus 102 to advance to the processing step 304.
  • the input signal(s) may be generated by a transmitting UE (or user device) and received by a receiving UE (or user device).
  • At least processing task can be performed in association with the received input signal(s) in a manner so as to generate one or more output signals, in accordance with an embodiment of the disclosure.
  • the processing step 304 may include at least one of: configuring a plurality of parameters indicative of uplink model transfer; communicating the plurality of parameters to a user device; and initiating an uplink model transfer by the user device based on the plurality of parameters.
  • Communicating the plurality of parameters comprises communicating via at least one of: system information message and/or dedicated RRC message.
  • the processing step 304 can also include determining whether a current model performance is below the model drift threshold and initiating the uplink model transfer if the current model performance is below the model drift threshold.
  • the processing step 304 may further include determining whether a current periodicity is within the uplink model transfer periodicity; determining whether a current model performance is below the model drift threshold; and initiating the uplink model transfer if the current model performance is below the model drift threshold and if the current periodicity is within the uplink model transfer periodicity.
  • the plurality of parameters indicative of uplink model transfer may comprise at least one of: an uplink model transfer periodicity and/or a model drift threshold. Initiating the uplink model transfer may include generating a new Radio Resource Control (RRC) message and transmitting an AIML model via the new RRC message.
  • RRC Radio Resource Control
  • the new RRC message may include an information element having a plurality of parameters related to an AIML model while the plurality of parameters related to an AIML model may include at least one of: an AIML payload, an AIML segment identification and/or an AIML model identification.
  • a new UL RRC message can be used for transferring the uplink AIML model, whereby the gNB (or base station) may configure the UE (or user device) to initiate based one (or more) of the following criteria.
  • One example criteria for the UE (or user device) to initiate uplink AIML model transfer can be periodical (or periodicity).
  • the UE (or user device) performs UL AIML model transfer or delivery periodically as configured by the gNB (or base station) via new RRC message.
  • the periodicity may be configured by the gNB (or base station) in system information message and/or dedicated RRC message.
  • a second example criteria for the UE (or user device) to initiate uplink AIML model transfer can be based on AIML model drift.
  • the UE (or user device) performs UL AIML model transfer/delivery based on the UE AIML model drift.
  • the gNB (or base station) configures a threshold for the UE (or user device) to determine AIML model drift.
  • the UE (or user device) may compare the AIML model performance with the configured threshold to check for AIML model drift. If the UE (or user device) determines the AIML model performance is below the configured threshold, then the UE (or user device) may transmit UL AIML model to the gNB (or base station) via a new RRC message.
  • a third example criteria for the UE (or user device) to initiate uplink AIML model transfer can be based on the combination of both periodicity and AIML model drift.
  • the UE UL AIML model transfer periodicity is met and the model performance has not degraded from AIML model drift (e.g. the AIML model performance is equal to or above the configured threshold)
  • the UE (or user device) will not perform UL AI/ML model transfer.
  • the UE UL AI/ML model transfer periodicity is met and the model performance has degraded from AI/ML model drift (e.g. the AIML model performance is below the configured threshold)
  • the UE (or user device) will perform UL AIML model transfer.
  • the new RRC message information element (IE) may carry the AIML model related parameters such as AIML payload, AIML segment ID, AI/ML model ID, etc. Such a method may be applicable to all RRC states.
  • the output signal(s) can, for example, be communicated, as an option, in accordance with an embodiment of the disclosure.
  • the output signal(s) can optionally be communicated from the apparatus 102.
  • the output signal(s) can optionally be communicated from the apparatus 102 to one or both of at least one device 104 and another apparatus 102, in accordance with an embodiment of the disclosure.
  • the present disclosure further contemplates a computer program (not shown) which can include instructions which, when the program is executed by a computer (not shown), cause the computer to carry out the input step 302, the processing step 304 and/or the output step 306 as discussed with reference to the method 300.
  • the computer program can include instructions which, when the program is executed by a computer, cause the computer to carry out the input step 302 and/or the processing step 304, in accordance with an embodiment of the invention.
  • the present disclosure yet further contemplates a computer readable storage medium (not shown) having data stored therein representing software executable by a computer (not shown), the software including instructions, when executed by the computer, to carry out the input step 302, the processing step 304 and/or the output step 306 as discussed with reference to the method 300.
  • the computer readable storage medium can have data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, cause the computer to carry out the input step 302 and/or the processing step 304, in accordance with an embodiment of the invention.
  • the present disclosure generally contemplates an apparatus 102 suitable for energy saving in a network which can include a first module 202, a second module 204 and/or a third module 206.
  • the first module 202 can be configured to receive one or more input signals.
  • the input signal(s) can, for example, be associated with a plurality of parameters indicative of uplink model transfer.
  • the second module 204 can be configured to process and/or facilitate processing of the input signal(s) according to the method 300 as discussed earlier to generate one or more output signals.
  • the third module 206 can be configured to communicate one or more output signals.
  • the output signal(s) can, for example, correspond to one or more control signals for uplink model transfer by the user device (or UE).
  • the apparatus 102 can correspond to a User Equipment (UE) which can communicate with a device 104 corresponding to a base station.
  • the base station can, for example, correspond to a Next generation Node B (gNB) which can be configured to communicate one or more signals (e.g., input signal(s)) to the UE.
  • gNB Next generation Node B
  • the present disclosure generally contemplates a system 100 which can include one or more apparatuses 102 and one or more devices 104.
  • the apparatus(es) 102 and the device(s) 104 can, for example, be capable of being coupled via wired coupling and/or wireless coupling.
  • the possibility of the output signal(s) being communicated from the apparatus(es) 102 was discussed. It is appreciable that the output signal(s) need not necessarily be communicated from the apparatus(es) 102. Specifically, the possibility that the output signal(s) need not necessarily be communicated outside of the apparatus(es) 102 is contemplated, in accordance with an embodiment of the invention. More specifically, the output signal(s) can, for example, correspond to internal command(s)/instruction(s) (e.g., communicated only within an apparatus 102) for adaptively controlling operational configuration of an apparatus 102, in accordance with an embodiment of the invention.
  • internal command(s)/instruction(s) e.g., communicated only within an apparatus 102
  • FIG. 4A to Fig. 4C show schematic diagrams illustrating example scenarios in association with the method 300, in accordance with an embodiment of the disclosure.
  • the base station may trigger the UE (or user device) for an uplink AIML model transfer.
  • the UE may then send an uplink RRC message containing the AIML model to the base station (or gNB).
  • the UE may be configured to receive a plurality of parameters indicative of uplink model transfer.
  • the UE may then determine if there is AIML model drift and/or periodicity. If AIML model drift and/or periodicity is present, the UE (or user device) transmits the UL AIML model to the gNB (or base station).
  • the gNB (or base station or network) may configure the periodicity and/or the AIML model drift for the UE (or user device) before sending them to the UE (or user device).
  • the gNB may configure the periodicity and/or the AIML model drift for the UE (or user device) before sending them to the UE (or user device).
  • PDSCH Physical downlink shared channel
  • PHY Physical Layer PMI Precoding Matrix Indicator PRB Physical resource block
  • PRG Precoding resource block group
  • PRS Positioning reference signal PSS Primary Synchronisation signal
  • PUCCH Physical uplink control channel QCL Quasi co-location RB Resource block
  • RBG Resource block group Rl Rank Indicator
  • RIV Resource indicator value RLF Radio Link Failure
  • RRC Radio Resource Control RS Reference signal RSRP Reference Signal Received Power
  • RSRQ Reference Signal Received Quality SCI Sidelink control information SN Secondary Node SLIV Start and length indicator value
  • SR Scheduling Request SRS Sounding reference signal SS Synchronisation signal SS-RSRP SS reference signal received power SS-RSRQ SS reference signal received quality
  • Transport Block TCI Transmission Configuration Indicator TDM Time division multiplexing UAI User Equipment Assistance Information UE User equipment

Landscapes

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

Abstract

L'invention concerne un système (100), un appareil (102) et un procédé (300) de transfert de modèle dans un réseau. Le procédé (300) consiste à configurer une pluralité de paramètres indicatifs d'un transfert de modèle de liaison montante ; à communiquer la pluralité de paramètres à un dispositif utilisateur ; et à initier un transfert de modèle de liaison montante par le dispositif utilisateur sur la base de la pluralité de paramètres.
PCT/EP2024/079752 2023-11-02 2024-10-22 Système et appareil de transfert de modèle dans un réseau et procédé associé Pending WO2025093364A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102023210843.7 2023-11-02
DE102023210843 2023-11-02

Publications (1)

Publication Number Publication Date
WO2025093364A1 true WO2025093364A1 (fr) 2025-05-08

Family

ID=93258780

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2024/079752 Pending WO2025093364A1 (fr) 2023-11-02 2024-10-22 Système et appareil de transfert de modèle dans un réseau et procédé associé

Country Status (1)

Country Link
WO (1) WO2025093364A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022235525A1 (fr) * 2021-05-02 2022-11-10 Intel Corporation Collaboration améliorée entre un équipement utilisateur et un réseau pour faciliter un apprentissage machine
WO2023187676A1 (fr) * 2022-03-29 2023-10-05 Telefonaktiebolaget Lm Ericsson (Publ) Mises à jour de modèle d'intelligence artificielle (ia) et d'apprentissage automatique (ml)
WO2024040476A1 (fr) * 2022-08-24 2024-02-29 Apple Inc. Conception de procédure rrc pour ia/ml sans fil

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022235525A1 (fr) * 2021-05-02 2022-11-10 Intel Corporation Collaboration améliorée entre un équipement utilisateur et un réseau pour faciliter un apprentissage machine
WO2023187676A1 (fr) * 2022-03-29 2023-10-05 Telefonaktiebolaget Lm Ericsson (Publ) Mises à jour de modèle d'intelligence artificielle (ia) et d'apprentissage automatique (ml)
WO2024040476A1 (fr) * 2022-08-24 2024-02-29 Apple Inc. Conception de procédure rrc pour ia/ml sans fil

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
FUJITSU: "Discussions on AIML model transfer via air interface", vol. 3GPP RAN 2, no. E-meeting; 20230417 - 20230426, 7 April 2023 (2023-04-07), XP052365285, Retrieved from the Internet <URL:https://ftp.3gpp.org/tsg_ran/WG2_RL2/TSGR2_121bis-e/Docs/R2-2303015.zip R2-2303015 Discussions on AIML model transfer via air interface.docx> [retrieved on 20230407] *
XIAOMI: "Discussion on model delivery", vol. 3GPP RAN 2, no. Electronic; 20230417 - 20230426, 7 April 2023 (2023-04-07), XP052365387, Retrieved from the Internet <URL:https://ftp.3gpp.org/tsg_ran/WG2_RL2/TSGR2_121bis-e/Docs/R2-2303120.zip R2-2303120.docx> [retrieved on 20230407] *

Similar Documents

Publication Publication Date Title
US12237569B2 (en) Facilitating user equipment beamforming control
US11653196B2 (en) System and method for updating user equipment capability
US12452787B2 (en) System and method for control channel reception in power save mode
WO2019085842A1 (fr) Système et procédé permettant d&#39;indiquer un état de canal sans fil
MX2013003548A (es) Metodo para coordinar la recepcion discontinua, drx.
US20240015759A1 (en) Adaptive Configuration for Monitoring a Downlink Control Channel
US20230318695A1 (en) Repeater for downlink transmission and uplink transmission
CN116686230A (zh) 基于组的波束报告
US20230421238A1 (en) Method and apparatus for beam management in communication system
KR20200138402A (ko) 채널 통신을 페이징하기 위한 빔 검색 파일럿
KR20230078660A (ko) 사용자 장비에서의 적응적 추적 루프 업데이트
CN116939779A (zh) Dtx传输方法、网络节点、网络设备和存储介质
WO2022205040A1 (fr) Activation et désactivation de signaux de référence périodiques
WO2025093364A1 (fr) Système et appareil de transfert de modèle dans un réseau et procédé associé
WO2025093280A1 (fr) Transfert de modèle dans un réseau
WO2025093284A1 (fr) Système et appareil pour le transfert de modèles dans un réseau et procédé en association avec celui-ci
WO2023069814A1 (fr) Retransmissions sans accusé de réception avec réception discontinue de liaison latérale en mode 1
WO2025030281A1 (fr) Dispositifs et procédés de communication
US20250105894A1 (en) Beamforming Control for Downlink Limited Access Node
WO2025176765A1 (fr) Système et appareil de rapport d&#39;une mesure dans un réseau et procédé associé
WO2025067885A1 (fr) Procédé de signalisation de modèle pour connectivité multiple
WO2025087719A1 (fr) Procédé de délestage d&#39;une opération de lcm ml dans un réseau sans fil
WO2025017056A1 (fr) Procédé de signalisation de mise en correspondance de modèle ia/ml
WO2025087720A1 (fr) Procédé d&#39;une opération de lcm ml indirect assistée par réseau
WO2025167528A1 (fr) Procédé de communication et appareil de communication

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24795111

Country of ref document: EP

Kind code of ref document: A1