| Sonstiges: |
- Nachgewiesen in: USPTO Patent Applications
- Sprachen: English
- Document Number: 20240056798
- Publication Date: February 15, 2024
- Appl. No: 17/886381
- Application Filed: August 11, 2022
- Claim: 1. An apparatus for wireless communication, comprising: a processor; memory coupled with the processor; and instructions stored in the memory and operable, when executed by the processor, to cause the apparatus to: receive, from a network node, a list of supported models or model structures (MS) identifiers (IDs) per machine learning function name (MLFN) or machine learning feature (MLF) at the network node; update a capability at the apparatus to an updated capability based on the list of supported models or MS IDs per MLFN or MLF at the network node; and download, from a model repository, one or more models or MSs per MLFN or MLF based on the updated capability and available resources at the apparatus.
- Claim: 2. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to receive the list of supported models or MS IDs per MLFN or MLF from the network node based on transmitting, to the network node, capability information including a list of UE-supported models or MS IDs per MLFN or MLF and list of one or more newly developed models or MS IDs per MLFN or MLF deployed or registered at a network.
- Claim: 3. The apparatus of claim 2, wherein the one or more newly developed models or MS IDs per MLFN or MLF deployed or registered at the network include one or more of UE vendor specific models or MS IDs per MLFN or MLF deployed or registered at the network, network vendor specific models or MS IDs per MLFN or MLF deployed or registered at the network, or third-party models or MS IDs per MLFN or MLF deployed or registered at the network, wherein the network node is within a validity area of the one or more models or MS IDs.
- Claim: 4. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to establish a connection for communicating with the network node, wherein the instructions, when executed by the processor, cause the apparatus to receive the list of supported models or MS IDs per MLFN or MLF at the network node as part of establishing the connection.
- Claim: 5. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to report, to the network node, further updated capabilities of the apparatus based on multiple models including the one or more models or MSs downloaded from the model repository or additional models or MS IDs available at the apparatus.
- Claim: 6. The apparatus of claim 5, wherein the instructions, when executed by the processor, cause the apparatus to receive, from the network node and based on the updated capabilities, a configuration configuring a subset of the multiple models or MS IDs per MLFN or MLF to use for an MLFN or MLF at the apparatus.
- Claim: 7. The apparatus of claim 6, wherein the configuration is received over radio resource control (RRC) signaling.
- Claim: 8. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to report, to the network node, the updated capability of the apparatus based on the list of supported models or MS IDs per MLFN or MLF at the network node.
- Claim: 9. The apparatus of claim 8, wherein the instructions, when executed by the processor, cause the apparatus to receive, from the network node and based on the updated capability, a configuration configuring at least a subset of the one or more models or MS IDs per MLFN or MLF to use for an operation at the apparatus, wherein the instructions, when executed by the processor, cause the apparatus to download the one or more models or MSs based on the configuration.
- Claim: 10. The apparatus of claim 9, wherein the instructions, when executed by the processor, cause the apparatus to transmit, based on downloading the one or more models or MSs, a ready indication that the one or more models or MSs are ready for use at the apparatus.
- Claim: 11. The apparatus of claim 10, wherein the ready indication is transmitted using a radio resource control (RRC) message, a media access control (MAC) control element (CE), or uplink control information (UCI).
- Claim: 12. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to receive the list of supported models or MS IDs per MLFN or MLF at a network node via dedicated signaling for the apparatus, system information (SI) or using multicast broadcast services (MBS).
- Claim: 13. The apparatus of claim 1, wherein the list of supported models or MS IDs at a network node includes multiple lists of supported models or MS IDs per MLFN or MLF.
- Claim: 14. The apparatus of claim 1, wherein the instructions, when executed by the processor, cause the apparatus to download the one or more models at least in part by: constructing a resource locator for the one or more models or MSs, and for a parameter set for the one or more MSs based on the MS IDs; transmitting, to the model repository, a request for downloading one or more models or MSs and the parameter set; and receiving, from the model repository, the one or more models or MSs and the parameter set based on the request.
- Claim: 15. The apparatus of claim 14, wherein the request for downloading the model is transmitted over user plane using a secure hypertext transfer protocol (HTTP), stream control transmission protocol (SCTP), file transfer protocol (FTP).
- Claim: 16. The apparatus of claim 14, wherein the instructions, when executed by the processor, cause the apparatus to cache the one or more models or the parameter set at the apparatus.
- Claim: 17. An apparatus for wireless communication, comprising: a processor; memory coupled with the processor; and instructions stored in the memory and operable, when executed by the processor, to cause the apparatus to: transmit, for a user equipment (UE), a list of supported models or model structures (MS) identifiers (IDs) per machine learning function name (MLFN) or machine learning feature (MLF) at the apparatus; and receive, for the UE and based on the list of supported models or MS IDs, a request to download, from a model repository, one or more models or MSs based on the list of supported models or MS IDs at the apparatus.
- Claim: 18. The apparatus of claim 17, wherein the instructions, when executed by the processor, cause the apparatus to transmit the list of supported models or MS IDs at the apparatus based on receiving, from the UE, capability information including a list of UE-supported models or MS IDs and a list of one or more newly developed models or MS IDs per MLFN or MFN deployed or registered in the network, wherein the apparatus is within a validity area of the one or more newly developed models or MS IDs.
- Claim: 19. The apparatus of claim 18, wherein the one or more newly developed models or MS IDs per MLFN or MLF deployed or registered at the network include one or more of UE vendor specific models or MS IDs per MLFN or MLF deployed or registered at the network, network vendor specific models or MS IDs per MLFN or MLF deployed or registered at the network, or third-party models or MS IDs per MLFN or MLF deployed or registered at the network, wherein the apparatus is within a validity area of the one or more models or MS IDs.
- Claim: 20. The apparatus of claim 17, wherein the instructions, when executed by the processor, cause the apparatus to establish a connection for communicating with the UE, wherein the instructions, when executed by the processor, cause the apparatus to transmit the list of supported models or MS IDs at the apparatus as part of establishing the connection.
- Claim: 21. The apparatus of claim 17, wherein the instructions, when executed by the processor, cause the apparatus to: receive, from the UE, a report of updated capabilities of the UE based on the one or more models or MSs downloaded from the model repository; and transmit, to the UE and based on the updated capabilities, a configuration configuring a subset of the one or more models or MSs to use for an operation.
- Claim: 22. The apparatus of claim 17, wherein the instructions, when executed by the processor, cause the apparatus to receive, from the UE and based on the list of supported models or MS IDs, a report of updated capabilities of the UE based on multiple models or MS IDs including one or more additional models or MS IDs supported by the UE.
- Claim: 23. The apparatus of claim 22, wherein the instructions, when executed by the processor, cause the apparatus to transmit, to the UE and based on the updated capabilities, a configuration configuring a subset of the multiple models or MS IDs, wherein the instructions, when executed by the processor, cause the apparatus to receive the request to download the one or more models or MSs based on the configuration.
- Claim: 24. The apparatus of claim 23, wherein the configuration is transmitted over radio resource control (RRC) signaling.
- Claim: 25. The apparatus of claim 22, wherein the instructions, when executed by the processor, cause the apparatus to receive, based on downloading the one or more models or MSs, a ready indication that the one or more models or MSs are ready for use at the UE.
- Claim: 26. The apparatus of claim 25, wherein the ready indication is received using a radio resource control (RRC) message, a media access control (MAC) control element (CE), or uplink control information (UCI).
- Claim: 27. The apparatus of claim 17, wherein the instructions, when executed by the processor, cause the apparatus to transmit the list of supported models or MS IDs via dedicated signaling for the UE, system information (SI) or using multicast broadcast services (MBS).
- Claim: 28. A method for wireless communication at a user equipment (UE), comprising: receiving, from a network node, a list of supported models or model structures (MS) identifiers (IDs) per machine learning function name (MLFN) or machine learning feature (MLF) at the network node; updating a capability at the UE to an updated capability based on the list of supported models or MS IDs per MLFN or MLF at the network node; and downloading, at the UE and from a model repository, one or more models or MSs per MLFN or MLF based on the updated capability and available resources at the UE.
- Claim: 29. The method of claim 28, wherein receiving the list of supported models or MS IDs per MLFN or MLF from the network node is based on transmitting, to the network node, capability information including a list of UE-supported models or MS IDs per MLFN or MLF and list of one or more newly developed models or MS IDs per MLFN or MLF deployed or registered at a network.
- Claim: 30. A method for wireless communication at a network node, comprising: transmitting, for a user equipment (UE), a list of supported models or model structures (MS)identifiers (IDs) per machine learning function name (MLFN) or machine learning feature (MLF) at the network node; and receiving, for the UE and based on the list of supported models or MS IDs, a request to download, from a model repository, one or more models or MSs based on the list of supported models or MS IDs at the network node.
- Current International Class: 04; 04; 04
|
