Artificial Intelligence Capability Reporting for Wireless Communication

Patent metadata

Field	Value
Publication number	US-2023164817-A1
Application number	US-202117535524-A
Country	US
Kind code	A1
Filing date	Nov 24, 2021
Priority date	Nov 24, 2021
Publication date	May 25, 2023
Grant date	—

Abstract

Various aspects of the present disclosure relate to reporting of AI capabilities between network nodes, such as between a user equipment (UE) and a base station. A UE, for instance, generates a capability report that specifies whether the UE supports AI-enabled functionality and/or specific supported and non-supported AI-enabled features. The UE communicates the capability report to a base station and supported AI features can be implemented in conjunction with wireless communication between the UE and the base station, such as by the UE, by the base station, and/or cooperatively between the UE and the base station.

First claim

What is claimed is:

1 . A device for wireless communication, the device comprising:
a communication manager configured to:
generate a capability report to indicate artificial intelligence enabled features of a first node associated with at least one protocol layer of a wireless protocol stack, wherein the capability report is generated to indicate that the first node includes artificial intelligence capability and to specify at least one supported artificial intelligence enabled feature of the first node including to select the at least one supported artificial intelligence enabled feature from available artificial intelligence features for the capability report that include:
one or more supported artificial intelligence model types;
one or more supported artificial intelligence model training techniques;
one or more supported artificial intelligence learning frameworks;
one or more supported artificial intelligence integration modes;
one or more artificial intelligence training modes selected from at least an offline training mode, an online training mode, and a mixed training mode; and
one or more transceiver application modes selected from at least a joint application mode and an individual block application mode; and

a transceiver configured to transmit the generated capability report for receipt by a second node, wherein the communication manager is further configured to engage in wireless connectivity between the first node and the second node based at least in part on the at least one supported artificial intelligence enabled feature.

2 . The device of claim 1 , wherein the communication manager is configured to generate the capability report in response to detection of a broadcast signal from the second node that indicates that the second node supports artificial intelligence capability.

3 . The device of claim 1 , wherein the communication manager is further configured to generate the capability report to indicate one or more of processing resources available for artificial intelligence capability or memory resources available for artificial intelligence capability.

4 . The device of claim 1 , wherein the communication manager is further configured to:
generate the capability report based at least in part on a request from the second node for artificial intelligence capability of the first node or independent of the request from the second node for artificial intelligence capability of the first node.

5 . The device of claim 1 , wherein the communication manager is further configured to receive a communication from the second node indicating at least one of: that the second node supports artificial intelligence capability or that the second node supports one or more of the available artificial intelligence enabled features for the capability report, and to generate the capability report in response to the communication from the second node.

6 . The device of claim 1 , wherein:
the one or more supported artificial intelligence model types are selected from at least a convolutional neural network, a recurrent neural network, a modular neural network, or a combination thereof; the one or more supported artificial intelligence learning frameworks are selected from at least unsupervised learning, supervised learning, federated learning, reinforced learning, or a combination thereof; and the one or more supported artificial intelligence integration modes are selected from at least non-assisted mode, assisted mode, distributed mode, joint mode, or a combination thereof.

7 . The device of claim 1 , wherein the available artificial intelligence features for the capability report correspond to one or more physical layer procedures in a wireless network, the one or more physical layer procedures comprising: channel state information framework, beam management framework, channel estimation artificial intelligence application framework, reference signal artificial intelligence application framework, positioning enhancements framework, channel coding or a combination thereof.

8 . The device of claim 7 , wherein one or more of:
an available artificial intelligence feature for the capability report corresponding to the channel state information framework further comprises capability sub-features for one or more of precoding matrix indicator prediction, rank indicator prediction, channel quality indictor prediction, spatial-domain compression, frequency-domain compression, or channel state information reference signal compression; an available artificial intelligence feature for the capability report corresponding to the beam management framework further comprises capability sub-features for one or more of beam prediction, blockage prediction, beam failure prediction, synchronization signal block compression, synchronization signal block, or reporting compression; an available artificial intelligence feature for the capability report corresponding to the reference signal artificial intelligence application framework further comprises capability sub-features for one or more of demodulation reference signal for physical downlink shared channel overhead reduction, demodulation reference signal for physical downlink control channel overhead reduction, synchronization signal block compression, synchronization signal block overhead reduction, or positioning reference signal overhead reduction; and an available artificial intelligence feature for the capability report corresponding to the positioning enhancements framework further comprises capability sub-features for one or more of line-of-sight positioning prediction, non-line-of-sight positioning prediction, or positioning reference signal compression.

9 . The device of claim 1 , wherein the communication manager is further configured to:
communicate the generated capability report via one or more of an artificial intelligence information element or a radio resource control information element; and communicate the generated capability report in response to receiving one or more of a master information block or a system information block.

10 . The device of claim 1 , wherein the communication manager is further configured to generate the capability report to indicate that the first node supports artificial intelligence-enabled channel state information compression, and to apply an artificial intelligence model to channel state information to generate compressed channel state information, and wherein the transceiver is further configured to transmit the compressed channel state information for reception by the second node as part of the wireless connectivity between the first node and the second node.

11 . The device of claim 1 , wherein:
the communication manager is further configured to generate the capability report to indicate that the first node supports artificial intelligence-enabled channel estimation; the transceiver is further configured to receive one or more channel estimation signals configured for artificial intelligence-enabled channel estimation; and the communication manager is further configured to perform artificial intelligence-enabled channel estimation utilizing the channel estimation signals configured for artificial intelligence-enabled channel estimation.

12 . A device for wireless communication, the device comprising:
a transceiver at a first node configured to receive a capability report from a second node that indicates one or more supported artificial intelligence enabled features of the second node associated with at least one protocol layer of a wireless protocol stack; and a communication manager at the first node configured to:
process the capability report and

Assignees

• Lenovo Singapore Pte Ltd

Inventors

• Bhamri Ankit
• Hindy Ahmed

Classifications

• H04W24/02

  Arrangements for optimising operational condition · CPC title

• G06N3/063 Primary

  using electronic means · CPC title

• H04W8/24 Primary

  Transfer of terminal data · CPC title

• H04W8/22

  Processing or transfer of terminal data, e.g. status or physical capabilities · CPC title

• H04W72/51 Primary

  based on terminal or device properties · CPC title