CN-122003903-A - Use of machine learning models in communication of wireless networks

Abstract

The present disclosure provides a user equipment, UE, configured for using a machine learning, ML, model at the UE for reasoning about a communication procedure of a wireless network, and for allowing a transition between using the ML model at the UE and using the ML model at a network entity of the wireless network for reasoning during the communication procedure. The communication procedure may be a handover procedure.

Inventors

• I. Z. Kovacs
• A. Alibaba
• E. Dosti
• M. M. Bart

Assignees

• 诺基亚技术有限公司

Dates

Publication Date

20260508

Application Date

20240820

Priority Date

20230928

Claims (20)

1. 1. A user equipment, UE, comprising: means for using a machine learning ML model at the UE for reasoning about a communication process of the wireless network, and Means for allowing conversion between using the ML model at the UE and using an ML model at a network entity of the wireless network for the reasoning during the communication procedure.
2. 2. The UE of claim 1, wherein the translating includes at least a transition from using the ML model at the UE to using the ML model at the network entity, or vice versa.
3. 3. The UE of any preceding claim, further comprising: Means for determining the occurrence of a predefined trigger, and Means for signaling an indication of a transition between using the ML model at the UE and using the ML model at the network entity in response to determining the occurrence of the predefined trigger.
4. 4. The UE of claim 1 or 2, further comprising: Means for determining the occurrence of a predefined trigger, and Means for activating or deactivating use of the ML model at the UE in response to determining occurrence of the predefined trigger.
5. 5. The UE of any preceding claim, further comprising: Means for temporarily allowing simultaneous use of the ML model at the UE and the ML model at the network entity in connection with a transition between using the ML model at the UE and using the ML model at the network entity.
6. 6. The UE of any preceding claim, further comprising: Means for collecting monitoring data during use of the ML model at the UE, and Means for sharing the collected monitoring data with the network entity.
7. 7. The UE of any preceding claim, further comprising: Means for sharing prediction state information with the network entity in relation to transitioning between using the ML model at the UE and using the ML model at the network entity.
8. 8. The UE of any preceding claim, wherein the communication procedure is a handover procedure.
9. 9. The UE of claim 8, wherein the converting is performed such that the ML model at the UE is used before and after the handover procedure, and the ML model at the network entity is used during the handover procedure.
10. 10. The UE of any of claims 1 to 7, wherein the communication procedure is a beam management procedure or is related to carrier aggregation reconfiguration.
11. 11. The UE of any preceding claim, wherein the ML model is configured for channel state information, CSI, prediction or for positioning.
12. 12. A network entity, comprising: Means for using a machine learning, ML, model at the network entity for reasoning about communication procedures of the wireless network, wherein the communication procedures are related to the UE, and Means for allowing a transition between using the ML model at the network entity and using an ML model at the UE for the reasoning during the communication procedure.
13. 13. The network entity of claim 12, further comprising: Means for determining the occurrence of a predefined trigger, and Means for signaling an indication of a transition between using the ML model at the UE and using the ML model at the network entity in response to determining the occurrence of the predefined trigger.
14. 14. The network entity of any of claims 12 to 13, further comprising: Means for determining the occurrence of a predefined trigger, and Means for activating or deactivating use of the ML model at the network entity in response to determining occurrence of the predefined trigger.
15. 15. The network entity of any of claims 12 to 14, further comprising: Means for temporarily allowing simultaneous use of the ML model at the UE and the ML model at the network entity in connection with a transition between using the ML model at the UE and using the ML model at the network entity.
16. 16. The network entity of any of claims 12 to 15, further comprising: Means for sharing prediction state information with the UE in relation to transitioning between using the ML model at the UE and using the ML model at the network entity.
17. 17. The network entity according to any of claims 12 to 14, wherein the communication procedure is a handover procedure and the network entity is a source network entity or a target network entity of the handover procedure.
18. 18. The network entity of claim 17, wherein the converting is performed such that the ML model at the UE is used before and after the handover procedure, and the ML model at the network entity is used during the handover procedure.
19. 19. The network entity according to any of claims 12 to 16, wherein the communication procedure is a beam management procedure or is related to carrier aggregation reconfiguration.
20. 20. The network entity of any of claims 12 to 19, wherein the ML model is configured for channel state information, CSI, prediction or for positioning.

Description

Use of machine learning models in communication of wireless networks Technical Field Various example embodiments relate to the use of machine learning models in the communication of wireless networks. Background This section describes useful background information, but is not an admission that any of the techniques described herein represent prior art. The use of Artificial Intelligence (AI)/Machine Learning (ML) technology in wireless networks is currently being investigated. The present disclosure provides some solutions related to the use of machine learning models in the course of communication of wireless networks. Disclosure of Invention The scope of protection sought for the various embodiments of the present disclosure is as set forth in the independent claims. The embodiments and features (if any) described in this specification that do not fall within the scope of the independent claims should be construed as examples useful for understanding the various example embodiments. According to a first example aspect of the present disclosure, there is provided a user equipment, UE, comprising: means for using a machine learning ML model at a UE for reasoning about a communication process of a wireless network, and Means for allowing conversion between using the ML model at the UE and using the ML model at a network entity of the wireless network for reasoning during the communication procedure. In some example embodiments of the first aspect, the UE further comprises means for determining an occurrence of the predefined trigger. In some example embodiments of the first aspect, the UE further comprises means for signaling an indication to transition between using the ML model at the UE and using the ML model at the network entity in response to determining that the predefined trigger occurs. In some example embodiments of the first aspect, the UE further comprises means for activating or deactivating use of the ML model at the UE in response to determining that the predefined trigger occurs. In some example embodiments of the first aspect, the UE further comprises means for temporarily allowing simultaneous use of the ML model at the UE and the ML model at the network entity in connection with converting between using the ML model at the UE and using the ML model at the network entity. In some example embodiments of the first aspect, the UE further comprises means for collecting monitoring data during use of the ML model at the UE, and means for sharing the collected monitoring data with the network entity. In some example embodiments of the first aspect, the UE further comprises means for sharing prediction state information with the network entity in connection with transitioning between using the ML model at the UE and using the ML model at the network entity. According to a second example aspect of the present disclosure, there is provided a method comprising: use of machine learning ML model at UE for reasoning about communication procedures of wireless network, and Transition between using the ML model at the UE and the ML model at the network entity using the wireless network is allowed for reasoning during the communication procedure. In some example embodiments of the second aspect, the method further comprises determining an occurrence of the predefined trigger. In some example embodiments of the second aspect, the method further comprises signaling an indication to transition between using the ML model at the UE and using the ML model at the network entity in response to determining that the predefined trigger occurs. In some example embodiments of the second aspect, the method further comprises activating or deactivating use of the ML model at the UE in response to determining occurrence of the predefined trigger. In some example embodiments of the first aspect, the method further comprises temporarily allowing simultaneous use of the ML model at the UE and the ML model at the network entity in connection with converting between using the ML model at the UE and using the ML model at the network entity. In some example embodiments of the second aspect, the method further comprises collecting monitoring data during use of the ML model at the UE and sharing the collected monitoring data with the network entity. In some example embodiments of the second aspect, the method further comprises sharing prediction state information with the network entity in connection with transitioning between using the ML model at the UE and using the ML model at the network entity. According to a third example aspect of the present disclosure, there is provided a computer program comprising instructions for performing at least the following: use of machine learning ML model at UE for reasoning about communication procedures of wireless network, and Transition between using the ML model at the UE and the ML model at the network entity using the wireless network is allowed for reasoning during the communication proce