Radio network node, user equipment and methods performed in a wireless communication network

Patent metadata

Field	Value
Publication number	US-2024049162-A1
Application number	US-202018266633-A
Country	US
Kind code	A1
Filing date	Dec 23, 2020
Priority date	Dec 23, 2020
Publication date	Feb 8, 2024
Grant date	—

Abstract

Embodiments herein relate to, for example, a method performed by a UE for handling positioning of the UE in a wireless communication network. The UE measures a CIR of a signal from a radio network node; and initiates a process for determining whether the UE is indoors or outdoors using an ML model with the measured CIR as input.

First claim

1 . A method performed by a user equipment, UE, for handling positioning of the UE in a wireless communication network, the method comprising:
measuring a channel impulse response, CIR, of a signal from a radio network node; and initiating a process for determining whether the UE is indoors or outdoors using a machine learning, ML, model with the measured CIR as input.

2 . The method according to claim 1 , wherein initiating the process comprises reporting the measured CIR to the radio network node.

3 . The method according to claim 2 , wherein data indicating indoor position or outdoor position is included in the reporting.

4 . The method according to claim 1 , wherein initiating the process comprises using the ML model with the CIR as input to determine whether the UE is indoors or outdoors.

5 . The method according to claim 4 , wherein initiating the process further comprises transmitting a result of the ML model to the radio network node.

6 . The method according to claim 1 , further comprising receiving a configuration for measuring the CIR.

7 . The method according to claim 1 , wherein the ML model comprises a supervised classifier model.

8 . A method performed by a radio network node for handling positioning of a user equipment, UE, in a wireless communication network, the method comprising:
obtaining a measurement of a channel impulse response, CIR, of a signal in the wireless communication network; and determining whether the UE is indoors or outdoors using a machine learning, ML, model with the measurement of the CIR as input.

9 . The method according to claim 8 , wherein obtaining the measurement of the OR comprises receiving, from the UE, a report with the measurement of the CIR.

10 . The method according to claim 8 , wherein obtaining the measurement of the OR comprises measuring the CIR of a signal from the UE.

11 . The method according to claim 8 , further comprising receiving data indicating indoor position or outdoor position of the UE.

12 . The method according to claim 11 , wherein the measurement of the CIR and the data is used to train the ML model.

13 . The method according to claim 8 , further comprising selecting the ML model out of a number of ML models based on characteristics of the CIR and/or positioning data.

14 . The method according to claim 8 , further comprising configuring the UE for measuring the CIR.

15 . The method according to claim 8 , further comprising providing a result of the used ML model to another network node and/or an application.

16 . The method according to claim 8 , wherein the ML model comprises a supervised classifier model.

17 . (canceled)

18 . (canceled)

19 . A user equipment, UE, for handling positioning of the UE in a wireless communication network, wherein the UE is configured to:
measure a channel impulse response, CIR, of a signal from a radio network node; and initiate a process for determining whether the UE is indoors or outdoors using a machine learning, ML, model with the measured CIR as input.

20 . The UE according to claim 19 , wherein the UE is configured to initiate the process by reporting the measured CIR to the radio network node.

21 . The UE according to claim 20 , wherein data indicating indoor position or outdoor position is included in the reporting.

22 . The UE according to claim 19 , wherein the UE is configured to initiate the process by using the ML model with the CIR as input to determine whether the UE is indoors or outdoors.

23 .- 32 . (canceled)

Assignees

• Ericsson Telefon Ab L M

Inventors

• Borsos Tamas
• Rácz András
• Veres András
• Eleftheriadis Lackis
• Bergkvist Adam

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• H04W64/00 Primary

  Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management · CPC title

• G01S5/012 Primary

  Identifying whether indoors or outdoors · CPC title

• H04W24/08

  Testing, {supervising or monitoring} using real traffic · CPC title