A device and a method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network

Abstract

A device (104) and a method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), wherein method comprises collecting data, in particular at least one current or historical performance indicator of the communication network (100), for example a signal-to- noise ratio, a bandwidth size, selecting a path based measurement method or a sample based measurement method according to the result of comparing the data to a selection criterion, and providing the measurement with the selected measurement method.

Description

[0001] R.414605

[0002] - 1 -

[0003] Description

[0004] Title

[0005] A device and a method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network

[0006] Background

[0007] The invention relates to a device and a method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network, in particular in a wireless cellular communication network.

[0008] Positioning accuracy in cellular communication networks is a critical component for various applications, including navigation, emergency services, and locationbased services. Traditional positioning technigues such as Global Satellite Navigation Systems have limitations, especially in urban environments where signal obstructions and reflections can degrade accuracy.

[0009] Disclosure of the invention

[0010] The device and the method according to the independent claims provides positioning enhancements.

[0011] A method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network, in particular a cellular communication network, characterized in that the method comprises collecting data, in particular at least one current or historical performance indicator of the communication network, for example a signal-to- noise ratio, a bandwidth size, selecting a path based measurement method or a sample based measurement method according to the result of comparing the R.414605

[0012] - 2 - data to a selection criterion, and providing the measurement with the selected measurement method.

[0013] Sample-Based Measurements: Sample-based measurements involve capturing detailed signal characteristics at regular intervals. This method provides high- resolution data that can significantly improve the accuracy of positioning models. However, the increased detail comes at the cost of higher signaling overhead, which can strain network resources and reduce efficiency. This method is particularly effective in complex environments, such as urban areas with high multipath interference, where detailed signal information is crucial for accurate positioning.

[0014] Path-Based Measurements: Path-based measurements, on the other hand, focus on identifying and reporting specific signal paths. This method reduces the amount of data that needs to be transmitted, thereby lowering signaling overhead. Path-based measurements are typically less detailed than samplebased measurements, which can lead to lower positioning accuracy in environments with significant signal reflections and obstructions. However, in less complex environments, such as rural areas, path-based measurements can provide sufficient accuracy with much lower resource usage.

[0015] Both methods have their advantages and limitations. Sample-based measurements offer higher accuracy but at the cost of increased overhead, while path-based measurements are more efficient but can be less accurate in certain conditions. The method provides a more adaptable solution to positioning that leverages the strengths of both approaches.

[0016] The collected data provides real-time information about an environment in which the entity communicates in the communication network. Comparing the collected data to the selection criterion provides a real-time environmental assessments. The method dynamically selects between sample-based and path-based measurements based on real-time environmental assessments. This approach combines the accuracy benefits of sample-based measurements with the efficiency of path-based measurements, providing a versatile solution that can adapt to various network conditions and requirements. By doing so, the method R.414605

[0017] - 3 - offers a balanced approach that maximizes both accuracy and efficiency of the positioning.

[0018] The method may comprise determining the selection criterion depending on the collected data, for example depending on a linear function of the collected data, wherein the collected data comprises at least one performance indicator or different performance indicators, in particular the signal-to-noise ratio and / or the bandwidth size, and / or the historical signal-to-noise ratio, and / or the historical bandwidth size. This approach refines the selection by adjusting the selection criteria based on the collected data.

[0019] The method for example comprises determining the selection criterion depending on the linear function of the collected data, wherein the linear function comprises a weight for at least one of the performance indicators.

[0020] For refining the decision-making and improve accuracy over time, the method may comprise adjusting the weight for at least one of the performance indicators depending on an accuracy of the measurement, wherein the accuracy is monitored or received as feedback.

[0021] The method may comprise iteratively learning the weight for at least one of the performance indicators that improves the accuracy.

[0022] The method may comprise detecting whether the entity is in a multipath environment or not, and selecting the sample based measurement method upon detecting that the entity is in the multipath environment, and otherwise selecting the path based measurement method. This means, in high-multipath environments (e.g., urban areas) the method prioritizes sample-based measurements to capture detailed signal variations. In low-complexity environments (e.g., rural areas) the method uses path-based measurements to reduce overhead while maintaining sufficient accuracy.

[0023] The method may comprise receiving a request for positioning the entity, determining the position of the entity depending on the (provided) measurement, and sending the position. The request may be received at a location management function (LMF), e.g., from the entity. The LMF determines the R.414605

[0024] - 4 - position, e.g. with an artificial intelligence or machine learning positioning system (AI / ML positioning system) and provides the position, e.g., to the entity.

[0025] A device for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network, in particular a cellular communication network is configured to execute the method. The device may host the LMF.

[0026] A computer program for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity in a wireless communication network, in particular a cellular communication network may be provided, wherein the computer program comprises computer readable instructions that, when executed by a computer and / or a device according to an embodiment, cause the computer and / or the device to execute the method.

[0027] Some examples relate to a computer-readable storage medium comprising instructions which, when executed by a computer and / or the device, cause the computer and / or the device to carry out the method according to the disclosure.

[0028] Some examples relate to a data carrier signal carrying and / or characterizing the computer program according to the disclosure.

[0029] Further exemplary embodiments are derived from the following description and the drawing. In the drawing:

[0030] Fig. 1 schematically depicts a wireless communication network,

[0031] Fig. 2 depicts a flowchart comprising steps of a method for providing a measurement, in particular for an artificial intelligence or machine learning based positioning of an entity in the communication network.

[0032] Figure 1 schematically depicts a wireless communication network 100, in particular a cellular communication network 100.

[0033] The wireless communications network 100 may be based on and / or adheres at least partially to at least one third generation partnership project, 3GPP, radio R.414605

[0034] - 5 - standard such as 4G (fourth generation), 5G (fifth generation), or 6G (sixth generation), or to another other radio access technology.

[0035] The communication network 100 comprises an entity 102, e.g., a user equipment (UE).

[0036] The communication network 100 comprises a device 104, e.g., a network entity. The device 104 hosts a location management function (LMF).

[0037] The entity 102 is configured to communicate with the device 104 in the communication network 100.

[0038] At least one current or historical performance indicator of the communication network 100 indicates the performance of the communication in the communication network 100.

[0039] The performance indicator is for example a key performance indicator, e.g., a signal-to-noise ratio or a bandwidth size.

[0040] The entity 102 is configured to send a request for a position of the entity 102 to the device 104. The device 104 is configured to determine the position in particular with an artificial intelligence or machine learning based method. The device 104 is configured to send the position to the entity 102.

[0041] The device 104 is configured to execute a method for The device 104 is configured to determine the position depending on a measurement. The device 104 is configured to execute a method for providing the measurement.

[0042] Figure 2 depicts a flowchart comprising steps of the method.

[0043] The method may comprise a step 200.

[0044] The step 200 comprises receiving a request for positioning the entity 102, e.g., from the entity 102.

[0045] The method may comprise a step 202. R.414605

[0046] - 6 -

[0047] The step 202 comprises detecting whether the entity 102 is in a multipath environment or not.

[0048] The entity 102 may be in a rural area or an urban area. The rural area provides an environment with low complexity. The urban area provides an environment with higher complexity. The complexity for example depends on the obstacles in the environment that cause reflections and thus multipath communication.

[0049] A path based measurement method is suitable for determining the position of the entity 102 with good accuracy in the low complexity environment. A sample based method is suitable for determining the position of the entity 102 with good accuracy in a high complexity environment.

[0050] The method comprises a step 204.

[0051] The step 204 comprises collecting data.

[0052] The data comprises at least one current or historical performance indicator of the communication network 100. The at least one historical performance indicator may be read from storage, e.g., from a data base.

[0053] The performance indicator is for example a signal-to-noise ratio or a bandwidth size.

[0054] The method comprises a step 206.

[0055] The step 206 comprises selecting the path based measurement method or the sample based measurement method according to the result of comparing the data to a selection criterion.

[0056] The selection criterion is for example determined depending on the collected data.

[0057] The selection criterion is for example determined depending at least one performance indicator. The selection criterion is for example determined R.414605

[0058] - 7 - depending on different performance indicators. The selection criterion is for example determined depending on at least two of the performance indicators, e.g., the signal-to-noise ratio, and the bandwidth size, and the historical signal-to- noise ratio, and the historical bandwidth size.

[0059] The selection criterion is for example determined depending on a linear function of the collected data.

[0060] The linear function for example comprises a weight for at least one of the performance indicators.

[0061] The step 206 may comprise selecting the sample based measurement method upon detecting, e.g., in step 202, that the entity is in the multipath environment, and otherwise selecting the path based measurement method.

[0062] A step 208 is executed upon selecting the path based measurement method.

[0063] A step 210 is executed upon selecting the sample based measurement method.

[0064] The step 208 comprises providing the measurement with the path based measurement method. Afterwards, a step 212 may be executed.

[0065] The step 210 comprises providing the measurement with the sample based measurement method. Afterwards, the step 212 may be executed.

[0066] The method may comprise the step 212.

[0067] The step 212 comprises adjusting the weight for at least one of the performance indicators depending on an accuracy of the measurement.

[0068] The accuracy is for example monitored or received as feedback.

[0069] The step 212 for example comprises determining the position of the entity 102 with the artificial intelligence or machine learning model depending on the measurement. Monitoring the accuracy for example comprises comparing the R.414605

[0070] - 8 - determined position with a reference position of the entity 102. The reference position may be provided by another entity or as ground truth in a training.

[0071] The method may comprise iteratively repeating the steps 202 to 212 and iteratively adjusting and learning the weight for at least one of the performance indicators that improves an accuracy of the position.

[0072] The step 212 may comprise storing the at least one performance indicator as historical performance indicator, e.g., in the data base.

[0073] The method may comprise a step 214.

[0074] The step 214 comprises sending the position, in particular to the entity 102.

[0075] An example for the sample based measurement is a power-per-sample-based approach:

[0076] Representation of timing information by taking Kfinespecific samples on the sampling grid of an estimated Channel Impulse Response (CIR) around (i.e. , on the left and right of, within an overall CIR window) N samples that correspond to the N samples with the highest power values within the estimated CIR.

[0077] An example for the path based measurement is a path-based approach:

[0078] Representation of timing information by taking K specific (not necessarily consecutive) time instances based on timing grid of output of path-detection. In specific, the timing information includes reference time, sampling period, and value of K, and K timing instance values.

[0079] An example for the hybrid approach that the method provides is:

[0080] Representation of timing information by taking Kfinespecific samples sampled at the nominal sampling rate and on the sampling grid of the estimated CIR defined by the nominal sampling rate around (i.e., on the left and right of, within the overall CIR window) each of M detected paths, while in between detected paths a R.414605

[0081] - 9 - coarser sampling rate with sampling period that is an integer multiple of the nominal sampling period according to the selection criterion.

Claims

R.414605- 10 -Claims1. A method for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), characterized in that the method comprises collecting data (204), in particular at least one current or historical performance indicator of the communication network (100), for example a signal-to-noise ratio, a bandwidth size, selecting (206) a path based measurement method or a sample based measurement method according to the result of comparing the data to a selection criterion, and providing (208, 210) the measurement with the selected measurement method.

2. The method according to claim 1 , characterized in that the method comprises determining (206) the selection criterion depending on the collected data, for example depending on a linear function of the collected data, wherein the collected data comprises at least one performance indicator or different performance indicators, o in particular the signal-to-noise ratio and / or the bandwidth size, and / or o the historical signal-to-noise ratio, and / or o the historical bandwidth size.

3. The method according to claim 2, characterized in that the method comprises determining (206) the selection criterion depending on the linear function of the collected data, wherein the linear function comprises a weight for at least one of the performance indicators.

4. The method according to claim 3, characterized in that the method comprisesR.414605- 11 - adjusting (212) the weight for at least one of the performance indicators depending on an accuracy of the measurement, wherein the accuracy is monitored or received as feedback.

5. The method according to claim 4, characterized in that the method comprises iteratively learning (212) the weight for at least one of the performance indicators that improves the accuracy.

6. The method according to one of the preceding claims, characterized in that the method comprises detecting (202) whether the entity (102) is in a multipath environment or not, and selecting (206) the sample based measurement method upon detecting that the entity is in the multipath environment, and otherwise selecting (206) the path based measurement method.

7. The method according to one of the preceding claims, characterized in that the method comprises receiving (200) a request for positioning the entity (102), determining (212) the position of the entity (102) depending on the measurement, and sending (214) the position.

8. A device (104) for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), characterized in that the device (104) is configured to execute the method according to one of the preceding claims.

9. A computer program for providing a measurement for an, in particular artificial intelligence or machine learning based, positioning of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), characterized in that the computer program comprises computer readable instructions that, when executed by a computer and / or the device (104) according to claim 8, cause the computerR.414605- 12 - and / or the device (104) to execute the method according to one of the claims 1 to 7.

10. A computer-readable storage medium comprising instructions which, when executed by a computer and / or the device (104) of claim 8, cause the computer and / or the device (104) to execute the method according to one of the claims 1 to 7.

11. A data carrier signal carrying and / or characterizing the computer program of claim 9.

Images