A device and a method for providing a measurement for determining the position of an entity in a wireless communication network, in particular based on artificial intelligence or machine learning.

Abstract

A device (104) and a method for providing a measurement for determining the position of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), based in particular on artificial intelligence or machine learning, wherein the 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 or a sample-based measurement method according to the result of comparing the data with a selection criterion, and - Providing the measurement using the selected measurement method.

Description

State of the art

[0001] The invention relates to a device and a method for providing a measurement for determining the position of an entity in a wireless communication network, in particular a cellular communication network, in particular based on artificial intelligence or machine learning.

[0002] Positioning accuracy in cellular communication networks is a critical component for various applications, including navigation, emergency services, and location-based services. Conventional positioning techniques, such as global satellite navigation systems, are subject to limitations, particularly in urban environments where signal interference and reflections can degrade accuracy. Disclosure of the invention

[0003] The device and method according to the independent claims provide improvements in position determination.

[0004] A method for providing a measurement for determining the position of an entity in a wireless communication network, in particular a cellular communication network, in particular based on artificial intelligence or machine learning, 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 data with a selection criterion, and providing the measurement using the selected measurement method.

[0005] 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 level of detail comes at the cost of higher signal overhead, which can strain network resources and reduce efficiency. This method is particularly effective in complex environments, such as urban areas with strong multipath interference, where detailed signal information is crucial for accurate positioning.

[0006] 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 decreasing signal overhead. Path-based measurements are generally less detailed than sample-based 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 significantly lower resource consumption.

[0007] Both methods have their advantages and disadvantages. Sample-based measurements offer higher accuracy, but at the cost of higher overhead, while path-based measurements are more efficient but can be less accurate under certain conditions. This method provides a more adaptable solution for position determination, leveraging the strengths of both approaches.

[0008] The collected data provides real-time information about the environment in which the entity communicates within the communication network. Comparing the collected data with the selection criteria provides real-time environmental assessments. The method dynamically selects between sample-based and path-based measurements based on these real-time environmental assessments. This approach combines the accuracy advantages of sample-based measurements with the efficiency of path-based measurements, providing a versatile solution that can be adapted to different network conditions and requirements. As a result, the method offers a balanced approach that maximizes both the accuracy and efficiency of position determination.

[0009] The procedure can include: determining the selection criterion based on the collected data, for example, based on a linear function of the collected data, where the collected data exhibits at least one performance indicator or several performance indicators, in particular the signal-to-noise ratio and / or 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.

[0010] The procedure includes, for example, determining the selection criterion depending on the linear function of the collected data, where the linear function has a weighting for at least one of the performance indicators.

[0011] To refine decision-making and improve accuracy over time, the procedure may include adjusting the weighting for at least one of the performance indicators depending on the accuracy of the measurement, with the accuracy being monitored or received as feedback.

[0012] The procedure can include iterative learning of the weighting for at least one of the performance indicators, thereby improving accuracy.

[0013] The procedure can include: detecting whether the entity is in a multipath environment, and if so, selecting the sample-based measurement method; otherwise, selecting the path-based measurement method. This means that in environments with many multipaths (e.g., urban areas), the procedure prioritizes sample-based measurements to capture detailed signal variations. In environments with low complexity (e.g., rural areas), the procedure uses path-based measurements to reduce overhead while maintaining sufficient accuracy.

[0014] The process can include: receiving a request to determine the entity's location, determining the entity's location based on the (provided) measurement, and sending the location. The request can be received by a Location Management Function (LMF), for example, from the entity itself. The LMF determines the location, for example, using an artificial intelligence or machine learning-based positioning system (AI / ML positioning system), and provides the location, for example, to the entity.

[0015] A device for providing a measurement for determining the position of an entity in a wireless communication network, particularly a cellular communication network, based in particular on artificial intelligence or machine learning, is designed to execute the method. The device can host the LMF.

[0016] A computer program can be provided for providing a measurement for determining the position of an entity in a wireless communication network, in particular a cellular communication network, based in particular on artificial intelligence or machine learning, wherein the computer program has computer-readable instructions which, when executed by a computer and / or a device according to an embodiment, cause the computer and / or the device to execute the method.

[0017] Some examples relate to a computer-readable storage medium containing instructions which, when executed by a computer and / or the device, cause the computer and / or the device to execute the method according to the disclosure.

[0018] Some examples relate to a data carrier signal that carries and / or characterizes the computer program according to the disclosure.

[0019] Further examples of implementation are derived from the following description and the drawing. In the drawing: Fig. Figure 1 schematically shows a wireless communication network, Fig. Figure 2 shows a flowchart that includes steps of a procedure for providing a measurement, in particular for determining the position of an entity in the communication network based on artificial intelligence or machine learning.

[0020] Fig. Figure 1 schematically shows a wireless communication network 100, in particular a cellular communication network 100.

[0021] The wireless communication network 100 can be based on at least one 3GPP (Third Generation Partnership Project) radio standard, such as 4G (fourth generation), 5G (fifth generation), or 6G (sixth generation), or another radio access technology and / or at least partially comply with it.

[0022] The communication network 100 has an entity 102, e.g. a user device (UE).

[0023] Communication network 100 includes a device 104, e.g., a network entity. Device 104 hosts a site management function (LMF).

[0024] Entity 102 is designed to communicate with device 104 in communication network 100.

[0025] At least one current or historical performance indicator of Communication Network 100 shows the performance of communication in Communication Network 100.

[0026] The performance indicator is, for example, an important performance indicator, such as a signal-to-noise ratio or bandwidth size.

[0027] Entity 102 is designed to send a request regarding the position of entity 102 to device 104. Device 104 is designed to determine the position, in particular using a method based on artificial intelligence or machine learning. Device 104 is designed to send the position to entity 102.

[0028] Device 104 is designed to perform a method for determining the position as a function of a measurement. Device 104 is designed to perform a method for providing the measurement.

[0029] Fig. Figure 2 shows a flowchart that includes the steps of the procedure.

[0030] The process can include 200 steps.

[0031] Step 200 involves receiving a request to determine the position of entity 102, e.g., from entity 102.

[0032] The procedure may include step 202.

[0033] Step 202 involves detecting whether entity 102 is in a multipath environment or not.

[0034] Entity 102 can be located in a rural or urban area. Rural areas represent environments of low complexity. Urban areas represent environments of higher complexity. This complexity depends, for example, on obstacles in the environment that cause reflections and thus multipath communication.

[0035] A path-based measurement method is suitable for determining the position of entity 102 with good accuracy in a low-complexity environment. A scan-based method is suitable for determining the position of entity 102 with good accuracy in a high-complexity environment.

[0036] The procedure includes step 204.

[0037] Step 204 involves collecting data.

[0038] The data includes at least one current or historical performance indicator of the communication network 100. The at least one historical performance indicator can be read from a memory, e.g., a database.

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

[0040] The procedure includes step 206.

[0041] Step 206 involves selecting the path-based measurement method or the sampling-based measurement method according to the result of comparing the data with a selection criterion.

[0042] The selection criterion is determined, for example, depending on the data collected.

[0043] The selection criterion is determined, for example, based on at least one performance indicator. The selection criterion is determined, for example, based on several performance indicators. The selection criterion is determined, for example, based on at least two of the performance indicators, such as the signal-to-noise ratio and bandwidth size, and the historical signal-to-noise ratio and bandwidth size.

[0044] The selection criterion is determined, for example, depending on a linear function of the collected data.

[0045] The linear function, for example, includes a weighting for at least one of the performance indicators.

[0046] Step 206 may include: selecting the sampling-based measurement method if, for example, step 202 detects that the entity is in the multipath environment, and selecting the path-based measurement method otherwise.

[0047] Step 208 is performed when selecting the path-based measurement method.

[0048] Step 210 is performed when selecting the scanning-based measurement method.

[0049] Step 208 involves providing the measurement using the path-based measurement method. Step 212 can then be executed.

[0050] Step 210 involves providing the measurement using the sampling-based measurement method. Step 212 can then be executed.

[0051] The procedure may include step 212.

[0052] Step 212 involves adjusting the weighting for at least one of the performance indicators depending on the accuracy of the measurement.

[0053] Accuracy is monitored, for example, or received as feedback.

[0054] Step 212, for example, involves determining the position of entity 102 using an artificial intelligence or machine learning model, depending on the measurement. Monitoring the accuracy includes, for example, comparing the determined position with a reference position of entity 102. The reference position can be provided by another entity or as a baseline in a training process.

[0055] The procedure may include: iteratively repeating steps 202 to 212 and iteratively adjusting and learning the weighting for at least one of the performance indicators, thereby improving the accuracy of the position.

[0056] Step 212 may include saving at least one performance indicator as a historical performance indicator, e.g. in the database.

[0057] The procedure may include a step 214.

[0058] Step 214 involves sending the position, specifically to entity 102.

[0059] An example of sample-based measurement is an approach based on power per sample: Representation of time information by extracting K fine specific sample values ​​on the sampling grid of an estimated channel impulse response (CIR) around (i.e., within a CIR total window left and right) (right of) N sample(s) corresponding to the N sample(s) with the highest power values ​​within the estimated CIR.

[0060] An example of path-based measurement is a path-based approach: Representation of time information by extracting K specific (not necessarily consecutive) time instances based on a time grid of a path detection output. Specifically, the time information includes a reference time, a sampling period, and a value of K, as well as K time instance values.

[0061] An example of the hybrid approach provided by the procedure is: Representation of time information by extracting K fine specific sample values ​​that are sampled at the nominal sampling rate and on the sampling grid of the estimated CIR, which is defined by the nominal sampling rate, around (i.e. within the entire CIR window to the left and right of) each of the M detected paths, while between detected paths according to the selection criterion a coarser sampling rate with a sampling period that is an integer multiple of the nominal sampling period.

Claims

[1] Method for providing a measurement for determining the position of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), based in particular on artificial intelligence or machine learning, characterized by , that the procedure includes: - 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 sampling-based measurement method according to the result of comparing the data with a selection criterion, and - Providing (208, 210) the measurement using the selected measurement method. [2] Method according to claim 1, characterized by , that the procedure includes: - Determining (206) the selection criterion depending on the data collected, for example, depending on a linear function of the data collected, wherein the data collected include at least one performance indicator or several 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. [3] Method according to claim 2, characterized by , that the procedure includes: - Determining (206) the selection criterion depending on the linear function of the collected data, wherein the linear function has a weighting for at least one of the performance indicators. [4] Method according to claim 3, characterized by , that the procedure includes: - Adjusting (212) the weighting for at least one of the performance indicators depending on the accuracy of the measurement, whereby the accuracy is monitored or received as feedback. [5] Method according to claim 4, characterized by , that the procedure includes: - iterative learning (212) of the weighting for at least one of the performance indicators, thereby improving accuracy. [6] Method according to any one of the preceding claims, characterized by , that the procedure includes: - Detect (202) whether the entity (102) is in a multipath environment or not, and - Select (206) the scanning-based measurement method if it is detected that the entity is in the multipath environment, and select (206) the path-based measurement method otherwise. [7] Method according to any one of the preceding claims, characterized by , that the procedure includes: - Receiving (200) a request to determine the position of the entity (102), - Determining (212) the position of the entity (102) depending on the measurement, and - Send (214) the position. [8] Device (104) for providing a measurement for determining the position of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), in particular based on artificial intelligence or machine learning, characterized by that the device (104) is designed to perform the method according to one of the preceding claims. [9] Computer program for providing a measurement for determining the position of an entity (102) in a wireless communication network (100), in particular a cellular communication network (100), based in particular on artificial intelligence or machine learning, characterized bythat the computer program comprises computer-readable instructions which, when executed by a computer and / or the device (104) according to claim 8, cause the computer and / or the device (104) to execute the method according to any one of claims 1 to 7. [10] Computer-readable storage medium comprising instructions which, when executed by a computer and / or the device (104) according to claim 8, cause the computer and / or the device (104) to execute the method according to any one of claims 1 to 7. [11] Data carrier signal that carries and / or characterizes the computer program according to claim 9.

Images