Devices and methods for providing information or for providing historical information or for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network

Abstract

Devices and methods for providing information or for providing historical information or for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network, wherein the method for providing the measurement strategy comprises receiving (202) a measurement for positioning the entity, wherein the measurement is captured with a sample-based measurement method or a path-based measurement method, receiving (206, 208, 210) messages comprising historical, context and movement information, determining (212) fused information depending on the measurement, historical, context and movement information, selecting (214) the path based measurement method or the sample based measurement method according to the result of analyzing the fused information, and sending (216) a message indicating the measurement strategy, in particular indicating to use the sample based or the path based method for measuring another measurement for positioning the entity.

Description

[0001] R.414607

[0002] Description

[0003] Title

[0004] Devices and methods for providing information or for providing historical information or for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network

[0005] Background

[0006] The invention relates to devices and methods for providing information or for providing historical information or for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network.

[0007] Positioning accuracy in cellular communication networks is a critical component for various applications, including navigation, emergency services, and locationbased services.

[0008] Positioning systems for a wireless communication network use either samplebased or path-based measurements to determine accurate positions.

[0009] Sample-Based Measurements: Sample-based measurements involve freguent, detailed captures of signal characteristics, offering high-resolution data that improves positioning accuracy. However, this method increases signaling overhead, which can burden network resources. Such detailed measurements are particularly useful in urban environments where signal reflections and interference are prevalent, but the overhead can be prohibitive in less complex environments.

[0010] Path-Based Measurements: Path-based measurements reduce signaling overhead by focusing on specific signal paths rather than capturing detailed R.414607

[0011] - 2 - signal characteristics continuously. This method is efficient and maintains sufficient accuracy in simpler environments, such as rural areas, but can suffer from reduced accuracy in more complex scenarios.

[0012] Disclosure of the invention

[0013] A method, in particular in a network entity, for providing a measurement strategy for providing 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, wherein the method comprises receiving a measurement for positioning the entity, wherein the measurement is captured with a sample-based measurement method or a path-based measurement method, receiving a message comprising historical information, wherein the historical information characterizes a historical performance indicator of the communication network, for example a signal-to-noise ratio, a bandwidth size, receiving a message comprising context information, wherein the context information characterizes the entity's setting, in particular a urban setting or a rural setting, receiving a message comprising movement information, wherein the movement information characterizes a movement of the entity or a user carrying the entity, in particular walking, driving, standing still, determining fused information depending on the measurement, the context information, the movement information, and the historical information, wherein the fused information characterizes an positioning environment of the entity, selecting the path based measurement method or the sample based measurement method according to the result of analyzing the fused information, and sending a message indicating the measurement strategy, in particular indicating to use the sample based or the path based method for measuring another measurement for positioning the entity. Here, the measurement for positioning, the message comprising context information, the message comprising movement information, and the message comprising historical information may be received simultaneously or in sequence. Accordingly, a plurality of embodiments is provided, wherein each of the embodiments represents a respective possible sequence of the steps, thus covering all possible sequences. Particularly, the step of receiving a message comprising historical information may follow after the step of receiving a message comprising movement information. R.414607

[0014] - 3 -

[0015] This method introduces a context-aware positioning enhancement using multilayer data fusion of the measurement and the information received. This approach leverages additional data layers, such as environmental context, user movement patterns, and historical signal data, to augment the measurement. The fusion of these diverse data sources aims to create a more robust and adaptive positioning system. By integrating contextual information, the system can dynamically adjust measurement strategies to maintain high accuracy while optimizing resource usage.

[0016] For the data fusion, the method may comprise, determining the fused information with a Kalman filter, wherein the Kalman filter comprises an input for the measurement the context information, the movement information, and the historical information, or determining the fused information with a Bayesian network, wherein the Bayesian network comprises an input for the measurement the context information, the movement information, and the historical information, or determining the fused information with a Dempster-Shafer rule of combination, wherein the Dempster-Shafer rule of combination comprises an input for the measurement the context information, the movement information, and the historical information, or determining the fused information with a Convolutional neural network, wherein the Convolutional neural network comprises an input for the measurement the context information, the movement information, and the historical information a, or determining the fused information with a Gaussian process, wherein the Gaussian process comprises an input for the measurement the context information, the movement information, and the historical information.

[0017] An artificial intelligence (Al) or machine learning (ML) based method may comprise determining the result of analyzing the fused information with an artificial intelligence, wherein the artificial intelligence comprises an input for the fused information, wherein the artificial intelligence is configured to output the result, in particular an output indicating to select the sample-based measurement method or the path-based measurement method.

[0018] The method adapts to varying environmental conditions and user contexts, providing a versatile and efficient solution for positioning accuracy. This enhances the overall reliability and performance of AI / ML-based positioning systems in diverse network scenarios. R.414607

[0019] - 4 -

[0020] For improving the accuracy, the method may comprise determining the positioning of the entity depending on the measurement, wherein the artificial intelligence comprises at least one adjustable parameter that influences the result, and adjusting the at least one adjustable parameter depending on an accuracy of the positioning, wherein the accuracy is monitored or received as feedback.

[0021] For training, the Al, the method comprises iteratively learning the at least one parameter that improves the accuracy.

[0022] The historical information may be provided without request. The method may comprise sending a request for the historical information.

[0023] A method, in particular in an user entity, for providing information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of the entity in a wireless communication network, in particular in a wireless cellular communication network, comprises sending a measurement for positioning the entity measured with a sample-based measurement method or a path-based measurement method, sending a message comprising context information, wherein the context information characterizes the entity's setting, in particular a urban setting or a rural setting, sending a message comprising movement information, wherein the movement information characterizes a movement of the entity or a user carrying the entity, in particular walking, driving, standing still, receiving a message indicating a measurement strategy, in particular indicating to use the sample based or the path based method for measuring another measurement for positioning the entity. Here, the measurement for positioning the entity is measured or captured with a sample-based measurement method or a path-based measurement method. This method improves the accuracy of the other measurement according to the received measurement strategy.

[0024] Here, a sequence of the steps of receiving

[0025] - the measurement for positioning the entity,

[0026] - the message comprising historical information,

[0027] - the message comprising context information, R.414607

[0028] - 5 -

[0029] - the message comprising movement information may be arbitraty. The measurement and the messages may also be received simulateneously. Here, the measurement and the messages may be part of a single message.

[0030] A method, in particular in an data repository, for providing historical information for providing a measurement strategy 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, comprises sending the historical information, wherein the historical information characterizes a historical performance indicator of the communication network, for example a signal-to-noise ratio, a bandwidth size. The historical information may be provided without request

[0031] The method for providing historical information may comprise receiving a request for historical information.

[0032] A device for providing a measurement strategy 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, is configured to execute the method for providing the measurement strategy.

[0033] A device for providing information for providing a measurement strategy 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, is configured to execute the method for providing information.

[0034] A device for providing historical information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of the entity in a wireless communication network, in particular in a wireless cellular communication network, is configured to execute the method for providing historical information. R.414607

[0035] - 6 -

[0036] A computer program may be provided, wherein the computer program comprises computer readable instructions that, when executed by a computer and / or at least one of the devices, cause the computer and / or at least one of the devices to execute the method for providing the measurement strategy, the method for providing information, or the method for providing historical information.

[0037] Some examples relate to a computer-readable storage medium comprising instructions which, when executed by a computer and / or at least one of the devices, cause the computer and / or the at least one device to carry out the method(s) according to the disclosure.

[0038] Some examples relate to a data carrier signal carrying and / or characterizing the computer program according to the disclosure.

[0039] Further exemplary embodiments are derived from the following description and the drawing. In the drawing:

[0040] Fig. 1 schematically depicts a wireless communication network,

[0041] Fig. 2 depicts a sequence diagram.

[0042] Figure 1 schematically depicts a wireless communication network 100, in particular a cellular communication network 100.

[0043] 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 standard such as 4G (fourth generation), 5G (fifth generation), or 6G (sixth generation), or to another other radio access technology.

[0044] The wireless communications network 100 comprises a first device. The first device is configured for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in the wireless communication network 100. The first device 102 for example comprises a network entity 102.

[0045] The wireless communications network 100 comprises a second device. The second device is configured for providing information for providing the R.414607

[0046] - 7 - measurement strategy. The second device for example comprises a user entity, in particular a user equipment (UE) 104.

[0047] The wireless communications network 100 comprises a third device. The third device is configured for providing historical information for providing the measurement strategy. The third device for example comprises a data repository 106.

[0048] Figure 2 depicts a sequence diagram. The sequence diagram comprises steps of methods for providing information, for providing historical information and for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in the wireless communication network 100. The methods are described by way of example referencing the network entity 102, the UE 104, and the data repository 106. The method for providing the measurement strategy executes in the network entity 102. The method for providing information executes in the UE 104. The method for providing the historical information executes in the data repository 106.

[0049] In a step 202, the UE 104 sends a measurement for positioning the UE 104.

[0050] The measurement is captured with a sample-based measurement method or a path-based measurement method.

[0051] In a step 204, the network entity 102 sends a request for historical information to the data repository 106. The historical information characterizes a historical performance indicator of the communication network 100, for example a signal- to-noise ratio, a bandwidth size.

[0052] In a step 206, the data repository 106 sends a message comprising the historical information to the network entity 102.

[0053] The step 204 is optional. The data repository 106 may be configured to send the message comprising the historical information to the network entity 102 without the request. R.414607

[0054] - 8 - ln a step 208, the UE 104 sends a message comprising context information to the network entity 102.

[0055] The context information characterizes the setting of the UE 104.

[0056] The setting may be an urban setting or a rural setting.

[0057] In a step 210, the UE 104 sends a message comprising movement information to the network entity 102.

[0058] The movement information characterizes a movement of the UE 104 or of a user carrying the UE 104.

[0059] The movement may be walking, driving, standing still.

[0060] In a step 212, the network entity 102 determines fused information depending on the measurement, the context information, the movement information, and the historical information.

[0061] The fused information characterizes a positioning environment of the UE 104.

[0062] The fused information is determined for example with a Kalman filter. The Kalman filter comprises an input for the measurement the context information, the movement information, and the historical information.

[0063] The fused information is determined for example with a Bayesian network. The Bayesian network comprises an input for the measurement the context information, the movement information, and the historical information.

[0064] The fused information is determined for example with a Dempster-Shafer rule of combination. The Dempster-Shafer rule of combination comprises an input for the measurement the context information, the movement information, and the historical information.

[0065] The fused information is determined for example with a Convolutional neural network. The Convolutional neural network comprises an input for the R.414607

[0066] - 9 - measurement the context information, the movement information, and the historical information.

[0067] The fused information is determined for example with a Gaussian process. The Gaussian process comprises an input for the measurement the context information, the movement information, and the historical information.

[0068] In a step 214, the network entity 102 selects the path based measurement method or the sample based measurement method according to the result of analyzing the fused information.

[0069] The result of analyzing the fused information may be determined with an artificial intelligence. The artificial intelligence comprises an input for the fused information. The artificial intelligence is configured to output the result, in particular an output indicating to select the sample-based measurement method or the path-based measurement method.

[0070] The artificial intelligence for example comprises at least one adjustable parameter that influences the result.

[0071] In a step 216, the network entity 102 sends a message indicating the measurement strategy.

[0072] The message indicating the measurement strategy indicates to use the sample based method or indicates to use the path based method.

[0073] The message indicating the measurement strategy may be sent for measuring another measurement for positioning the UE 104.

[0074] The positioning of the UE 104 may be determined in a step 218 depending on the measurement.

[0075] The at least one adjustable parameter that influences the result may be adjusted depending on an accuracy of the positioning. R.414607

[0076] - 10 -

[0077] The accuracy may be monitored by the network entity 102 or received by the network entity 102 as feedback, e.g., from the UE 104.

[0078] The at least one parameter that improves the accuracy may be iteratively learned, e.g., by repeatedly executing the step 202 to 218.

[0079] The methods and devices introduce a context-aware AI / ML-based positioning system that leverages multi-layer data fusion to enhance positioning accuracy and optimize resource usage. The system dynamically adjusts measurement strategies based on real-time environmental conditions and user contexts, providing a versatile and efficient solution for various network environments.

[0080] The following section provides a description of exemplary components, their interactions, and an exemplary overall workflow.

[0081] The description refers to Environmental context as example for the context information, to User Movement Patterns as example for movement information, and to Historical Signal Data as example for historical information.

[0082] Multi-Layer Data Fusion Framework:

[0083] The multi-layer data fusion framework integrates various data sources to provide a comprehensive view of the positioning environment. These data sources include:

[0084] Environmental Context: Information about the current environment, such as urban or rural settings, building density, and geographical features.

[0085] User Movement Patterns: Data from motion sensors and user devices that indicate whether the user is walking, driving, or stationary.

[0086] Historical Signal Data: Previously collected signal data that helps predict current conditions based on past patterns.

[0087] Measurements: Both sample-based and path-based signal measurements are incorporated to provide detailed signal characteristics and efficient path reporting. R.414607

[0088] - 11 -

[0089] The Multi-Layer Data Fusion Framework combines these data sources using, for example, a data fusion algorithm. The data fusion algorithm for example comprises the Kalman filter, the Bayesian network, the Dempster-Shafer rule of combination, the convolutional neural network, the Gaussian process.

[0090] The data fusion algorithm for example creates a rich, multi-dimensional dataset, i.e. , the fused information, that supports accurate and adaptive decision-making.

[0091] Example: In an urban environment, the system collects data from multiple sources:

[0092] Environmental Context: High building density, urban canyon effect. User Movement Patterns: The user is walking through a crowded street. Historical Signal Data: Past data indicates frequent signal reflections and multipath interference.

[0093] Measurements: Both sample-based (detailed signal characteristics) and pathbased (specific signal paths).

[0094] The Multi-Layer Data Fusion Framework combines these data layers to create a comprehensive dataset, i.e., the fused information, that provides a detailed understanding of the positioning environment.

[0095] This dataset is then used by a context-aware Al algorithm to make informed decisions about measurement strategies. The context-aware Al algorithm comprises the artificial intelligence that is configured to output the result.

[0096] Context-Aware Al Algorithm:

[0097] The context-aware Al algorithm analyzes the fused information to determine the optimal measurement strategy in real-time. The context-aware Al algorithm may comprise Al algorithms that perform the following functions:

[0098] Environmental Assessment: Continuously evaluate signal strength, interference levels, and bandwidth availability to assess the current environmental conditions. R.414607

[0099] - 12 -

[0100] Measurement Selection: Based on the environmental assessment, dynamically switch between sample-based and path-based measurements to balance accuracy and resource usage.

[0101] Predictive Analysis: Use historical signal data and user movement patterns to predict future conditions and proactively adjust measurement strategies.

[0102] The Al algorithms may be designed to be flexible and scalable, allowing for the integration of new data sources and continuous improvement through machine learning.

[0103] Example: The Al algorithms analyze the fused information and determine that, due to high building density and signal reflections, a sample-based measurement approach is necessary to maintain high positioning accuracy. The Al algorithms also predict potential signal blockages based on historical data and adjust the measurement strategy accordingly.

[0104] Real-Time Environmental Assessment:

[0105] The system employs sensors and network data to continuously monitor environmental conditions. Key metrics for example include:

[0106] Signal Strength: Measurement of the received signal power.

[0107] Interference Levels: Analysis of the noise and interference affecting the signal.

[0108] Bandwidth Availability: Assessment of the available network resources.

[0109] This real-time assessment provides the necessary data for the context-aware Al algorithms to make informed decisions about measurement strategies.

[0110] Example: Sensors and network data continuously monitor the following metrics:

[0111] Signal Strength: Fluctuating due to reflections and obstructions. Interference Levels: High, due to multiple signal sources.

[0112] Bandwidth Availability: Limited, as multiple users are accessing the network. R.414607

[0113] - 13 -

[0114] The real-time environmental assessment feeds this data into the Al algorithms, which then adjust the measurement strategy dynamically.

[0115] Optimized Signaling Protocols:

[0116] The existing 3GPP signaling protocols may be modified to support the integration of multi-layer data fusion and context-aware algorithms. These modifications include:

[0117] New Message Types: For example, the messages for transmitting environmental context, user movement patterns, and historical signal data are introduced.

[0118] Extended Headers: For example, fields are added to existing message headers to include AI / ML model parameters and performance metrics.

[0119] Efficient Communication: The steps described above introduce messages of a protocol that is optimized for minimal signaling overhead. The protocol may be implemented while maintaining backward compatibility with current standards.

[0120] Example Protocol:

[0121] Environmental Context Message: Sent from the UE 104 to the network entity 102, including details about the current environment (e.g., urban, high building density).

[0122] Movement Pattern Message: Sent periodically, updating the network on the user’s movement (e.g., walking, speed, direction).

[0123] Historical Data Request / Response: The network entity 102 requests historical signal data relevant to the current location, and the data repository 106 or the UE 104 responds with stored historical signal data.

[0124] Exemplary Performance Monitoring and Feedback:

[0125] The system may include advanced monitoring tools that continuously assess the system performance. Key features include: R.414607

[0126] - 14 -

[0127] Continuous Monitoring: Collect data on positioning accuracy, latency, and resource usage.

[0128] Feedback Loops: Use performance data to refine and improve the Al algorithms and measurement strategies over time.

[0129] - Adaptive Learning: Implement machine learning techniques to learn from performance data and adapt to changing conditions.

[0130] Example: The system continuously monitors the following performance metrics: Positioning Accuracy: Measured against known benchmarks.

[0131] Latency: Time taken to process measurements and provide position updates. Resource Usage: Bandwidth and processing power consumed.

[0132] Exemplary Implementation Steps:

[0133] 1. Simulations and Validation:

[0134] - Conduct extensive simulations to validate the performance improvements of the context-aware, multi-layer data fusion system.

[0135] - Fine-tune the Al algorithms and measurement strategies based on simulation results.

[0136] 2. Software Updates:

[0137] - Develop software updates for existing network infrastructure to incorporate the new system.

[0138] - Ensure that these updates are compatible with current 3GPP standards.

[0139] 3. Pilot Projects:

[0140] - Execute pilot projects in real-world scenarios to test and refine the system.

[0141] - Gather feedback from pilot deployments to make necessary adjustments before full-scale implementation.

[0142] Exemplary System Workflow:

[0143] 1. Data Collection:

[0144] - Collect environmental context, user movement patterns, historical signal data, and traditional measurements. R.414607

[0145] - 15 -

[0146] 2. Data Fusion:

[0147] - Integrate the collected data using the multi-layer data fusion framework.

[0148] 3. Environmental Assessment:

[0149] - Continuously monitor environmental conditions and assess real-time metrics.

[0150] 4. Al Decision-Making:

[0151] - Use context-aware Al algorithms to determine the optimal measurement strategy.

[0152] 5. Measurement Adjustment:

[0153] - Dynamically switch between sample-based and path-based measurements based on the Al decision.

[0154] 6. Performance Monitoring:

[0155] - Continuously monitor system performance and provide feedback to improve Al algorithms.

[0156] Benefits and Impact:

[0157] Improved Positioning Services: Enhanced accuracy and reliability of positioning services for end-users.

[0158] Operational Efficiency: Reduced signaling overhead leads to more efficient network operations.

[0159] Scalability: The flexible nature of the multi-layer data fusion framework allows for easy adaptation to future advancements and network expansions.

Claims

R.414607- 16 -Claims1. A method, in particular in a network entity (102), for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the method comprises- receiving (202) a measurement for positioning the entity, wherein the measurement is captured with a sample-based measurement method or a path-based measurement method,- receiving (206) a message comprising historical information, wherein the historical information characterizes a historical performance indicator of the communication network, for example a signal-to-noise ratio, a bandwidth size,- receiving (208) a message comprising context information, wherein the context information characterizes the entity's setting, in particular a urban setting or a rural setting,- receiving (210) a message comprising movement information, wherein the movement information characterizes a movement of the entity or a user carrying the entity, in particular walking, driving, standing still,- determining (212) fused information depending on the measurement, the context information, the movement information, and the historical information, wherein the fused information characterizes an positioning environment of the entity,- selecting (214) the path based measurement method or the sample based measurement method according to the result of analyzing the fused information, and- sending (216) a message indicating the measurement strategy, in particular indicating to use the sample based or the path based method for measuring another measurement for positioning the entity.

2. The method according to claim 1 , characterized in that the method comprises,R.414607- 17 -- determining (212) the fused information with a Kalman filter, wherein the Kalman filter comprises an input for the measurement the context information, the movement information, and the historical information, or- determining (212) the fused information with a Bayesian network, wherein the Bayesian network comprises an input for the measurement the context information, the movement information, and the historical information, or- determining (212) the fused information with a Dempster-Shafer rule of combination, wherein the Dempster-Shafer rule of combination comprises an input for the measurement the context information, the movement information, and the historical information, or- determining (212) the fused information with a Convolutional neural network, wherein the Convolutional neural network comprises an input for the measurement the context information, the movement information, and the historical information, or- determining (212) the fused information with a Gaussian process, wherein the Gaussian process comprises an input for the measurement the context information, the movement information, and the historical information.

3. The method according to claim 1 or 2, characterized in that the method comprises- determining (214) the result of analyzing the fused information with an artificial intelligence, wherein the artificial intelligence comprises an input for the fused information, wherein the artificial intelligence is configured to output the result, in particular an output indicating to select the sample-based measurement method or the path-based measurement method.

4. The method according to claim 3, characterized in that the method comprises- determining (218) the positioning of the entity depending on the measurement, wherein the artificial intelligence comprises at least one adjustable parameter that influences the result, andR.414607- 18 -- adjusting (218) the at least one adjustable parameter depending on an accuracy of the positioning, wherein the accuracy is monitored or received as feedback.

5. The method according to claim 4, characterized in that the method comprises- iteratively learning (202, ... , 218) the at least one parameter that improves the accuracy.

6. The method according to one of the preceding claims, characterized in that the method comprises- sending (204) a request for the historical information.

7. A method, in particular in an user entity (104), for providing information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of the entity (104) in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the method comprises- sending (202) a measurement for positioning the entity (104) measured with a sample-based measurement method or a path-based measurement method,- sending (208) a message comprising context information, wherein the context information characterizes the entity's setting, in particular a urban setting or a rural setting,- sending (210) a message comprising movement information, wherein the movement information characterizes a movement of the entity or a user carrying the entity, in particular walking, driving, standing still,- receiving (216) a message indicating a measurement strategy, in particular indicating to use the sample based or the path based method for measuring another measurement for positioning the entity.

8. A method, in particular in an data repository (106), for providing historical information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the method comprisesR.414607- 19 -- sending (206) the historical information, wherein the historical information characterizes a historical performance indicator of the communication network, for example a signal-to-noise ratio, a bandwidth size.

9. The method according to claim 8, characterized in that the method comprises receiving (204) a request for historical information.

10. A device (102) for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the device (102) is configured to execute the method according to one of the claims 1 to 6.11 . A device (104) for providing information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of an entity in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the device (104) is configured to execute the method according to claim 7.

12. A device (106) for providing historical information for providing a measurement strategy for an in particular artificial intelligence or machine learning based positioning of the entity in a wireless communication network (100), in particular in a wireless cellular communication network, characterized in that the device (106) is configured to execute the method according to claim 8 or 9.

13. A computer program, characterized in that the computer program comprises computer readable instructions that, when executed by a computer and / or the device (102) of claim 10 and / or the device (104) of claim 11 and / or the device (106) of claim 12, cause- the computer (102) and / or the device (102) to carry out the method according to at least one of the claims 1 to 6, and / or- the computer (102) and / or the device (104) to carry out the method according to claim 7, and / orR.414607- 20 -- the computer (102) and / or the device (106) to carry out the method according to at least one of the claims 8 or 9.

14. A computer-readable storage medium comprising instructions which, when executed by a computer and / or the device (102) of claim 10 and / or the device (104) of claim 11 and / or the device (106) of claim 12, cause- the computer (102) and / or the device (102) to carry out the method according to at least one of the claims 1 to 6, and / or- the computer (102) and / or the device (104) to carry out the method according to claim 7, and / or- the computer (102) and / or the device (106) to carry out the method according to at least one of the claims 8 or 9.

15. A data carrier signal carrying and / or characterizing the computer program of claim 13.

Images