Data acquisition method, and apparatus

Abstract

A data acquisition method and an apparatus, relating to the technical field of communications. The method comprises: sending a first request to a location management function network element, the first request being used for requesting first sample data, and the first request comprising a label quality policy indication; and receiving a first response from the location management function network element, the first response comprising the first sample data, the first sample data comprising N pieces of sample data and a label corresponding to each of the N pieces of sample data, N being a positive integer greater than or equal to 1, and the first sample data satisfying a requirement of the label quality policy indication. The method improves the accuracy of sample data acquired by a data subscriber with respect to a sample requirement, such that the data subscriber can collect measurement data that satisfies a first threshold requirement and / or a sample quantity requirement, thereby improving the efficiency of the data subscriber in executing model training and model performance monitoring of an AI positioning model.

Description

A data acquisition method and apparatus

[0001] This application claims priority to Chinese Patent Application No. 202510049423.0, filed on January 9, 2025, entitled "A Data Acquisition Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a data acquisition method and apparatus. Background Technology

[0003] The 3rd Generation Partnership Project (3GPP) proposes applying Artificial Intelligence (AI) to New Radio (NR) systems. Through data collection and analysis, network performance and user experience can be improved. For example, AI / machine learning (ML) can be implemented in core network nodes, such as Location Management Functions (LMFs).

[0004] Deploying AI models on LMF (Line-of-Sight Array) for localization in non-line-of-sight (NLOS) environments, instead of traditional wireless localization algorithms, can achieve higher localization accuracy. However, training such AI localization models requires channel measurement data and user equipment (UE) location as training data. The accuracy of the AI ​​localization model is closely related to the quality of the training data; therefore, obtaining satisfactory training data is a problem that needs to be solved. Summary of the Invention

[0005] This application provides a data acquisition method and apparatus that improves the accuracy of sample data acquired by data subscribers in meeting sample requirements, enabling data subscribers to collect measurement data that meets quality and / or sample quantity requirements, and improving the efficiency of data subscribers in performing AI localization model training and model performance monitoring.

[0006] Firstly, this application provides a data acquisition method, which can be executed by a first communication device, a device including the first communication device, or a chip (or chip system) or other functional module. The chip or functional module can implement the functions of the first communication device; for example, the chip or functional module is disposed within the first communication device. Optionally, the first communication device can also be a virtual device or software possessing the functions of a first communication device, such as a computer-readable storage medium or computer program product capable of executing methods related to the first communication device. The first communication device can be a network-side device; for example, it can be an access network device, a core network device, or a third-party device, without limitation.

[0007] The AI / Machine Learning (ML) models currently used by the LMF may be pre-configured on the LMF or obtained by the LMF from other sources, such as the Network Data Analytics Function (NWDAF). The following explanation uses a first communication device as an example, with the NWDAF network element as the execution entity. It should be understood that this method is applicable to scenarios where model training data is subscribed to from the LMF. The data subscriber includes, but is not limited to, the NWDAF network element; that is, the execution entity of this method includes, but is not limited to, the NWDAF network element. The data subscriber is used to instruct the device to subscribe to / obtain data from the LMF. This method may include:

[0008] The network data analysis function network element sends a first request to the location management function network element. The first request is used to request the first sample data and includes a label quality policy indication. The network data analysis function network element receives a first response from the location management function network element. The first response includes the first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

[0009] The data acquisition method provided in this application involves sending a first request containing a tag quality policy instruction to a location management function (LMF) via a network data analysis (NWDAF) network element. The LMF then returns first sample data that meets the requirements based on this instruction. This method effectively improves the relevance and quality of the data required for AI / ML localization model training or performance monitoring, thereby enhancing the accuracy of AI / ML localization models and the efficiency of model training / monitoring.

[0010] In this embodiment, the label quality policy indicator is an indicator related to label quality. It should be understood that the label quality policy indicator is a strategic indication made for label quality, not the quality threshold itself. Considering that when acquiring / subscribing to data, setting the quality threshold too high may result in insufficient labels being acquired, while setting the threshold too low may affect the model training quality, the label quality policy indicator reflects the data subscriber's (NWDAF) demand for sample data. This enables the LMF to adjust the data acquisition or data processing method based on the label quality policy indicator, thereby allowing the data subscriber to acquire sample data that meets its requirements.

[0011] Optionally, the label quality policy indication is an indication of adjusting the relevant strategy for acquiring sample data, or the label quality policy indication includes one or more indications for label policy thresholds.

[0012] It should be noted that NWDAF can be divided into two categories: Model Training Logic Function (MTLF) and Analysis Logic Function (AnLF). MTLF can collect data from the network and train AI / ML models based on this data, and can provide the trained models to AnLF upon request. AnLF can perform data statistics and inference, or perform model inference based on the AI / ML model, derive corresponding analysis results according to the service consumer's request, and make these analysis results available to the consumer. For example, the service consumer can be an Access and Mobility Management Function (AMF), a Session Management Function (SMF), or a Policy Control Function (PCF). Therefore, an AI / ML model for localization can be trained by MTLF and then sent to LMF, which performs AI localization based on the AI / ML model and the collected measurement data.

[0013] Training an AI / ML localization model using MTLF requires collecting training data. This training data includes channel measurement data and corresponding labels. For example, channel measurement data can be Channel Impulse Response (CIR) or Power Delay Profile (PDP), and the corresponding labels can be the location of the User Equipment (UE) (hereinafter referred to as the terminal device). MTLF can use the channel measurement data as model input to calculate the model output and update the model parameters based on the error between the model output and the labels until the error is sufficiently small. Before training the AI / ML localization model, MTLF needs to collect channel measurement data and corresponding labels from LMF.

[0014] In one optional implementation, the first sample data includes channel measurement information, which includes the aforementioned channel measurement data. Optionally, the channel measurement information further includes a quality indicator of channel measurement and / or a timestamp of channel measurement corresponding to the channel measurement data. The first sample data also includes tag information associated with the channel measurement data, which includes first location information. Optionally, the first location information includes any of the following:

[0015] Cell identifier; or tracking zone identifier; or location coordinates (e.g., latitude and longitude coordinates); or location coordinates and location deviation value.

[0016] In this scheme, the first location information can be implemented in multiple ways. For example, the first location information can be the cell identifier, the tracking area identifier, the location coordinates, or the location coordinates and the location deviation value, which is quite flexible.

[0017] Optionally, the label information may also include a label quality indicator and / or a timestamp corresponding to the label. For example, the label quality indicator is used to represent the quality of the sample data corresponding to the label through a specific numerical value. For example, the higher the value of the label quality indicator, the higher the quality of the label; specifically, higher quality means more accurate positioning. In other words, the higher the value of the label quality indicator, the more accurate the first location information corresponding to the label, and the smaller the positioning deviation.

[0018] Optionally, the NWDAF enables the LMF to explicitly specify the number N of sample data requested in the first request information through pre-set, pre-defined, protocol, or pre-contact information transmission. Therefore, the first sample data returned by the LMF includes N sample data points and the tag corresponding to each of the N sample data points, where N is a positive integer greater than or equal to 1. Optionally, the pre-contact information includes information sent by the NWDAF to the LMF before sending the first request. In this embodiment, the first sample data returned by the LMF needs to meet the requirements of the tag quality policy indication and the quantity requirement N.

[0019] Alternatively, the first sample data returned by the LMF may consist of only N sample data points, and the label corresponding to each of the N sample data points is used by the LMF to filter the sample data. Alternatively, the first sample data returned by the LMF may consist of N sample data points and a label corresponding to each of the N sample data points, and the label may or may not include a label quality indicator.

[0020] In one alternative implementation, the first request further includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

[0021] By incorporating a sample quantity indicator into the first request, NWDAF can precisely control the amount of data acquired from LMF, ensuring sufficient data for training or monitoring while avoiding unnecessary data transfer, thus optimizing the efficiency and resource utilization of the data acquisition process.

[0022] In one alternative implementation, the label quality policy indication includes a highest quality indication, which indicates that sample data corresponding to the label with the highest label quality should be returned. The first sample data includes sample data corresponding to the N labels with the highest label quality.

[0023] In this implementation, the highest quality indicator (NWDAF) prioritizes acquiring sample data corresponding to high-quality labels, which is crucial for improving the training performance and localization accuracy of AI / ML models. This method ensures that model learning is based on the most reliable data, accelerates model convergence, and improves the efficiency and accuracy of AI / ML localization model training / monitoring.

[0024] Optionally, the first sample data in this embodiment includes the sample data corresponding to the N tags with the highest tag quality. N can be the N sample data obtained by enabling the LMF to clearly specify the number N sample data requested by the first request information through the transmission of pre-set, pre-defined, protocol or pre-information mentioned in the previous embodiment. Alternatively, it can be the N sample data returned by the LMF through a sample quantity indication. The N in the subsequent embodiments may be implemented in a similar way, and will not be described in detail hereafter.

[0025] In one alternative implementation, the label quality strategy indication includes a quality ranking indication for instructing the sample data to be ranked according to the label quality indication; the first sample data includes N sample data ranked according to the label quality indication.

[0026] In this embodiment, the quality sorting indicator enables LMF to return sample data in order of high to low quality. Thus, the data subscriber NWDAF can select the required sample data based on the sample data included in the first sample data, which is sorted according to the label quality indicator.

[0027] It should be noted that the N data mentioned above can refer to all data, which is all data collected by LMF based on the first request. In this case, N sample data only refers to all sample data, not the N sample data collected / filtered / determined by LMF based on quantity requirements (including sample quantity indication).

[0028] By using quality ranking indicators, NWDAF can prioritize acquiring sample data corresponding to high-quality labels, thereby improving the training effect and localization accuracy of AI / ML models.

[0029] Optionally, the label quality strategy indicator may include a quality ranking indicator and a highest quality indicator, corresponding to the return of the first sample data including sample data corresponding to the N labels with the highest label quality indicators, sorted according to the label quality indicators. Optionally, the quality ranking indicator and the highest quality indicator may also be used in combination with other implementation methods (such as sample quantity indicators), providing a more flexible data acquisition strategy that ensures both data quality and meets data quantity requirements, further enhancing the model's generalization ability and practical application effect.

[0030] In an optional implementation, the first request further includes a first threshold, which is used to indicate the sample data corresponding to the labels whose label quality meets the first threshold. The label quality strategy indication includes a first priority indication, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of meeting the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indication.

[0031] Optionally, the first threshold includes a label quality threshold.

[0032] In this implementation, a first threshold and priority indicator are introduced, allowing NWDAF to make trade-offs between data quality and quantity based on actual needs, thus improving the flexibility and adaptability of data acquisition. This mechanism ensures that sample data meeting specific quality requirements can be obtained even under resource constraints, supporting efficient and effective model training or performance evaluation.

[0033] In one optional implementation, when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the sample quantity indicator is met, the first sample data includes N sample data, the N sample data including Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N; when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the first threshold is met, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

[0034] Optionally, when the first priority indicator is used to indicate that the requirement of the sample quantity indicator is met first, the first sample data includes N sample data. The label quality indicator corresponding to the N sample data may meet the requirement of the first threshold, or may not meet the requirement of the first threshold, or may partially meet the requirement of the first threshold and the remaining part may not meet the requirement of the first threshold.

[0035] Alternatively, when the first priority indicator is used to indicate that the requirement of the first threshold is met first, there may be a situation where the number of sample data that meets the first threshold requirement exceeds the number indicated by the sample number indicator. For example, there are Z sample data that meet the first threshold requirement, where Z is a positive integer greater than N. In the case of the excess, the Z sample data that meet the first threshold requirement must also meet the requirement indicated by the sample number indicator. Therefore, in this case, the first sample data includes N sample data that meet the first threshold requirement.

[0036] In an optional implementation, the first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

[0037] In this embodiment, the introduction of label quality deviation indication provides additional flexibility in data acquisition, allowing for consideration of a certain range of quality fluctuations on the basis of strict quality thresholds, thereby expanding the range of available datasets and helping to improve the robustness and generalization ability of the model.

[0038] In one optional implementation, the label quality policy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality indication is within the label quality range, and the first sample data includes sample data whose label quality indication is within the label quality range.

[0039] In this implementation, a label quality range indicator is used instead of a specific threshold, providing a broader standard for data selection. This helps to capture more diverse data features, promotes the applicability of the model in different scenarios, and enhances the model's versatility and practicality.

[0040] In one optional implementation, the first request includes a plurality of first thresholds, and the label quality policy indication includes a second priority indication, which is used to indicate the priority of the plurality of first thresholds and to indicate that sample data corresponding to the labels that meet the first threshold requirements of the label quality indication are returned in descending order of priority of the plurality of first thresholds. The first sample data includes sample data that the label quality indication meets the second threshold requirement among the plurality of first thresholds and the second priority indication requirement.

[0041] In this embodiment, by setting multiple first thresholds and corresponding priorities, NWDAF can more precisely control the data acquisition process, prioritize the acquisition of high-quality data, and avoid the need to interact with LMF multiple times due to insufficient sample data, thus providing a more comprehensive and balanced dataset for model training.

[0042] It should be understood that the second priority indication includes priorities corresponding to a plurality of first thresholds, and the aforementioned second threshold requirement can be any one or more of the plurality of first thresholds. For example, the second threshold requirement specifically refers to which one or more of the plurality of first thresholds are related to the quantity indicated by the sample quantity indication.

[0043] In one optional implementation, the tag quality policy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

[0044] In this implementation, sample data corresponding to the Positioning Reference Unit (PRU) is returned first, directly targeting the key elements of the positioning service. This improves the relevance and relevance of the data, helps the model learn positioning features more accurately, and enhances the accuracy of the AI / ML positioning model.

[0045] In one optional implementation, the label quality policy indication further includes at least one of the following: highest quality indication, quality ranking indication, first priority indication, second priority indication, label quality deviation indication, or label quality range indication, wherein the NM non-PRU corresponding sample data in the first sample data meet the requirements of the label quality policy indication.

[0046] In this embodiment, the third priority indicator can also be used in combination with various label quality strategy indicators, such as the highest quality indicator and the quality ranking indicator, to ensure that sample data corresponding to non-PRUs can also meet certain quality standards. This ensures data diversity without sacrificing data quantity and quality, laying a solid foundation for building a high-performance AI / ML localization model.

[0047] Secondly, this application provides a data acquisition method, which can be executed by a location management function network element, or by a device including location management functions, or by a chip (or chip system) or other functional module. The chip or functional module can realize the functions of the location management function network element. For example, the chip or functional module is set in the location management function network element. Optionally, the location management function network element can also be a virtual device or software for the functions of the location management function network element, such as a computer-readable storage medium, computer program product, etc., that can execute methods related to the location management function network element. This application does not limit this.

[0048] The following explanation uses a location management function network element as the implementing entity as an example. The method includes:

[0049] The location management function network element receives a first request from the network data analysis function network element. The first request is used to request first sample data and includes a tag quality policy indication.

[0050] The location management function network element sends a first response to the network data analysis function network element. The first response includes first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

[0051] The data acquisition method provided in this application involves the LMF responding to a request from the NWDAF and providing first sample data according to the label quality policy. This method not only meets the NWDAF's need for high-quality training or monitoring data but also promotes data sharing and collaborative work between the LMF and NWDAF, enhancing the intelligence and automation level of the entire network system.

[0052] In one alternative implementation, the method further includes:

[0053] In response to the first request, the location management function network element obtains the first sample data.

[0054] In one optional implementation, in response to a first request, obtaining first sample data includes:

[0055] The location management function network element acquires the second sample data, which includes the first sample data.

[0056] In response to the tag quality policy indication included in the first request, the location management function network element determines the first sample data in the second sample data.

[0057] In one alternative implementation, the first request further includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

[0058] In one optional implementation, the label quality policy indication includes a highest quality indication, which is used to indicate the sample data corresponding to the label with the highest label quality indication. The first sample data includes sample data corresponding to the N labels with the highest label quality indication.

[0059] In one alternative implementation, the label quality strategy indication includes a quality ranking indication, which indicates that the sample data should be ranked according to the label quality indication;

[0060] The first sample data consists of N sample data sorted according to the label quality indicator.

[0061] In an optional implementation, the first request further includes a first threshold, which is used to indicate the sample data corresponding to the labels whose label quality meets the first threshold. The label quality strategy indication includes a first priority indication, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of meeting the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indication.

[0062] In one optional implementation, when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the sample quantity indicator is met, the first sample data includes N sample data, the N sample data including Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N; when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the first threshold is met, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

[0063] In an optional implementation, the first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

[0064] In one optional implementation, the label quality policy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality indication is within the label quality range, and the first sample data includes sample data whose label quality indication is within the label quality range.

[0065] In one optional implementation, the first request includes a plurality of first thresholds, and the label quality policy indication includes a second priority indication, which is used to indicate the priority of the plurality of first thresholds and to indicate that sample data corresponding to labels whose label quality indications meet the corresponding first threshold requirements are returned in descending order of priority of the plurality of first thresholds. The first sample data includes sample data whose label quality indications meet the second threshold requirements among the plurality of first thresholds and the requirements of the second priority indication.

[0066] In one optional implementation, the tag quality policy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

[0067] Thirdly, a communication device is provided, including a unit for performing the method described in the first aspect. This communication device may be an NWDAF (Network Data Attached Function), or a chip or circuit disposed within the NWDAF, or a device / equipment capable of implementing NWDAF functionality. It should be understood that the NWDAF here can be replaced by other data subscribers. The communication device includes at least a communication unit, specifically as follows:

[0068] The communication unit is used to send a first request to the location management function network element. The first request is used to request first sample data and includes a tag quality policy indication.

[0069] The communication unit is also used to receive a first response from the location management function network element. The first response includes first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

[0070] In one alternative implementation, the first request further includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

[0071] In one optional implementation, the label quality policy indication includes a highest quality indication, which is used to indicate the sample data corresponding to the label with the highest label quality indication. The first sample data includes sample data corresponding to the N labels with the highest label quality indication.

[0072] In one alternative implementation, the label quality strategy indication includes a quality ranking indication for instructing the sample data to be ranked according to the label quality indication; the first sample data includes N sample data ranked according to the label quality indication.

[0073] In an optional implementation, the first request further includes a first threshold, which is used to indicate the sample data corresponding to the labels whose label quality meets the first threshold. The label quality strategy indication includes a first priority indication, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of meeting the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indication.

[0074] In one optional implementation, when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the sample quantity indicator is met, the first sample data includes N sample data, the N sample data including Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N; when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the first threshold is met, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

[0075] In an optional implementation, the first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

[0076] In one optional implementation, the label quality policy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality indication is within the label quality range, and the first sample data includes sample data whose label quality indication is within the label quality range.

[0077] In one optional implementation, the first request includes a plurality of first thresholds, and the label quality policy indication includes a second priority indication, which is used to indicate the priority of the plurality of first thresholds and to indicate that sample data corresponding to the labels that meet the first threshold requirements of the label quality indication are returned in descending order of priority of the plurality of first thresholds. The first sample data includes sample data that the label quality indication meets the second threshold requirement among the plurality of first thresholds and the second priority indication requirement.

[0078] In one optional implementation, the tag quality policy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

[0079] In one optional implementation, the label quality policy indication further includes at least one of the following: highest quality indication, quality ranking indication, first priority indication, second priority indication, label quality deviation indication, or label quality range indication, wherein the NM non-PRU corresponding sample data in the first sample data meet the requirements of the label quality policy indication.

[0080] The explanations and beneficial effects of the communication device provided in the third aspect can be found in the method described in the first aspect, and will not be repeated here.

[0081] Fourthly, a communication device is provided, including a unit for performing the method described in the second aspect above. This communication device may be executed by a location management function network element, or by a device including location management functions, or by a chip (or chip system) or other functional module capable of implementing the functions of the location management function network element. Alternatively, it may be executed by a chip or circuit disposed in a candidate auxiliary terminal; this application does not limit this. The communication device includes: a communication unit and a processing unit. Specifically, as follows:

[0082] The communication unit is used to receive a first request from a network data analysis function network element. The first request is used to request first sample data and includes a tag quality policy indication.

[0083] The communication unit is also used to send a first response to the network data analysis function network element. The first response includes first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

[0084] In an alternative implementation, the communication unit is further configured to acquire first sample data in response to a first request.

[0085] In one alternative implementation, in response to a first request, first sample data is acquired, and the communication unit is further configured to acquire second sample data, the second sample data including the first sample data; the processing unit is configured to, in response to the tag quality policy indication included in the first request, determine the first sample data in the second sample data.

[0086] In one alternative implementation, the first request further includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

[0087] In one optional implementation, the label quality policy indication includes a highest quality indication, which is used to indicate the sample data corresponding to the label with the highest label quality indication. The first sample data includes sample data corresponding to the N labels with the highest label quality indication.

[0088] In one alternative implementation, the label quality strategy indication includes a quality ranking indication, which indicates that the sample data should be ranked according to the label quality indication;

[0089] The first sample data consists of N sample data sorted according to the label quality indicator.

[0090] In an optional implementation, the first request further includes a first threshold, which is used to indicate the sample data corresponding to the labels whose label quality meets the first threshold. The label quality strategy indication includes a first priority indication, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of meeting the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indication.

[0091] In one optional implementation, when the first priority indicator is used to indicate that the requirement of prioritizing the satisfaction of the sample quantity indicator is met, the first sample data includes N sample data, and the N sample data includes Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N.

[0092] In the case where the first priority indicator is used to indicate that the requirement of the first threshold is met first, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

[0093] In an optional implementation, the first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

[0094] In one optional implementation, the label quality policy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality indication is within the label quality range, and the first sample data includes sample data whose label quality indication is within the label quality range.

[0095] In one optional implementation, the first request includes a plurality of first thresholds, and the label quality policy indication includes a second priority indication, which is used to indicate the priority of the plurality of first thresholds and to indicate that sample data corresponding to labels whose label quality indications meet the corresponding first threshold requirements are returned in descending order of priority of the plurality of first thresholds. The first sample data includes sample data whose label quality indications meet the second threshold requirements among the plurality of first thresholds and the requirements of the second priority indication.

[0096] In one optional implementation, the tag quality policy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

[0097] The explanations and beneficial effects of the communication device provided in the fourth aspect can be found in the methods shown in the second aspect, and will not be repeated here.

[0098] Fifthly, a communication device is provided, the device comprising a processor coupled to a memory; the memory for storing computer programs or instructions; the processor for executing the computer programs or instructions stored in the memory to cause the device to perform the method as described in any one of the first aspects above, or the method as described in any one of the second aspects above.

[0099] In a sixth aspect, a computer-readable storage medium is provided, the computer-readable storage medium storing computer-executable instructions, which, when invoked by the computer, are used to cause the computer to perform the method as described in any one of the first aspects above, or the method as described in any one of the second aspects above.

[0100] In a seventh aspect, a computer program product comprising instructions is provided, which, when run on a computer, causes the computer to perform the method as described in any one of the first aspects above, or the method as described in any one of the second aspects above.

[0101] Eighthly, a chip or chip system is provided, the chip or chip system including at least one processor for supporting a communication device to implement any possible implementation of the method described in the first or second aspect above. For example, the chip may be a baseband chip, a modem chip, a system-on-a-chip (SoC) chip containing a modem core, a system-in-package (SIP) chip, or a communication module, etc.

[0102] In one possible design, the chip or chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0103] Ninth aspect, a communication system is provided, the communication system comprising the communication device as described in any one of the fifth aspects above.

[0104] It is understood that any of the communication methods, communication devices, communication systems, computer program products, computer-readable storage media or chips provided above can be implemented by the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the first and second aspects above, and will not be repeated here. Attached Figure Description

[0105] Figure 1 is a schematic diagram of an AI positioning scenario provided in an embodiment of this application;

[0106] Figure 2 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0107] Figure 3 is a flowchart illustrating a data acquisition method provided in an embodiment of this application;

[0108] Figure 4 is a schematic diagram of a first sample data provided in an embodiment of this application;

[0109] Figure 5 is a schematic diagram of another type of first sample data provided in an embodiment of this application;

[0110] Figure 6 is a schematic diagram of yet another type of first sample data provided in an embodiment of this application;

[0111] Figure 7 is a schematic diagram of yet another type of first sample data provided in an embodiment of this application;

[0112] Figure 8 is a schematic diagram of another type of first sample data provided in an embodiment of this application;

[0113] Figure 9 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0114] Figure 10 is a schematic diagram of the structure of another communication device provided in an embodiment of this application. Detailed Implementation

[0115] First, the devices, equipment, network elements, and functional entities that may be involved in the embodiments of this application will be described in detail.

[0116] The access network (AN) or radio access network (RAN) can be either an AN or a RAN. Specifically, the (R)AN can be various types of base stations, such as macro base stations, micro base stations, and distributed unit-control unit (DU-CU). Additionally, these base stations can also be radio controllers in cloud radio access network (CRAN) scenarios, or relay stations, access points, vehicle-mounted equipment, wearable devices, or network equipment in future public land mobile networks (PLMNs). The (R)AN is primarily responsible for air interface-side radio resource management, quality of service management, data compression, and encryption.

[0117] User plane function (UPF): Primarily responsible for forwarding and receiving user data. The UPF can receive downlink data from the DN and then transmit that downlink data to the UE via the (R)AN. The UPF can also receive uplink data from the UE via the (R)AN and then forward that uplink data to the DN.

[0118] Data network (DN): For example, a DN can be a carrier service network, an internet access network, or a third-party service network. The DN can exchange information with the UE through PDU sessions. PDU sessions can be of various types, such as Internet Protocol version 4 (IPv4) and IPv6.

[0119] Access and Mobility Management Function (AMF): Primarily responsible for processing control plane messages and managing user mobility, including mobility state management, assigning temporary user identities, and authenticating and authorizing users. Examples include access control, mobility management, registration and deregistration, and network element selection.

[0120] Session Management Function (SMF): Primarily used for session management, session establishment, UE IP address allocation and management, responsible for session establishment, modification and release, and Quality of Service (QoS) control, etc.

[0121] Policy control function (PCF): Primarily used to manage policy rules and user subscription information.

[0122] Unified data management (UDM): Primarily used for authentication and credit processing, it manages subscription data, user identification, access authorization, registration / mobility management, subscription management, and SMS management. For example, when a user's subscription data is modified, UDM is responsible for notifying the relevant network elements.

[0123] Network Exposure Function (NEF): Primarily used to provide corresponding security guarantees to ensure the security of external applications to the communication network, providing functions such as opening up QoS customization capabilities for external applications, subscription to mobility state events, and distribution of AF requests.

[0124] Network storage function (NF repository function, NRF): mainly used to provide internal / external addressing functions, etc.

[0125] Application function (AF): mainly used to send data routing information affecting the application to the network side, and to perform policy control by interacting with the policy framework through network open function elements.

[0126] NWDAF: Network Data Analysis Function. It possesses functions such as data collection, model training, data analysis, and model inference. It can collect relevant data from network elements, third-party service servers, terminal devices, or network management systems, perform data analysis or model training based on this data, and provide the data analysis results to network elements, third-party service servers, terminal devices, or network management systems, or provide trained models to other network elements with data analysis functions. Optionally, NWDAF provides data analysis functions to network elements such as 5GC NF and OAM. 5GC NF or OAM can request network data analysis results from NWDAF. After receiving the request, NWDAF can collect data from the relevant network elements and train the data to obtain an AI model; then, NWDAF can use the AI ​​model to perform data inference and feed the inference results back to the corresponding 5GC NF or OAM.

[0127] For example, depending on the different functions performed, an NWDAF can include a Model Training Logical Function (MTLF) and an Analytics Logical Function (AnLF). MTLF supports data training, while AnLF supports data inference. An NWDAF containing only AnLF can be represented as NWDAF(AnLF), an NWDAF containing only MTLF can be represented as NWDAF(MTLF), or an NWDAF can contain both AnLF and MTLF, and is represented as NWDAF.

[0128] It should be noted that in the following embodiments of this application, NWDAF is used to send requests to obtain sample data, mainly for training the model and monitoring its performance. The embodiments of this application primarily focus on the process of obtaining sample data; the process of using the sample data is not specifically limited. The NWDAF in the embodiments of this application may refer to an NWDAF including MTLF, or an NWDAF including both AnLF and MTLF. This will not be elaborated further below.

[0129] LMF: Primarily used to provide the UE's location information. Specifically, the LMF can obtain location measurements and other information from the RAN, or from the UE's location measurement information, and thus calculate the UE's real-time location information.

[0130] Before detailing the methods involved in the embodiments of this application, it is necessary to first explain the scenarios involved in the embodiments of this application.

[0131] With the development and application of high-precision positioning technology, more and more scenarios require it to improve management and production efficiency. For example, high-precision positioning systems can provide drones with real-time, high-precision location information, flight attitude, speed information, and accurate time information; or, high-precision positioning services can enable autonomous driving or indoor navigation. Furthermore, with the development of semiconductor technology, terminal devices are taking on increasingly diverse forms. Because different terminal devices have different functions and application scenarios, the relative distance between terminal devices becomes a crucial consideration in some situations. For example, in some hazardous industrial equipment, no other equipment is allowed to operate nearby to avoid communication interference. Another example is unmanned inspection vehicles; during inspections, the inspection and measuring devices on the vehicle must be accurately installed to ensure the accuracy of the measurement data.

[0132] Currently, 3GPP standards discuss various AI positioning scenarios. This application mainly considers scenarios where AI / ML models are deployed on network elements (such as core network elements). For example, this network element can be an LMF (Local Model Filter). The following describes the scenario where AI / ML models are deployed on an LMF. Specifically, it includes two scenarios: Scenario 1 is a downlink positioning method, and Scenario 2 is an uplink positioning method. Please refer to Figure 1, which is a schematic diagram of an AI positioning scenario provided by an embodiment of this application.

[0133] Scenario 1 is a downlink positioning method. The access network device sends a downlink positioning reference signal, such as a positioning reference signal (PRS), to the UE. The UE performs measurements to obtain PRS measurement data and sends the measurement data to the core network device (the embodiments of this application mainly involve LMF). The LMF infers the UE position estimation result based on the local AI / ML model and the UE's measurement data.

[0134] Scenario 2 is the uplink positioning method. The UE sends an uplink channel sounding reference signal, such as a channel sounding reference signal (SRS), to the access network device. The access network device performs measurements to obtain SRS measurement data and sends the measurement data to the LMF. The LMF infers the UE location estimation result based on the local AI / ML model and the measurement data of the access network device.

[0135] Localization AI / ML models are mainly divided into two categories based on their output type. One category is AI-assisted localization (A-AIML), which outputs intermediate localization information, such as the line-of-sight (LOS) / non-line-of-sight (NLOS) probability of the path, or the estimated time of arrival (TOA) of the path. The Localization Filter (LMF) uses this intermediate information to obtain the estimated UE location based on traditional localization algorithms (such as the Time Difference of Arrival algorithm). The other category is AI-direct localization (D-AIML), which directly outputs the estimated UE location. The LMF-side models in scenarios 1 and 2 shown in Figure 1 are both D-AIML models, meaning the model output is the UE location.

[0136] Considering that the AI / ML model of LMF may be obtained from NWDAF, and the MTLF in NWDAF needs to collect training data / sample data, while LMF itself, as a functional entity / network element used to provide UE location information, can provide training data / sample data. However, in practical applications, NWDAF will indicate a first threshold when acquiring sample data / training data, but how to set the quality threshold of NWDAF is a problem. If the threshold is set too high, it may not be able to obtain enough labels, and if the threshold is set too low, it will affect the model training quality.

[0137] It should be noted that the above-mentioned labels can also be called target variables or response variables. In different training tasks, labels can also be called categories (in classification tasks), answers (in question-answering systems), or expected outputs, etc. The names used in the embodiments of this application are only for illustrating their characteristics and functions and are not intended to limit them.

[0138] Based on this, embodiments of this application propose a data acquisition method and apparatus, enabling NWDAF to collect measurement data that meets the requirements of label quality and / or sample quantity, assisting NWDAF in performing model training and model performance monitoring of AI localization models, enabling data subscribers to acquire sample data in a balanced manner, thereby improving the accuracy of sample data in meeting sample requirements.

[0139] First, it needs to be explained that:

[0140] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0141] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0142] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0143] In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "network device sending information" can be understood as a network device sending information to another device (such as a terminal or other network device), or it can be understood as logical module 1 in the network device sending information to logical module 2 in the network device.

[0144] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "network device receiving information" can be understood as a network device receiving information from another device (such as a terminal or other network device), or it can be understood as logical module 1 in the network device receiving information from logical module 2 in the network device.

[0145] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is a terminal. This can include sending information directly or indirectly to a terminal. Similarly, phrases such as "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent by (e.g., a terminal)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is a terminal. This can include receiving information directly or indirectly from a terminal. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0146] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0147] The “protocol” mentioned in the embodiments of this application may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. The embodiments of this application do not specifically limit this.

[0148] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0149] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. In the embodiments of this application, "and / or" is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0150] In the embodiments of this application, the terms "system" and "network" can be used interchangeably; "cell", "base station" and "network device" can also be used interchangeably. For example, "target cell" can also be called "target base station" or "target network device", and "source cell" can also be called "source base station" or "source network device".

[0151] Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply difference. Meanwhile, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. To be precise, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete way to facilitate understanding.

[0152] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0153] To facilitate understanding of the embodiments of this application, a communication system will be used as an example to describe in detail the communication system applicable to the embodiments of this application.

[0154] The communication method provided in this application embodiment can be applied to the system architecture shown in Figure 1. Figure 1 illustrates the interaction relationship between network functions (NFs) and entities, as well as the corresponding interfaces, using the network service architecture of a 5th generation (5G) mobile communication system as an example. The 3rd generation partnership project (3GPP) for 5G systems includes a service-based architecture (SBA) that encompasses network functions and entities such as: User Equipment (UE), Access Network (AN) or Radio Access Network (RAN), User Plane Function (UPF), Data Network (DN), Network Data Analytics Function (NWDAF), Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), Application Function (AF), Unified Data Management (UDM), Network Exposure Function (NEF), Unified Data Repository (UDR), Operations, Administration and Management (OAM) (i.e., network management), Binding Support Function (BSF), Location Management Function (LMF), and Network Storage Function (NF repository). Functions, NRF, etc.

[0155] In this context, UE, (R)AN, UPF, and DN are generally referred to as user plane network functions and entities (or user plane network elements), while the others are generally referred to as control plane network functions and entities (or control plane network elements). Control plane network elements are defined by 3GPP as having processing functions within a network. They possess 3GPP-defined functional behaviors and interfaces. An NF can function as a network element running on proprietary hardware, a software instance running on proprietary hardware, or a virtual function instantiated on a suitable platform, such as being implemented in a cloud infrastructure.

[0156] The functions of the other network elements included in Figure 1 can be found in the relevant descriptions in conventional technologies, and will not be repeated here.

[0157] It should be noted that Figure 1 above is only an example of a network service architecture. The communication method provided in this application embodiment can also be applied to other network architectures. For example, the network architecture of a fourth-generation (4G) mobile communication system. Alternatively, the communication method in this application embodiment can also be applied to other mobile communication systems developed after the fifth generation, and this application embodiment does not limit this application.

[0158] In this application embodiment, the UE can be a netbook, tablet computer, smartwatch, etc. Alternatively, the UE can also be other desktop devices, laptop devices, handheld devices, wearable devices, smart home devices, and vehicle-mounted devices with radio communication capabilities, such as Ultra-mobile Personal Computers (UMPCs), smart cameras, netbooks, Personal Digital Assistants (PDAs), Portable Multimedia Players (PMPs), AR (Augmented Reality) / VR (Virtual Reality) devices, aircraft, robots, etc. This application embodiment does not limit the specific type and structure of the UE.

[0159] Furthermore, the communication system can also be applied to future communication technologies. The system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0160] The data acquisition method provided in the embodiments of this application will be described in detail below based on the architecture shown in Figure 2.

[0161] In the embodiments of this application, the communication device (including terminal device and network device) can perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application can also perform other operations or variations of various operations. Furthermore, the steps can be performed in different orders as presented in the embodiments of this application, and it is not necessary to perform all the operations in the embodiments of this application.

[0162] For example, the data acquisition method provided in this application can be applied to scenarios related to AI localization models, such as scenario 1 and scenario 2 in Figure 1. Of course, it can also be applied to other scenarios related to model sample data, such as training scenarios for models other than AI localization models, data collection scenarios, etc. This application does not specifically limit the application scenarios. The above exemplary application scenarios do not impose any limitations on the solution of this application.

[0163] The following describes in detail, with reference to Figure 3, a data acquisition method provided by an embodiment of this application. This data acquisition method can be applied to the communication system shown in Figure 2, and can also be applied to any scenario in Figure 1; the embodiments of this application are not limited thereto.

[0164] The flowchart shown in Figure 3 illustrates the method from the perspective of the interaction between core network devices (including various functional entities / network elements), but this application does not limit the subject implementing the method. The following description uses the application of the above method to the network data analysis function network element (NWDAF or MTLF in NWDAF), AMF, NRF, and location management function network element (LMF) in the communication system shown in Figure 2 as an example. Exemplarily, the network data analysis function network element NWDAF (or MTLF in NWDAF) involved in Figure 3 can be referred to as a data subscriber, data requester, or data consumer. Specifically, it can be an NWDAF, a device including an NWDAF, a chip (or chip system), or other functional modules that can implement the functions of the NWDAF. For example, the chip or functional module is set in the NWDAF. Further, the network data analysis function network element NWDAF refers to the MTLF in the NWDAF, a device including an MTLF, or a chip (or chip system) or other functional modules that can implement the functions of the MTLF.

[0165] Figure 3 is a flowchart illustrating a data acquisition method according to an embodiment of this application. As shown in Figure 3, the method may include steps S301 to S305. Steps S301, S302, and S304 are optional. The specific flow of this method is described below:

[0166] Step S301: The network data analysis function element determines the input data to be collected from the location management function element.

[0167] For example, the determination process can be based on the corresponding message received by the network data analysis function network element after receiving the message from the location management function network element; or it can be based on an internal trigger.

[0168] Optionally, the internal trigger may specifically instruct the request to train the AI / ML localization model or to perform model performance monitoring of the AI / ML localization model.

[0169] Optionally, the network data analysis function network element determines the data collection requirements based on business objectives, which may include specific business tasks such as model training and model performance monitoring.

[0170] Optionally, prior to step S301, the method further includes the location management function network element sending a second request to the network data analysis function network element, and correspondingly, the network data analysis function network element receiving the second request from the location management function network element. The second request may be a request for an AI localization model, a request to update model training data, or a request related to model training data, such as a request to update the AI ​​localization model. It should be understood that the aforementioned second request can trigger step S301.

[0171] Step S302: The network data analysis function network element discovers the location management function network element through NRF.

[0172] Specifically, network data analysis function elements discover location management function elements through the NRF. The service area of ​​the discovered location management function elements needs to include the area of ​​interest (AoI) and support open data services. It should be noted that the process by which network data analysis function elements discover location management function elements through the NRF relies primarily on the information stored and provided by the NRF. As a key component of the network, the NRF is responsible for storing and managing information about various functions (such as LMFs) in the network, including their service areas, supported interfaces, and services.

[0173] For example, the specific process by which NWDAF discovers LMF is as follows:

[0174] First, NWDAF sends a third request to NRF to query LMF. This third request includes specific conditions or attributes that the LMF (which it wants to discover) needs to support, such as AoI (Aspect-Oriented Identifier), supported service operations, etc., or it may include specific requirements. Optionally, these specific conditions include service area requirements: the AoI specified by NWDAF is the geographical area where it collects and analyzes data. Therefore, when querying NRF, NWDAF requires that the returned LMF service area must include this AoI. Data Exposure Service Requirements: In order to obtain data from the LMF, NWDAF needs the LMF to support specific data exposure service operations (such as the Nlmf_DataExposure service). This service allows NWDAF to access the data stored by the LMF through standard interfaces and protocols. It should be understood that supporting data exposure service operations is a prerequisite for data exchange between LMF and NWDAF.

[0175] Secondly, based on the NWDAF's request, the NRF searches its stored information for LMFs that meet the criteria and returns a third response. This third response may include the LMFs that satisfy the specific conditions or attribute requirements included in the third request. Specifically, the third response includes parameters such as the identifier, address, and service area of ​​the LMFs that satisfy the specific conditions or attribute requirements included in the third request.

[0176] Next, based on the information returned by the NRF, NWDAF selects LMFs that meet its requirements for subsequent data subscription and collection.

[0177] Step S303: The network data analysis function network element sends a first request to the location management function network element. Correspondingly, the location management function network element receives the first request from the network data analysis function network element.

[0178] The first request is used to request the first sample data, and the first request includes a label quality policy indication.

[0179] Optionally, the first request may also include a data time window of data samples. The data time window of data samples may include a specified time window, which may be used to indicate that the timestamp of the requested first sample data is within the specified time window, or to indicate that only sample data with data timestamps within the specified time window is required.

[0180] The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) localization model. The first sample data includes N sample data and label information corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality strategy indication.

[0181] For example, if the model's input data is CIR and the output is UE location, then one of the N sample data can be...<CIR 1,UE location 1> This refers to a set of data corresponding to a CIR value and a UE location value. The CIR value is measurement data, and the UE location is a tag.

[0182] It should be noted that the labels in the embodiments of this application may also be called target variables or response variables. In different training tasks, the labels may also be called categories (in classification tasks), answers (in question-answering systems), or expected outputs, etc. The names used in the embodiments of this application are only for illustrating their characteristics and functions and are not intended to limit them.

[0183] Optionally, the first sample data includes channel measurement information, which includes the aforementioned channel measurement data. Optionally, the channel measurement information also includes a quality indicator of channel measurement and / or a timestamp of channel measurement corresponding to the channel measurement data. In this embodiment, the tag information is used to indicate tag-related information associated with the channel measurement data, and this tag information includes first location information. Optionally, the first location information includes any of the following:

[0184] Cellular identifier; or tracking zone identifier table; or location coordinates (e.g., latitude and longitude coordinates); or location coordinates and location deviation value.

[0185] Optionally, the label information includes a quality indicator of the label, which indicates the quality of the label. Optionally, the label information includes a timestamp of the label, which indicates the time when the label was measured.

[0186] In one possible implementation, the label quality indicator can be represented as a quality value. For example, the label quality indicator is used to reflect the quality of the label through a specific numerical value. It should be understood that the higher the value of the label quality indicator, the higher the quality of the label; specifically, higher quality means more accurate positioning. In other words, the higher the value of the label quality indicator, the more accurate the primary location information corresponding to the label, and the smaller the positioning deviation.

[0187] Optionally, the label information in the first sample data requested in the first request may also include a label quality indicator.

[0188] Alternatively, the first sample data requested in the first request may not include the tag quality indicator in the tag information, which is only used by the location management function network element to filter the sample data.

[0189] For example, the first sample data returned by the location management function network element includes only N sample data, and the label corresponding to each of the N sample data is used by the location management function network element to filter the sample data.

[0190] Optionally, the first sample data returned by the location management function network element includes N sample data and the tag information corresponding to each of the N sample data. The tag information may or may not include a tag quality indicator.

[0191] In this embodiment, the label quality policy indicator is an indicator related to label quality. It should be understood that the label quality policy indicator is a strategic indication made for label quality, not the quality threshold itself. Considering that when acquiring / subscribing to data, setting the quality threshold too high may result in insufficient labels being acquired, while setting the threshold too low may affect the model training quality, the label quality policy indicator reflects the data subscriber's (NWDAF) demand for sample data. This enables the LMF to adjust the data acquisition or data processing method based on the label quality policy indicator, thereby allowing the data subscriber to acquire sample data that meets its requirements.

[0192] Optionally, the label quality strategy indication is an indication of adjusting the relevant strategy for acquiring sample data, or the label quality strategy indication includes one or more indications for a label quality threshold (first threshold).

[0193] In one alternative implementation, the first request includes a requested number for data measurements (or a requested number for data samples), indicating that the number of samples returned is N, where N is a positive integer greater than or equal to 1. For example, N is 100, which represents either a request for first sample data comprising 100 sample data points, or a request for 100 first sample data points.

[0194] Optionally, the network data analysis function network element enables the location management function network element to specify the number N of sample data requested by the first request information through pre-set, pre-defined, protocol, or pre-contact information transmission. Therefore, the first sample data returned by the location management function network element includes N sample data and the tag corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. Optionally, the pre-contact information includes information before the network data analysis function network element sends and receives the first request to the location management function network element. In this embodiment, the first sample data returned by the location management function network element needs to meet the requirements of the tag quality policy indication and the quantity requirement N.

[0195] In one alternative implementation, the first request includes a first threshold, which indicates the return of sample data corresponding to labels whose label quality meets the first threshold. It should be understood that the first threshold is a limit for label quality indication.

[0196] Optionally, the first threshold may include a label quality threshold; for example, the first threshold may be a label quality threshold.

[0197] For example, the first threshold is 70, which represents the sample data for which the first request requests a tag quality greater than or equal to the first threshold (70).

[0198] Location management network elements can filter out tags that meet the first threshold requirement and the tag quality policy indication based on tag quality indicators, a first threshold for the tag, and tag quality policy indicators. It should be understood that the filtered data also includes sample data corresponding to the tags.

[0199] In one alternative implementation, the label quality policy indication includes one or more of the following:

[0200] Indicator 1: Highest quality of label. The highest quality of label indicator is used to indicate the sample data corresponding to the label with the highest quality.

[0201] Optionally, the highest quality indicator is used to indicate the sample data corresponding to the N labels with the highest returned label quality. It should be understood that the highest quality indicator does not need to indicate a specific first threshold, nor does it need to meet the requirements of a first threshold. Instead, it indicates the N labels with the highest returned label quality, along with their corresponding sample data. The term "highest label quality" can be understood as either a relatively high value corresponding to the label quality indicator, or a list of label quality indicators from high to low.

[0202] For example, if the first threshold is 70, and the requested first sample data should include 100 samples, but only 60 samples meet the first threshold, then a situation arises where meeting the first threshold doesn't meet the quantity requirement, and vice versa. In this case, if the label quality policy indication in the first request includes a highest quality indicator, then the request is for high-quality sample data that meets the quantity requirement. Accordingly, the obtained first sample data may include the top N samples sorted by label quality.

[0203] Optionally, if the label quality strategy indication includes indication 1, the highest quality indication, the first request may also include a sample quantity indication.

[0204] Optionally, when the tag quality policy indication includes indication 1 and the highest quality indication, the first request does not include the sample quantity indication. The location management function network element can determine the number of sample data in the first sample data by the number N of sample data indicated by the transmission of pre-set, pre-defined, protocol or pre-information.

[0205] It should be noted that, in the case where the tag quality policy indication includes indication 1, the first request may or may not include the sample quantity indication, and the process by which the location management function network element generates the corresponding first sample data will be explained in detail in subsequent steps, and will not be elaborated here.

[0206] Indicator 2: Label quality sorting indicator. The label quality sorting indicator is used to indicate how the sample data should be sorted according to the label quality indicator.

[0207] Optionally, Instruction 2 can be used alone to instruct the location management function network element to return the sorted first sample data. For example, if there is no quantity requirement, the location management function network element will sort and return all collected sample data according to the instruction. All collected sample data by the location management function network element can also be referred to as the second sample data.

[0208] Considering different use cases, the quality sorting indicator can be used to indicate sorting by label quality indicator from high to low, or to indicate sorting by label quality indicator from low to high.

[0209] Optionally, if the label quality strategy indication includes indication 2 and the quality ranking indication, the first request may or may not include a sample quantity indication.

[0210] Indication 3: Priority indication. The priority indication indicates whether the quantity requirement or the first threshold requirement should be met first. Meeting the quantity requirement includes meeting the requirement indicated by the sample quantity indication. It should be understood that the priority indication can be used in conjunction with the sample quantity indication and the first threshold, specifically to indicate the return of sample data that meets the requirement corresponding to the first priority.

[0211] Optionally, meeting the quantity requirement also includes meeting the number N of sample data indicated by the transmission of pre-set, pre-defined, protocol, or pre-construction information.

[0212] Optionally, the first priority indicator is specifically used to indicate the priority of the sample quantity indicator and the priority of the first threshold. The priority of the sample quantity indicator and the priority of the first threshold are not equal.

[0213] It should be noted that, in cases where the label quality policy indication includes indication 3 and the first priority indication, the first request may or may not include the sample quantity indication.

[0214] Optionally, if the label quality strategy indication includes indication 3 and a first priority indication, the first request may include a sample quantity indication and a first threshold.

[0215] For example, in the case where the label quality policy indication includes indication 3 and the first priority indication, the first request may include a sample quantity indication and a first threshold.

[0216] In cases where the label quality strategy indication includes indication 3, a first priority indication, and the first priority indication is used to indicate priority in meeting quantity requirements, the first request may include a sample quantity indication. It should be understood that in cases where the first request does not include a first threshold, the first threshold may be preset or predefined.

[0217] In the case where the label quality policy indication includes indication 3, a first priority indication, and the first priority indication is used to indicate that a first threshold is met first, the first request may include a first threshold.

[0218] Indicator 4: Label Quality Deviation Indicator (quality threshold of label with Acceptable deviation). This indicator shows the permissible deviation between the label quality indicator of the returned sample data and a first threshold. The permissible deviation can be understood as the fluctuation range of the first threshold. For example, if the permissible deviation is 10 and the first threshold is 70, then it means that the lowest permissible label quality indicator returned is 60. For example, the first sample data returned after sending the label quality deviation indicator includes sample data with a label quality indicator as low as 60.

[0219] Optionally, if the label quality policy indication includes indication 4, and the label quality deviation indication is included, the first request includes a first threshold.

[0220] Instruction 5: Quality range of label. The quality range of label is used to indicate the sample data corresponding to labels whose quality indicators are within the quality range of label. The first sample data includes the sample data whose quality indicators are within the quality range of label.

[0221] Optionally, if the label quality strategy indication includes indication 5, and the label quality range is specified, the first request may include a sample quantity indication.

[0222] Instruction 6: Second priority instruction (multiple quality threshold with priority). The second priority instruction is used to indicate the priority of multiple first thresholds, and to indicate the return of sample data corresponding to the labels that meet the requirements of the first threshold corresponding to the label quality instruction, in descending order of priority of the multiple first thresholds.

[0223] Optionally, if the label quality policy indication includes indication 6, the second priority indication, the first request includes multiple first thresholds. The second priority indication specifically indicates the priority of the multiple first thresholds included in the first request.

[0224] Optionally, if the label quality strategy indication includes indication 6 and the second priority indication, the first request includes multiple first thresholds and sample number indications.

[0225] For example, the second priority indicator specifically indicates (quality threshold = 90, priority = high), (quality threshold = 80, priority = medium), and (quality threshold = 75, priority = low), which means that the priority corresponding to the first threshold 90 is high, the priority corresponding to the first threshold 80 is medium, and the priority corresponding to the first threshold 70 is low.

[0226] Indication 7: Third Priority Indication (PRU first indication) The third priority indication is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first.

[0227] Optionally, the third priority indicator is also used to indicate that if the number of samples corresponding to the PRU is insufficient, sample data (including samples corresponding to non-PRU UEs) should be returned based on other parameters indicated by the label quality policy.

[0228] Optionally, the LMF can also determine other sample data through pre-configuration or a custom method. For example, the pre-configuration method may refer to sorting other sample data (samples not corresponding to the PRU UE) according to label quality and then selecting the label with the highest quality. The custom method may refer to the location management function network element deciding on its own method to determine other sample data.

[0229] It should be noted that a PRU is a capability of a terminal device (or a special type of terminal device). The location of the PRU is known (and its location accuracy is generally considered high). Positioning measurements can be performed on the PRU to correct the positions of other devices based on the positioning measurement data and the PRU's known location. Alternatively, AI / ML positioning models can be trained based on the PRU's positioning measurement data and its known location. The relationship between the PRU and other network elements includes: 1. The terminal device can support PRU functions, and the terminal device can associate PRU information with one or more LMFs through a PRU association process. The PRU information associated with the LMF includes one or more of the following: PRU Positioning Capabilities; PRU Location information; PRU ON / OFF state: the ON / OFF state of the PRU, indicating whether the PRU function in the terminal device is enabled. 2. When LMF and PRU information are associated, the LMF can update its NF profile to the NRF, that is, store / update the "PRU existence indication" of the Tracking Area Identifier Level (TAI Level) in the NF profile. This allows the AMF / other LMFs to discover LMFs that support PRUs from the NRF based on this information. 3. If the terminal device supports PRU capability, it can also store LCS subscription data in the UDM. The subscription data includes a "PRU indication," which indicates that the UE can act as a PRU.

[0230] It should be noted that the numerical values ​​and sample numbers of the label quality indicators mentioned above are only examples. The specific data that may be included in the first sample data returned after the label quality policy indicator is sent will be explained in subsequent steps and will not be repeated here.

[0231] As can be seen from the above examples, the label quality strategy indication can also be combined with the sample quantity indication and / or the first threshold. This means that there are cases where the above-mentioned indications 1 to 7 are combined with the sample quantity indication and / or the first threshold. It should be understood that the above-mentioned cases where the label quality strategy indication can be combined with the sample quantity indication and / or the first threshold are only illustrative examples. The above does not illustrate possible situations, but does not mean that they are impossible. In practical applications, any indication in the label quality strategy indication may be combined with the sample quantity indication and / or the first threshold. This application does not limit this.

[0232] It should be understood that instructions 1 to 7 above can be combined arbitrarily, and this application does not limit the content of the label quality strategy instructions.

[0233] To illustrate the combination of instructions, Instruction 1 and Instruction 2 are combined. Accordingly, the label quality policy instruction includes a highest quality instruction and a quality ranking instruction. Then, the label quality policy instruction is used to instruct the return of sample data according to the requirements of the highest quality instruction and the quality ranking instruction.

[0234] When Indicator 1 and Indicator 7 are combined, the corresponding label quality strategy indication includes the highest quality indication and the third priority indication. The label quality strategy indication can be used to indicate that the sample data corresponding to the positioning reference unit (PRU) is returned first, and other sample data besides the sample data corresponding to the PRU are returned according to the highest quality indication, and the sample data corresponding to the label with the highest label quality indication is returned.

[0235] By combining Indicator 2 and Indicator 4, the label quality strategy indicator includes a quality ranking indicator and a label quality deviation indicator. The label quality strategy indicator can be used to indicate that sample data that meets the first threshold and sample data within the allowable deviation range will be ranked according to the label quality indicator.

[0236] By combining Instruction 3 and Instruction 4, the label quality strategy instruction includes a first priority instruction and a label quality deviation instruction. The label quality strategy instruction can then be used to indicate priority in meeting quantity requirements, priority in meeting a first threshold requirement, or priority in meeting both the first threshold and the label quality deviation instruction. For example, in the case where the label quality strategy instruction prioritizes meeting both the first threshold and the label quality deviation instruction, the first sample data requested by the first request may include sample data that does not meet the first threshold requirement but meets the permissible deviation requirement of the label quality deviation instruction.

[0237] Optionally, if a data subscription request is sent to the location management function network element before step S303, step S303 can also be a data unsubscription request.

[0238] Step S304: The location management function network element responds to the first request and obtains the first sample data.

[0239] Optionally, the sample data collected by the location management function network element includes samples and corresponding tags, as well as tag quality indicators. The location management function network element can filter out tags that at least meet the requirements of the tag quality policy indicator based on the tag quality indicator and the tag quality policy indicator, thereby obtaining the sample data corresponding to the tag.

[0240] Optionally, the location management function network element collects and processes first sample data based on the tag quality policy indication, and the first sample data at least meets the requirements of the tag quality policy indication.

[0241] Optionally, the location management function network element responds to the first request to collect / acquire sample data and obtain second sample data, the second sample data including the first sample data, the second sample data being unfiltered / screened sample data.

[0242] Furthermore, in response to the first request / label quality policy indication in the first request, the first sample data in the second sample data is determined.

[0243] It should be understood that this application does not restrict the method by which the location management function network element obtains the first sample data. It is possible for the location management function network element to directly obtain the first sample data, or to obtain the first sample data by performing relevant operations (such as filtering, sorting, etc.) after obtaining all the sample data that can be collected (the second sample data).

[0244] In one optional implementation, the tag quality policy indication includes indication 1, the highest quality indication. In step S304, the location management function network element may perform the following operations:

[0245] Based on the highest quality indicator, the second sample data is filtered to obtain the first sample data, which includes the sample data corresponding to the N tags with the highest tag quality.

[0246] Optionally, in step S304, the location management function network element may also perform the following operations:

[0247] Based on the highest quality indicator, the second sample data is sorted to obtain the third sample data, which includes the first sample data. The first N items in the third sample data are determined to be the first sample data. Please refer to Figure 4 for details. Figure 4 is a schematic diagram of the first sample data provided in an embodiment of this application. The shaded area in Figure 4 represents the first sample data, and the rectangle containing the shaded area represents the second sample data, which includes the first sample data. It should be understood that the sorting by label quality indicator from high to low shown in Figure 4 is only for the convenience of illustrating the first sample data and does not mean that the second sample data is the sorted sample data (sorted by label quality indicator from high to low).

[0248] It should be understood that N in this embodiment may be the N indicated by the sample number indication included in the first request, where N is a positive integer greater than or equal to 1. Therefore, in the embodiment where the first sample data includes N sample data, N may be the N indicated by the sample number indication included in the first request. That is, in the relevant embodiment, the first request includes at least a sample number indication.

[0249] In one alternative implementation, the number of first sample data is predefined by the protocol or included in a preamble message, which indicates a message preceding the first request. This means that the first request does not include a sample number indication, but the number of sample data returned for the first sample data is N, where N may or may not be equal to the N in the sample number indication.

[0250] The first sample data in this embodiment will be described by way of example.

[0251] Taking N=100 as an example, the first sample data may include 100 sample data whose label quality is higher than other sample data after being filtered from high to low label quality. Other sample data is used to indicate other sample data in the second sample data besides the 100 sample data in the first sample data.

[0252] In this implementation, the first sample data includes the sample data corresponding to the N labels with the highest label quality after sorting.

[0253] In an optional implementation, the tag quality policy indication includes indication 2 and a quality ranking indication, which indicates that the sample data should be ranked according to the tag quality indication. Optionally, the first request does not include a sample quantity indication, and the first sample data includes all sample data ranked according to the tag quality indication. In step S304, the location management function network element may perform the following operations:

[0254] Based on the quality ranking indicator, the second sample data is sorted to obtain the first sample data.

[0255] The first sample data obtained from the above operations includes all sample data sorted according to the label quality indication (second sample data).

[0256] Optionally, if the first request includes a sample quantity indication, or if the location management function network element has pre-set, pre-defined, or has received a relevant quantity indication in advance, the location management function network element may also perform the following operations in step S304:

[0257] Based on the quality ranking indicator, the second sample data is sorted and filtered to obtain the first sample data.

[0258] The first sample data obtained by the above operation includes N sample data sorted according to the label quality indicator. The first sample data corresponding to this operation can also be seen in the first sample data shown in Figure 4.

[0259] Considering different use cases, the quality sorting indicator can be used to indicate sorting by label quality from high to low, or to indicate sorting by label quality from low to high.

[0260] Accordingly, the aforementioned N sample data are either N sample data sorted from high to low label quality, or N sample data sorted from low to high label quality.

[0261] Optionally, the label quality strategy indication includes a highest quality indication and a quality ranking indication. The first sample data includes sample data corresponding to the N labels with the highest label quality, which are ranked according to the label quality indication.

[0262] In one optional implementation, the label quality strategy indication includes indication 3, a first priority indication, which indicates whether to prioritize meeting quantity requirements or a first threshold requirement, wherein meeting quantity requirements includes meeting the requirement of the sample quantity indication.

[0263] It should be noted that, in the case where the label quality policy indication includes indication 3 and the first priority indication, the first request may or may not include the sample quantity indication, and the first request may or may not include the first threshold.

[0264] For example, when the label quality policy indication includes indication 3 and a first priority indication, the first request may include a sample quantity indication and a first threshold. When the label quality policy indication includes indication 3 and a first priority indication, and the first priority indication is used to indicate that quantity requirements are prioritized, the first request may include a sample quantity indication. When the label quality policy indication includes indication 3 and a first priority indication, and the first priority indication is used to indicate that a first threshold is prioritized, the first request may include a first threshold.

[0265] The following example illustrates the label quality policy indication, which includes indication 3, a first priority indication, a first request including a sample quantity indication, and a first threshold.

[0266] In cases where the quantity requirement is met, including the requirement of meeting the sample quantity indication, or where the quantity requirement is specifically the requirement of meeting the sample quantity indication, the first priority indication may be used in combination with the sample quantity indication and the first threshold, specifically to indicate the return of sample data that meets the requirement corresponding to the first priority.

[0267] In one optional implementation, when the first priority indicator is used to indicate that the requirement of prioritizing the sample quantity indicator is met, the first sample data includes N sample data. Optionally, when the first priority indicator is used to indicate that the requirement of prioritizing the sample quantity indicator is met, the first sample data includes N sample data. Considering that the label quality corresponding to the N sample data may meet the first threshold requirement, or may not meet the first threshold requirement, or may partially meet the first threshold requirement and the remaining part does not meet the first threshold requirement, the aforementioned N sample data includes Y sample data whose label quality meets the first threshold requirement, where Y is a positive integer greater than or equal to 0 and less than or equal to N.

[0268] The following example illustrates the case of N sample data in this embodiment. When the first priority indicator is used to indicate that the requirement of satisfying the sample quantity indicator should be prioritized, the location management function network element may perform the following operations:

[0269] Y1 sample data are selected based on the first threshold, where Y1 is a positive integer greater than or equal to 0;

[0270] If the number of Y1 sample data meets the requirement of the sample number indication, then N sample data among the Y1 sample data are determined as the first sample data.

[0271] It should be understood that if the number of Y1 sample data satisfies the requirement of the sample quantity indication, such as Y1 being greater than or equal to N, then N sample data are selected from the Y1 sample data as the first sample data. Optionally, the above selection process can be a selection process similar to indication 1 / indication 2, such as sorting all sample data (second sample data) according to the label quality of the sample data from largest to smallest, and selecting Y1 sample data that meet the first threshold requirement; the above determination process can also be a process similar to the selection / sorting process similar to indication 1 / indication 2, such as sorting the Y1 sample data according to the label quality of the sample data from largest to smallest, and selecting the first N sample data as the first sample data.

[0272] Considering that the number of sample data meeting the first threshold requirement may not meet the sample quantity requirement, when the first priority indicator is used to indicate that the sample quantity indicator requirement should be met first, the location management function network element may perform the following operations:

[0273] Y2 sample data are selected based on the first threshold, where Y2 is a positive integer greater than or equal to 0;

[0274] If the number of Y2 sample data does not meet the sample size requirement, select N-Y2 sample data.

[0275] Based on the above Y2 sample data and N - Y2 sample data, the first sample data is obtained, and the first sample data includes N sample data.

[0276] It should be understood that the number of Y2 sample data not meeting the requirements indicated by the sample quantity can mean Y2 < N. Therefore, if the sample quantity indication is to be met, N - Y2 sample data needs to be supplemented. Optionally, supplementing / screening N - Y2 sample data can also be a screening / sorting process similar to indication 1 / indication 2. For details, please refer to the above text and will not be elaborated here.

[0277] Please refer to FIG. 5. FIG. 5 is a schematic diagram of another type of first sample data provided by an embodiment of the present application. FIG. 5 shows that when the first priority indication is used to indicate that the requirement of the sample quantity indication is to be preferentially met, among the N sample data included in the first sample data, some meet the requirement of the first threshold, and the remaining part does not meet the requirement of the first threshold. The shaded part in it is the first sample data. In FIG. 5, the Y sample data above the first threshold are the sample data in the first sample data that meet the requirement of the first threshold, and the part (N - Y) below the first threshold is the sample data in the first sample data that do not meet the requirement of the first threshold.

[0278] In an optional implementation manner, when the first priority indication is used to indicate that the requirement of the first threshold is to be preferentially met, the first sample data includes X sample data that meet the requirement of the first threshold, and X is a positive integer less than or equal to N. Please refer to FIG. 6. FIG. 6 is a schematic diagram of another type of first sample data provided by an embodiment of the present application. Part (a) in FIG. 6 shows a possible implementation of the first sample data when the first priority indication is used to indicate that the requirement of the first threshold is to be preferentially met.

[0279] Exemplarily, when the first priority indication is used to indicate that the requirement of the first threshold is to be preferentially met, there may be a situation where the number of sample data meeting the requirement of the first threshold exceeds the number indicated by the sample quantity. For example, there are T sample data whose labels meet the requirement of the first threshold, and T is a positive integer greater than N. In the case of exceeding, the T sample data that meet the requirement of the first threshold also need to meet the requirement of the sample quantity indication. Therefore, in this case, the first sample data includes N sample data that meet the requirement of the first threshold. For details, please refer to part (b) in FIG. 6. Part (b) in FIG. 6 shows another possible implementation of the first sample data when the first priority indication is used to indicate that the requirement of the first threshold is to be preferentially met.

[0280] Of course, without the requirement / quantity requirement of the sample quantity indication, the first sample data may include T sample data that meet the requirement of the first threshold.

[0281] In other words, if the first priority indicator is used to indicate that the number of samples is prioritized, then when the number of samples that meet the quality threshold is insufficient, the location management function network element will supplement the samples that do not meet the quality threshold to make up the number of samples (for example, the location management function network element can supplement the samples according to the label quality from high to low); if the first priority indicator is used to indicate that the quality threshold is prioritized, then only samples whose label quality meets the quality threshold will be fed back, and the sample quantity requirement can be ignored (applicable to scenarios where the network data analysis function network element is not sensitive to the number of samples, for example, the network data analysis function network element can also obtain labels from other data sources).

[0282] In an optional implementation, the first request further includes a first threshold, and the tag quality policy indication includes indication 4, a tag quality deviation indication, which indicates the allowable deviation between the quality of the tag corresponding to the returned sample data and the first threshold. In step S304, the location management function network element may perform the following operations:

[0283] Based on the first threshold and the label quality deviation indication, the second sample data is sorted to obtain the first sample data. The first sample data includes sample data that meets the first threshold and / or sample data that meets the label quality corresponding to the allowable deviation level.

[0284] For example, if the allowable deviation level is 10 and the first threshold is 70, then this means that the minimum allowable tag quality indication is 60. For example, the first sample data returned after sending the tag quality deviation indication includes sample data with a tag quality indication of at least 60. Please refer to Figure 7, which is a schematic diagram of another type of first sample data provided in an embodiment of this application. The first sample data mainly illustrated in Figure 7 includes Q sample data whose tag quality indications meet the first threshold, and NQ sample data whose tag quality indications meet the allowable deviation level requirement, where Q is a positive integer greater than or equal to 0. In the implementation corresponding to Figure 7, Q is less than or equal to N. When Q equals N, the first sample data corresponding to Figure 7 should only include Q or N sample data whose tag quality indications meet the first threshold. In other words, when the network data analysis function element indicates N (including indicating N through the number of samples), or the location management function element is configured with N (including a predefined, pre-set quantity requirement of N), there is a possibility that Q is less than or equal to N.

[0285] It should be understood that the second sample data illustrated in Figure 7 mainly represents sample data where at least NQ labels meet the allowable deviation requirements. In another possible implementation, the second sample data may not contain NQ labels that meet the allowable deviation requirements; the number of samples meeting the allowable deviation requirements may be less than NQ. In the case of fewer than NQ samples, indicator 4 can be combined with indicators 1 and 2 to supplement the missing portion, or it can be combined with indicator 3 to enable the first sample data to include only sample data that meets the first threshold and sample data with label quality corresponding to the allowable deviation. Alternatively, it can supplement the missing portion based on the quantity priority corresponding to indicator 3. Here, the missing portion can also be combined with indicator 1 or indicator 2 to select relatively high-quality sample data to supplement the missing portion.

[0286] Based on the above description, the label quality strategy instructions may include instructions 4 and 1, or instructions 4 and 2, or instructions 4 and 3, or instructions 4, 3 and 1, or instructions 4, 3 and 2.

[0287] Considering that the allowable deviation mainly changes the lower limit of tag quality, and the purpose of acquiring data in this application embodiment is mainly to obtain excellent and high-quality data, in an optional implementation, sample data that meets the first threshold requirement is acquired first. If the sample data that meets the first threshold requirement does not meet the requirement for the number of samples, then sample data within the allowable deviation range is considered. In step S304, the location management function network element may perform the following operations:

[0288] Identify Q sample data points from the second sample data that meet the first threshold requirement;

[0289] When Q is less than N, NQ sample data that meet the allowable deviation level / label quality deviation indication requirements are determined to obtain the first sample data. The first sample data includes Q sample data that meet the first threshold requirement and NQ sample data that meet the allowable deviation level / label quality deviation indication requirements. In this case, Q is a positive integer greater than or equal to 0 and less than N.

[0290] When Q is greater than or equal to N, N sample data points out of the Q sample data points that meet the first threshold requirement are determined as the first sample data points. Accordingly, the first sample data points include the N sample data points that meet the first threshold requirement. In this case, Q is a positive integer greater than or equal to N.

[0291] It should be understood that in this implementation, the first request may include a sample quantity indication and a first threshold.

[0292] In this embodiment, the label quality deviation indicator / label quality strategy indicator is specifically used to indicate the return of sample data that meets the first threshold and / or allowable deviation requirements. If there is a quantity requirement, such as 100 samples, the allowable deviation is 10, the first threshold is 70, and there are 70 sample data that meet the first threshold, then the indicated sample data may include 70 sample data that meet the first threshold and 30 sample data that meet the allowable deviation. For example, the 30 sample data that meet the allowable deviation can be used to indicate 30 sample data with a label quality indicator of 60, or 30 sample data with a label quality indicator between 60 and 70.

[0293] Of course, there may be a situation where the number of sample data that meet the above allowable deviation requirements, other than the sample data that meet the first threshold requirement, does not meet the quantity requirement. For example, if there are 70 sample data that meet the first threshold and N is 100, then 30 more sample data are needed. However, if there are fewer than 30 sample data that meet the first threshold requirement, then the first sample data may be returned preferentially for the sample data that meets both the first threshold requirement and the allowable deviation requirement.

[0294] It should be noted that when the label quality indicator is a quality value, the allowable deviation is a specific value similar to the quality value, such as the allowable deviation of 10 mentioned above. However, in other possible implementations, such as when the quality value is a high, medium, or low grade evaluation, the allowable deviation may also be data related to the high, medium, or low grades, or an indication that can fluctuate by one or more grades. For example, the label quality deviation indicator is specifically used to indicate sample data that can return one or more grades of label quality indicator below a first threshold.

[0295] In one alternative implementation, the label quality strategy indication includes indication 5, a label quality range, which indicates the return of sample data corresponding to labels whose label quality indication falls within the label quality range.

[0296] In step S304, the location management function network element may perform the following operations:

[0297] Based on the label quality range, the second sample data is filtered to obtain the first sample data, which includes sample data whose label quality indicators are within the label quality range.

[0298] For example, if the label quality range indicates [70, 90], then the operation of filtering the second sample data based on the label quality range to obtain the first sample data includes:

[0299] The sample data with label quality between 70 and 90 from the second sample data are selected as the first sample data. Please refer to Figure 8 for the first sample data, which is a schematic diagram of another type of first sample data provided in an embodiment of this application.

[0300] Optionally, in the case where the label quality strategy indication includes indication 5 and the label quality range, the first request may include a sample quantity indication, and correspondingly, the first sample data includes sample data corresponding to N labels whose label quality indications are within the label quality range.

[0301] It should be noted that in implementations where there is a required number of sample data points in the first set of sample data to be returned, these can be combined with Indication 1 and / or Indication 2 to filter out higher quality sample data. For example, when the first request includes a sample quantity indication, the label quality policy indication includes a label quality range and Indication 1, the highest quality indication.

[0302] It should be understood that the above-mentioned instructions 1, 2, 3, 4, 5, 6, and 7 are merely pronouns used to represent the corresponding instruction messages.

[0303] In one optional implementation, the first request includes a plurality of first thresholds, and the label quality policy indication includes indication 6, a second priority indication, the second priority indication being used to indicate the priority of the plurality of first thresholds, and to indicate that sample data corresponding to labels that meet the requirements of the first thresholds corresponding to the label quality indication are returned in descending order of priority of the plurality of first thresholds.

[0304] In step S304, the location management function network element may perform the following operations:

[0305] Based on multiple first thresholds and second priority indicators, the second sample data is filtered to obtain the first sample data. The first sample data includes sample data whose label quality indicators meet the second threshold requirement and the second priority indicator requirement among the multiple first thresholds.

[0306] It should be understood that the second priority indication includes priorities corresponding to a plurality of first thresholds, and the aforementioned second threshold requirement can be any one or more of the plurality of first thresholds. For example, the second threshold requirement specifically refers to which one or more of the plurality of first thresholds are related to the quantity indicated by the sample quantity indication; in this embodiment, the first request may also include the sample quantity indication.

[0307] For example, the location management function network element prioritizes selecting samples based on the first threshold corresponding to the highest priority. If the number of samples does not meet the requirement, it supplements the sample selection with samples that meet the first threshold corresponding to lower priorities. For instance, the second priority indication in the tag quality policy instruction sent by the network data analysis function network element specifically indicates (quality threshold = 90, priority = high), (quality threshold = 80, priority = medium), and (quality threshold = 75, priority = low). Among these, the first threshold (quality threshold = 90) has a high priority, the first threshold (quality threshold = 80) has a medium priority, and the first threshold (quality threshold = 75) has a low priority. The location management function network element prioritizes selecting samples according to quality threshold = 90. When the number of samples does not meet the requirement, the location management function network element then selects samples according to quality threshold = 80. If the number of samples meets the requirement at this point, the selected samples are fed back. If the number of samples still does not meet the requirement, samples are then selected according to quality threshold = 75. If the number of samples meets the requirement at this point, the selected samples are fed back.

[0308] If the number of samples still does not meet the requirements, the location management function network element can send feedback to the network data analysis function network element indicating the selected samples or a failure.

[0309] In one alternative implementation, the tag quality strategy indication includes indication 7 and a third priority indication, which indicates that sample data corresponding to the positioning reference unit (PRU) should be returned first.

[0310] Optionally, the sample data corresponding to the PRU includes the measurement data of the PRU and the location of the PRU.

[0311] In step S304, the location management function network element may perform the following operations:

[0312] Based on the third priority instruction, at least the sample data corresponding to the PRU is obtained to obtain the first sample data, or...

[0313] Based on the third priority instruction, obtain the sample data corresponding to the PRU and the sample data corresponding to the non-PRU to obtain the first sample data.

[0314] The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

[0315] In this embodiment, the first request may include a sample quantity indication, or at least a quantity requirement. For details regarding the quantity requirement, please refer to the above description, which will not be repeated here.

[0316] Optionally, the first sample data also includes sample data corresponding to NM non-PRUs, and the sample data corresponding to NM non-PRUs meet the requirements of the label quality policy indication.

[0317] This means that in this implementation, the first sample data may include sample data corresponding to N PRUs, or it may include sample data corresponding to M PRUs and NM sample data corresponding to non-PRUs.

[0318] For example, when the network data analysis function element indicates the third priority indication (PRU first indication) in the tag quality policy indication, the location management function element first obtains the samples corresponding to the PRU. If the number of samples corresponding to the PRU is sufficient, the location management function element feeds back the PRU samples to the network data analysis function element. If the number of samples corresponding to the PRU is insufficient, the location management function element supplements a sufficient number of samples based on the first threshold or other information and feeds them back to the network data analysis function element. For example, the location management function element can filter out sample data that does not correspond to the PRU based on the quality threshold, or the location management function element can filter out sample data that does not correspond to the PRU with the highest tag quality based on the highest quality indication.

[0319] Considering that in this implementation, there may be cases where sample data corresponding to non-PRUs are returned, in order to further optimize the sample data and obtain relatively higher quality sample data, the label quality strategy indication may also include other indications, such as at least one of the following: highest quality indication, quality ranking indication, first priority indication, second priority indication, label quality deviation indication, and label quality range indication.

[0320] In one optional implementation, the tag quality policy indication includes a third priority indication and a highest quality indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the non-PRU sample data is processed according to the requirements of the highest quality indication to obtain non-PRU sample data that meets the requirements of the highest quality indication and then returned. That is, the first sample data may include sample data corresponding to the PRU and non-PRU sample data that meets the requirements of the highest quality indication.

[0321] It should be noted that the possible implementation of sample data corresponding to non-PRUs that meet the requirements of the highest quality indication adopts a similar operation to the aforementioned highest quality indication. For details, please refer to the possible implementation of the first sample data related to the highest quality indication mentioned above. It will not be repeated here. The possible implementation of other label quality policy indications is the same.

[0322] In one optional implementation, the tag quality policy indication includes a third priority indication and a quality ranking indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the quality ranking indication to obtain sample data corresponding to non-PRUs that meets the requirements of the quality ranking indication and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meet the requirements of the quality ranking indication.

[0323] In one optional implementation, the tag quality policy indication includes a third priority indication, a highest quality indication, and a quality ranking indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the highest quality indication and the quality ranking indication to obtain sample data corresponding to non-PRUs that meets the requirements of the highest quality indication and the quality ranking indication, and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meets the requirements of the highest quality indication and the quality ranking indication.

[0324] In one optional implementation, the tag quality policy indication includes a third priority indication and a first priority indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the first priority indication to obtain sample data corresponding to non-PRUs that meets the requirements of the first priority indication and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meet the requirements of the first priority indication.

[0325] In one optional implementation, the tag quality policy indication includes a third priority indication and a second priority indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to a non-PRU, the non-PRU sample data is processed according to the requirements of the second priority indication to obtain non-PRU sample data that meets the requirements of the second priority indication and then returned. That is, the first sample data may include sample data corresponding to the PRU and non-PRU sample data that meets the requirements of the second priority indication.

[0326] In one optional implementation, the tag quality policy indication includes a third priority indication and a tag quality deviation indication. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the tag quality deviation indication to obtain sample data corresponding to non-PRUs that meets the requirements of the tag quality deviation indication and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meets the requirements of the tag quality deviation indication.

[0327] In one optional implementation, the tag quality policy indication includes a third priority indication and a tag quality range. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the tag quality range to obtain sample data corresponding to non-PRUs that meets the requirements of the tag quality range and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meet the requirements of the tag quality range.

[0328] In one optional implementation, the tag quality policy indication includes a third priority indication, and the first request includes a first threshold. This means that the location management function network element prioritizes returning sample data corresponding to the PRU. If it is also necessary to return sample data corresponding to non-PRUs, the sample data corresponding to non-PRUs is processed according to the requirements of the first threshold to obtain sample data corresponding to non-PRUs that meets the requirements of the first threshold and then returned. That is, the first sample data may include sample data corresponding to the PRU and sample data corresponding to non-PRUs that meet the tag quality range requirements.

[0329] Step S305: The location management function network element sends a first response to the network data analysis function network element. Correspondingly, the network data analysis function network element receives the first response from the location management function network element.

[0330] The first response includes first sample data, which is used for model training or model performance monitoring of the AI ​​localization model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data at least meets the requirements of the label quality policy indication mentioned above.

[0331] Optionally, the location management function network element sends the first response / first sample data to the network data analysis function network element through service operations such as LMF data exposure notification (Nlmf_DataExposure_Notify).

[0332] Optionally, if the first request includes a sample quantity indication and / or a time window for sample data, and the location management function network element is unable to provide the requested sample quantity or sample data within the specified time window (e.g., the RAN / UE load is high within the specified time window, making data collection impossible), the location management function network element may return a cause code, which indicates the reason why the requirements (quantity requirement and / or time requirement) cannot be met.

[0333] It should be noted that the first sample data involved in step S305 can be any of the first sample data in the aforementioned embodiments.

[0334] It should be noted that the numerical values ​​and sample quantities of all label quality indicators involved in the embodiments of this application are merely examples and are not intended to limit the embodiments of this application.

[0335] This application's embodiments, through sophisticated data acquisition strategies and control mechanisms, achieve end-to-end optimization from data request to response, ensuring both the quantity and quality of data while improving the efficiency and effectiveness of data processing and model training. This mechanism is of great significance for promoting the intelligent development of positioning services in 5G and future networks, and helps to build a more accurate, efficient, and reliable network positioning system.

[0336] The methods of the embodiments of this application have been described above. Below, some apparatuses for implementing the aforementioned methods are described. It should be understood that the division of units in the apparatuses provided in the embodiments of this application is only a logical functional division. In actual implementation, all or part of the units can be integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the apparatus can be implemented in the form of a processor calling software; for example, the apparatus includes a processor connected to a memory, the memory storing instructions, and the processor calling the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit of the apparatus. The processor is, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory is either internal to the apparatus or external to the apparatus. Alternatively, the units in the device can be implemented as hardware circuits. The functionality of some or all units can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the above units is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through a configuration file, thereby achieving the functionality of some or all of the above units. All units of the above device can be implemented entirely through processor-invoked software, entirely through hardware circuits, or partially through processor-invoked software with the remaining parts implemented through hardware circuits.

[0337] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships of hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), a Deep Learning Processing Unit (DPU), etc.

[0338] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0339] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together as a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0340] Several possible devices are listed below.

[0341] Please refer to Figure 9, which is a schematic diagram of a communication device provided in an embodiment of this application. Optionally, the communication device 90 can be an independent device, such as a terminal device like a personal computer, a network device, etc. Alternatively, the communication device 90 can also be a component in an independent device (such as a node), such as a chip or integrated circuit. The communication device 90 is used to implement the methods executed by the communication device in the aforementioned data acquisition methods, such as the methods executed by the communication device in any one or more embodiments shown in Figure 3.

[0342] As shown in Figure 9, the communication device 90 includes a communication unit 901 and a processing unit 902. The communication unit 901 is used to perform one or more operations such as acquiring, receiving, transmitting, establishing a connection, and responding, and further includes other operations for implementing the data acquisition method. The processing unit 902 is used to perform one or more operations such as processing, calculating, determining, and generating, and further includes other operations for implementing the data acquisition method.

[0343] For a related description, please refer to the description of the embodiment shown in Figure 3. It should be understood that during the execution of the relevant methods of the network data analysis function network element in the embodiment shown in Figure 3, the communication unit 901 may also be referred to as the first communication unit, and during the execution of the relevant methods of the location management function network element in the embodiment shown in Figure 3, the communication unit 901 may also be referred to as the second communication unit. The specific execution flow will not be described in detail here.

[0344] Please refer to Figure 10, which is a schematic diagram of another communication device provided in an embodiment of this application. The communication device 100 can be a standalone device, such as a personal computer or other terminal device, or a network device. The communication device 100 may include at least one processor 1001 and a communication interface 1002. Optionally, it may also include at least one memory 1003. Further optionally, it may also include a connection line 1004, wherein the processor 1001, the communication interface 1002, and / or the memory 1003 are connected via the connection line 1004, and / or communicate with each other via the connection line 1004 to transmit control signals and / or data signals.

[0345] in:

[0346] Processor 1001 is a module that performs arithmetic and / or logical operations, and may specifically include one or more of the following modules: filter, modem, power amplifier, low noise amplifier (LNA), baseband processor, radio frequency processor, radio frequency circuit, central processing unit (CPU), application processor (AP), microcontroller unit (MCU), electronic control unit (ECU), graphics processing unit (GPU), microprocessor unit (MPU), application specific integrated circuit (ASIC), image signal processor (ISP), digital signal processor (DSP), field programmable gate array (FPGA), complex programmable logic device (CPLD), or coprocessor, etc.

[0347] The communication interface 1002 can be used to provide information input or output to the at least one processor, or to receive signals sent from the outside and / or send signals to the outside.

[0348] For example, communication interface 1002 may include interface circuitry.

[0349] For example, the communication interface 1002 may include a wired link interface such as an Ethernet cable, or a wireless link interface (Wi-Fi, Bluetooth, general wireless transmission, vehicle short-range communication technology and other short-range wireless communication technologies, etc.).

[0350] Optionally, the communication interface 1002 may also include a radio frequency transmitter, an antenna, etc. When the communication interface 1002 includes an antenna, the number of antennas can be one or more.

[0351] As one possible design, if the communication device 100 is a standalone device, the communication interface 1002 may include a receiver and a transmitter. The receiver and transmitter may be the same component or different components. When the receiver and transmitter are the same component, this component may be referred to as a transceiver.

[0352] As another possible design, if the communication device 100 is a chip or circuit, the communication interface 1002 may include an input interface and an output interface. The input interface and the output interface may be the same interface or they may be different interfaces.

[0353] Alternatively, the functions of the communication interface 1002 can be implemented by a transceiver circuit or a dedicated transceiver chip.

[0354] The memory 1003 provides storage space, in which data such as the operating system and computer programs can be stored. The memory 1003 can be one or a combination of several of the following: random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0355] The functions and operations of each module or unit in the communication device 100 listed above are merely illustrative examples.

[0356] Each functional unit in the communication device 100 can be used to implement the method implemented by the communication device in the aforementioned data acquisition method, such as the method implemented by the communication device in the data acquisition method shown in FIG3.

[0357] Optionally, the processor 1001 may be a processor specifically designed to execute the aforementioned methods (for ease of distinction, referred to as a dedicated processor), or a processor that executes the aforementioned methods by calling a computer program (for ease of distinction, referred to as a dedicated processor). Optionally, at least one processor may include both dedicated processors and general-purpose processors.

[0358] Optionally, if the communication device 100 includes at least one memory 1003, and the processor 1001 implements the aforementioned data acquisition method by calling a computer program, the computer program may be stored in the memory 1003.

[0359] This application also provides a chip, which includes logic circuitry and a communication interface. The communication interface is used to receive or transmit signals; the logic circuitry is used to receive or transmit signals through the communication interface. The chip is used to implement the aforementioned data acquisition method, such as the data acquisition method shown in Figure 3.

[0360] This application also provides a computer-readable storage medium storing instructions that, when executed on at least one processor (or communication device), implement the aforementioned data acquisition method, such as the data acquisition method shown in FIG3.

[0361] This application also provides a computer program product, which includes computer instructions for implementing the aforementioned data acquisition method, such as the data acquisition method shown in Figure 3.

[0362] This application embodiment also provides a terminal, which includes the aforementioned communication device 90 or communication device 100.

[0363] In the description of this application, the terms “center,” “upper,” “lower,” “vertical,” “horizontal,” “inner,” “outer,” “left,” “side,” etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0364] In the embodiments of this application, the term "end" appearing in terms such as "one end", "the other end", "left end", "right end", "upper end", "lower end", and "connecting end" is not limited to end head, end point, or end face, but also includes a portion extending axially and / or radially from the end head, end point, or end face on the device or element to which the end head, end point, or end face belongs.

[0365] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0366] In this application, "at least one" in the embodiments refers to one or more items, and "more than one" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, (a and b), (a and c), (b and c), or (a and b and c), where a, b, and c can be single or multiple. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0367] Furthermore, unless otherwise stated, the use of ordinal numbers such as "first" and "second" in the embodiments of this application is for distinguishing multiple objects and is not for limiting the order, timing, priority, or importance of multiple objects. Similarly, terms like "first angle measurement data" and "second angle measurement data" are merely for the convenience of describing new parameters in different implementations and do not indicate differences in their execution operations, importance, data content, etc.

[0368] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

Claims

1. A data acquisition method, characterized in that, The method includes: Send a first request to the location management function network element. The first request is used to request first sample data. The first request includes a tag quality policy indication. The system receives a first response from the location management function network element. The first response includes the first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

2. The method according to claim 1, characterized in that, The first request also includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

3. The method according to claim 1 or 2, characterized in that, The label quality strategy indicator includes a highest quality indicator, which is used to indicate the sample data corresponding to the label with the highest label quality indicator. The first sample data includes sample data corresponding to the N labels with the highest label quality indicators.

4. The method according to any one of claims 1-3, characterized in that, The label quality strategy indication includes a quality ranking indication, which is used to indicate that the sample data should be ranked according to the label quality indication; The first sample data includes N sample data sorted according to the label quality indicator.

5. The method according to any one of claims 1-4, characterized in that, The first request further includes a first threshold, which is used to indicate the return of sample data whose label quality indicator meets the first threshold. The label quality policy indicator includes a first priority indicator, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indicator.

6. The method according to claim 5, characterized in that, When the first priority indicator is used to indicate that the quantity requirement is met first, the first sample data includes N sample data, and the N sample data includes Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N; When the first priority indicator is used to indicate that the requirement of the first threshold is met first, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

7. The method according to any one of claims 1-4, characterized in that, The first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

8. The method according to any one of claims 1-6, characterized in that, The label quality strategy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality is within the label quality range. The first sample data includes sample data whose label quality is indicated within the label quality range.

9. The method according to any one of claims 1-8, characterized in that, The first request includes multiple first thresholds, and the label quality policy indication includes a second priority indication. The second priority indication is used to indicate the priority of the multiple first thresholds and to indicate that sample data corresponding to the labels that meet the first threshold requirements of the label quality indication are returned in descending order of priority of the multiple first thresholds. The first sample data includes sample data that meet the second threshold requirements of the multiple first thresholds and the requirements of the second priority indication.

10. The method according to claim 1 or 2, characterized in that, The tag quality strategy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

11. A data acquisition method, characterized in that, The method includes: Receive a first request from a network data analysis function element, the first request being used to request first sample data, the first request including a tag quality policy indication; Send a first response to the network data analysis function network element. The first response includes the first sample data. The first sample data is used for model training or model performance monitoring of the artificial intelligence (AI) positioning model. The first sample data includes N sample data and a label corresponding to each of the N sample data, where N is a positive integer greater than or equal to 1. The first sample data meets the requirements of the label quality policy indication.

12. The method according to claim 11, characterized in that, The method further includes: In response to the first request, the first sample data is obtained.

13. The method according to claim 11 or 12, characterized in that, The step of responding to the first request and obtaining the first sample data includes: Obtain second sample data, which includes the first sample data; In response to the label quality policy indication included in the first request, the first sample data in the second sample data is determined.

14. The method according to any one of claims 11-13, characterized in that, The first request also includes a sample count indicator, which indicates that the number of returned samples is N, where N is a positive integer greater than or equal to 1.

15. The method according to any one of claims 11-14, characterized in that, The label quality strategy indicator includes a highest quality indicator, which is used to indicate the sample data corresponding to the label with the highest label quality indicator. The first sample data includes sample data corresponding to the N labels with the highest label quality indicators.

16. The method according to any one of claims 11-15, characterized in that, The label quality strategy indication includes a quality ranking indication, which is used to indicate that the sample data should be ranked according to the label quality indication; The first sample data includes N sample data sorted according to the label quality indicator.

17. The method according to any one of claims 11-16, characterized in that, The first request further includes a first threshold, which is used to indicate the sample data corresponding to the labels whose label quality meets the first threshold. The label quality strategy indication includes a first priority indication, which is used to indicate whether to prioritize meeting the quantity requirement or the requirement of the first threshold. Meeting the quantity requirement includes meeting the requirement of the sample quantity indication.

18. The method according to claim 17, characterized in that, When the first priority indicator is used to indicate that the requirement of the sample quantity indicator is met first, the first sample data includes N sample data, and the N sample data includes Y sample data whose label quality indicators meet the requirement of the first threshold, where Y is a positive integer greater than or equal to 0 and less than or equal to N; When the first priority indicator is used to indicate that the requirement of the first threshold is met first, the first sample data includes X sample data that meet the requirement of the first threshold, where X is a positive integer less than or equal to N.

19. The method according to any one of claims 11-16, characterized in that, The first request further includes a first threshold, and the label quality policy indication includes a label quality deviation indication, which is used to indicate the permissible deviation between the label quality indication corresponding to the returned sample data and the first threshold. The first sample data includes sample data whose label quality indication meets the first threshold and / or sample data whose label quality indication meets the permissible deviation.

20. The method according to any one of claims 11-18, characterized in that, The label quality strategy indication includes a label quality range, which is used to indicate the return of sample data corresponding to labels whose label quality is within the label quality range. The first sample data includes sample data whose label quality is indicated within the label quality range.

21. The method according to any one of claims 11-20, characterized in that, The first request includes multiple first thresholds, and the label quality policy indication includes a second priority indication. The second priority indication is used to indicate the priority of the multiple first thresholds and to indicate that sample data corresponding to labels whose label quality indications meet the corresponding first threshold requirements are returned in descending order of priority of the multiple first thresholds. The first sample data includes sample data whose label quality indications meet the second threshold requirements among the multiple first thresholds and the requirements of the second priority indication.

22. The method according to any one of claims 11-14, characterized in that, The tag quality strategy indication includes a third priority indication, which is used to indicate that sample data corresponding to the positioning reference unit (PRU) should be returned first. The first sample data includes sample data corresponding to M PRUs, where M is a positive integer less than or equal to N.

23. A communication method, characterized in that, The method includes: Send a first request to the location management function, the first request being used to request or subscribe to first sample data, the first request including a sample quantity indication, the sample quantity indication being used to indicate the number of samples of the first sample data being requested or subscribed to; Receive a first response from the location management function, the first response including a first indication, the first indication being used to indicate why the location management function cannot provide the first sample data that meets the sample quantity.

24. The method according to claim 23, characterized in that, The first request also includes the time window corresponding to the first sample data.

25. The method according to claim 24, characterized in that, The time window corresponding to the first sample data is used to indicate the time range corresponding to the timestamp of the first sample data within the time window.

26. The method according to claim 24 or 25, characterized in that, The first indication information is also used to indicate the reason why the location management function cannot provide the first sample data corresponding to the time window.

27. The method according to any one of claims 23 to 26, characterized in that, The method further includes: A third request is sent to the network function discovery function. The third request is used to discover the location management function. The third request includes information about the region of interest. The service area of ​​the location management function network element includes the region of interest.

28. A communication method, characterized in that, The method includes: Receive a first request from a network data analysis function, the first request being for requesting or subscribing to first sample data, the first request including a sample quantity indication, the sample quantity indication being for indicating the number of samples of the first sample data being requested or subscribed to; Send a first response to the network data analysis function. The first response includes a first indication, which indicates the reason why the first sample data that cannot meet the sample quantity cannot be provided.

29. The method according to claim 28, characterized in that, The first request also includes the time window corresponding to the first sample data.

30. The method according to claim 29, characterized in that, The time window corresponding to the first sample data is used to indicate the time range corresponding to the timestamp of the first sample data within the time window.

31. The method according to claim 29 or 30, characterized in that, The first indication information is also used to indicate the reason why the first sample data corresponding to the time window cannot be provided.

32. The method according to any one of claims 23 to 31, characterized in that, The reason is that the access network equipment and / or terminal equipment are under high load.

33. A communication device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program stored in the memory, such that the communication device performs the method of any one of claims 1 to 10, or performs the method of any one of claims 11 to 22, or performs the method of any one of claims 23 to 27, or performs the method of any one of claims 28 to 32.

34. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a communication device, causes the device to perform the method as described in any one of claims 1 to 10, or the method as described in any one of claims 11 to 22, or the method as described in any one of claims 23 to 27, or the method as described in any one of claims 28 to 32.

35. A chip system, characterized in that, include: A processor for retrieving and running a computer program from memory, causing a communication device on which the chip system is mounted to perform the method as described in any one of claims 1 to 10; or, perform the method as described in any one of claims 11 to 22; or, perform the method as described in any one of claims 23 to 27; or, perform the method as described in any one of claims 28 to 32.

36. A computer program product containing instructions, characterized in that, When it is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 10; or, to perform the method as described in any one of claims 11 to 22; or, to perform the method as described in any one of claims 23 to 27; or, to perform the method as described in any one of claims 28 to 32.

37. A communication system, characterized in that, include: A network data analysis function element is used to perform the method as described in any one of claims 1 to 10; A location management function network element is used to perform the method as described in any one of claims 11 to 22.

38. A communication system, characterized in that, include: A network data analysis function element is used to perform the method as described in any one of claims 23 to 27; A location management function network element is used to perform the method as described in any one of claims 28 to 32.

Images