Data collection method, apparatus, device, and medium

Abstract

The application provides a data collection method, device, equipment and medium. The method of the application comprises: receiving first information sent by a second device, the first information being used for training data collection and / or supervised data collection of a first positioning model; and obtaining training sample data and / or supervised sample data of the first positioning model according to the first information. The application supports the second device to send various information related to AI positioning model data collection to the first device, perfects the data collection process of the AI positioning model, provides data assistance for subsequent model training and / or model supervision, and thus achieves the effect of improving the positioning performance of the model.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a data collection method, apparatus, device and medium. Background Technology

[0002] In the research on the integration of Artificial Intelligence (AI) / Machine Learning (ML) and air interface technology, AI technology can be used to solve some complex problems in communication, such as improving positioning accuracy in complex scenarios.

[0003] AI positioning models include direct positioning models and assisted positioning models. Currently, the data collection process for AI positioning models is not yet perfect, which affects positioning performance. Summary of the Invention

[0004] The purpose of this application is to provide a data collection method, apparatus, device, and medium to solve the problem that the existing data collection process of AI positioning models is not perfect enough, which affects positioning performance.

[0005] To achieve the above objectives, in a first aspect, embodiments of this application provide a data collection method applied to a first device, comprising:

[0006] Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model;

[0007] Based on the first information, the training sample data and / or supervision sample data of the first localization model are obtained.

[0008] Secondly, embodiments of this application also provide a data collection method, applied to a second device, comprising:

[0009] Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0010] Thirdly, embodiments of this application also provide a first device, including: a memory, a transceiver, and a processor: the memory for storing computer programs; the transceiver for sending and receiving data under the control of the processor, wherein the processor performs the following operations:

[0011] Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model;

[0012] Based on the first information, the training sample data and / or supervision sample data of the first localization model are obtained.

[0013] Fourthly, embodiments of this application also provide a data collection device, including:

[0014] The first receiving unit is configured to receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model;

[0015] The first processing unit is configured to obtain training sample data and / or supervision sample data of the first localization model based on the first information.

[0016] Fifthly, embodiments of this application also provide a second device, including: a memory, a transceiver, and a processor: the memory for storing computer programs; the transceiver for sending and receiving data under the control of the processor, and performing the following operations:

[0017] Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0018] Sixthly, embodiments of this application also provide a data collection device, including:

[0019] The first sending unit is used to send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0020] In a seventh aspect, embodiments of this application also provide a non-transitory readable storage medium storing a program for executing the steps of the data collection method described in the first aspect, or executing the steps of the data collection method described in the second aspect.

[0021] The above-mentioned technical solution of this application has at least the following beneficial effects:

[0022] In the above technical solution of this application embodiment, by receiving first information sent by a second device, the first information is used for training data collection and / or supervision data collection of a first positioning model; and by obtaining training sample data and / or supervision sample data of the first positioning model based on the first information, the data collection process of the AI ​​positioning model is improved by supporting the second device to send various information related to the data collection of the AI ​​positioning model to the first device, providing data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model. Attached Figure Description

[0023] Figure 1 This is one of the flowcharts illustrating the data collection method according to an embodiment of this application;

[0024] Figure 2This is one of the schematic diagrams illustrating the pairing process of measurement information and location information in an embodiment of this application;

[0025] Figure 3 This is a second schematic diagram illustrating the pairing process of measurement information and location information in an embodiment of this application.

[0026] Figure 4 This is the third schematic diagram illustrating the pairing process of measurement information and location information in an embodiment of this application.

[0027] Figure 5 This is a second schematic flowchart of the data collection method according to an embodiment of this application;

[0028] Figure 6 This is the third flowchart illustrating the data collection method according to an embodiment of this application;

[0029] Figure 7 This is a schematic diagram of the hardware structure of the first device according to an embodiment of this application;

[0030] Figure 8 This is one of the schematic diagrams of a data collection device according to an embodiment of this application;

[0031] Figure 9 This is a schematic diagram of the hardware structure of the second device according to an embodiment of this application;

[0032] Figure 10 This is a second schematic diagram of the data collection device according to an embodiment of this application. Detailed Implementation

[0033] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0034] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0036] To facilitate understanding of the solution in this application, the relevant content of this application will be introduced first.

[0037] AI localization models include direct localization models and assisted localization models. Both the model input and the ground truth label may carry a corresponding quality indicator. For direct localization models, during the training or supervised data collection phase, it is necessary to collect the model input (channel measurements) and the ground truth label (terminal location information). The quality indicator corresponding to the location information has been determined to be the location uncertainty. For assisted localization models, during the training or supervised data collection phase, it is necessary to collect the model input (channel measurements) and the ground truth label (localization-related time information, line-of-sight (LOS) / non-line-of-sight (NLOS) indication information, etc.). Currently, when the ground truth label is localization-related time information or LOS / NLOS indication information, its quality indicator has not yet been discussed.

[0038] For AI-assisted positioning, the entities providing training data input to the model include the user equipment (UE), positioning reference unit (PRU), or generation NodeB (gNB). The entities providing real labels include the UE, PRU, or location management function (LMF). This means that there are situations where the LMF sends real labels to the UE / PRU / gNB. However, in existing assisted positioning protocols, for downlink positioning, the LMF only supports sending LOS / NLOS indicators to the UE under the UE-based positioning method. For uplink positioning, the current protocol only supports the gNB reporting LOS / NLOS indicators to the LMF, and does not support the LMF providing LOS / NLOS indicators to the gNB. Therefore, the existing protocol is insufficient to support the LMF sending real labels to the UE / PRU / gNB in ​​AI-assisted positioning training data collection.

[0039] In summary, the data collection process for current AI positioning models is not yet perfect, which in turn affects positioning performance.

[0040] To address the aforementioned technical problems, embodiments of this application provide data collection methods, apparatus, devices, and media. The methods and apparatus are based on the same concept. Since the methods and apparatus solve problems in similar ways, their implementations can be mutually referenced, and repeated details will not be elaborated further.

[0041] like Figure 1The diagram shown is a flowchart illustrating a data collection method provided in an embodiment of this application. This method is applied to a first device, meaning it is executed by the first device. The method may include the following steps:

[0042] Step 101: Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0043] The first device can be a UE (User Equipment), a base station (such as a gNB), a Transmission Reception Point (TRP), a Next Generation Radio Access Network (NG-RAN) device, an On Board Unit (OBU), or a Road Side Unit (RSU). The second device can be an LMF (Authentication Management Function) or an Authentication Management Function (AMF).

[0044] It should be noted that the method in this application embodiment can be applied to the training of a localization model, and can also be used for the supervision of a localization model.

[0045] Optionally, the first localization model is an auxiliary localization model. The first information includes information related to the collection of training data and / or supervised data for the first localization model, such as the true label and its quality indicator. Specifically, when the true label includes LOS / NLOS indicator information, the first information also includes the quality indicator information of that true label.

[0046] Step 102: Based on the first information, obtain the training sample data and / or supervision sample data of the first localization model.

[0047] The data collection method of this application embodiment receives first information sent by a second device. The first information is used for training data collection and / or supervision data collection of a first positioning model. Based on the first information, training sample data and / or supervision sample data of the first positioning model are obtained. In this way, by supporting the second device to send various information related to the data collection of the AI ​​positioning model to the first device, the data collection process of the AI ​​positioning model is improved, providing data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model.

[0048] In some embodiments, the first information includes at least one of the following:

[0049] The first real label is location-related time information; wherein, the location-related time information may include Time of Arrival (TOA), Relative Time of Arrival (RTOA), Reference Signal Time Difference (RSTD), etc.

[0050] The first quality indication information is the quality indication information of the first real tag; it should be understood that the first quality indication information is a quality representation of the time information required for positioning.

[0051] The second true tag is a line-of-sight (LOS) / non-line-of-sight (NLOS) indication information; here, the second true tag can be obtained based on the terminal's value information and the reference signal propagation time information.

[0052] The second quality indicator information is the quality indicator information of the second true label; it should be noted that the second quality indicator information can be used not only for localization model training, but also for localization model supervision.

[0053] The third real tag is terminal location information;

[0054] The third quality indication information is the quality indication information of the third real tag. It should be understood that the third quality indication information includes uncertainty information and / or confidence information of the terminal location.

[0055] Optionally, the second quality indication information includes at least one of the following:

[0056] Uncertainty information about the terminal location;

[0057] Confidence information regarding the terminal's location;

[0058] LOS probability information.

[0059] It should be noted that the LOS / NLOS indication information refers to whether the reference signal transmission between the UE and TRP includes a LOS path (also known as a line-of-sight path, indicating that there is a line-of-sight propagation path between the transceiver devices). During the training data collection phase, the LOS / NLOS path provided by LMF should be a hard value (i.e., 0 or 1), where 1 represents LOS and 0 represents NLOS.

[0060] For AI localization models on the terminal or TRP / gNB side (i.e., the first device side), when the model output is LOS / NLOS indication information, the ground truth labels required for the model training data (or model supervision data) are the LOS / NLOS indication information (i.e., the first information includes the second ground truth label). In the above steps, the first device receives the first information sent by the second device, indicating that the second ground truth label can be provided by the second device, such as the LMF. In other words, this application supports the LMF sending LOS / NLOS indication information, localization-related time information, and corresponding quality indication information to the gNB.

[0061] In addition, whether there is a LOS path between the UE and TRP is related to the UE's location. If the UE's location quality is high, the quality of the corresponding LOS / NLOS indication information will also be high. Therefore, the uncertainty of the terminal location and / or the confidence of the terminal location can be used to represent the quality of the LOS / NLOS indication information. That is, the above-mentioned second quality indication information may include the uncertainty information of the terminal location and / or the confidence information of the terminal location.

[0062] Of course, quality indicators are not required for LOS / NLOS indication information. In other words, quality indicators that do not require additional LOS / NLOS indication information can be used as quality indicators for the second real tag (i.e., LOS / NLOS indication information) according to the protocol.

[0063] This application can also introduce a new quality indication representation for LOS / NLOS indication information, namely LOS probability information, which is a value between 0 and 1, with a granularity of 0.1 or other values. This quality indication can be used in some cases where LOS / NLOS indication tags are obtained without UE location information, such as based on visual methods (light detection), or using the IE LOS / NLOS soft value in existing protocols.

[0064] In summary, when sending the first message, LMF may include at least one of the following:

[0065] Send the first real tag and the first quality indication information;

[0066] Send the second real tag and the second quality indication information;

[0067] Send third-party real tag and third-party quality indication information;

[0068] Send the first real tag, the first quality indication information, the second real tag, and the second quality indication information;

[0069] Send a third real tag;

[0070] Send the second real tag and the third quality indication information;

[0071] Send the second real tag;

[0072] Send the first real tag.

[0073] It should be understood that, in addition to the information described above, the first information may also include other information required for positioning, including but not limited to the information in the table below.

[0074]

[0075] During the training or supervised data collection process, since the model input and the ground truth label may be provided by different entities, it is necessary to pair the model input and the ground truth label. Currently, pairing is based on the timestamps carried by the model input and the ground truth label. However, the model input may contain measurement information of multiple Time-Related Response Points (TRPs) (such as Channel Impulse Response (CIR), Power Delay Profile (PDP), and Delay Profile (DP)). Each TRP measurement information contains a timestamp, while the ground truth label (i.e., location information) only contains a timestamp. How to pair the information of multiple TRPs with a location information based on the timestamp information to form a training sample can be achieved through the following embodiments.

[0076] In some embodiments, the method of this application further includes:

[0077] Send a data request message to the second device.

[0078] Here, for the first positioning model on the first device side, the first device can send a data request message to the second device and then receive the first message sent by the second device.

[0079] Optionally, the data request information may include at least one of the following:

[0080] The types of real labels;

[0081] The time requirement for the real tag; here, the time requirement for the real tag may be requesting location information for a certain time period or multiple time points.

[0082] Quality indicators of authentic labels;

[0083] Reference signal configuration information. Here, the reference signal configuration information is used by the first device to generate real tags or channel measurements. The reference signal is the reference information required for positioning, including Sounding Reference Signal (SRS), Positioning Reference Signal (PRS), or Channel State Information Reference Signal (CSI-RS).

[0084] It should be noted that, when the first positioning model is on the first device, the location information may be provided by the second device (such as LMF). When the location information is provided by the second device, the first device initiates a data request, that is, sends a data request to the second device. When the data request includes the time requirement of the real tag, it can request the second device to send the location information corresponding to the time requirement (a certain time period or multiple time points). In this way, the second device provides location information feedback as required, thereby achieving the pairing of measurement information and location information.

[0085] In other embodiments, the method of this application further includes:

[0086] Receive the data request information sent by the second device;

[0087] Send a second message to the second device, the second message being used for training data collection and / or supervision data collection of the second localization model.

[0088] Optionally, the data request information may include at least one of the following:

[0089] The types of real labels;

[0090] The time requirement for the real tag; here, the time requirement for the real tag may be requesting location information for a certain time period or multiple time points.

[0091] Quality indicators of authentic labels;

[0092] Reference signal configuration information. Here, the reference signal configuration information is used by the first device to generate real tag or channel measurements. The reference signal is the reference information required for positioning, including SRS, PRS, or CSI-RS.

[0093] Optionally, the second information includes at least one of the following:

[0094] The third real label is terminal location information; here, the third real label is terminal location information that meets the corresponding time requirement in the above data request information.

[0095] The third quality indication information is the quality indication information of the third real label;

[0096] The timestamp information of the third real label.

[0097] This embodiment corresponds to the situation where the positioning model (the second positioning model mentioned below) is on the second device side. In this case, the location information may be provided by the first device. For example, if the model is on the LMF side, the location information may be provided by the UE / PRU. When the location information is provided by the first device, the second device initiates a data request message. That is, the first device receives the data request message sent by the second device. When the data request message contains a time requirement for the real tag, it can request the first device to send the location information corresponding to the time requirement (a certain time period or one or more time points). In this way, the first device provides location information feedback according to the requirements, thereby realizing the pairing of measurement information and location information.

[0098] The following examples illustrate how the pairing of measurement information and location information is implemented.

[0099] The following explanation is provided before proceeding:

[0100] During the training data collection phase, the model input consists of N TRP measurements of CIR / PDP / DP, denoted as A. Each TRP measurement carries a timestamp, but the corresponding ground truth label (location information, denoted as B) contains only one timestamp. Timestamps A and B are paired, but since A contains N timestamps and B contains only one, the entity that receives or generates A can request B corresponding to the specified timestamp, ensuring a match between A and B. For example, a request can be made for B corresponding to any of the N timestamps in A (with a time difference less than a certain threshold) or any timestamp that overlaps with one or more of the N timestamps.

[0101] Example 1

[0102] On the UE side, location information may be provided by the UE or the LMF. When provided by the LMF, see [link to relevant documentation]. Figure 2 The UE can initiate a data request, that is, request location information for a specified time based on the timestamps corresponding to N channel measurements. The LMF then provides location information feedback as requested. Specifically:

[0103] Step 201: N TRPs send reference signals to the UE;

[0104] Step 202: The UE obtains N channel measurements and the corresponding N timestamps;

[0105] Step 203: The UE sends a data request message to the LMF, requesting location information for a specified time.

[0106] Step 204: The LMF sends the location information for the specified time to the UE.

[0107] Of course, on the UE side, the location information may be provided by the UE or the LMF. When provided by the LMF, the LMF can also send the location information to the UE independently, and then the UE performs the pairing of measurement quantity and location information based on the timestamp.

[0108] Example 2

[0109] The model is on the LMF side, and the location information may be provided by the UE. When it is provided by the UE, see [link to relevant documentation]. Figure 3 The LMF can initiate a data request, that is, to request location information at a specified time based on the timestamps corresponding to N channel measurements. The UE then provides location information feedback as requested. Specifically:

[0110] Step 301: N TRPs send reference signals to the UE;

[0111] Step 302: The UE obtains N channel measurements and the corresponding N timestamps;

[0112] Step 303: The UE reports channel measurements to the LMF;

[0113] Step 304: The LMF sends a data request message to the UE, requesting location information for a specified time.

[0114] Step 305: The UE sends the location information for the specified time to the LMF.

[0115] Of course, on the LMF side, the location information may be provided by the UE or the LMF. When provided by the UE, the UE can also send the location information to the LMF independently, and then the LMF will match the measurement quantity and location information according to the timestamp.

[0116] Example 3

[0117] The model is on the gNB side, and the location information may be provided by the LMF. When it is provided by the LMF, see [link to relevant documentation]. Figure 4 The gNB can initiate a data request, that is, to request location information at a specified time based on the timestamps corresponding to N channel measurements. The LMF then provides location information feedback as requested. Specifically:

[0118] Step 401, the UE sends a reference signal to the gNB;

[0119] Step 402, gNB acquires N channel measurements and the corresponding N timestamps;

[0120] Step 403: The gNB sends a data request message to the LMF, requesting location information for a specified time.

[0121] Step 404: The LMF sends the location information for the specified time to the gNB.

[0122] Of course, on the gNB side, the location information may be provided by the LMF. When provided by the LMF, the LMF can also send the location information to the gNB independently, and then the gNB matches the measurement quantity and location information according to the timestamp.

[0123] In some embodiments, the method of the present invention further includes:

[0124] The device receives an instruction message sent by the second device, which is used to activate the first device to enter the data collection state.

[0125] It should be noted that after the data collection state of the first device is activated, the first device can record historical location information. When requesting a location at a specific time through data request information, the UE can generate the location at that time through interpolation or smoothing.

[0126] This application supports the LMF sending LOS / NLOS indication information and location-related time information to the gNB. Specifically, this can be achieved through the following methods:

[0127] 1. Enhance existing protocols, such as supporting the LMF to send LOS / NLOS indication information and positioning-related time information to the gNB during training data collection and uplink positioning signaling.

[0128] 2. Introduce a new AI positioning field IE (i.e., a new AI positioning field), such as AI-based-UL-RTOA. In IE, LMF can send LOS / NLOS indication information and positioning-related time information to gNB.

[0129] 3. Supports UE / gNB initiating data collection requests (i.e., data request information) or location assistance information requests to the LMF. The LMF triggers reference signal transmission and sends the requested real tag to the UE / gNB. See details in [link to documentation]. Figure 5 The specific steps are as follows:

[0130] Before proceeding, it should be noted that steps 501 to 503 below are not required to be in any particular order, nor are they limited to being completed in the same signaling message. They can be divided into multiple signaling messages, and LOS / NLOS indication information can be requested / sent separately without the need for time information.

[0131] Step 501, the UE / gNB sends a data collection request to the LMF;

[0132] The data collection request includes at least one of the following:

[0133] The types of real labels;

[0134] Quality requirements for authentic labels.

[0135] Step 502: LMF obtains UE location information.

[0136] UE location information can be obtained from UE reporting or LMF (Local Method Function). After obtaining the UE location information, a real tag is generated. Corresponding time information, or LOS / NLOS indication information and quality requirements, can be generated using information such as the distance between the UE and the gNB (Gate NB).

[0137] Step 503: The LMF sends a data collection request response to the UE / gNB.

[0138] The data collection request response includes at least one of the following:

[0139] Parameter signal configuration information;

[0140] Ground-truth label;

[0141] The timestamp information of the real tag;

[0142] The quality indication information on the actual label;

[0143] The response failed.

[0144] like Figure 6 The diagram shown is a flowchart illustrating a data collection method provided in an embodiment of this application. This method is applied to a second device, meaning it is executed by the second device. The method may include the following steps:

[0145] Step 601: Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0146] It should be noted that this embodiment is a method embodiment corresponding to the second device side, which is the opposite side to the first device described above. For a detailed understanding and explanation of the relevant terms or steps, please refer to the description of the method on the first device side; it will not be repeated here.

[0147] The data collection method of this application embodiment sends first information to a first device. This first information is used for training data collection and / or supervision data collection of a first positioning model. In this way, by supporting a second device to send various information related to the data collection of the AI ​​positioning model to the first device, the data collection process of the AI ​​positioning model is improved, providing data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model.

[0148] In some embodiments, the first information includes at least one of the following:

[0149] The first real label is location-related time information; wherein, the location-related time information may include TOA, RTOA, RSTD, etc.

[0150] The first quality indication information is the quality indication information of the first real tag; it should be understood that the first quality indication information is a quality representation of the time information required for positioning.

[0151] The second true tag is a line-of-sight (LOS) / non-line-of-sight (NLOS) indication information; here, the second true tag can be obtained based on the terminal's value information and the reference signal propagation time information.

[0152] The second quality indicator information is the quality indicator information of the second true label; it should be noted that the second quality indicator information can be used not only for localization model training, but also for localization model supervision.

[0153] The third real tag is terminal location information;

[0154] The third quality indication information is the quality indication information of the third real tag. It should be understood that the third quality indication information includes uncertainty information and / or confidence information of the terminal location.

[0155] Optionally, the second quality indication information includes at least one of the following:

[0156] Uncertainty information about the terminal location;

[0157] Confidence information regarding the terminal's location;

[0158] LOS probability information.

[0159] For AI localization models on the terminal or TRP / gNB side (i.e., the first device side), when the model output is LOS / NLOS indication information, the ground truth labels required for the model training data (or model supervision data) are the LOS / NLOS indication information (i.e., the first information includes the second ground truth label). The second device sends the first information to the first device, indicating that the second ground truth label can be provided by the second device, such as the LMF. In other words, this application supports the LMF sending LOS / NLOS indication information and localization-related time information to the gNB.

[0160] During the training or supervised data collection process, since the model input and the ground truth label may be provided by different entities, it is necessary to pair the model input and the ground truth label. Currently, pairing is based on the timestamps carried by the model input and the ground truth label. However, the model input may contain measurement information of multiple Time-Related Response Points (TRPs) (such as Channel Impulse Response (CIR), Power Delay Profile (PDP), and Delay Profile (DP)). Each TRP measurement information contains a timestamp, while the ground truth label (i.e., location information) only contains a timestamp. How to pair the information of multiple TRPs with a location information based on the timestamp information to form a training sample can be achieved through the following embodiments.

[0161] In some embodiments, the method of this application further includes:

[0162] Receive data request information sent by the first device.

[0163] Here, corresponding to the first positioning model on the first device side, the first device can send data request information to the second device. The second device receives the data request information sent by the first device and then sends the first information corresponding to the request to the first device.

[0164] Optionally, the data request information may include at least one of the following:

[0165] The types of real labels;

[0166] The time requirement for the real tag; here, the time requirement for the real tag may be requesting location information for a certain time period or multiple time points.

[0167] Quality indicators of authentic labels;

[0168] Reference signal configuration information. Here, the reference signal configuration information is used by the first device to generate real tag or channel measurements. The reference signal is the reference information required for positioning, including SRS, PRS, or CSI-RS.

[0169] It should be noted that, when the first positioning model is on the first device, the location information may be provided by the second device (such as LMF). When the location information is provided by the second device, the first device initiates a data request, that is, sends a data request to the second device. When the data request includes the time requirement of the real tag, it can request the second device to send the location information corresponding to the time requirement (a certain time period or multiple time points). In this way, the second device provides location information feedback as required, thereby achieving the pairing of measurement information and location information.

[0170] In other embodiments, the method of this application further includes:

[0171] Data request information sent to the first device;

[0172] Receive second information sent by the first device, the second information being used for training data collection and / or supervision data collection of the second localization model;

[0173] Based on the second information, the training sample data and / or supervision sample data of the second localization model are obtained.

[0174] Optionally, the data request information may include at least one of the following:

[0175] The types of real labels;

[0176] The time requirement for the real tag; here, the time requirement for the real tag may be requesting location information for a certain time period or multiple time points.

[0177] Quality indicators of authentic labels;

[0178] Reference signal configuration information. Here, the reference signal configuration information is used by the first device to generate real tag or channel measurements. The reference signal is the reference information required for positioning, including SRS, PRS, or CSI-RS.

[0179] Optionally, the second information includes at least one of the following:

[0180] The third real label is terminal location information; here, the third real label is terminal location information that meets the corresponding time requirement in the above data request information.

[0181] The third quality indication information is the quality indication information of the third real label;

[0182] The timestamp information of the third real label.

[0183] This embodiment corresponds to the scenario where the second positioning model is on the second device side. In this case, the location information may be provided by the first device, for example, if the model is on the LMF side, the location information may be provided by the UE. When the location information is provided by the first device, the second device initiates a data request message. That is, the first device receives the data request message sent by the second device. When the data request message includes a time requirement for the real tag, it can request the first device to send the location information corresponding to the time requirement (a certain time period or multiple time points). In this way, the first device provides location information feedback according to the requirements, thereby achieving the pairing of measurement information and location information. Subsequently, the second device can obtain the training sample data and / or supervision sample data of the second positioning model on the second device side based on the second information.

[0184] In some embodiments, the method of the present invention further includes:

[0185] Send an instruction message to the first device, the instruction message being used to activate the first device to enter the data collection state.

[0186] It should be noted that after the data collection state of the first device is activated, the first device can record historical location information. When requesting a location at a specific time via data request information, the UE can generate the location at that time through interpolation.

[0187] The data collection method of this application embodiment improves the data collection process of the AI ​​positioning model by supporting the second device to send various information related to the data collection of the AI ​​positioning model to the first device, and provides data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model.

[0188] like Figure 7 As shown, this application embodiment also provides a first device, including: a memory 720, a transceiver 700, and a processor 710: the memory 720 is used to store program instructions; the transceiver 700 is used to send and receive data under the control of the processor 710; the processor 710 performs the following operations:

[0189] Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model;

[0190] Based on the first information, the training sample data and / or supervision sample data of the first localization model are obtained.

[0191] Among them, Figure 7 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 710 and memory represented by memory 720 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 700 can be multiple elements, including transmitters and receivers, providing units for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, and other transmission media.

[0192] The processor 710 is responsible for managing the bus architecture and general processing, while the memory 720 can store the data used by the processor 710 during operation.

[0193] Optionally, the processor 710 can be a CPU (Central Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or CPLD (Complex Programmable Logic Device), and the processor 710 can also adopt a multi-core architecture.

[0194] When the first device is a terminal, the user interface 730 can also be an interface that can connect to external or internal devices for different user devices. The connected devices include, but are not limited to, keypads, displays, speakers, microphones, joysticks, etc.

[0195] The processor 710 executes any of the methods provided in the embodiments of this application according to the obtained executable instructions by calling program instructions stored in the memory. The processor 710 and the memory 720 may also be physically separated.

[0196] In some embodiments, the first information includes at least one of the following:

[0197] The first real label is location-related time information;

[0198] First quality indication information, wherein the first quality indication information is the quality indication information of the first real label;

[0199] The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information;

[0200] The second quality indication information is the quality indication information of the second real label.

[0201] The third real tag is terminal location information;

[0202] The third quality indication information is the quality indication information of the third real label.

[0203] In some embodiments, the second quality indication information includes at least one of the following:

[0204] Uncertainty information about the terminal location;

[0205] Confidence information regarding the terminal's location;

[0206] LOS probability information.

[0207] In some embodiments, the transceiver 700 is further configured to:

[0208] The device receives an instruction message sent by the second device, which is used to activate the first device to enter the data collection state.

[0209] In some embodiments, the transceiver 700 is further configured to:

[0210] Send a data request message to the second device.

[0211] In some embodiments, the transceiver 700 is further configured to:

[0212] Receive the data request information sent by the second device;

[0213] Send second information to the second device. The second information is used for training data collection and / or supervision data collection of the second localization model.

[0214] In some embodiments, the data request information includes at least one of the following:

[0215] The types of real labels;

[0216] Time requirements for accurate labeling;

[0217] Quality indicators of authentic labels;

[0218] Reference signal configuration information.

[0219] In some embodiments, the second information includes at least one of the following:

[0220] The third real tag is terminal location information;

[0221] The third quality indication information is the quality indication information of the third real label;

[0222] The timestamp information of the third real label.

[0223] The first device in this application embodiment receives first information sent by a second device. The first information is used for training data collection and / or supervision data collection of a first positioning model. Based on the first information, training sample data and / or supervision sample data of the first positioning model are obtained. In this way, by supporting the second device to send various information related to the data collection of the AI ​​positioning model to the first device, the data collection process of the AI ​​positioning model is improved, providing data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model.

[0224] like Figure 8 As shown in the illustration, this application also provides a data collection device applied to a first device, comprising:

[0225] The first receiving unit 801 is used to receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first positioning model;

[0226] The first processing unit 802 is used to obtain training sample data and / or supervision sample data of the first localization model based on the first information.

[0227] In some embodiments, the first information includes at least one of the following:

[0228] The first real label is location-related time information;

[0229] First quality indication information, wherein the first quality indication information is the quality indication information of the first real label;

[0230] The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information;

[0231] The second quality indication information is the quality indication information of the second real label.

[0232] The third real tag is terminal location information;

[0233] The third quality indication information is the quality indication information of the third real label.

[0234] In some embodiments, the second quality indication information includes at least one of the following:

[0235] Uncertainty information about the terminal location;

[0236] Confidence information regarding the terminal's location;

[0237] LOS probability information.

[0238] In some embodiments, the device further includes:

[0239] The second sending unit is used to send data request information to the second device.

[0240] In some embodiments, the device further includes:

[0241] The first receiving unit is configured to receive data request information sent by the second device;

[0242] The third sending unit is used to send second information to the second device. The second information is used for training data collection and / or supervision data collection of the second positioning model.

[0243] In some embodiments, the data request information includes at least one of the following:

[0244] The types of real labels;

[0245] Time requirements for accurate labeling;

[0246] Quality indicators of authentic labels;

[0247] Reference signal configuration information.

[0248] In some embodiments, the second information includes at least one of the following:

[0249] The third real tag is terminal location information;

[0250] The third quality indication information is the quality indication information of the third real label;

[0251] The timestamp information of the third real label.

[0252] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0253] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0254] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0255] like Figure 9 As shown in the illustration, this application also provides a second device, including: a memory 920, a transceiver 900, and a processor 910: the memory 920 is used to store computer programs; the transceiver 900 is used to send and receive data under the control of the processor 910, and to perform the following operations:

[0256] Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

[0257] Among them, Figure 9 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 910 and memory represented by memory 920 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 900 can be multiple elements, including transmitters and receivers, providing units for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, and other transmission media.

[0258] The processor 910 is responsible for managing the bus architecture and general processing, while the memory 920 can store the data used by the processor 910 during operation.

[0259] The processor 910 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

[0260] The processor 910 executes any of the methods described in the embodiments of this application according to the obtained executable instructions by calling program instructions stored in the memory. The processor 910 and the memory 920 may also be physically separated.

[0261] In some embodiments, the first information includes at least one of the following:

[0262] The first real label is location-related time information;

[0263] First quality indication information, wherein the first quality indication information is the quality indication information of the first real label;

[0264] The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information;

[0265] The second quality indication information is the quality indication information of the second real label.

[0266] The third real tag is terminal location information;

[0267] The third quality indication information is the quality indication information of the third real label.

[0268] In some embodiments, the second quality indication information includes at least one of the following:

[0269] Uncertainty information about the terminal location;

[0270] Confidence information regarding the terminal's location;

[0271] LOS probability information.

[0272] In some embodiments, the transceiver 900 is further configured to:

[0273] Send an instruction message to the first device, the instruction message being used to activate the first device to enter the data collection state.

[0274] In some embodiments, the transceiver 900 is further configured to:

[0275] Receive data request information sent by the first device.

[0276] In some embodiments, the transceiver 900 is further configured to:

[0277] Data request information sent to the first device;

[0278] Receive second information sent by the first device, the second information being used for training data collection and / or supervision data collection of the second localization model;

[0279] The processor 910 is also configured to: obtain training sample data and / or supervision sample data of the second localization model based on the second information.

[0280] In some embodiments, the data request information includes at least one of the following:

[0281] The types of real labels;

[0282] Time requirements for accurate labeling;

[0283] Quality indicators of authentic labels;

[0284] Reference signal position information.

[0285] In some embodiments, the second information includes at least one of the following:

[0286] The third real tag is terminal location information;

[0287] The third quality indication information is the quality indication information of the third real label;

[0288] The timestamp information of the third real label.

[0289] The second device in this application embodiment sends first information to the first device. This first information is used for training data collection and / or supervision data collection of the first positioning model. In this way, by supporting the second device to send various information related to the data collection of the AI ​​positioning model to the first device, the data collection process of the AI ​​positioning model is improved, providing data assistance for subsequent model training and / or model supervision, thereby achieving the effect of improving the positioning performance of the model.

[0290] like Figure 10 As shown, this application also provides a data collection device, applied to a second device, comprising:

[0291] The first sending unit 1001 is used to send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first positioning model.

[0292] In some embodiments, the first information includes at least one of the following:

[0293] The first real label is location-related time information;

[0294] First quality indication information, wherein the first quality indication information is the quality indication information of the first real label;

[0295] The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information;

[0296] The second quality indication information is the quality indication information of the second real label.

[0297] The third real tag is terminal location information;

[0298] The third quality indication information is the quality indication information of the third real label.

[0299] In some embodiments, the second quality indication information includes at least one of the following:

[0300] Uncertainty information about the terminal location;

[0301] Confidence information regarding the terminal's location;

[0302] LOS probability information.

[0303] In some embodiments, the device further includes:

[0304] The fourth sending unit is used to send indication information to the first device, the indication information being used to activate the first device to enter the data collection state.

[0305] In some embodiments, the device further includes:

[0306] The second receiving unit is used to receive data request information sent by the first device.

[0307] In some embodiments, the device further includes:

[0308] The fifth sending unit is used to send data request information to the first device;

[0309] The third receiving unit is used to receive the second information sent by the first device. The second information is used for training data collection and / or supervision data collection of the second positioning model.

[0310] The second processing unit is used to obtain training sample data and / or supervision sample data of the second localization model based on the second information.

[0311] In some embodiments, the data request information includes at least one of the following:

[0312] The types of real labels;

[0313] Time requirements for accurate labeling;

[0314] Quality indicators of authentic labels;

[0315] Reference signal position information.

[0316] In some embodiments, the second information includes at least one of the following:

[0317] The third real tag is terminal location information;

[0318] The third quality indication information is the quality indication information of the third real label;

[0319] The timestamp information of the third real label.

[0320] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0321] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0322] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0323] In some embodiments of this application, a non-transient readable storage medium is also provided, which stores a program for executing the data collection method described above.

[0324] The non-transiently readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., compact disc (CD), digital video disc (DVD), Blu-ray disc (BD), high-definition versatile disc (HVD)), and semiconductor memory (e.g., ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drives (SSD), etc.).

[0325] When executed by the processor, this program can achieve the above-mentioned applications, such as... Figure 1 The method shown on the first device side or as follows Figure 6 All implementations of the method embodiments on the second device side shown are not described again here to avoid repetition.

[0326] The technical solutions provided in this application can be applied to a variety of systems. For example, applicable systems may include Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS), Long Term Evolution (LTE), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), Long Term Evolution Advanced (LTE-A), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX), 5G New Radio (NR) and its evolutionary communication systems, and 6G (sixth generation mobile communication technology) systems. All of these systems include terminal equipment and network equipment. The system may also include a core network component, such as the Evolved Packet System (EPS) or the 5G system (5GS).

[0327] The terminal devices involved in the embodiments of this application can be devices that provide voice and / or data connectivity to users, handheld devices with wireless connectivity, or other processing devices connected to a wireless modem. The names of the terminal devices may differ in different systems; for example, in 5G or 6G systems, the terminal device may be called User Equipment (UE). Wireless terminal devices can be USB storage devices, other personal computer memory devices, and dongles. They can also communicate with one or more core networks (CNs) via a Radio Access Network (RAN). Wireless terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones) and computers with mobile terminal devices. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the radio access network. Examples of such devices include Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), personal computers, tablets, and Machine-type Communication (MTC) terminal devices. Wireless terminal devices can also be referred to as systems, subscriber units, subscriber stations, mobile stations, mobile devices, remote stations, access points, remote terminals, access terminals, user terminals, user agents, user devices, and wireless access devices and routers / modems that meet the limitations of this definition; however, this application does not limit the scope of the embodiments.

[0328] The network device involved in this application embodiment can be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, a base station may also be called an access point, or a device in the access network that communicates with wireless terminal devices through one or more sectors on the air interface, or other names. The network device can be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device can also coordinate the attribute management of the air interface. For example, the network equipment involved in the embodiments of this application can be a base transceiver station (BTS) in a Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), a NodeB in a Wide-band Code Division Multiple Access (WCDMA) system, an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, a Home evolved Node B (HeNB), a relay node, a femto, a pico, network testing equipment, etc., and is not limited in the embodiments of this application. In some network structures, the network equipment may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and distributed unit may also be geographically separated.

[0329] Network devices and terminal devices can each use one or more antennas for multiple-input multiple-output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multiple-user MIMO (MU-MIMO). Depending on the configuration and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO, and can also be diversity transmission, precoding transmission, or beamforming transmission, etc.

[0330] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0331] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0332] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0333] These processors can execute instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0334] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A data collection method, applied to a first device, characterized in that, include: Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model; Based on the first information, the training sample data and / or supervision sample data of the first localization model are obtained.

2. The method according to claim 1, characterized in that, The first information includes at least one of the following: The first real label is location-related time information; First quality indication information, wherein the first quality indication information is the quality indication information of the first real label; The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information; The second quality indication information is the quality indication information of the second real label. The third real tag is terminal location information; The third quality indication information is the quality indication information of the third real label.

3. The method according to claim 2, characterized in that, The second quality indication information includes at least one of the following: Uncertainty information about the terminal location; Confidence information regarding the terminal's location; LOS probability information.

4. The method according to claim 1, characterized in that, The method further includes: The device receives an instruction message sent by the second device, which is used to activate the first device to enter the data collection state.

5. The method according to claim 1, characterized in that, The method further includes: Send a data request message to the second device.

6. The method according to claim 1, characterized in that, The method further includes: Receive the data request information sent by the second device; Send a second message to the second device, the second message being used for training data collection and / or supervision data collection of the second localization model.

7. The method according to claim 5 or 6, characterized in that, The data request information includes at least one of the following: The types of real labels; Time requirements for accurate labeling; Quality indicators of authentic labels; Reference signal configuration information.

8. The method according to claim 6, characterized in that, The second information includes at least one of the following: The third real tag is terminal location information; The third quality indication information is the quality indication information of the third real label; The timestamp information of the third real label.

9. A data collection method applied to a second device, characterized in that, include: Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

10. The method according to claim 9, characterized in that, The first information includes at least one of the following: The first real label is location-related time information; First quality indication information, wherein the first quality indication information is the quality indication information of the first real label; The second real label is the line-of-sight (LOS) / non-line-of-sight (NLOS) indication information; The second quality indication information is the quality indication information of the second real label. The third real tag is terminal location information; The third quality indication information is the quality indication information of the third real label.

11. The method according to claim 10, characterized in that, The second quality indication information includes at least one of the following: Uncertainty information about the terminal location; Confidence information regarding the terminal's location; LOS probability information.

12. The method according to claim 9, characterized in that, The method further includes: Send an instruction message to the first device, the instruction message being used to activate the first device to enter the data collection state.

13. The method according to claim 9, characterized in that, The method further includes: Receive data request information sent by the first device.

14. The method according to claim 9, characterized in that, The method further includes: Send a data request message to the first device; Receive second information sent by the first device, the second information being used for training data collection and / or supervision data collection of the second localization model; Based on the second information, the training sample data and / or supervision sample data of the second localization model are obtained.

15. The method according to claim 13 or 14, characterized in that, The data request information includes at least one of the following: The types of real labels; Time requirements for accurate labeling; Quality indicators of authentic labels; Reference signal configuration information.

16. The method according to claim 14, characterized in that, The second information includes at least one of the following: The third real tag is terminal location information; The third quality indication information is the quality indication information of the third real label; The timestamp information of the third real label.

17. A first device, characterized in that, include: Memory, transceiver, processor: Memory is used to store program instructions; A transceiver, used to send and receive data under the control of the processor, the processor performing the following operations: Receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model; Based on the first information, the training sample data and / or supervision sample data of the first localization model are obtained.

18. A data collection device, characterized in that, include: The first receiving unit is configured to receive first information sent by the second device, the first information being used for training data collection and / or supervision data collection of the first localization model; The first processing unit is configured to obtain training sample data and / or supervision sample data of the first localization model based on the first information.

19. A second device, characterized in that, include: Memory, transceiver, processor: Memory is used to store program instructions; A transceiver, used to send and receive data under the control of the processor, and to perform the following operations: Send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

20. A data collection device, characterized in that, include: The first sending unit is used to send first information to the first device, the first information being used for training data collection and / or supervision data collection of the first localization model.

21. A non-transiently readable storage medium, characterized in that, The non-transiently readable storage medium stores a program for performing the steps of the data collection method according to any one of claims 1 to 8, or for performing the steps of the data collection method according to any one of claims 9 to 16.

Images