Data processing methods, apparatus, equipment, storage media and program products
Patent Information
- Application Number
- CN202410403560.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-03
- Publication Date
- 2026-09-01
- Estimated Expiration
- 2044-04-03
AI Technical Summary
[0004]本申请的目的在于提供一种数据处理方法、装置、设备、存储介质及程序产品,从而解决目前模型训练和推理阶段不同设备对数据的理解不一致,造成模型性能差的问题
[0102]本申请实施例的数据处理方法中,第一通信设备确定目标参数的参考时间,所述参考时间用于调整目标模型对应的数据集中的目标参数,以保证所述目标模型在训练阶段的数据表示和在推理阶段的数据表示的一致性;其中,所述目标模型对应的数据集包括训练阶段的第一数据集和/或推理阶段的第二数据集。如此,使得不同设备之间对目标参数具有一致的理解,进而提升所述目标模型的性能。
Smart Images

Figure CN120782006B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a data processing method, apparatus, device, storage medium, and program product. Background Technology
[0002] In communication scenarios based on Artificial Intelligence Machine Learning (AIML), the model's input is obtained from channel estimation measurements, which can include time, phase, and power information. The reporting of channel estimation measurements is involved in both the training data collection and model inference phases. For example, the data generation entity reports channel estimation measurements to the data collection entity, or during the model inference phase, the User Equipment (UE) / 5G Generation NodeB (gNB) reports measurements to the Location Management Function (LMF) for model inference.
[0003] To ensure that the model's performance meets the requirements, the determination of data such as channel estimation measurements during the data collection and inference phases needs to ensure consistent understanding among different devices. However, no definitive conclusion has yet been reached on this issue. Summary of the Invention
[0004] The purpose of this application is to provide a data processing method, apparatus, device, storage medium, and program product to solve the problem of inconsistent data understanding by different devices during the current model training and inference stages, which leads to poor model performance.
[0005] Firstly, in order to achieve the above objectives, embodiments of this application provide a data processing method applied to a first communication device, comprising:
[0006] A reference time for determining the target parameters is used to adjust the target parameters in the dataset corresponding to the target model, so as to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0007] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0008] Optionally, the reference time includes at least one of the following:
[0009] The first communication device receives the subframe boundary where the reference signal is located;
[0010] The first communication device receives the time slot boundary where the reference signal is located.
[0011] Optionally, the first dataset and / or the second dataset includes at least one of the following:
[0012] Channel measurements, including the target parameters, are obtained by measuring a received reference signal;
[0013] First label;
[0014] The quality of the first label;
[0015] Confidence level of the first label;
[0016] The quality of channel measurements;
[0017] Confidence level of channel measurements;
[0018] First timestamp;
[0019] The identification ID information of the first communication device;
[0020] Information about the reference transmitting device, wherein the reference transmitting device is one of a group of target transmitting devices that transmit reference signals to the first communication device.
[0021] Optionally, the first label includes at least one of the following:
[0022] The propagation time of the reference signal;
[0023] The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication;
[0024] Target time difference information;
[0025] Location information of the first communication device;
[0026] Information related to beam management;
[0027] Second timestamp;
[0028] ID information of the first communication device.
[0029] Optionally, the target time difference information includes at least one of the following:
[0030] First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal;
[0031] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0032] Optionally, the method further includes at least one of the following:
[0033] Receive the first tag sent by the second communication device;
[0034] The first tag is obtained based on the information related to the first tag sent by the second communication device;
[0035] The first tag-related information includes at least one of the following:
[0036] The distance information between the first communication device and the transmitting device, wherein the transmitting device belongs to the target transmitting device group;
[0037] First auxiliary information;
[0038] Third timestamp;
[0039] Refer to the information of the transmitting device.
[0040] Optionally, the first auxiliary information includes at least one of the following:
[0041] The timing information of the transmitting device;
[0042] The timing difference information between the transmitting devices.
[0043] Optionally, the method further includes:
[0044] The information of the reference transmitting device is sent to the second communication device and / or the third communication device.
[0045] Optionally, the method further includes:
[0046] Send the first dataset and / or the second dataset to a third communication device.
[0047] Optionally, the method further includes:
[0048] According to preset rules, adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset;
[0049] Send the adjusted first dataset and / or second dataset to a third communication device.
[0050] Optionally, the target parameter includes time information for channel estimation; wherein the time information for channel estimation includes delay position, or the time information for channel estimation is represented by at least one of the following:
[0051] First image bitmap;
[0052] First bitmap and slot offset;
[0053] Additional path.
[0054] Secondly, in order to achieve the above objectives, embodiments of this application provide a data processing method applied to a second communication device, comprising at least one of the following:
[0055] Send the first tag to the first communication device;
[0056] Send first tag-related information to the first communication device. The first tag-related information is used by the first communication device to obtain the first tag. The first tag is carried in the first dataset, which is the dataset used in the training phase of the target model.
[0057] Optionally, the first label includes at least one of the following:
[0058] The propagation time of the reference signal;
[0059] The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication;
[0060] Target time difference information;
[0061] Location information of the first communication device;
[0062] Information related to beam management;
[0063] Second timestamp;
[0064] ID information of the first communication device.
[0065] Optionally, the target time difference information includes at least one of the following:
[0066] First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal; wherein, the target transmitting device group includes devices that send reference signals to the first communication device, and the reference transmitting device is one of the target transmitting device group;
[0067] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0068] Optionally, the information related to the first tag includes at least one of the following:
[0069] The distance information between the first communication device and the transmitting device, wherein the transmitting device is a device in the target transmitting device group that sends a reference signal to the first communication device;
[0070] First auxiliary information;
[0071] Third timestamp;
[0072] Information about a reference transmitting device, wherein the reference transmitting device is one of the target transmitting devices in the group.
[0073] Optionally, before sending the first tag to the first communication device and / or sending information related to the first tag to the first communication device, the method further includes:
[0074] Obtain first auxiliary information;
[0075] Receive information about the reference transmitting device sent by the first communication device;
[0076] Based on the first auxiliary information and / or the information of the reference transmitting device, obtain the first tag and / or information related to the first tag;
[0077] The reference transmitting device is one of the target transmitting devices in the group, and the target transmitting device includes a device that transmits a reference signal to the first communication device.
[0078] Optionally, the first auxiliary information includes at least one of the following:
[0079] The timing information of the transmitting device;
[0080] The timing difference information between the transmitting devices.
[0081] Thirdly, in order to achieve the above objectives, embodiments of this application provide a data processing method applied to a third communication device, comprising:
[0082] The system receives a dataset corresponding to the target model sent by a first communication device, wherein the target parameters in the dataset are information adjusted according to a reference time; in order to ensure the consistency of the data representation of the target model during the training phase and the data representation during the inference phase.
[0083] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0084] Optionally, the method further includes:
[0085] The device receives information about a reference transmitting device sent by the first communication device, wherein the reference transmitting device is one of a group of target transmitting devices that send reference signals to the first communication device.
[0086] Optionally, the method further includes:
[0087] According to preset rules, adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset.
[0088] Fourthly, in order to achieve the above objectives, embodiments of this application provide a data processing apparatus applied to a first communication device, comprising:
[0089] The determination module is used to determine the reference time for the target parameters. The reference time is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0090] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0091] Fifthly, in order to achieve the above objectives, embodiments of this application provide a data processing apparatus applied to a second communication device, comprising:
[0092] The sending module is configured to perform at least one of the following:
[0093] Send the first tag to the first communication device;
[0094] Send first tag-related information to the first communication device. The first tag-related information is used by the first communication device to obtain the first tag. The first tag is carried in the first dataset, which is the dataset used in the training phase of the target model.
[0095] Sixthly, in order to achieve the above objectives, embodiments of this application provide a data processing apparatus applied to a third communication device, comprising:
[0096] The receiving module is used to receive a dataset corresponding to the target model sent by the first communication device, wherein the target parameters in the dataset are information adjusted according to the reference time; so as to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0097] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0098] In a seventh aspect, to achieve the above objectives, embodiments of this application provide a communication device, including: a transceiver, a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the data processing method as described in the first aspect, or the data processing method as described in the second aspect, or the data processing method as described in the third aspect.
[0099] Eighthly, in order to achieve the above objectives, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the data processing method as described in the first aspect, or the data processing method as described in the second aspect, or the data processing method as described in the third aspect.
[0100] Ninthly, in order to achieve the above objectives, this application provides a computer program product, including computer instructions, which, when executed by a processor, implement the data processing method as described in the first aspect, or the data processing method as described in the second aspect, or the data processing method as described in the third aspect.
[0101] The above-mentioned technical solution of this application has at least the following beneficial effects:
[0102] In the data processing method of this application embodiment, a first communication device determines a reference time for the target parameters. This reference time is used to adjust the target parameters in the dataset corresponding to the target model to ensure consistency between the data representation of the target model during the training phase and the data representation during the inference phase. The dataset corresponding to the target model includes a first dataset from the training phase and / or a second dataset from the inference phase. This ensures that different devices have a consistent understanding of the target parameters, thereby improving the performance of the target model. Attached Figure Description
[0103] Figure 1 This is one of the flowcharts illustrating the data processing method according to an embodiment of this application;
[0104] Figure 2 This is a second schematic flowchart of the data processing method according to an embodiment of this application;
[0105] Figure 3 This is the third flowchart illustrating the data processing method according to an embodiment of this application;
[0106] Figure 4 This is one of the flowcharts illustrating the process of generating the first dataset in this application embodiment;
[0107] Figure 5This is the second schematic diagram of the process for generating the first dataset in the embodiments of this application;
[0108] Figure 6 This is a schematic diagram of the process for reporting the first dataset in an embodiment of this application;
[0109] Figure 7 This is a schematic diagram of the process for reporting the second dataset in an embodiment of this application;
[0110] Figure 8 This is a schematic diagram of the process for obtaining the first tag in an embodiment of this application;
[0111] Figure 9 This is one of the schematic diagrams illustrating an example of achieving consistency between the reference transmitting device and data collection and inference in the embodiments of this application;
[0112] Figure 10 This is a second schematic diagram illustrating an example of achieving consistency between the reference transmitting device and data collection and inference in the embodiments of this application;
[0113] Figure 11 This is a schematic diagram of channel estimation in an embodiment of this application;
[0114] Figure 12 This is one of the structural schematic diagrams of the data processing apparatus according to an embodiment of this application;
[0115] Figure 13 This is a second schematic diagram of the structure of the data processing device according to an embodiment of this application;
[0116] Figure 14 This is the third schematic diagram of the structure of the data processing device according to an embodiment of this application;
[0117] Figure 15 This is a schematic diagram of the structure of a communication device according to an embodiment of this application. Detailed Implementation
[0118] 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 some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0119] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0120] The data processing methods, apparatus, devices, storage media, and program products provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.
[0121] Embodiments of this application provide a data processing method applied to a first communication device. The first communication device generates a training dataset for a training phase and / or an inference dataset for an inference phase. The training dataset is used to train a model, and the inference dataset is used as input to the trained model to achieve model inference. The model is used for positioning and / or beam management. Specifically, the first communication device may be, for example, any one of a UE, a Positioning Reference Unit (PRU), a Roadside Unit (RSU), an Onboard Unit (OBU), a Transmission Reception Point (TRP) / gNB, and an LMF entity, but is not limited thereto. Figure 1 As shown, the method includes:
[0122] Step 101: Determine the reference time for the target parameters. The reference time is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency between the data representation of the target model in the training phase and the data representation in the inference phase.
[0123] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0124] Here, the relevant content involved in step 101 will be explained:
[0125] The target parameters include channel estimation time information and / or propagation time information. For example, the channel estimation time information includes one or more of the following: Channel Impulse Response (CIR), Power Delay Profile (PDP), and Delay Profile (DP); the propagation time information includes, for example, Time of Arrival (TOA) and / or Time of Flight (TOF).
[0126] The target model is, for example, an artificial intelligence (AI) model, which can be used for positioning or beam management, but is not limited thereto.
[0127] The data representation refers to the target parameters being represented based on the reference time.
[0128] The training phase refers to the phase of training the target model, and the inference phase refers to the phase of using the trained target model to perform inference and prediction.
[0129] In the data processing method provided in this application embodiment, the first communication device determines a reference time for adjusting the target parameters in the dataset corresponding to the target model, so that the target parameters in the dataset corresponding to the target model can be adjusted based on the determined adjustment time, so that the target parameters in the dataset corresponding to the target model are all represented based on the reference time, and different devices have a consistent understanding of the target parameters. The dataset corresponding to the target model includes a first dataset in the model training stage and / or a second dataset in the model inference stage. In this way, it can be ensured that the data representation of the target model in the training stage is consistent with the data representation in the inference stage, thereby improving the performance of the target model.
[0130] As an optional implementation, the reference time includes at least one of the following:
[0131] The first communication device receives the subframe boundary where the reference signal is located;
[0132] The first communication device receives the time slot boundary where the reference signal is located.
[0133] It should be noted here that the reference signal includes: a Positioning Reference Signal (PRS) and / or a Sounding Reference Signal (SRS); wherein, the PRS includes a Downlink Positioning Reference (DL-PRS) and / or a Sidelink Positioning Reference (SL-PRS), and the SRS includes an Uplink Sounding Reference Signal (UL-SRS). Additionally, in this optional implementation, the reference signal may be a signal transmitted by a transmitting device in the target transmitting device group.
[0134] In other words, the reference time is the subframe / time slot boundary where the local timing reception reference signal is located.
[0135] in:
[0136] When the subframe boundary where the local timing reception reference signal is located is taken as the reference time, the reference time is defined as: T0+t SRS Where T0 is the nominal start time of SFN 0 provided by the System Frame Number (SFN) initialization time; t SRS =(10n) f +n sf )*10 -3 , where n f It is the system frame number of PRS / SRS, n sf It is the system subframe number of SRS / PRS;
[0137] When the slot boundary where the local timing reception reference signal is located is taken as the reference time, the reference time is defined as: T0+t slot Where T0 is the nominal start time of SFN 0 provided by the SFN initialization time; t slot =(10n) f +n sf +n slot )*10 -3 / 2 μ , where n f It is the system frame number of PRS / SRS, n sf It is the system subframe number of SRS / PRS, n slot is the slot number in the subframe, and μ is a parameter defined by the protocol.
[0138] As an optional implementation, the first dataset and / or the second dataset includes at least one of the following:
[0139] The channel measurement quantity includes the target parameter, and the channel measurement quantity is obtained by measuring the received reference signal; for example, the channel measurement quantity includes at least one of channel estimation H, time information of channel estimation H (belonging to the target parameter), power information of channel estimation H, and phase information of channel estimation H; wherein, the device transmitting the reference signal is, for example, one or more of UE, PRU, RSU, OBU, and TRP / gNB;
[0140] The first tag; also known as the real tag; for example, the first tag can be used for positioning and / or for beam management;
[0141] The quality of the first label; the quality of the first label is used to indicate the accuracy of the first label;
[0142] Confidence level of the first label;
[0143] The quality of the channel measurement; the quality of the channel measurement is used to represent the accuracy of the channel measurement;
[0144] Confidence level of channel measurements;
[0145] First timestamp; the first timestamp is related to the first tag and / or the channel measurement, and the first timestamp can be used to pair the channel measurement and the first tag. For example, the first timestamp is the time information when the first communication device receives the reference signal;
[0146] The identification (ID) information of the first communication device; the ID information of the first communication device can be used to pair the channel measurement quantity with the first tag;
[0147] The reference transmitting device is one of a group of target transmitting devices that send reference signals to the first communication device. Specifically, the reference transmitting device may be determined by the first communication device based on its internal implementation, or it may be selected from the transmitting devices recommended or specified by the second communication device.
[0148] As an example, the first dataset may include, but is not limited to, one or more of the following: channel measurement, first tag, quality of the first tag, confidence level of the first tag, quality of the channel measurement, confidence level of the channel measurement, first timestamp, ID information of the first communication device, and information of the reference transmitting device.
[0149] As another example, the second dataset may include, but is not limited to, one or more of the following: channel measurements, quality of channel measurements, confidence level of channel measurements, first timestamp, ID information of the first communication device, and information of the reference transmitting device.
[0150] As a specific implementation, the first tag includes at least one of the following:
[0151] The propagation time of the reference signal; wherein, the propagation time of the reference signal can be obtained by the location information of the device transmitting the reference signal; the propagation time of the reference signal can also be part of the target parameter, therefore, the propagation time of the reference signal can be represented based on the reference time; in addition, in AI positioning, the propagation time of the reference signal is used to assist positioning.
[0152] The first indication information includes: a line-of-sight (LOS) indication, or a non-line-of-sight (NLOS) indication; that is, the first indication information is used to indicate whether there is a visible path between the entities transmitting and receiving reference signals, wherein it can be obtained by the relationship between the actual propagation time of the reference signal and the propagation time of the reference signal (based on the actual propagation time represented by the reference time); in addition, in a positioning scenario, the first indication information can be used to assist in positioning.
[0153] Target time difference information; in a positioning scenario, the target time difference information can be used to assist in positioning;
[0154] The location information of the first communication device; the location information of the first communication device may be pre-calibrated location information or location information obtained by a positioning method. In the positioning scenario, the location information of the first communication device is used for direct positioning.
[0155] Information related to beam management; the information related to beam management includes beam ID and / or beam energy information, wherein the beam energy information includes, but is not limited to, one or more of the following: Reference Signal Received Power (RSRP), Signal Noise Ratio (SNR), and Signal to Interference plus Noise Ratio (SINR);
[0156] The second timestamp; the second timestamp is associated with the first tag, and the second timestamp can be used for pairing the first tag and the channel measurement; for example, the second timestamp can be the time when the second communication device sends information related to the first tag;
[0157] The ID of the first communication device is used for pairing the channel measurement with the first tag.
[0158] As a more specific implementation, the target time difference information includes at least one of the following:
[0159] The first time difference information includes: the time difference between the time when the first communication device receives the reference signal transmitted by each transmitting device in the target transmitting device group and the time when the reference transmitting device transmits the reference signal; that is, one reference signal received by the first communication device corresponds to one first time difference information, i.e., for one reference signal received by the first communication device, the first time difference information is the time difference between the time when the first communication device receives the reference signal and the time when the reference transmitting device transmits the same reference signal. Additionally, the first time difference information is, for example, the Reference Signal Time Difference (RSTD).
[0160] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0161] It should be noted here that, as mentioned above, the first time difference information is RSTD information, which is the difference between the propagation time of the UE and the regular TRP (the devices in the aforementioned target transmitting device group other than the reference transmitting device) and the propagation time of the UE and the reference TRP (the aforementioned reference transmitting device). The relevant definition of RSTD information can refer to the provisions in the existing protocol.
[0162] Furthermore, as an optional implementation, the method also includes at least one of the following:
[0163] Receive the first tag sent by the second communication device;
[0164] The first tag is obtained based on the information related to the first tag sent by the second communication device;
[0165] Wherein, the second communication device is a network-side device, for example, the second communication device includes an LMF entity and / or an Operations Administration and Maintenance (OAM) entity;
[0166] Specifically, the information related to the first tag includes at least one of the following:
[0167] The distance information between the first communication device and the transmitting device, wherein the transmitting device belongs to the target transmitting device group;
[0168] The timing information for the propagation of the reference signal between the first communication device and the transmitting device; wherein, this information may also be obtained based on the distance information between the first communication device and the transmitting device;
[0169] First auxiliary information;
[0170] A third timestamp; the third timestamp is associated with the first tag, and the third timestamp can be used for pairing the first tag and the channel measurement; wherein, the third timestamp may be the same as or different from the second timestamp; as an example, the third timestamp may be the time when the second communication device sends information related to the first tag;
[0171] Information about the reference transmitting device; the reference transmitting device may be represented as (Reference TRP), and the information about the reference transmitting device includes at least one of: PRS ID, Positioning Reference Signal Resource ID (PRS resource ID), and TRP ID.
[0172] As a specific implementation, the first auxiliary information includes at least one of the following:
[0173] The timing information of the transmitting device; wherein, the timing information of the transmitting device is used to obtain timing difference information between different transmitting devices;
[0174] The timing difference information between the transmitting devices refers to the timing difference information between different transmitting devices in the target transmitting device group.
[0175] Furthermore, as an optional implementation, the method also includes:
[0176] The information of the reference transmitting device is sent to the second communication device and / or the third communication device.
[0177] It should be noted that the reference transmitting device may be a device selected by the first communication device based on the target transmitting device group, or it may be a device selected by the first communication device based on the transmitting devices recommended or specified by the second communication device.
[0178] Alternatively, in this optional implementation, the information of the reference transmitting device may be sent to the second communication device and / or the third communication device when the first dataset and / or the second dataset does not include the information of the reference transmitting device.
[0179] In this optional implementation, by sending information about the reference transmitting device to the second communication device and / or the third communication device, the data representations in both the data collection phase and the inference phase are related to the reference transmitting device, thereby ensuring the consistency between the data representations in the data collection phase and the data representations in the inference phase.
[0180] Furthermore, as an optional implementation, the method also includes:
[0181] The first dataset and / or the second dataset are transmitted to a third communication device. Here, the target parameters in the first dataset and / or the second dataset have been adjusted based on the reference time.
[0182] Wherein, after the third communication device receives the first dataset and / or the second dataset, the third communication device will adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset according to a preset rule.
[0183] It should be noted that when the first dataset and / or the second dataset includes information about the reference transmitting device, the third communication device adjusts the position of the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset based on the information about the reference transmitting device and the preset rules. Therefore, when the first dataset and / or the second dataset does not include information about the reference transmitting device, before executing the steps of this optional implementation, the first communication device also needs to send the information about the reference transmitting device to the third communication device. The information about the reference transmitting device can indicate the position of the channel measurement quantity and / or the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset.
[0184] It should be noted here that the channel measurements corresponding to the reference transmitting device and / or the position of the first tag in the dataset (first dataset and / or second dataset) are not considered in the data collection phase and the inference phase. Figure 9In the case shown below, that is, when the first communication device does not adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset, in order to ensure the consistency of the reference transmitting device in the two stages, the following steps can be performed:
[0185] 1. The LMF entity (corresponding to the aforementioned third communication device) collects training data from different UEs (corresponding to the aforementioned first communication device). The dimensions of the training data are consistent, but the channel measurement and first tag position corresponding to the reference TRP (corresponding to the aforementioned reference transmitting device) are not fixed.
[0186] 2. Train an AI model (corresponding to the aforementioned target model) using the collected training data. The function of this model is to output RSTD labels relative to the reference TRP (corresponding to the aforementioned target time difference information / first time difference information) based on information such as CIR / PDP in the training data.
[0187] 3. When performing inference on the UE side, the order of reference TRPs is not considered, and N CIRs / PDPs are directly input into the AI model;
[0188] 4. The AI model outputs RSTD labels;
[0189] 5. The UE reports the RSTD tag and the corresponding reference TRP information (corresponding to the information of the aforementioned reference transmitting device).
[0190] Furthermore, as an optional implementation, the method also includes:
[0191] According to preset rules, the positions of the channel measurement quantity corresponding to the reference transmitting device and / or the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset are adjusted; specifically, the preset rule is to place the channel measurement quantity corresponding to the reference transmitting device and / or the first tag corresponding to the reference transmitting device in the nth position in the first dataset and / or the second dataset, where n∈{1…N}, N is the total amount of data in the first dataset and / or the second dataset, and the value of n can be based on pre-configuration / pre-definition;
[0192] The adjusted first dataset and / or second dataset are sent to a third communication device; wherein the third communication device includes, for example, one or more of an LMF entity, an OAM entity, a UE vendor entity, and other third-party devices.
[0193] Below, taking the first communication device as the UE and the third communication device as the LMF entity as an example, combined with... Figure 10 Examples related to the above optional implementation methods are explained, wherein, Figure 10 R-TRP in this context stands for reference-TRP (corresponding to the aforementioned reference transmitting device):
[0194] In this example, the data collection phase and the (model) inference phase consider the location of the channel measurements and / or the first tag corresponding to the reference transmitting device in the dataset (first dataset and / or second dataset). In this way, the location of the reference TRP is consistent in both the data collection and model inference phases and can be pre-configured, for example, the nth location is the reference TRP, such as... Figure 10 As shown, the first position is the Reference TRP; specifically, to ensure that the reference TRP positions for data collection are consistent, the following methods can be used:
[0195] (1) The reference TRP sorting is completed by the UE and then uploaded to the data collection entity (third communication device);
[0196] (2) Reference TRP sorting is performed by the data collection entity (third communication device);
[0197] In Method 2, during the inference phase, the UE needs to place the reference TRP in a specified / specific location, perform inference, and then report the RSTD to the LMF. If the LMF knows the pre-configuration information of the reference TRP, the UE does not need to report the reference TRP information to the LMF.
[0198] As an optional implementation, the target parameter includes channel estimation time information, which can be based on sampling points or non-sampling points; wherein, the channel estimation time information includes delay position, or, the channel estimation time information is represented by at least one of the following:
[0199] The first bitmap; that is, the channel estimation time information is transmitted in the form of a bitmap. In the first bitmap, the bits corresponding to the delays that need to be reported are 1, and the bits corresponding to the delays that do not need to be reported are 0. The length of the first bitmap is N.
[0200] The first bitmap and time slot offset; this case applies to the situation where the reference time is the boundary of the subframe where the first communication device receives the reference signal;
[0201] Additional path.
[0202] It should be noted here that the channel estimation time information includes the case of delay position, which is aimed at the case where the first communication device needs to directly report N' delay values that meet specific conditions / preset conditions / predefined conditions / first conditions. Here, N' can be pre-configured or predefined. The specific conditions / preset conditions / predefined conditions / first conditions can include at least one of the following: the path with power greater than the set threshold a, the first N' paths with larger power, and N' less than the set threshold b.
[0203] by Figure 11 For example, when reporting channel estimation time information in bitmap format, assuming the required reporting length is N, then compared with... Figure 11 The corresponding bitmap is: 01100100100000…; when the time information of channel estimation includes the delay position, it is consistent with… Figure 11 The corresponding delay position that needs to be reported can be represented as: 000000001 / 000000010 / 00000101 / 00001000.
[0204] As an optional implementation, when the channel measurement includes power information of the channel estimate H, this information is reported / transmitted in at least one of the following ways:
[0205] The uplink sounding reference signal received power (UL-SRS RSRP) or the uplink sounding reference signal received path power (UL-SRS RSRPP) are used in existing protocols.
[0206] The reference signal received by the direct link channel sounding reference signal (DL-SRS RSRP) or the reference signal received path power (DL-SRS RSRPP) in the existing protocol.
[0207] The reference signal received power (DL-SRS RSRP) or reference signal received path power (DL-SRS RSRPP) used in existing protocols for downlink channel sounding are used.
[0208] Embodiments of this application also provide a data processing method applied to a second communication device, wherein the second communication device is a network-side device, for example, the second communication device includes an LMF entity and / or an OAM entity; such as Figure 2 As shown, the method includes:
[0209] Step 201: Send a first tag to a first communication device; and / or send first tag-related information to the first communication device, wherein the first tag-related information is used by the first communication device to obtain the first tag, the first tag is carried in a first dataset, and the first dataset is the dataset of the training phase of the target model.
[0210] It should be noted that the target parameters in the first tag are adjusted by the reference time. Specifically, the target parameters include the propagation time information of the reference signal (such as TOA); that is, the target parameters in the first tag can be represented based on the reference time. In this way, it can be ensured that the propagation time representation of the reference signal sent by different transmitting devices to the first transmitting device is consistent, so that different devices have a consistent understanding of the target parameters, thereby improving the performance of the target model. In addition, the reference time includes the subframe boundary where the first communication device receives the reference signal, and / or the time slot boundary where the first communication device receives the reference signal.
[0211] In the embodiments of this application, the second communication device sends the first tag and / or first tag-related information to the first communication device, wherein the first tag-related information is used by the first communication device to obtain the first tag, the first tag is carried in a first dataset, and the first dataset is a dataset for the training phase of the target model; in this way, the first communication device can obtain target time difference information (such as RSTD) based on the received first tag and / or first tag-related information, thus providing a way for the first communication device to obtain RSTD, thereby generating a first dataset for training the target model.
[0212] Optionally, the first dataset may include one or more of the following: channel measurement, first tag, quality of the first tag, confidence level of the first tag, quality of the channel measurement, confidence level of the channel measurement, first timestamp, ID information of the first communication device, and information of the reference transmitting device, but is not limited thereto.
[0213] As an optional implementation, the first tag includes at least one of the following:
[0214] The propagation time of the reference signal; that is, the aforementioned target parameter in the embodiments of this application; therefore, the propagation time of the reference signal can be represented based on the reference time, wherein the propagation time of the reference signal can be obtained through the location information of the device transmitting the reference signal; in addition, in AI positioning, the propagation time of the reference signal is used to assist positioning;
[0215] The first indication information includes: LOS indication, or NLOS indication; that is, the first indication information is used to indicate whether there is a line of sight between the entities transmitting and receiving reference signals, wherein it can be obtained by the relationship between the actual propagation time of the reference signal and the propagation time of the reference signal; in addition, in the positioning scenario, the first indication information can be used to assist in positioning.
[0216] Target time difference information; in a positioning scenario, the target time difference information can be used to assist in positioning;
[0217] The location information of the first communication device; the location information of the first communication device may be pre-calibrated location information or location information obtained by a positioning method. In the positioning scenario, the location information of the first communication device is used for direct positioning.
[0218] Information related to beam management, including beam ID and / or beam energy information, wherein the beam energy information includes one or more of RSRP, SNR and SINR, but is not limited thereto.
[0219] As a specific implementation, the target time difference information includes at least one of the following:
[0220] First time difference information, which includes: the time difference between the time when the first communication device receives the reference signal transmitted by each transmitting device in the target transmitting device group and the time when the reference transmitting device transmits the reference signal; wherein, the target transmitting device group includes devices that transmit reference signals to the first communication device, and the reference transmitting device is one of the target transmitting device group; in addition, the first time difference information is, for example, the reference signal time difference (RSTD).
[0221] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0222] As an optional implementation, the information related to the first tag includes at least one of the following:
[0223] The distance information between the first communication device and the transmitting device, wherein the transmitting device is a device in the target transmitting device group that sends a reference signal to the first communication device;
[0224] The timing information for the propagation of the reference signal between the first communication device and the transmitting device; wherein, this information may also be obtained based on the distance information between the first communication device and the transmitting device;
[0225] First auxiliary information;
[0226] A third timestamp; the third timestamp is associated with the first tag, and the third timestamp can be used for pairing the first tag and the channel measurement; as an example, the third timestamp can be the time when the second communication device sends information related to the first tag;
[0227] The reference transmitting device is one of the target transmitting devices in the group. The reference transmitting device may be represented as (Reference TRP). The information of the reference transmitting device includes, but is not limited to, at least one of PRS ID, PRSresource ID and TRP ID.
[0228] It should be noted that the reference transmitting device may be a device selected by the first communication device based on the target transmitting device group, or it may be a device selected by the first communication device based on the transmitting devices recommended or specified by the second communication device.
[0229] Furthermore, as an optional implementation, prior to step 201, the method further includes:
[0230] Obtain first auxiliary information; here, the first auxiliary information may be provided by other devices (such as gNB) and / or known internally by the second communication device;
[0231] Receive information about the reference transmitting device sent by the first communication device;
[0232] Based on the first auxiliary information and / or the information of the reference transmitting device, obtain the first tag and / or information related to the first tag;
[0233] The reference transmitting device is one of the target transmitting devices in the group, and the target transmitting device includes a device that transmits a reference signal to the first communication device.
[0234] As a specific implementation, the first auxiliary information includes at least one of the following:
[0235] The timing information of the transmitting device; wherein, the timing information of the transmitting device is used to obtain timing difference information between different transmitting devices;
[0236] The timing difference information between the transmitting devices refers to the timing difference information between different transmitting devices in the target transmitting device group.
[0237] Below, in conjunction with Figure 8 This document describes an implementation example for obtaining first time difference information (such as RSTD), in which... Figure 8 In this context, UE represents the first communication device. Figure 8 In this context, LMF represents the second communication device. Figure 8 In this context, TRP1 and TRP2 represent different transmitting devices, with TRP1 being the reference transmitting device (reference TRP); assuming... Figure 8 The distances between TRP1 and TRP2 and the UE are d1 and d2, respectively. Based on this, the UE can obtain the first tag in any of the following ways:
[0238] Method 1: LMF provides real labels (such as RSTD); specifically, it includes the following two implementation methods:
[0239] Implementation method 1: The LMF knows the location information of TRP1, TRP2 and UE, obtains RSTD information according to (d1-d2) / c, and sends it to UE;
[0240] Implementation Method 2: The LMF knows the location information of TRP1, TRP2, and UE, and also knows the timing deviation Δt between TRP1 and TRP2. Based on the known information, the LMF calculates (d1-d2) / c+Δt to obtain the RSTD information and sends it to the UE. The Δt information may be provided to the LMF by the gNB. The auxiliary data transmitted from the gNB to the LMF can refer to the relevant provisions of the existing protocol.
[0241] Method 2: The UE provides a real tag (such as RSTD), which includes the following two implementation methods:
[0242] Implementation method 1: The UE knows the location information of TRP1, TRP2 and the UE, and obtains the RSTD information according to (d1-d2) / c;
[0243] Implementation Method 2: The UE knows the location information of TRP1, TRP2, and the UE, and the UE has obtained the timing deviation △t between TRP1 and TRP2. Based on the known information, (d1-d2) / c+△t is calculated to obtain the RSTD information. The timing deviation △t between TRP1 and TRP2 may be obtained by the LMF. The auxiliary data transmitted from the LMF to the UE can also refer to the relevant provisions of the existing protocol.
[0244] Below, in conjunction with Figure 4 and Figure 5 The process by which the first communication device generates the first dataset for the training phase through the interaction between the first and second communication devices is described below:
[0245] like Figure 4 As shown, firstly, the first communication device receives a reference signal (sent by the aforementioned transmitting device); secondly, the first communication device generates a channel measurement A (generated based on the received reference signal); thirdly, the second communication device acquires auxiliary information (corresponding to the aforementioned first auxiliary information); further, it generates a real label B (target time difference information corresponding to the reference signal received by the first communication device) based on the auxiliary information; then, the second communication device sends the real label B to the first communication device; finally, the first communication device generates training data (A, B, ...).
[0246] like Figure 5 As shown, firstly, the first communication device receives a reference signal (sent by the aforementioned transmitting device); secondly, the first communication device generates a channel measurement quantity A (generated based on the received reference signal); thirdly, the second communication device acquires auxiliary information (corresponding to the aforementioned first auxiliary information); then, the second communication device sends the auxiliary information to the first communication device; then, the first communication device generates a real label B (generated based on the auxiliary information); finally, the first communication device generates training data (A, B, ...).
[0247] Embodiments of this application also provide a data processing method applied to a third communication device. The third communication device is either a device for collecting training data or a device for model inference. The third communication device for collecting training data includes, for example, at least one of the following: an LMF entity, OAM, a UE vendor, and other third-party devices. The third communication device for model inference includes, for example, at least one of the following: an LMF entity, a TRP / gNB, and a UE. Figure 3 As shown, the method includes:
[0248] Step 301: Receive the dataset corresponding to the target model sent by the first communication device, wherein the target parameters in the dataset are information adjusted according to the reference time; to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0249] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0250] It should be noted that when the third communication device is used to collect training data, after receiving the dataset corresponding to the target model sent by the first communication device, the third communication device can provide the collected data to the device that performs model training; when the third communication device is used for model inference, after receiving the dataset corresponding to the target model sent by the first communication device, the third communication device can use the target model to perform inference based on the received dataset to obtain output information (such as RSTD) corresponding to the information input to the model.
[0251] The reference time includes: the subframe boundary where the first communication device receives the reference signal; and / or the time slot boundary where the first communication device receives the reference signal.
[0252] The first dataset and / or the second dataset includes at least one of the following: channel measurements, the channel measurements including the target parameters, the channel measurements being obtained by measuring a received reference signal; a first tag; the quality of the first tag; the confidence level of the first tag; the quality of the channel measurements; the confidence level of the channel measurements; a first timestamp; ID information of a first communication device; and information of a reference transmitting device, the reference transmitting device being one of a group of target transmitting devices that transmit reference signals to the first communication device.
[0253] In the embodiments of this application, a third communication device receives a dataset corresponding to a target model sent by a first communication device. The target parameters in the dataset are information adjusted according to a reference time to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase. The dataset corresponding to the target model includes a first dataset in the training phase and / or a second dataset in the inference phase. This ensures that different devices have a consistent understanding of the same data, thereby improving model performance.
[0254] Furthermore, as an optional implementation, the method also includes:
[0255] The system receives information about a reference transmitting device sent by the first communication device. The reference transmitting device is one of a group of target transmitting devices that transmit reference signals to the first communication device. Here, the information about the reference transmitting device may, for example, indicate the location of the channel measurement and / or the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset.
[0256] Furthermore, as an optional implementation, the method also includes:
[0257] According to preset rules, adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset.
[0258] Here, the adjustment process of the third communication device is similar to that of the first communication device. Specifically, it involves adjusting the channel measurement quantity corresponding to the reference transmission device and / or the position of the first tag corresponding to the reference transmission device in the first dataset and / or the second dataset according to preset rules and information of the reference transmission device. This will not be elaborated further here.
[0259] Below, in conjunction with Figure 6 and Figure 7 The process of reporting the first and second datasets through the interaction between the first and third communication devices is described below:
[0260] like Figure 6 As shown, firstly, the first communication device obtains training data (A, B, ...) (corresponding to the first dataset); secondly, the first communication device sends the training data (A, B, ...) to the third communication device; as... Figure 7 As shown, the first communication device obtains inference data (A, ...) (corresponding to the second dataset); then, the first communication device sends the inference data (A, ...) to the third communication device.
[0261] It should be noted that the relevant content of the above methods can be referred to each other, and the repeated parts will not be repeated.
[0262] The data processing method provided in this application is specifically a method to improve AI positioning performance. By setting a reference time, the consistency of data representation in the training and inference phases can be guaranteed, thereby ensuring model performance. When the model output is target time difference information (such as RSTD), a selection rule for the reference TRP that the UE-side AI model needs to align in the training and inference phases is provided to ensure consistency between the training and inference phases. Furthermore, a method and process for obtaining training data labels (target time difference information) of the AI positioning model is provided, filling the current gap in the lack of methods and processes for obtaining target time difference information.
[0263] Embodiments of this application also provide a data processing apparatus, applied to a first communication device, such as... Figure 12 As shown, the device includes:
[0264] The determination module 1201 is used to determine the reference time of the target parameters. The reference time is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0265] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0266] Optionally, the reference time includes at least one of the following:
[0267] The first communication device receives the subframe boundary where the reference signal is located;
[0268] The first communication device receives the time slot boundary where the reference signal is located.
[0269] Optionally, the first dataset and / or the second dataset includes at least one of the following:
[0270] Channel measurements, including the target parameters, are obtained by measuring a received reference signal;
[0271] First label;
[0272] The quality of the first label;
[0273] Confidence level of the first label;
[0274] The quality of channel measurements;
[0275] Confidence level of channel measurements;
[0276] First timestamp;
[0277] The identification ID information of the first communication device;
[0278] Information about the reference transmitting device, wherein the reference transmitting device is one of a group of target transmitting devices that transmit reference signals to the first communication device.
[0279] Optionally, the first label includes at least one of the following:
[0280] The propagation time of the reference signal;
[0281] The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication;
[0282] Target time difference information;
[0283] Location information of the first communication device;
[0284] Information related to beam management;
[0285] Second timestamp;
[0286] ID information of the first communication device.
[0287] Optionally, the target time difference information includes at least one of the following:
[0288] First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal;
[0289] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0290] Optionally, the device further includes at least one of the following:
[0291] The receiving module is used to receive the first tag sent by the second communication device;
[0292] The acquisition module is used to obtain the first tag based on the first tag-related information sent by the second communication device;
[0293] The first tag-related information includes at least one of the following:
[0294] The distance information between the first communication device and the transmitting device, wherein the transmitting device belongs to the target transmitting device group;
[0295] First auxiliary information;
[0296] Third timestamp;
[0297] Refer to the information of the transmitting device.
[0298] Optionally, the first auxiliary information includes at least one of the following:
[0299] The timing information of the transmitting device;
[0300] The timing difference information between the transmitting devices.
[0301] Optionally, the device further includes:
[0302] The first transmitting module is used to transmit information about the reference transmitting device to the second communication device and / or the third communication device.
[0303] Optionally, the device further includes:
[0304] The second sending module is used to send the first dataset and / or the second dataset to the third communication device.
[0305] Optionally, the device further includes:
[0306] The adjustment module is used to adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset according to preset rules;
[0307] The third sending module is used to send the adjusted first dataset and / or the second dataset to the third communication device.
[0308] Optionally, the target parameter includes time information for channel estimation; wherein the time information for channel estimation includes delay position, or the time information for channel estimation is represented by at least one of the following:
[0309] First image bitmap;
[0310] First bitmap and slot offset;
[0311] Additional path.
[0312] It should be noted that the data processing apparatus provided in this application embodiment can implement all the method steps implemented in the data processing method embodiment of the first communication device side, 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.
[0313] Embodiments of this application also provide a data processing apparatus, applied to a second communication device, such as... Figure 13 As shown, the device includes:
[0314] Sending module 1301 is configured to perform at least one of the following:
[0315] Send the first tag to the first communication device;
[0316] Send first tag-related information to the first communication device. The first tag-related information is used by the first communication device to obtain the first tag. The first tag is carried in the first dataset, which is the dataset used in the training phase of the target model.
[0317] Optionally, the first label includes at least one of the following:
[0318] The propagation time of the reference signal;
[0319] The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication;
[0320] Target time difference information;
[0321] Location information of the first communication device;
[0322] Information related to beam management;
[0323] Second timestamp;
[0324] ID information of the first communication device.
[0325] Optionally, the target time difference information includes at least one of the following:
[0326] First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal; wherein, the target transmitting device group includes devices that send reference signals to the first communication device, and the reference transmitting device is one of the target transmitting device group;
[0327] The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
[0328] Optionally, the information related to the first tag includes at least one of the following:
[0329] The distance information between the first communication device and the transmitting device, wherein the transmitting device is a device in the target transmitting device group that sends a reference signal to the first communication device;
[0330] First auxiliary information;
[0331] Third timestamp;
[0332] Information about a reference transmitting device, wherein the reference transmitting device is one of the target transmitting devices in the group.
[0333] Optionally, the device further includes:
[0334] The first acquisition module is used to acquire first auxiliary information;
[0335] A receiving module is used to receive information about a reference transmitting device sent by the first communication device;
[0336] The second acquisition module is used to acquire the first tag and / or information related to the first tag based on the first auxiliary information and / or the information of the reference transmitting device;
[0337] The reference transmitting device is one of the target transmitting devices in the group, and the target transmitting device includes a device that transmits a reference signal to the first communication device.
[0338] Optionally, the first auxiliary information includes at least one of the following:
[0339] The timing information of the transmitting device;
[0340] The timing difference information between the transmitting devices.
[0341] It should be noted that the data processing apparatus provided in this application embodiment can implement all the method steps implemented in the data processing method embodiment on the second communication device side, 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.
[0342] Embodiments of this application also provide a data processing apparatus applied to a third communication device, such as... Figure 14 As shown, it includes:
[0343] The first receiving module 1401 is used to receive a dataset corresponding to the target model sent by the first communication device, wherein the target parameters in the dataset are information adjusted according to the reference time, so as to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase.
[0344] The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase.
[0345] Optionally, the device further includes:
[0346] The second receiving module is used to receive information about a reference transmitting device sent by the first communication device, wherein the reference transmitting device is one of a group of target transmitting devices that send reference signals to the first communication device.
[0347] Optionally, the device further includes:
[0348] The adjustment module is used to adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset according to preset rules.
[0349] It should be noted that the data processing apparatus provided in this application embodiment can implement all the method steps implemented in the data processing method embodiment on the third communication device side, 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.
[0350] An embodiment of this application also provides a communication device, including: a transceiver 1510, a processor 1500, a memory 1520, and a program or instructions stored in the memory 1520 and executable on the processor 1500. When the program or instructions are executed by the processor 1500, they implement the data processing method applied to a first communication device as described above, or implement the data processing method applied to a second communication device as described above, or implement the data processing method applied to a third communication device as described above.
[0351] The transceiver 1510 is used to receive and send data under the control of the processor 1500.
[0352] Among them, Figure 15 In this context, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 1500) and memory (memory 1520). The bus architecture may also link together 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 1510 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium. The processor 1500 is responsible for managing the bus architecture and general processing, and the memory 1520 may store data used by the processor 1500 during operation.
[0353] It should be noted that the communication device provided in this application embodiment can implement the data processing method applied to the first communication device as described above, or implement the data processing method applied to the second communication device as described above, or implement the data processing method applied to the third communication device as described above, and can achieve the same technical effect. Here, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail.
[0354] This application also provides a readable storage medium storing a program. When executed by a processor, this program can implement the data processing method described above for a first, second, or third communication device, achieving the same technical effect. To avoid repetition, it will not be described again here. The readable storage medium may be, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0355] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, disk, optical disk) and includes several instructions for executing the methods described in the various embodiments of this application.
[0356] Therefore, embodiments of this application also provide a computer program product, including computer instructions. When the computer instructions are executed by a processor, they can implement the data processing method applied to the first communication device, the second communication device, or the third communication device as described above, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described in detail.
[0357] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0358] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles described in this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A data processing method, characterized in that, Applied to a first communication device, including: A reference time for determining the target parameters is used to adjust the target parameters in the dataset corresponding to the target model, so as to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase. The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase. The reference time includes at least one of the following: The first communication device receives the subframe boundary where the reference signal is located; The first communication device receives the time slot boundary where the reference signal is located.
2. The method according to claim 1, characterized in that, The first dataset and / or the second dataset includes at least one of the following: Channel measurements, including the target parameters, are obtained by measuring a received reference signal; First label; The quality of the first label; Confidence level of the first label; The quality of channel measurements; Confidence level of channel measurements; First timestamp; The identification ID information of the first communication device; Information about the reference transmitting device, wherein the reference transmitting device is one of a group of target transmitting devices that transmit reference signals to the first communication device.
3. The method according to claim 2, characterized in that, The first label includes at least one of the following: The propagation time of the reference signal; The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication; Target time difference information; Location information of the first communication device; Information related to beam management; Second timestamp; ID information of the first communication device.
4. The method according to claim 3, characterized in that, The target time difference information includes at least one of the following: First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal; The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
5. The method according to claim 2, characterized in that, The method further includes at least one of the following: Receive the first tag sent by the second communication device; The first tag is obtained based on the information related to the first tag sent by the second communication device; The first tag-related information includes at least one of the following: The distance information between the first communication device and the transmitting device, wherein the transmitting device belongs to the target transmitting device group; First auxiliary information; Third timestamp; Refer to the information of the transmitting device.
6. The method according to claim 4 or 5, characterized in that, The first auxiliary information includes at least one of the following: The timing information of the transmitting device; The timing difference information between the transmitting devices.
7. The method according to claim 2, characterized in that, The method further includes: The information of the reference transmitting device is sent to the second communication device and / or the third communication device.
8. The method according to claim 2 or 7, characterized in that, The method further includes: Send the first dataset and / or the second dataset to a third communication device.
9. The method according to claim 2, characterized in that, The method further includes: According to preset rules, adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset; Send the adjusted first dataset and / or second dataset to a third communication device.
10. The method according to claim 1, characterized in that, The target parameters include time information for channel estimation; wherein, the time information for channel estimation includes delay position, or, the time information for channel estimation is represented by at least one of the following: First image bitmap; First bitmap and slot offset; Additional path.
11. A data processing method, characterized in that, Applied to a second communication device, including at least one of the following: Send the first tag to the first communication device; Send first tag-related information to the first communication device. The first tag-related information is used by the first communication device to obtain the first tag. The first tag is carried in the first dataset, which is the dataset of the training phase of the target model. Wherein, the first communication device is used for: A reference time for determining the target parameters is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency of the data representation of the target model during the training phase and the data representation during the inference phase; wherein, the dataset corresponding to the target model includes a first dataset during the training phase and / or a second dataset during the inference phase; the reference time includes at least one of the following: the subframe boundary where the first communication device receives the reference signal; the time slot boundary where the first communication device receives the reference signal; The first label includes the target parameters.
12. The method according to claim 11, characterized in that, The first label includes at least one of the following: The propagation time of the reference signal; The first indication information includes: line-of-sight (LOS) indication, or non-line-of-sight (NLOS) indication; Target time difference information; Location information of the first communication device; Information related to beam management; Second timestamp; ID information of the first communication device.
13. The method according to claim 12, characterized in that, The target time difference information includes at least one of the following: First time difference information, the first time difference information includes: the time difference between the time when the first communication device receives the reference signal sent by each of the transmitting devices in the target transmitting device group and the time when the reference transmitting device sends the reference signal; wherein, the target transmitting device group includes devices that send reference signals to the first communication device, and the reference transmitting device is one of the target transmitting device group; The second time difference information includes: the time difference after adjusting the first time difference information using the first auxiliary information.
14. The method according to claim 11, characterized in that, The information related to the first tag includes at least one of the following: The distance information between the first communication device and the transmitting device, wherein the transmitting device is a device in the target transmitting device group that sends a reference signal to the first communication device; First auxiliary information; Third timestamp; Information about a reference transmitting device, wherein the reference transmitting device is one of the target transmitting devices in the group.
15. The method according to any one of claims 11 to 14, characterized in that, Before sending the first tag to the first communication device, and / or sending information related to the first tag to the first communication device, the method further includes: Obtain first auxiliary information; Receive information about the reference transmitting device sent by the first communication device; Based on the first auxiliary information and / or the information of the reference transmitting device, obtain the first tag and / or information related to the first tag; The reference transmitting device is one of the target transmitting devices in the group, and the target transmitting device includes a device that transmits a reference signal to the first communication device.
16. The method according to claim 14, characterized in that, The first auxiliary information includes at least one of the following: The timing information of the transmitting device; The timing difference information between the transmitting devices.
17. A data processing method, characterized in that, Applied to third-party communication devices, including: The system receives a dataset corresponding to the target model sent by a first communication device, wherein the target parameters in the dataset are information adjusted according to a reference time; in order to ensure the consistency of the data representation of the target model during the training phase and the data representation during the inference phase. The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase. The reference time includes at least one of the following: the subframe boundary where the first communication device receives the reference signal; and the time slot boundary where the first communication device receives the reference signal.
18. The method according to claim 17, characterized in that, The method further includes: The device receives information about a reference transmitting device sent by the first communication device, wherein the reference transmitting device is one of a group of target transmitting devices that send reference signals to the first communication device.
19. The method according to claim 18, characterized in that, The method further includes: According to preset rules, adjust the channel measurement quantity corresponding to the reference transmitting device and / or the position of the first tag corresponding to the reference transmitting device in the first dataset and / or the second dataset.
20. A data processing apparatus, characterized in that, Applied to a first communication device, including: The determination module is used to determine the reference time for the target parameters. The reference time is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase. The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase. The reference time includes at least one of the following: The first communication device receives the subframe boundary where the reference signal is located; The first communication device receives the time slot boundary where the reference signal is located.
21. A data processing apparatus, characterized in that, Applied to a second communication device, including: The sending module is configured to perform at least one of the following: Send the first tag to the first communication device; Send first tag-related information to the first communication device. The first tag-related information is used by the first communication device to obtain the first tag. The first tag is carried in the first dataset, which is the dataset of the training phase of the target model. Wherein, the first communication device is used for: A reference time for determining the target parameters is used to adjust the target parameters in the dataset corresponding to the target model to ensure the consistency of the data representation of the target model during the training phase and the data representation during the inference phase; wherein, the dataset corresponding to the target model includes a first dataset during the training phase and / or a second dataset during the inference phase; the reference time includes at least one of the following: the subframe boundary where the first communication device receives the reference signal; the time slot boundary where the first communication device receives the reference signal; The first label includes the target parameters.
22. A data processing apparatus, characterized in that, Applied to third-party communication devices, including: The receiving module is used to receive a dataset corresponding to the target model sent by the first communication device, wherein the target parameters in the dataset are information adjusted according to the reference time; so as to ensure the consistency of the data representation of the target model in the training phase and the data representation in the inference phase. The dataset corresponding to the target model includes a first dataset for the training phase and / or a second dataset for the inference phase. The reference time includes at least one of the following: the subframe boundary where the first communication device receives the reference signal; and the time slot boundary where the first communication device receives the reference signal.
23. A communication device, characterized in that, include: A transceiver, a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the data processing method as described in any one of claims 1 to 10, or implement the data processing method as described in any one of claims 11 to 16, or implement the data processing method as described in any one of claims 17 to 19.
24. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the data processing method as described in any one of claims 1 to 10, or implement the data processing method as described in any one of claims 11 to 16, or implement the data processing method as described in any one of claims 17 to 19.
25. A computer program product, characterized in that, The method includes computer instructions that, when executed by a processor, implement the data processing method as described in any one of claims 1 to 10, or implement the data processing method as described in any one of claims 11 to 16, or implement the data processing method as described in any one of claims 17 to 19.
Citation Information
Patent Citations
AI network model training method, positioning method, device and communication equipment
CN117574951A
Positioning configuration management for ML training and inference
TW202408287A