Data processing method and communication device

Abstract

The present application provides a data processing method and a communication device. The method includes: receiving or transmitting a plurality of reference signals; acquiring a first channel data set, which is a set of a plurality of channel data acquired based on the plurality of reference signals; acquiring a data quality screening policy, the data quality screening policy being used to acquire model training data that meets a data quality condition by screening; and screening the channel data in the first channel data set according to the data quality screening policy to acquire a training data set. In this way, the quality of the training data for model training is improved, so that the trained intelligent model meets the performance requirement.

Description

[Technical field]

[0001]

[0001] This application claims priority to Chinese Patent Application No. 202111406870.5, entitled "DATA PROCESSING METHOD AND COMMUNICATION DEVICE", filed with the State Intellectual Property Office of the People's Republic of China on November 24, 2021, the entire contents of which are incorporated herein by reference.

[0002]

[0002] TECHNICAL FIELD The present application relates to the field of communications, and more particularly to a data processing method and a communications device. [Background technology]

[0003]

[0003] Applying artificial intelligence (AI) to wireless communication systems has become a current research hotspot in order to improve communication performance. Wireless channel data is the necessary data for applying AI, training AI models, and verifying the performance of AI models.

[0004]

[0004] By performing modeling on the wireless channel, simulated channel data can be obtained. However, the wireless channel environment is complex and variable, and the simulated channel data differs from the actual channel data. Therefore, currently, the actually measured channel data set obtained by measuring the reference signal by the wireless communication device is mainly used as the training sample or sample label of the AI ​​model. However, in reality, the actually measured channel data is affected by the noise of the internal components of the communication device, the calibration error of the communication system, etc. As a result, during validation, there is still a large deviation in the performance of the AI ​​model obtained based on the actually measured channel data. Summary of the Invention

[0005]

[0005] Embodiments of the present application provide a data processing method and a communication device to improve the quality of training data for model training, and ensure that the trained intelligent model meets performance requirements.

[0006] According to a first aspect, there is provided a communication method, the method being capable of being performed by a communication device or a module (eg a chip) configured in (or used in) a communication device.

[0007]

[0007] The method includes: a step of receiving or transmitting a plurality of reference signals; a step of acquiring a first channel data set, the first channel data set being a set of a plurality of channel data acquired based on the plurality of reference signals; a step of acquiring a data quality screening policy, the data quality screening policy being used to acquire, by screening, model training data that satisfies a data quality condition; and a step of screening the channel data in the first channel data set in accordance with the data quality screening policy to acquire a training data set.

[0008]

[0008] According to the above solution, the first device can obtain channel data that satisfies a data quality condition from a channel data set obtained by measurement according to a data quality screening policy, so that an intelligent model obtained by training based on the screened training data set can satisfy a performance condition, and thus the intelligent model is used in wireless communication to improve communication quality.

[0009]

[0009] Regarding the first aspect, in some implementations of the first aspect, the data quality screening policy may include: Screening policy based on received power stability of the same reference signal; Screening policy based on the transmission delay stability of the reference signal; A screening policy based on the phase stability of different channel data components corresponding to the same transceiver antenna pair; a screening policy based on the received signal-to-noise ratio of the reference signal; and Screening policies based on channel type diversity; Contains one or more of the following:

[0010]

[0010] According to the aforementioned solution, the data quality screening policy may be a screening policy based on one or more of the following: a received power stability condition, a transmission delay stability condition of the reference signal, a phase stability condition, a received signal-to-noise ratio condition of the reference signal, and a diversity condition of the training data. In this way, the first device can obtain channel data that meets the conditions by screening as training data, and eliminate channel data that cannot truly reflect the channel state due to errors in the channel data caused by noise of the components of the communication device that measure the channel data, and / or time and / or frequency asynchrony of the reference signal of the transceiver device, etc. The performance of the intelligent model is improved, and as a result, the intelligent model can be used in the communication system to improve communication quality.

[0011]

[0011] Regarding the first aspect, in some implementations of the first aspect, a screening policy based on received power stability of the same reference signal includes: A difference in received power when the same reference signal is received by different receiving antennas corresponding to one channel data is equal to or less than a first threshold value. The method includes selecting channel data that satisfies the received power stability condition as training data.

[0012]

[0012] Regarding the first aspect, in some implementations of the first aspect, the different receiving antennas are two receiving antennas that are spatially adjacent to each other and have the same polarization direction.

[0013]

[0013] Regarding the first aspect, in some implementations of the first aspect, the screening policy based on the transmission delay stability of the reference signal includes: The difference in transmission delays of the reference signals of different transceiver antenna pairs corresponding to one channel data is equal to or less than a second threshold value. and selecting, as training data, channel data that satisfies a delay stability condition:

[0014]

[0014] Regarding the first aspect, in some implementations of the first aspect, a screening policy based on phase stability of different channel data components corresponding to the same transceiver antenna pair includes: The phase difference value of the channel data components of the same transceiver antenna pair in multiple channel data acquired within a preset interval is equal to or less than a third threshold value. and selecting, as training data, channel data that satisfies a phase stability condition:

[0015]

[0015] Regarding the first aspect, in some implementations of the first aspect, the screening policy based on the received signal-to-noise ratio of the reference signal includes: The method includes using, as training data, channel data corresponding to the reference signal, the received signal-to-noise ratio of which is equal to or greater than a fourth threshold.

[0016]

[0016] Regarding the first aspect, in some implementations of the first aspect, the screening policy based on channel type diversity may be one of the following: where N pieces of line-of-sight LOS channel data and M pieces of non-line-of-sight NLOS channel data are selected to form a training data set, where N and M are positive integers; The ratio of LOS channel data to NLOS channel data in the training data set is a predefined ratio; and the Q channel data are selected to form a training data set if the Q channel data include at least N LOS channel data and at least M NLOS channel data, where Q>N+M; Contains one or more of the following:

[0017]

[0017] With regard to the first aspect, in some implementations of the first aspect, the step of transmitting a plurality of reference signals includes a step of transmitting a plurality of reference signals to a second device; and the step of acquiring a first channel data set includes a step of receiving the first channel data set from the second device.

[0018]

[0018] According to the above solution, the first device can transmit a reference signal to the second device, and obtain a channel data set obtained by measuring the reference signal by the first device, so that actual measured channel data can be obtained, and the data obtained by screening the actual measured channel data can be used for training an intelligent model.

[0019]

[0019] With regard to the first aspect, in some implementations of the first aspect, the step of receiving a plurality of reference signals includes a step of receiving a plurality of reference signals from a second device; and the step of acquiring a first channel data set includes a step of measuring the plurality of reference signals to acquire the first channel data set.

[0020]

[0020] According to the above solution, the first device can receive a reference signal from the second device and measure the reference signal to obtain actual measured channel data, so that the data obtained by screening the actual measured channel data can be used for training an intelligent model.

[0021]

[0021] Regarding the first aspect, in some implementations of the first aspect, the method further includes a step of training the intelligent model by using the training data set.

[0022]

[0022] According to the above solution, the first device may be an intelligent model training device. After performing data quality screening on the channel data obtained by actual measurement (i.e., real measurement), model training is performed by using the channel data that meets the condition and is obtained by screening. An intelligent model that meets the performance condition can be obtained.

[0023]

[0023] Regarding the first aspect, in some implementations of the first aspect, obtaining the data quality screening policy includes: receiving first information, the first information indicating the data quality screening policy. Regarding the first aspect, in some implementations of the first aspect, the first information is included in a first message, the first message is used to request a training data set for the intelligent model. The method further includes transmitting the training data set.

[0024]

[0024] According to the above solution, the channel data can be collected by the first device, and the training of the intelligent model can be performed by another node (third device) in the network. The third device can indicate a data quality screening policy to the first device based on the data quality condition, so that the first device can provide the third device with channel data that meets the data quality condition, and the intelligent model obtained by training by the third device based on the channel data set that meets the condition can meet the performance condition.

[0025]

[0025] Regarding the first aspect, in some implementations of the first aspect, the first message further includes second information, and the second information indicates a dimension arrangement manner of the training data set. Screening the channel data in the first channel data set according to the data quality screening policy to obtain the training data set includes: screening the first channel data set according to the data quality screening policy to obtain a plurality of channel data; and arranging the plurality of channel data in a dimension arrangement manner to obtain the training data set.

[0026]

[0026] According to the above solution, the first device performs a dimensional transformation on the channel data based on a dimension configuration method, so that the training data meets the training data dimension definition of the intelligent model.

[0027]

[0027] Regarding the first aspect, in some implementations of the first aspect, the first message further includes third information, and the third information indicates filtering the channel data obtained by screening. The step of screening the channel data in the first channel data set according to the data quality screening policy to obtain a training data set includes: screening the first channel data set according to the data quality screening policy to obtain a plurality of channel data; and filtering the plurality of channel data to obtain a training data set, where the training data set includes data obtained by filtering the plurality of channel data.

[0028]

[0028] According to the above solution, the first device can filter the channel data to reduce noise interference.

[0029]

[0029] Regarding the first aspect, in some implementations of the first aspect, the first information is included in a second message, and the second message is used to request to evaluate channel data in a channel data set that satisfies a data quality condition. The method further includes: transmitting fourth information, the fourth information indicating a data amount, the data amount being an amount of data in the channel data set that satisfies the data quality condition; receiving the first message, the first message being used to request a training data set; and transmitting the training data set.

[0030]

[0030] With regard to the first aspect, in some implementations of the first aspect, the first message includes second information and / or third information, where the second information indicates a dimension configuration manner of the training data set, and the third information indicates filtering of the channel data obtained by screening.

[0031] According to a second aspect, there is provided a data processing method, the method being capable of being performed by a communications device or a module (e.g. a chip) configured in (or used in) a communications device.

[0032]

[0032] The method includes: a step of transmitting first information, where the first information indicates a data quality screening policy, the data quality screening policy being used to obtain, by screening, model training data that satisfies a data quality condition; a step of receiving a training data set from the first device, where the training data set includes channel data that satisfies the data quality condition; and a step of training an intelligent model by using the training data set.

[0033]

[0033] With respect to the second aspect, in some implementations of the second aspect, the data quality screening policy is one of the following: Screening policy based on received power stability of the same reference signal; Screening policy based on the transmission delay stability of the reference signal; A screening policy based on the phase stability of different channel data components corresponding to the same transceiver antenna pair; a screening policy based on the received signal-to-noise ratio of the reference signal; and Screening policies based on channel type diversity; Contains one or more of the following:

[0034]

[0034] Regarding the second aspect, in some implementations of the second aspect, a screening policy based on received power stability of the same reference signal includes: A difference in received power when the same reference signal is received by different receiving antennas corresponding to one channel data is equal to or less than a first threshold value. The method includes selecting channel data that satisfies the received power stability condition as training data.

[0035]

[0035] Regarding the second aspect, in some implementations of the second aspect, the different receiving antennas are two receiving antennas that are spatially adjacent to each other and have the same polarization direction.

[0036]

[0036] Regarding the second aspect, in some implementations of the second aspect, the screening policy based on the transmission delay stability of the reference signal includes: The difference in transmission delays of the reference signals of different transceiver antenna pairs corresponding to one channel data is equal to or less than a second threshold value. and selecting, as training data, channel data that satisfies the delay stability condition:

[0037]

[0037] With respect to the second aspect, in some implementations of the second aspect, the screening policy based on phase stability of different channel data components corresponding to the same transceiver antenna pair includes: The phase difference value of the channel data components of the same transceiver antenna pair in multiple channel data acquired within a preset interval is equal to or less than a third threshold value. and selecting, as training data, channel data that satisfies the phase stability condition:

[0038]

[0038] Regarding the second aspect, in some implementations of the second aspect, the screening policy based on the received signal-to-noise ratio of the reference signal includes: The method includes using, as training data, channel data corresponding to the reference signal, the received signal-to-noise ratio of which is equal to or greater than a fourth threshold.

[0039]

[0039] Regarding the second aspect, in some implementations of the second aspect, the screening policy based on channel type diversity may be one of the following: where N pieces of line-of-sight LOS channel data and M pieces of non-line-of-sight NLOS channel data are selected to form a training data set, where N and M are positive integers; The ratio of LOS channel data to NLOS channel data in the training data set is a predefined ratio; and the Q channel data are selected to form a training data set if the Q channel data include at least N LOS channel data and at least M NLOS channel data, where Q>N+M; Contains one or more of the following:

[0040]

[0040] With respect to the second aspect, in some implementations of the second aspect, the first information is included in a first message, and the first message is used to request a training data set for the intelligent model.

[0041]

[0041] Regarding the second aspect, in some implementations of the second aspect, the first message further includes second information, where the second information indicates a dimension configuration manner of the training data set, and the configuration manner of the channel data in the training data set is the dimension configuration manner.

[0042]

[0042] Regarding the second aspect, in some implementations of the second aspect, the first message further includes third information, and the third information indicates filtering of the channel data obtained by screening.

[0043]

[0043] Regarding the second aspect, in some implementations of the second aspect, the first information is included in a second message, and the second message is used to request the evaluation of channel data in the channel data set that satisfies a data quality condition. The method further includes the steps of receiving fourth information from the first device, the fourth information indicating a data amount, the data amount being an amount of data in the channel data set that satisfies the data quality condition; and sending the first message to the first device, the first message being used to request the training data set.

[0044]

[0044] Regarding the second aspect, in some implementations of the second aspect, the first message includes second information and / or third information, where the second information indicates a dimension configuration manner of the training data set, and the third information indicates filtering of the channel data obtained by screening.

[0045] According to a third aspect, there is provided a communications apparatus. In design, the apparatus may include modules that correspond one-to-one to the methods / operations / steps / actions described in the first aspect. The modules may be hardware circuits or software, or may be implemented by a combination of hardware circuits and software. In design, the apparatus may: a transceiver unit configured to receive or transmit a plurality of reference signals; an acquisition unit configured to acquire a first channel data set, the first channel data set being a set of multiple channel data acquired based on multiple reference signals, the acquisition unit further configured to acquire a data quality screening policy, the data quality screening policy being used to acquire, by screening, model training data that satisfies a data quality condition; and The processing unit is configured to screen the channel data in the first channel data set according to a data quality screening policy to obtain a training data set.

[0046]

[0046] The data quality screening policy is the same as that in the first embodiment, and the details will not be described again here.

[0047]

[0047] With regard to the third aspect, in some implementations of the third aspect, the transceiver unit is specifically configured to transmit a plurality of reference signals to the second device; and the acquisition unit is specifically configured to receive a first channel data set from the second device.

[0048]

[0048] With regard to the third aspect, in some implementations of the third aspect, the transceiver unit is specifically configured to receive a plurality of reference signals from the second device; and the acquisition unit is specifically configured to measure the plurality of reference signals to acquire the first channel data set.

[0049]

[0049] With respect to the third aspect, in some implementations of the third aspect, the processing unit is further configured to train the intelligent model by using the training data set.

[0050]

[0050] With regard to the third aspect, in some implementations of the third aspect, the acquisition unit is specifically configured to receive first information, where the first information indicates a data quality screening policy.

[0051]

[0051] With regard to the third aspect, in some implementations of the third aspect, the first information is included in a first message, the first message is used to request a training data set for the intelligent model, and the transceiver unit is further configured to transmit the training data set.

[0052]

[0052] With regard to the third aspect, in some implementations of the third aspect, the first message further includes second information, the second information indicating a dimension configuration manner of the training data set, and the processing unit is further configured to screen the first channel data set according to the data quality screening policy to obtain multiple channel data; and configure the multiple channel data in the dimension configuration manner to obtain the training data set.

[0053]

[0053] With regard to the third aspect, in some implementations of the third aspect, the first message further includes third information, where the third information indicates filtering the channel data obtained by screening; the processing unit is specifically configured to screen the first channel data set according to the data quality screening policy to obtain the plurality of channel data; and filter the plurality of channel data to obtain a training data set, where the training data set includes data obtained by filtering the plurality of channel data.

[0054]

[0054] With regard to the third aspect, in some implementations of the third aspect, the first information is included in a second message, the second message is used to request evaluation of channel data in the channel data set that satisfies a data quality condition, and the transceiver unit is further configured to: transmit fourth information, the fourth information indicating an amount of data, the amount of data being an amount of data in the channel data set that satisfies the data quality condition; the transceiver unit is further configured to receive the first message, which is used to request a training data set; and transmit the training data set.

[0055]

[0055] Regarding the third aspect, in some implementations of the third aspect, the first message includes second information and / or third information, where the second information indicates a dimension configuration manner of the training data set, and the third information indicates filtering of the channel data obtained by screening.

[0056] According to a fourth aspect, there is provided a communications apparatus. In design, the apparatus may include modules that correspond one-to-one to the methods / operations / steps / actions described in the first aspect. The modules may be hardware circuits or software, or may be implemented by a combination of hardware circuits and software. In design, the apparatus may: a transceiver unit configured to transmit first information, the first information indicating a data quality screening policy, the data quality screening policy being used to obtain, by screening, model training data that satisfies a data quality condition; a transceiver unit configured to receive a training data set from a first device, the training data set including channel data that satisfies a data quality condition; and The processing unit is configured to train the intelligent model by using the training data set.

[0057]

[0057] The data quality screening policy is the same as that in the second embodiment, and the details will not be described again here.

[0058]

[0058] With respect to the fourth aspect, in some implementations of the fourth aspect, the first information is included in a first message, and the first message is used to request a training data set for the intelligent model.

[0059]

[0059] Regarding the fourth aspect, in some implementations of the fourth aspect, the first message further includes second information, the second information indicating a dimension configuration manner of the training data set, and the configuration manner of the channel data in the training data set is the dimension configuration manner.

[0060]

[0060] With respect to the fourth aspect, in some implementations of the fourth aspect, the first message further includes third information, and the third information indicates filtering of the channel data obtained by screening.

[0061]

[0061] With regard to the fourth aspect, in some implementations of the fourth aspect, the first information is included in a second message, and the second message is used to request evaluation of channel data in the channel data set that satisfies a data quality condition, and the transceiver unit is further configured to receive fourth information from the first device (the fourth information indicating an amount of data, the amount of data being the amount of data in the channel data set that satisfies the data quality condition); and send the first message to the first device (the first message is used to request a training data set).

[0062]

[0062] With regard to the fourth aspect, in some implementations of the fourth aspect, the first message includes second information and / or third information, where the second information indicates a dimension configuration manner of the training data set, and the third information indicates filtering of the channel data obtained by screening.

[0063]

[0063] According to a fifth aspect, a communication device is provided, the communication device including a processor. The processor is capable of performing the method of the first aspect and any of the possible implementations of the first aspect, or the method of the second aspect and any of the possible implementations of the second aspect. Optionally, the communication device further includes a memory. The processor may be coupled to the memory and configured to execute instructions in the memory to perform the method of the first aspect and any of the possible implementations of the first aspect, or the method of the second aspect and any of the possible implementations of the second aspect. Optionally, the communication device further includes a communication interface, the processor is coupled to the communication interface.

[0064]

[0064] In an implementation, the communication apparatus is a communication device. The communication interface may be a transceiver or an input / output interface.

[0065]

[0065] In another implementation, the communication device is a chip configured in a communication device. When the communication device is a chip configured in a communication device, the communication interface may be an input / output interface.

[0066] Optionally, the transceiver may be a transceiver circuit. Optionally, the input / output interface may be an input / output circuit.

[0067] According to a sixth aspect, there is provided a processor including an input circuit, an output circuit, and a processing circuit configured to: receive a signal using the input circuit and transmit a signal using the output circuit to enable the processor to perform the method of the first aspect and any of the possible implementations of the first aspect, or to perform the method of the second aspect and any of the possible implementations of the second aspect.

[0068]

[0068] In a particular implementation, the processor may be one or more chips, the input circuits may be input pins, the output circuits may be output pins, and the processing circuits may be transistors, gate circuits, triggers, various logic circuits, etc. The input signals received by the input circuits may be, for example, but not limited to, received and input by a receiver, and the signals output by the output circuits may be, for example, but not limited to, output to a transmitter and transmitted by the transmitter. The input circuits and the output circuits may be the same circuit, and the circuit is used as an input circuit and an output circuit at different times. The specific implementation of the processor and various circuits is not limited to the embodiments of the present application.

[0069]

[0069] According to a seventh aspect, there is provided a computer program product. The computer program product includes a computer program (also called code or instructions). When the computer program is executed, it enables a computer to perform the method of the first aspect and any of the possible implementations of the first aspect, or the method of the second aspect and any of the possible implementations of the second aspect.

[0070]

[0070] According to an eighth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program (also called code or instructions). When the computer program is executed on a computer, the computer is enabled to perform the method in the first aspect and any of the possible implementations of the first aspect, or the method in the second aspect and any of the possible implementations of the second aspect.

[0071]

[0071] According to a ninth aspect, there is provided a communication system including the communication device provided in the third aspect and the communication device provided in the fourth aspect. [Brief description of the drawings]

[0072] [Figure 1]

[0072] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application. [Diagram 2]

[0073] FIG. 2 is a schematic flowchart of a data processing method according to an embodiment of the present application. [Diagram 3]

[0074] FIG. 3 is another schematic flowchart of a data processing method according to an embodiment of the present application. [Figure 4]

[0075] FIG. 4 is another schematic flowchart of a data processing method according to an embodiment of the present application. [Diagram 5]

[0076] FIG. 5 is a block diagram of an example of a communication device according to an embodiment of the present application. [Figure 6]

[0077] FIG. 6 is a block diagram of an example of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0073]

[0078] The technical solutions of the present application are described below with reference to the accompanying drawings.

[0074]

[0079] In the present application, "at least one" may alternatively be stated as "one" or "multiple", and "multiple" may be two, three, four, or more. This is not limited. " / " may indicate an "or" relationship between associated objects, for example, A / B may indicate A or B; "and / or" may indicate that there are three relationships between associated objects, for example, A and / or B may indicate three cases: A exists alone, A and B both exist, and B exists alone, where A and B may be singular or plural. To facilitate the description of the technical solution of the present application, words such as "first", "second", "A", or "B" may be used to distinguish technical features having the same or similar functions. Words such as "first", "second", "A", and "B" do not limit the quantity and execution order. Additionally, words such as "first," "second," "A," and "B" do not indicate definite distinctions. Words such as "example" or "for example" are used to provide an example, illustration, or explanation, and should not be construed as any design solution described as an "example" or "for example" being preferred or having more advantages over other design solutions. Words such as "example" or "for example" are used to present related concepts in a concrete manner to facilitate understanding.

[0075]

[0080] FIG. 1 is a schematic diagram of the architecture of a communication system 1000 to which the present application may be applied. As shown in FIG. 1, the communication system includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 1000 may further include an Internet 300. The radio access network 100 may include at least one access network node (e.g., 110a, 110b in FIG. 1), and may further include at least one terminal (e.g., 120a to 120j in FIG. 1). The terminal is connected to the access network node in a wireless manner. The access network node is connected to the core network in a wireless or wired manner. The core network device and the access network node may be separate and different physical devices, or may be the same physical device that integrates the functions of the core network device and the access network node, or other possible cases. For example, the functions of the access network node and some functions of the core network device may be integrated into one physical device, and another physical device may implement the remaining functions of the core network device. The physical existence of the core network device and the access network node is not limited in this application. The terminals may be connected to each other in a wired or wireless manner. The access network nodes may be connected to each other in a wired or wireless manner. FIG. 1 is only a schematic diagram. The communication system may further include other network devices, for example, a wireless relay device and a wireless backhaul device.

[0076]

[0081] The access network node may be a base station, a NodeB, an evolved NodeB (eNodeB, eNB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5th generation (5G) mobile communication system, an access network node in an open radio access network (O-RAN, open RAN), a next generation NodeB in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, an access node in a wireless fidelity (Wi-Fi) system, or the like. Alternatively, the access network node may be a module or unit that realizes part of the functionality of a base station, such as a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP) module, or a central unit user plane (CU-UP) module. The access network node may be a macro base station (e.g., 110a in FIG. 1), a micro base station, an indoor station (e.g., 110b in FIG. 1), a relay node, a donor node, etc. The specific technology and the specific device form used by the access network node are not limited in this application. The 5G system may also be called a new radio (NR) system.

[0077]

[0082] In the present application, the apparatus configured to realize the functions of an access network node may be an access network node; or may be an apparatus capable of supporting the access network node in realizing the functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The apparatus may be introduced into the access network node or may be used in harmony with the access network node. In the present application, the chip system may include a chip, or may include a chip and another discrete component. In the following, for ease of description, the technical solution provided in the present application will be described by using an example in which the apparatus configured to realize the functions of an access network node is an access network node, and the access network node is a base station.

[0078]

[0083] The terminal may be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal may be widely used in various scenarios for communication. The scenarios include, but are not limited to, at least one of the following scenarios: enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), massive machine-type communication (mMTC), device-to-device (D2D), vehicle-to-everything (V2X), machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a wearable device, a vehicle, a drone, a helicopter, an aircraft, a ship, a robot, a robotic arm, a smart home device, etc. The specific technology used by the terminal and the specific device form are not limited in this application.

[0079]

[0084] In this application, the device implementing the functions of the terminal may be a terminal; or may be a device capable of supporting the terminal in implementing the functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. The device may be introduced into the terminal or used in harmony with the terminal. In the following, for ease of description, the technical solution provided in this application will be described by using an example in which the device configured to implement the functions of the terminal is a terminal, and optionally an example in which the terminal is a UE.

[0080]

[0085] The base station and / or the terminal may be fixed or mobile. The base station and / or the terminal may be deployed on the ground, including indoor or outdoor, mobile or vehicle-mounted; on water; or on an airborne aircraft, balloon, or satellite. The environment / scenario in which the base station and the terminal are located is not limited in this application. The base station and the terminal may be deployed in the same environment / scenario or different environments / scenario. For example, both the base station and the terminal are deployed on the ground; or the base station is deployed on the ground and the terminal is deployed on water. Specific examples are not provided one by one.

[0081]

[0086] The following definitions apply to the embodiments of the present application.

[0082]

[0087] 1. Artificial Intelligence

[0088] Artificial intelligence (AI) enables machines to learn and accumulate experience so that they can solve problems that were previously solved through human experience, such as natural language understanding, image recognition, and playing chess.

[0083]

[0089] 2. Machine Learning

[0090] Machine learning is an implementation of artificial intelligence, a method to provide machines with the ability to learn to complete functions that are difficult to achieve through direct programming. In practice, machine learning is a method to train a model using data and then use that model to predict outcomes. Reinforcement learning is a branch of machine learning that reinforces how a machine behaves based on its environment to maximize expected benefits. Transfer learning is another branch of machine learning. Transfer learning focuses on storing a solution model of an existing problem and leveraging that solution model to other related but different problems.

[0084]

[0091] 3. Training or learning

[0092] Training is a process of optimizing parameters, such as weighted values, in an AI or ML model to enable the model to perform a specific task. The embodiments of the present application are applicable to one or more of the following training methods, including but not limited to supervised learning, unsupervised learning, reinforcement learning, transfer learning, and the like. Supervised learning uses a group of correctly labeled training samples for training (where correctly labeled training samples means that each sample has an expected output value). Unlike supervised learning, unsupervised learning is a method of automatically classifying or grouping input data without pre-marked training samples.

[0085]

[0093] 4.Inference

[0094] Inference means using a trained AI or ML model to perform a task, and inputting real data into the AI ​​or ML model for processing to obtain a corresponding predicted result, which may also be referred to as an inference result or a judgment result.

[0086]

[0095] In the present application, an independent network element (e.g., referred to as an AI network element, AI node, or AI device) may be introduced into the communication system shown in FIG. 1 to perform AI-related operations. The AI ​​network element may be directly connected to the base station or indirectly connected to the base station via a third-party network element. Optionally, the third-party network element may be a core network element, such as an AMF network element or a UPF network element. Alternatively, an AI entity (or AI module, or may be referred to by another name) may be built in another network element in the communication system to perform AI-related operations. Optionally, the other network element may be a third-party independent network element in a base station, a core network device, a network management system (operation, administration and maintenance, OAM), a network data analysis function (NWDAF), or an open radio access network (O-RAN, open RAN, or ORAN), etc. In this case, the network element performing the AI-related operations is a network element with an AI function built in. Since both the AI ​​network element and the AI ​​entity realize AI-related functions, for ease of explanation, in the following description, the AI ​​network element and the network element incorporating the AI ​​function are collectively referred to as an AI unit. The OAM is configured to operate, manage, and / or maintain the core network device (network management system of the core network device) and / or to operate, manage, and / or maintain the access network device (network management system of the access network device).

[0087]

[0096] Optionally, to accommodate and support AI, an AI entity may be integrated into the terminal or terminal chip.

[0088]

[0097] Optionally, in this application, an AI entity may be referred to by other names such as an AI module or an AI unit, and is configured to mainly realize an AI function (also referred to as an AI-related operation). In this application, the specific name of the AI ​​entity is not limited.

[0089]

[0098] In this application, an AI model is a specific way to implement an AI function. An AI model represents a mapping relationship between the inputs and outputs of the model. An AI model may be a neural network or another machine learning model. An AI model may be referred to as a model for short. AI-related operations may include at least one of the following: data collection, model training, model information release, model inference (or called model inference, inference, prediction, etc.), inference result release, etc.

[0090]

[0099] The network architecture and service scenarios described in this application are intended to more clearly explain the technical solutions in this application, but do not constitute limitations on the technical solutions provided in this application. Those skilled in the art know that with the development of network architectures and the emergence of new service scenarios, the technical solutions provided in this application can also be applied to similar technical problems.

[0091]

[0100] In response to the problem of deviations in the performance of actually measured channel data caused by the influence of noise in the internal components of the communication device, calibration errors in the communication system, etc., the present application proposes that when the communication system needs to perform model training by using the actually collected channel data as training data, the communication system screens out the channel data having errors from the collected channel data set according to the obtained data quality screening policy, for example, screening out the channel data that cannot truly reflect the channel state due to the channel data errors caused by the noise in the components of the communication device that measure the channel data, and / or the time and / or frequency asynchrony of the reference signal transceiver device, etc. In this way, the channel data obtained by screening by the first device according to the data quality screening policy can meet the quality condition, so that the intelligent model trained based on the training data set obtained by screening can meet the performance condition and can be used in communication to improve the communication quality.

[0092]

[0101] Hereinafter, a data processing method provided in an embodiment of the present application will be described with reference to the accompanying drawings.

[0093]

[0102] FIG. 2 is a schematic flowchart of a data processing method 200 according to an embodiment of the present application. In the following, an example in which a first device executes the method is used for explanation. The first device may be an access network node or a device disposed in the access network node (e.g., a chip disposed in the access network node). For example, the access network node may be a base station. Alternatively, the first device may be a terminal or a device disposed in the terminal (e.g., a chip disposed in the terminal). However, the present application is not limited thereto.

[0094]

[0103] S201: A first device acquires a channel data set, where the channel data set is a set of channel data obtained by measuring a plurality of reference signals.

[0095]

[0104] In an implementation, the first device acquiring the channel data set includes: the first device transmitting a plurality of reference signals to the second device; and the first device receiving the channel data set from the second device.

[0096]

[0105] The first device is capable of transmitting a plurality of reference signals to the second device, and the second device receives the plurality of reference signals from the first device and measures each of the plurality of reference signals to obtain a plurality of channel data. The second device transmits a channel data set including the plurality of channel data to the first device. In response, the first device receives the channel data set from the second device.

[0097]

[0106] For example, the first device may be an access network node and the second device may be a terminal. The access network node may transmit a plurality of reference signals to the terminal and obtain from the terminal a channel data set obtained by the terminal measuring the plurality of reference signals. Alternatively, the first device is a terminal and the second device is an access network node. The terminal may transmit a plurality of reference signals to the access network node and obtain from the access network node a channel data set obtained by the terminal measuring the plurality of reference signals.

[0098]

[0107] In another implementation, the first device acquiring the channel data set includes: the first device receiving a plurality of reference signals from the second device and measuring the plurality of reference signals to acquire the channel data set.

[0099]

[0108] The second device transmits a plurality of reference signals to the first device, and the first device measures each of the plurality of reference signals from the second device to obtain a channel data set.

[0100]

[0109] For example, the first device may be an access network node, and the second device may be a terminal. The access network node may receive multiple reference signals from the terminal and measure the multiple reference signals to obtain the channel data set. Alternatively, the first device may be a terminal, and the second device may be an access network node. The terminal may receive multiple reference signals from the access network node and measure the multiple reference signals to obtain the channel data set. This is not limited in the present application.

[0101]

[0110] S202: The first device obtains a data quality screening policy, and the data quality screening policy is used to obtain, through screening, model training data that satisfies a data quality condition.

[0102]

[0111] In an implementation, the first device obtaining the data quality screening policy includes: the first device receiving the data quality screening policy from a third device.

[0103]

[0112] The third device may be a device that performs intelligent model training. The third device may determine a data quality screening policy based on the data quality conditions of the model training. The third device may transmit first information to the first device, the first information being indicative of the data quality screening policy.

[0104]

[0113] For example, the first device may be an access network node and the third device may be a network node configured to comprise an AI entity in the network, e.g., the third device may be a core network node, an NWDAF, an OAM, or any other node in the network.

[0105]

[0114] As another example, the first device may be a terminal, and the third device may be a network node configured to include an AI entity in the network. For example, the third device may be an access network node, a core network node, or other node in the network. The third device may send the first information to the terminal to inform the terminal of the data quality screening policy.

[0106]

[0115] In another implementation, the first device obtaining the data quality screening policy includes: the data quality screening policy being pre-configured for the first device, and the first device obtaining the data quality screening policy from the pre-configured information.

[0107]

[0116] After acquiring the channel data set, the first device may screen the channel data in the channel data set according to a preset data quality screening policy.

[0108]

[0117] Optionally, data quality screening policies may include, but are not limited to, one or more of the following: (1) Screening policy based on received power stability of the same reference signal; (2) A screening policy based on the transmission delay stability of the reference signal; (3) A screening policy based on the phase stability of different channel data components corresponding to the same transceiver antenna pair; (4) a screening policy based on the received signal-to-noise ratio of the reference signal; and (5) Screening policies based on channel type diversity.

[0109]

[0118] The first device can screen out erroneous channel data from the channel data set according to the data quality screening policy, for example, channel data that cannot truly reflect the channel state due to channel data errors caused by noise of components of the communication device (e.g., the first device or the second device) for measuring the channel data, time and / or frequency asynchrony of the reference signal in the transceiver device, etc. In this way, the channel data obtained through screening by the first device according to the data quality screening policy can meet the quality condition, so that the intelligent model trained based on the training data set obtained by screening can meet the performance condition and can be used in communication to improve communication quality.

[0110]

[0119] In this embodiment of the present application, the reference signal transmitting device can simultaneously transmit a reference signal through T transmitting antennas, and the reference signal receiving device receives the reference signal transmitted by each of the T transmitting antennas through R receiving antennas, where T and R are positive integers. The receiving device can measure the reference signal received by the R receiving antennas and obtain one channel data through the measurement. One channel data includes multiple channel data components. For example, for one channel data H that does not include multipath components, the channel data H can include R×T channel data components. This is expressed as follows:

[0111]

number

[0120] hr,t is one channel data component, which represents the channel state between the transmitting antenna t and the receiving antenna r. r,t A transmit antenna t and a receive antenna r corresponding to may be referred to as a transceiver antenna pair, where r is a positive integer less than or equal to R and t is a positive integer less than or equal to T.

[0112]

[0121] The following describes each of the above screening policies (1) to (5) and provides examples of the screening policies. However, the present application is not limited thereto. In a specific implementation, all or part of the screening policies may be selected as a data quality screening policy based on a certain condition, or the data quality screening policy may further include another screening policy.

[0113]

[0122] (1) Screening policy based on received power stability of the same reference signal

[0123] The screening policy based on the received power stability of the same reference signal includes: the difference value between the received powers when receiving the same reference signal by different receiving antennas corresponding to one channel data satisfies the received power stability condition, in this case, the channel data obtained based on the reference signal can be used as model training data. That is, one reference signal transmitted from one transmitting antenna is received by multiple receiving antennas. The difference value between the received powers when receiving the reference signal by different receiving antennas among the multiple receiving antennas satisfies the stability condition, in this case, the channel data obtained based on the reference signal can be used as model training data. If the data quality screening policy further includes a policy other than the policy (1), the first device needs to further determine whether the conditions of the other screening policies are met and determine whether to select the channel data obtained based on the reference signal as model training data.

[0114]

[0124] The data quality condition includes a received power stability condition. The received power stability condition may include, but is not limited to, that a difference value between received powers when receiving the same reference signal by different receiving antennas is less than or equal to a first threshold. For example, the first threshold may be referred to as a power stability threshold, and may be a power stability threshold. TH It is marked as.

[0115]

[0125] In implementation, in the policy based on the received power stability of the same reference signal, the different receiving antennas are specifically two receiving antennas that are spatially adjacent and have the same polarization direction, that is, the policy may be specifically that the difference value between the received powers when the same reference signal is received by two receiving antennas that are spatially adjacent and have the same polarization direction satisfies the received power stability condition.

[0116]

[0126] In another implementation, policy (1) may specifically be that a difference value between the received powers when the same reference signal is received for two different receive antennas corresponding to one channel data satisfies a received power stability condition.

[0117]

[0127] (2) Screening policy based on the transmission delay stability of the reference signal

[0128] The screening policy based on the delay stability of the channel data components in one channel data includes: the difference value between the transmission delays of the reference signals of different transceiver antenna pairs corresponding to one channel data satisfies the delay stability condition, in which case the channel data can be used as model training data, and the same transceiver antenna pair includes one transmitting antenna and one receiving antenna of one reference signal. If the data quality screening policy further includes a policy other than (2), the first device needs to further determine whether the channel data satisfies the conditions of other screening policies to determine whether to select the channel data as model training data.

[0118]

[0129] The data quality condition includes a delay stability condition. The delay stability condition may include, but is not limited to, that a difference value between the transmission delays of the reference signals of different transceiver antenna pairs is less than or equal to a second threshold. For example, the second threshold may be referred to as a delay stability threshold, ΔT TH It is marked as.

[0119]

[0130] For example, the first device may obtain a channel delay power spectrum of each transceiver antenna pair corresponding to one channel data. The channel delay power spectrum is a correspondence between a transmission delay caused by multipath transmission and an expected value of a received signal power. The first device may calculate a delay difference value between delays corresponding to peak values ​​of the channel delay power spectrum for each of two transceiver antenna pairs. If a difference value between the transmission delays of the reference signals of any two transceiver antenna pairs in the channel data is equal to or less than a second threshold, the channel data satisfies the delay stability condition and can be used as model training data.

[0120]

[0131] (3) A screening policy based on the phase stability of channel data components corresponding to the same transceiver antenna pair.

[0132] The screening policy based on the phase stability of channel data components corresponding to the same transceiver antenna pair includes: the phases of the channel data components of the same transceiver antenna pair in multiple channel data obtained within a predetermined interval satisfy a phase stability condition, in which case the channel data obtained within the predetermined interval can be used as model training data.

[0121]

[0133] The data quality condition includes a phase stability condition. The phase stability condition may include, but is not limited to, that the phase difference between the peak values ​​of the channel impulse responses obtained by the same antenna pair based on different reference signals is less than or equal to a third threshold. For example, the third threshold may be referred to as a phase stability threshold, θ TH It is marked as.

[0122]

[0134] For example, the preset time interval may be one or more time frames, one or more subframes, or one or more slots. The first device acquires a plurality of channel data obtained in one preset time interval. If a phase difference between peak values ​​of channel impulse responses corresponding to the same transceiver antenna pair in the plurality of channel data is equal to or less than a third threshold, the first device can use the plurality of channel data as model training data. If the data quality screening policy further includes other policies, the first device needs to further determine whether the plurality of channel data meets the conditions of the other policies to determine whether to select the plurality of channel data as training data.

[0123]

[0135] Optionally, one or more of the aforementioned policies (1) to (3) may be specifically used as a screening policy for the first channel data, and the first channel data satisfying a quality condition in the channel data set may be obtained through screening. The first channel data includes a channel data component of a line of sight (LOS) transmission path.

[0124]

[0136] (4) Screening policy based on received signal-to-noise ratio of reference signal

[0137] The screening policy based on the received signal-to-noise ratio of the reference signal includes: the received signal-to-noise ratio of the reference signal is equal to or greater than a fourth threshold, in which case the channel data obtained based on the reference signal can be used as model training data. For example, the fourth threshold may be referred to as a signal-to-noise ratio threshold, SNR TH It is marked as.

[0125]

[0138] (5) Screening policy based on channel type diversity

[0139] A screening policy based on channel type diversity may include, but is not limited to, one or more of the following: A N number of first channel data and M number of second channel data are selected to form a training data set. The second channel data does not include channel data components of LOS transmission paths. That is, the second channel data includes only channel data components of non-line-of-sight (NLOS) transmission paths. N and M are positive integers.

[0126] b. The ratio of LOS channel data to NLOS channel data in the training data set is a preset ratio.

[0127] cQ channel data are selected to form a training data set, where the Q channel data includes at least N first channel data and at least M second channel data, and Q>N+M.

[0128]

[0140] Optionally, the aforementioned thresholds (e.g., the first threshold, the second threshold, the third threshold, the fourth threshold) may be predefined or may be obtained by the first device from another device.

[0129]

[0141] For example, the first device may be a terminal, and the terminal may obtain one or more of the thresholds from a network node in the network, or one or more of the thresholds may be preconfigured in the terminal.

[0130]

[0142] As another example, the first device may be an access network node, and the access network node may obtain one or more of the aforementioned thresholds from another network node, or one or more of the aforementioned thresholds may be preconfigured in the access network node.

[0131]

[0143] S203: The first device screens the channel data in the channel data set according to the data quality screening policy to obtain a training data set.

[0132]

[0144] The first device obtains channel data that satisfies a quality condition from the channel data set according to a data quality screening policy as a training data set.

[0133]

[0145] In the implementation, the first device trains the intelligent model by using a training data set. The training data set may be used as sample data for training the intelligent model, or the training data set may be used as sample labels in the model training process or for other purposes, which is not limited in the present application.

[0134]

[0146] In another implementation, a first device transmits a training data set.

[0135]

[0147] For example, the first device transmits a training data set to a network node including an AI entity in the network. After receiving the training data set, the network node trains an intelligent model based on the training data set. Optionally, the network node may transmit first information to the first device to inform the first device of a data quality screening policy. After obtaining a training data set that satisfies the data quality condition of the network node according to the data quality screening policy, the first device transmits the training data set to the network node. The network node trains an intelligent model based on the training data set.

[0136]

[0148] Optionally, the first device screens the channel data in the channel data set according to a data quality screening policy to obtain multiple channel data, and arranges the multiple channel data based on a tensor dimension definition to obtain a training data set.

[0137]

[0149] By way of example and not limitation, the tensor dimension definition may define one or more of the following dimensions: the number of transmit antennas, the number of receive antennas, and the number of time intervals or subcarriers.

[0138]

[0150] Optionally, the first device screens the channel data in the channel data set according to the data quality screening policy to obtain a plurality of channel data, and filters the plurality of channel data to obtain a training data set, the training data set including data obtained by filtering the plurality of channel data.

[0139]

[0151] For example, the first device may convert the multiple channel data (i.e., frequency channel response) obtained by screening into time domain data and filter the time domain data. Noise is reduced by the time domain filtering. The filtered time domain data is then converted into frequency domain data to obtain a training data set. However, the present application is not limited thereto. The first device may perform frequency domain filtering on the multiple channel data obtained by screening.

[0140]

[0152] In one example, a network node including an AI entity may send first information to a first device and notify the first device to provide a training data set for training an intelligent model by using the first information. The first information may include a data quality screening policy, so that the first device may obtain a channel data set that satisfies the conditions of the network node as a training data set through screening according to the data screening policy. The first information may further include an address of the first device, so that the first information may be transmitted to the first device through multiple nodes in the network. The first information may further include data processing parameters and data amounts of the training data required by the network node. For example, the data processing parameters may include parameters of a filter and tensor dimension definitions of the training data. The first information may include one or more of the information shown in Table 1.

[0141] Table 1

[0142] [Table 1]

[0153] After obtaining channel data that meets the data quality condition of the network node based on the first information, the first device performs data processing on the channel data obtained by screening based on the data processing parameters to obtain a training data set, and sends the training data set to the network node. The network node trains an intelligent model based on the training data set.

[0143]

[0154] According to the solution provided in this embodiment of the present application, the first device can obtain channel data that meets the data quality condition from the channel data set obtained by measurement through screening according to the data quality screening policy, and remove the channel data that cannot truly reflect the channel state due to the channel data error caused by the noise of the components of the communication device (e.g., the first device or the second device) that measures the channel data, the time and / or frequency asynchrony of the reference signal transceiver device, etc. In this way, the intelligent model obtained through training based on the screened training data set can meet the performance condition, so that the intelligent model is used in wireless communication to improve the communication quality.

[0144]

[0155] It should be noted that in the embodiments disclosed in the present application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions in different embodiments are consistent and can be mutually referenced, and the technical features in different embodiments may be combined based on their internal logical relationships to form a new embodiment.

[0145]

[0156] FIG. 3 is a diagram of a data processing method 300 according to an embodiment of the present application. In the embodiment shown in FIG. 3, the first device is an access network node, and the third device is a network node comprising an AI entity in the network. For example, the third device may be a core network node, an NWDAF, an OAM, or other node in the network. Alternatively, the first device may be an access network node, and the third device may be an access network node or the aforementioned network node. However, the present application is not limited thereto.

[0146]

[0157] S301: A third device sends a first message to a first device, requesting a training data set for an intelligent model.

[0147]

[0158] In response, the first device receives a first message from the third device.

[0148]

[0159] Optionally, the first message includes first information, the first information indicating a data quality screening policy.

[0149]

[0160] The third device determines a quality condition for the training data based on the training condition and notifies the first device of the quality condition by using the first message, so that the first device can provide the third device with a training data set that satisfies the quality condition.

[0150]

[0161] The first message may further include one or more of the types of information shown in Table 1.

[0151]

[0162] Optionally, the first message includes second information, the second information indicating a dimensional arrangement scheme for the training data set.

[0152]

[0163] Optionally, the first message includes third information, the third information indicating filtering of the channel data obtained through screening.

[0153] S302: The first device screens channel data in a data set according to a data quality screening policy to obtain a channel data set.

[0154]

[0164] In response to the third device requesting a training data set for the intelligent model, the first device screens the channel data in the channel data set to obtain the training data set. The data quality screening policy may be pre-configured in the first device, or the first message may include the data quality screening policy. The channel data set may be obtained by measuring a reference signal by the first device, or may be obtained by the first device from the second device. However, the present application is not limited thereto.

[0155]

[0165] If the first message further includes the second information, the first device can arrange the channel data in the training data set according to a dimension configuration scheme specified by the second information, and if the first message further includes the third information, the first device filters the channel data that meets a data quality condition according to the third information to obtain the training data set.

[0156]

[0166] S303: The first device transmits a training data set to a third device.

[0157]

[0167] Correspondingly, the third device receives a training data set from the first device.

[0158]

[0168] After receiving the training data set that satisfies the data quality condition, the third device trains an intelligent model using the training data set.

[0159]

[0169] According to the solution provided in this embodiment of the present application, an intelligent model obtained through training based on a screened training data set can meet performance requirements, so that the intelligent model is used in wireless communication to improve communication quality.

[0160]

[0170] FIG. 4 is a diagram of a data processing method 400 according to an embodiment of the present application.

[0161]

[0171] S401: A third device transmits a second message to a first device, the second message being used to request evaluation of channel data in a channel data set that satisfies a data quality condition.

[0162]

[0172] In response, the first device receives a second message from the third device. The second message can include first information, where the first information indicates a data quality screening policy. The third device can determine a quality condition of the training data based on the training condition and inform the first device of the quality condition by using the second message, so that the first device evaluates channel data that satisfies the quality condition.

[0163]

[0173] S402: The first device screens channel data in the channel data set according to a data quality screening policy.

[0164]

[0174] The first device screens the channel data in the channel data set according to the data quality screening policy, and determines the channel data in the channel data set that meets the data quality condition. The channel data set may be obtained by measuring a reference signal by the first device, or may be obtained by the first device from the second device. However, the present application is not limited thereto.

[0165]

[0175] S403: The first device transmits fourth information to the third device, where the fourth information indicates an amount of data, the amount of data indicating an amount of data in the channel data set that satisfies a data quality condition.

[0166]

[0176] In response, the third device receives fourth information from the first device.

[0167]

[0177] After determining channel data in the channel data set that satisfies the data quality condition according to the data quality screening policy, the first device transmits fourth information to the third device, notifying the third device of an amount of channel data in the channel data set that satisfies the data quality condition.

[0168]

[0178] S404: The third device sends a first message to the first device requesting a training data set for the intelligent model.

[0169]

[0179] In response, the first device receives a first message from the third device. The third device can determine whether the amount of data indicated by the fourth information satisfies a condition for training an intelligent model. If the data amount condition is met, the third device can send a first message to the first device to request channel data that satisfies a data quality condition as a training data set.

[0170]

[0180] Optionally, the first message may include the second information and / or the third information mentioned above.

[0171]

[0181] S405: The first device transmits the training data set to the third device.

[0172]

[0182] Correspondingly, the third device receives a training data set from the first device.

[0173]

[0183] The first device determines a training data set in response to the first message, and the training data set includes channel data that satisfies a data quality condition. If the first message further includes second information, the first device can arrange the channel data in the training data set based on a dimension configuration scheme specified by the second information. If the first message further includes third information, the first device filters the channel data that satisfies the data quality condition based on the third information to obtain the training data set.

[0174]

[0184] According to the solution provided in this embodiment of the present application, an intelligent model obtained through training based on a screened training data set can meet performance requirements, so that the intelligent model is used in wireless communication to improve communication quality.

[0175]

[0185] In the present application, a device may perform all or a portion of the steps or operations associated with the device. These steps or operations are merely examples. Other operations or variations of various operations may also be performed in the present application. Furthermore, steps may be performed in a different sequence than the sequence presented in the present application, and not all operations in the present application are necessarily performed.

[0176]

[0186] In the embodiments of the present application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions in different embodiments are consistent and can be mutually referenced, and the technical features in different embodiments can be combined based on their internal logical relationships to form a new embodiment.

[0177]

[0187] The method provided in the embodiment of the present application has been described in detail above with reference to Figures 2 and 4. The following attached drawings illustrate the communication apparatus and communication device provided in the embodiment of the present application. To realize the functions in the method provided in the embodiment of the present application, the network element may include a hardware structure and / or a software module, and may realize the above-mentioned functions in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module. Whether a function among the above-mentioned functions is performed using a hardware structure, a software module, or a combination of a hardware structure and a software module depends on the design constraints of a specific application and technical solution.

[0178]

[0188] 5 is a block diagram of a communication device according to an embodiment of the present application. As shown in FIG. 5, the communication device 500 may include a transceiver unit 520.

[0179]

[0189] In a possible design, the communications device 500 could correspond to a first device in an embodiment of the method described above, a chip configured in (or used in) the first device, or another device, module, circuit, unit, etc. capable of implementing the method of the first device.

[0180]

[0190] It should be understood that the communication device 500 may include units configured to perform the methods performed by the first device in the methods illustrated in Figures 2, 3, and 4. Also, the units in the communication device 500 and other operations and / or functions described above are used to realize corresponding steps of the methods illustrated in Figures 2, 3, and 4, respectively.

[0181]

[0191] Optionally, the communication device 500 may further include a processing unit 510. The processing unit 510 may be configured to process instructions or data and perform corresponding operations.

[0182]

[0192] It should be further understood that if the communication device 500 is a chip configured (or used) in a first device, the transceiver unit 520 in the communication device 500 may be an input / output interface or a circuit of the chip, and the processing unit 510 in the communication device 500 may be a processor in the chip.

[0183]

[0193] Optionally, the communication device 500 may further include a storage unit 530. The storage unit 530 may be configured to store instructions and data, and the processing unit 510 may execute the data and instructions stored in the storage unit to enable the communication device to realize corresponding operations.

[0184]

[0194] It should be understood that the transceiver unit 520 of the communication device 500 may be implemented using a communication interface (e.g., a transceiver or an input / output interface) and may, for example, correspond to the transceiver 610 in the communication device 600 shown in FIG. 6. The processing unit 510 in the communication device 500 may be implemented using at least one processor and may, for example, correspond to the processor 620 in the communication device 600 shown in FIG. 6. The processing unit 510 in the communication device 500 may be implemented by using at least one logic circuit. The storage unit 530 of the communication device 500 may correspond to the memory of the communication device 600 shown in FIG. 6.

[0185]

[0195] It should be further understood that the specific process in which each unit performs the above corresponding step has been described in detail in the above method embodiments, and for the sake of brevity, the details will not be described again here.

[0186]

[0196] In another possible design, the communications device 500 could correspond to a third device in an embodiment of the aforementioned method, such as a chip configured (or used) in the third device, or other device, module, circuit, unit, etc. capable of implementing the method of the third device.

[0187]

[0197] It should be understood that the communication device 500 may include units configured to perform the methods performed by the third device in the methods shown in Figures 2, 3, and 4. Also, the units in the communication device 500 and other operations and / or functions described above are used to realize corresponding steps of the methods shown in Figures 2, 3, and 4, respectively.

[0188]

[0198] Optionally, the communication device 500 may further include a processing unit 510. The processing unit 510 may be configured to process instructions or data and perform corresponding operations.

[0189]

[0199] It should be further understood that if the communication device 500 is a chip configured (or used) in a third device, the transceiver unit 520 in the communication device 500 may be an input / output interface or a circuit of the chip, and the processing unit 510 in the communication device 500 may be a processor in the chip.

[0190]

[0200] Optionally, the communication device 500 may further include a storage unit 530. The storage unit 530 may be configured to store instructions and data, and the processing unit 510 may execute the data and instructions stored in the storage unit to enable the communication device to realize corresponding operations.

[0191]

[0201] It should be understood that when the communication device 500 is a third device, the transceiver unit 520 of the communication device 500 may be realized using a communication interface (e.g., a transceiver or an input / output interface) and may, for example, correspond to the transceiver 610 in the communication device 600 shown in FIG. 6. The processing unit 510 in the communication device 500 may be realized using at least one processor and may, for example, correspond to the processor 620 in the communication device 600 shown in FIG. 6. The processing unit 510 in the communication device 500 may be realized by using at least one logic circuit. The storage unit 530 of the communication device 500 may correspond to the memory of the communication device 600 shown in FIG. 6.

[0192]

[0202] It should be further understood that the specific process in which each unit performs the above corresponding step has been described in detail in the above method embodiments, and for the sake of brevity, the details will not be described again here.

[0193]

[0203] FIG. 6 is a structural diagram of a communication device 600 according to an embodiment of the present application. The communication device 600 can be used to perform the functions of the communication device in the embodiment of the above-mentioned method in the system shown in FIG. 1. As shown in the figure, the communication device 600 includes a processor 620 and a transceiver 610. Optionally, the communication device 600 further includes a memory. The processor 620, the transceiver 610, and the memory can communicate with each other using an internal connection path to transfer control signals and / or data signals. The memory is configured to store a computer program, and the processor 620 is configured to execute the computer program in the memory and control the transceiver 610 to transmit and receive signals.

[0194]

[0204] The processor 620 and the memory may be integrated in a processing device. The processor 620 is configured to execute program code stored in the memory to implement the above-mentioned functions. In a particular implementation, the memory may alternatively be integrated into the processor 620 or may be separate from the processor 620. The processor 620 may correspond to the processing unit of FIG. 5.

[0195]

[0205] The transceiver 610 may correspond to the transceiver unit of Figure 5. The transceiver 610 may include a receiver (or what may be referred to as a receiver machine or receiver circuitry) and a transmitter (or what may be referred to as a transmitter machine or transmitter circuitry). The receiver is configured to receive signals, and the transmitter is configured to transmit signals.

[0196]

[0206] In implementation, the communication device 600 shown in Fig. 6 can perform the processes related to the first device in the method embodiments shown in Fig. 2, Fig. 3, and Fig. 4. The operations and / or functions of the modules in the communication device 600 are respectively used to perform the corresponding procedures in the aforementioned method embodiments. For details, please refer to the description of the aforementioned method embodiments. To avoid repetition, detailed descriptions are omitted here as appropriate.

[0197]

[0207] In another implementation, the communication device 600 shown in Fig. 6 can perform the process related to the third device in the method embodiments shown in Fig. 2, Fig. 3, and Fig. 4. The operations and / or functions of the modules in the communication device 600 are respectively used to perform the corresponding procedures in the aforementioned method embodiments. For details, please refer to the description of the aforementioned method embodiments. To avoid repetition, detailed descriptions are omitted here as appropriate.

[0198]

[0208] Optionally, the first device may be an access network device and the third device may be a network node in the network, such as a core network node, an OAM, an NWDAF, or a third party independent network element in an ORAN. Alternatively, the first device may be a terminal device and the third device may be an access network device.

[0199]

[0209] The processor 620 may be configured to execute the operations performed inside the communication device in the above-mentioned method embodiments, and the transceiver 610 may be configured to execute the operations of transmitting from the communication device to the network device in the above-mentioned method embodiments, or the operations of receiving from the network device in the above-mentioned method embodiments. For details, please refer to the description in the above-mentioned method embodiments. Details will not be described again here.

[0200]

[0210] Optionally, the communications device 600 may further include a power source configured to provide power to various components or circuits within the communications device.

[0201]

[0211] An embodiment of the present application further provides a processing device including a processor and a (communication) interface, the processor configured to perform the method in any of the embodiments of the method described above.

[0202]

[0212] It should be understood that a processing device may be one or more chips, for example, a processing device may be a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system on chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chip.

[0203]

[0213] According to the methods provided in the embodiments of the present application, the present application further provides a computer program product, which includes computer program code that, when executed by one or more processors, enables an apparatus including the processors to perform the methods in the embodiments shown in Figures 2, 3, and 4.

[0204]

[0214] All or part of the technical solutions in the embodiments of the present application can be implemented by using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded into a computer and executed, all or part of the procedures or functions according to the embodiments of the present invention are generated. The aforementioned computer instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. The computer-readable storage medium may be any available medium accessible by a computer, or a data storage device such as a server or a data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), a semiconductor medium, etc.

[0205]

[0215] According to the methods provided in the embodiments of the present application, the present application further provides a computer-readable storage medium, which stores program code, which, when executed by one or more processors, enables an apparatus including the processors to perform the methods in the embodiments shown in Figures 2, 3, and 4.

[0206]

[0216] According to the method provided in the embodiment of the present application, the present application further provides a system including one or more of the first devices described above. The system may further include one or more of the third devices described above.

[0207]

[0217] In some embodiments provided in the present application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the described device embodiment is merely schematic. For example, the division into multiple units is merely a logical functional division. In actual implementation, other division methods may be used. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. Furthermore, the shown or described mutual couplings or direct couplings or communication connections may be implemented through any interface. Indirect couplings or communication connections between devices or units may be implemented in electronic, mechanical, or other forms.

[0208]

[0218] The units described as separate parts may or may not be physically separate, and the parts shown as units may or may not be physical units, i.e., they may be located in one place or distributed among multiple network units. All or some of the units may be selected based on the actual conditions to achieve the objectives of the solutions of the embodiments.

[0209]

[0219] The above description is only a specific embodiment of the present application, and is not intended to limit the protection scope of the present application. Any modifications or replacements that are easily grasped by those skilled in the art within the technical scope disclosed in the present application shall be within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. 1. A data processing method comprising: receiving or transmitting a plurality of reference signals; acquiring a first channel data set, the first channel data set being a set of a plurality of channel data acquired based on the plurality of reference signals; obtaining a data quality screening policy, the data quality screening policy being used to obtain, by screening, training data for an intelligent model that satisfies a data quality condition; and screening the channel data in the first channel data set according to the data quality screening policy to obtain a training data set; The method includes:

2. 2. The method of claim 1, wherein the data quality screening policies include: A screening policy based on the received power stability of the same reference signal; A screening policy based on the transmission delay stability of the reference signal; a screening policy based on phase stability of channel data components corresponding to the same transceiver antenna pair; a screening policy based on the received signal-to-noise ratio of the reference signal; or Screening policies based on channel type diversity; The method includes one or more of the following:

3. 3. The method of claim 2, wherein the screening policy based on received power stability of the same reference signal comprises: A difference in reception power when the same reference signal is received by different receiving antennas corresponding to one channel data is equal to or less than a first threshold value. selecting, as the training data, channel data that satisfies a received power stability condition:

4. The method of claim 3, wherein the different receive antennas are two receive antennas that are spatially adjacent and have the same polarization direction.

5. In the method according to any one of claims 2 to 4, the screening policy based on the transmission delay stability of the reference signal comprises: The difference in transmission delays of the reference signals of different transceiver antenna pairs corresponding to one channel data is equal to or less than a second threshold value. and selecting, as the training data, channel data that satisfies a delay stability condition:

6. 6. The method according to claim 2, wherein the screening policy based on phase stability of channel data components corresponding to the same transceiver antenna pair comprises: A phase difference value of channel data components of the same transceiver antenna pair in a plurality of channel data acquired within a preset interval is equal to or less than a third threshold value. and selecting, as the training data, channel data that satisfies a phase stability condition:

7. 7. The method according to claim 2, wherein the screening policy based on the received signal-to-noise ratio of the reference signal is: using channel data corresponding to a reference signal whose received signal-to-noise ratio is greater than or equal to a fourth threshold as the training data.

8. 8. The method according to claim 2, wherein the channel type diversity based screening policy is one of the following: selecting N pieces of line-of-sight LOS channel data and M pieces of non-line-of-sight NLOS channel data to form the training data set, where N and M are positive integers; a ratio of the LOS channel data to the NLOS channel data in the training data set is a predetermined ratio; and selecting Q channel data to form the training data set, where Q channel data includes at least N LOS channel data and at least M NLOS channel data, and Q>N+M; The method includes one or more of the following:

9. The method according to any one of claims 1 to 8, wherein transmitting the plurality of reference signals comprises transmitting the plurality of reference signals to a second device; and obtaining the first channel data set comprises receiving the first channel data set from the second device; or 4. The method of claim 3, wherein receiving the plurality of reference signals comprises receiving the plurality of reference signals from a second device; and acquiring the first channel data set comprises measuring the plurality of reference signals to acquire the first channel data set.

10. The method of any one of claims 1-9, further comprising the step of training the intelligent model by using the training data set.

11. The method according to any one of claims 1 to 10, wherein the step of obtaining the data quality screening policy comprises: A method comprising receiving first information, the first information indicating the data quality screening policy.

12. 12. The method according to any one of claims 1 to 11, wherein the first information is included in a first message, the first message being used to request the training data set for the intelligent model, the method further comprising: transmitting said training data set; The method includes:

13. 13. The method of claim 12, wherein the first message further comprises second information, the second information indicating a dimensional configuration manner of the training data set; Screening the channel data in the first channel data set according to the data quality screening policy to obtain a training data set includes: screening the first channel data set according to the data quality screening policy to obtain a plurality of channel data; and structuring the plurality of channel data in the dimensional structure manner to obtain the training data set; A method comprising:

14. 14. The method according to claim 12 or 13, wherein the first message further includes third information, the third information indicating filtering the channel data acquired by screening; The step of screening the channel data in the first channel data set according to the data quality screening policy to obtain the training data set includes: screening the first channel data set according to the data quality screening policy to obtain the plurality of channel data; and filtering the plurality of channel data to obtain the training data set, the training data set including data obtained by filtering the plurality of channel data; A method comprising:

15. 12. The method according to claim 1, wherein the first information is included in a second message, the second message being used to request evaluation of channel data in the channel data set that satisfies the data quality condition, the method further comprising: transmitting fourth information, the fourth information indicating an amount of data, the amount of data being an amount of data in the channel data set that satisfies the data quality condition; receiving a first message, the first message being used to request the training data set; and transmitting said training data set; The method includes:

16. 1. A data processing method comprising: sending first information, the first information indicating a data quality screening policy, the data quality screening policy being used to obtain, by screening, model training data that satisfies a data quality condition; receiving a training data set from a first device, the training data set including channel data that satisfies the data quality condition; and training an intelligent model by using the training data set; The method includes:

17. 17. The method of claim 16, wherein the data quality screening policies include: A screening policy based on the received power stability of the same reference signal; A screening policy based on the transmission delay stability of the reference signal; a screening policy based on phase stability of channel data components corresponding to the same transceiver antenna pair; A screening policy based on a received signal-to-noise ratio of a reference signal; and Screening policies based on channel type diversity; The method includes one or more of the following:

18. 18. The method of claim 17, wherein the screening policy based on received power stability of the same reference signal comprises: A difference in reception power when the same reference signal is received by different receiving antennas corresponding to one channel data is equal to or less than a first threshold value. selecting, as the training data, channel data that satisfies a received power stability condition:

19. 20. The method of claim 18, wherein the different receive antennas are two receive antennas that are spatially adjacent and have the same polarization direction.

20. In the method according to any one of claims 17 to 19, the screening policy based on the transmission delay stability of the reference signal comprises: The difference in transmission delays of the reference signals of different transceiver antenna pairs corresponding to one channel data is equal to or less than a second threshold value. and selecting, as the training data, channel data that satisfies a delay stability condition:

21. 21. The method according to claim 17, wherein the screening policy based on phase stability of channel data components corresponding to the same transceiver antenna pair comprises: A phase difference value of channel data components of the same transceiver antenna pair in a plurality of channel data acquired within a preset interval is equal to or less than a third threshold value. and selecting, as the training data, channel data that satisfies a phase stability condition:

22. 22. The method according to any one of claims 17 to 21, wherein the screening policy based on the received signal-to-noise ratio of the reference signal comprises: using channel data corresponding to a reference signal whose received signal-to-noise ratio is greater than or equal to a fourth threshold as the training data.

23. 23. The method according to any one of claims 17 to 22, wherein the channel type diversity based screening policy is one of the following: selecting N pieces of line-of-sight LOS channel data and M pieces of non-line-of-sight NLOS channel data to form the training data set, where N and M are positive integers; a ratio of the LOS channel data to the NLOS channel data in the training data set is a predetermined ratio; and selecting Q channel data to form the training data set, where Q channel data includes at least N LOS channel data and at least M NLOS channel data, and Q>N+M; The method includes one or more of the following:

24. 24. The method of any one of claims 17-23, wherein the first information is included in a first message, and the first message is used to request the training data set for the intelligent model.

25. 25. The method of claim 24, wherein the first message further includes second information, the second information indicating a dimensional configuration manner of the training data set, and a configuration manner of channel data in the training data set is the dimensional configuration manner.

26. 26. The method of claim 24 or 25, wherein the first message further includes third information, the third information indicating filtering of channel data acquired by screening.

27. 27. The method according to any one of claims 16-26, wherein the first information is included in a second message, the second message being used to request evaluation of channel data in the channel data set that satisfies the data quality condition, the method further comprising: receiving fourth information from the first device, the fourth information indicating an amount of data, the amount of data being an amount of data in the channel data set that satisfies the data quality condition; sending a first message to the first device, the first message being used to request the training data set; and receiving the training data set from the first device; The method includes:

28. A communications device adapted to perform the method according to any one of claims 1-15 or to perform the method according to any one of claims 16-27.

29. A communications device comprising a processor and a memory, the memory coupled to the processor, the processor configured to perform a method according to any one of claims 1-15 or any one of claims 16-27.

30. A computer readable storage medium storing instructions which, when executed on a computer, enable the computer to perform the method of any one of claims 1-27.

31. A communication system comprising an apparatus configured to perform a method according to any one of claims 1-15 and an apparatus configured to perform a method according to any one of claims 16-27.

Images