WO2024148528A1 - 通信方法以及通信设备 - Google Patents
通信方法以及通信设备 Download PDFInfo
- Publication number
- WO2024148528A1 WO2024148528A1 PCT/CN2023/071739 CN2023071739W WO2024148528A1 WO 2024148528 A1 WO2024148528 A1 WO 2024148528A1 CN 2023071739 W CN2023071739 W CN 2023071739W WO 2024148528 A1 WO2024148528 A1 WO 2024148528A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- channel data
- sampling points
- communication device
- power
- group
- Prior art date
Links
- 238000004891 communication Methods 0.000 title claims abstract description 176
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000005070 sampling Methods 0.000 claims description 131
- 238000013473 artificial intelligence Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 14
- 230000000694 effects Effects 0.000 abstract description 11
- 238000012216 screening Methods 0.000 abstract 1
- 238000004140 cleaning Methods 0.000 description 18
- 238000005516 engineering process Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000005259 measurement Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 3
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 101000827703 Homo sapiens Polyphosphoinositide phosphatase Proteins 0.000 description 2
- 102100023591 Polyphosphoinositide phosphatase Human genes 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
Definitions
- the present application relates to the field of communication technology, and more specifically, to a communication method and a communication device.
- AI Artificial intelligence
- the wireless communication system itself is most affected by the external environment.
- Directly collected physical layer data, such as channel data often contains a lot of noise and has varying quality. If the model is directly trained or tuned using low-quality channel data, it may affect the improvement of model performance.
- the present application provides a communication method and a communication device.
- the following introduces various aspects involved in the present application.
- a communication method comprising: a first communication device determines whether first channel data is valid or invalid; wherein, when the first channel data is valid, the first channel data can be used to train a first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- a communication method comprising: a second communication device sends first configuration information to a first communication device; wherein the first configuration information is used to configure the content and/or parameters of a first condition, and when the first channel data satisfies the first condition, the first channel data is valid, and when the first channel data is valid, the first channel data can be used to train a first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- a communication device which is a first communication device, and includes: a judgment unit, used to judge whether first channel data is valid or invalid; wherein, when the first channel data is valid, the first channel data can be used to train the first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- a communication device which is a second communication device, and the communication device includes: a second sending unit, used to send first configuration information to a first communication device; wherein the first configuration information is used to configure the content and/or parameters of a first condition, and when the first channel data satisfies the first condition, the first channel data is valid, and when the first channel data is valid, the first channel data can be used to train a first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- a communication device comprising a processor and a memory, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the methods of the above aspects.
- an embodiment of the present application provides a communication system, which includes the above-mentioned communication device.
- the system may also include other devices that interact with the communication device in the solution provided by the embodiment of the present application.
- an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a communication device to execute part or all of the steps in the methods of the above aspects.
- an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a communication device to perform some or all of the steps in the above-mentioned various aspects of the method.
- the computer program product can be a software installation package.
- an embodiment of the present application provides a chip, which includes a memory and a processor, and the processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.
- the data used to train the first model is screened, and the first channel data can be used to train the first model only when the first channel data is valid. It is understandable that for the training of the first model, the quality of valid channel data is higher than that of invalid channel data. Therefore, based on the method provided in the present application, the low-quality part of the channel data can be effectively filtered out, and the first model can be trained using the higher-quality channel data, thereby improving the training effect and performance of the first model.
- FIG1 is a schematic diagram of a wireless communication system used in an embodiment of the present application.
- FIG2 is a schematic flow chart of a communication method provided in an embodiment of the present application.
- FIG. 3A and FIG. 3B are diagrams showing examples of distribution of power of different channel data in the delay domain.
- FIG4 is a schematic flowchart of another communication method provided in an embodiment of the present application.
- FIG5 is a schematic flowchart of another communication method provided in an embodiment of the present application.
- FIG. 6 is an example diagram of a method for determining whether the power distribution of first channel data satisfies a condition provided in the present application.
- FIG. 7 is a schematic structural diagram of a communication device provided in an embodiment of the present application.
- FIG8 is a schematic structural diagram of another communication device provided in an embodiment of the present application.
- FIG. 9 is a schematic structural diagram of a device for communication provided in an embodiment of the present application.
- FIG1 is a wireless communication system 100 used in an embodiment of the present application.
- the wireless communication system 100 may include a communication device.
- the communication device may include, for example, a network device 110 or a terminal device 120.
- the network device 110 may be a device that communicates with the terminal device 120.
- the network device 110 may provide communication coverage for a specific geographical area, and may communicate with the terminal device 120 located in the coverage area.
- FIG1 exemplarily shows a network device and two terminals.
- the wireless communication system 100 may include multiple network devices and each network device may include other number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.
- the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
- network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
- the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: the fifth generation (5th generation, 5G) system or new radio (new radio, NR), long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD), etc.
- 5G fifth generation
- NR new radio
- long term evolution long term evolution
- LTE long term evolution
- LTE frequency division duplex frequency division duplex
- FDD frequency division duplex
- TDD time division duplex
- future communication systems such as the sixth generation mobile communication system, satellite communication system, etc.
- the terminal device in the embodiment of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.
- the terminal device in the embodiment of the present application may be a device that provides voice and/or data connectivity to a user, and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc.
- the terminal device in the embodiment of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.
- the UE can be used to act as a base station.
- the UE can act as a scheduling entity, which provides sidelink signals between UEs in vehicle-to-everything (V2X) or device-to-device (D2D), etc.
- V2X vehicle-to-everything
- D2D device-to-device
- cell phones and cars use sidelink signals to communicate with each other.
- Cell phones and smart home devices communicate with each other without relaying the communication signals through a base station.
- the network device in the embodiment of the present application may be a device for communicating with a terminal device, and the network device may also be referred to as an access network device or a wireless access network device, such as a base station.
- the network device in the embodiment of the present application may refer to a wireless access network (RAN) node (or device) that connects a terminal device to a wireless network.
- RAN wireless access network
- Base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master eNB (MeNB), secondary eNB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc.
- NodeB evolved NodeB
- gNB next generation NodeB
- TRP transmitting and receiving point
- TP transmitting point
- MeNB master eNB
- SeNB secondary eNB
- MSR multi-standard radio
- the base station may be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof.
- the base station may also refer to a communication module, a modem or a chip used to be arranged in the aforementioned device or apparatus.
- the base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, machine-to-machine (M2M) communications, a network-side device in a 6G network, a device that performs the base station function in a future communication system, and the like.
- the base station may support networks with the same or different access technologies. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.
- Base stations can be fixed or mobile.
- a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station.
- a helicopter or drone can be configured to act as a device that communicates with another base station.
- the network device in the embodiments of the present application may refer to a CU or a DU, or the network device includes a CU and a DU.
- the gNB may also include an AAU.
- the network equipment and terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on the water surface; they can also be deployed on aircraft, balloons and satellites in the air.
- the embodiments of the present application do not limit the scenarios in which the network equipment and terminal equipment are located.
- AI artificial intelligence
- deep learning technology uses the powerful nonlinear fitting ability of deep artificial neural network models to successfully solve a series of problems that were difficult to handle before.
- deep learning technology has been successfully applied and even shows better performance than humans.
- AI technology is highly dependent on data. Whether there is enough data and the quality of the data will largely affect the final performance of the AI algorithm. For example, the concept of convolutional neural network was proposed in the 1980s and 1990s, but it did not attract much attention for a long time afterwards.
- Data cleaning can normalize the collected raw data to improve data quality and further improve the training effect of AI models.
- the most basic logic of data cleaning is to identify abnormal samples from the raw data and perform processing such as deletion and replacement.
- abnormal data can be identified and cleaned through subjective judgment by the human eye or some objective evaluation indicators based on image quality.
- Objective evaluation indicators may include, for example, image blur, brightness, color difference, etc.
- abnormal data can be screened and identified based on subjective judgment or objective rules such as grammar and format.
- the quality of the collected physical layer data is affected by the wireless environment in which the data collection device is located. For example, if the physical layer data is directly collected by the terminal device, the quality of the physical layer data is greatly affected by the wireless environment in which the terminal device is located. For example, for some terminal devices with poor channel quality, the collected data may contain a lot of noise. If the model is directly trained or tuned with data containing a lot of noise, its performance may be affected.
- AI technology in the field of wireless communications requires not only data, but also clean, high-quality data.
- the wireless communication system itself, especially the physical layer is most affected by the external environment.
- Directly collected physical layer data, such as wireless channel data (or channel data or channel samples) often contains a lot of noise and has varying quality.
- Wireless channel data implicitly contains rich environmental information, so it will be used in using AI to solve many wireless communication physical layer problems.
- potential AI use cases such as CSI feedback, channel estimation, and positioning may use channel data in the model training process.
- RS reference signal
- the network equipment For the measurement of downlink channels, it is often necessary for the network equipment to configure and send a reference signal (RS), and then the terminal equipment to detect the RS to complete the channel measurement and obtain the wireless channel data.
- RS reference signal
- the terminal equipment may detect the RS to complete the channel measurement and obtain the wireless channel data.
- there may be some poor quality channel data due to reasons such as measurement position, angle, and poor RS detection effect. Because the form of the channel data itself is ever-changing and disorganized, these poor quality channel data do not have explicit physical meaning.
- Fig. 2 is a schematic flow chart of a communication method provided by an embodiment of the present application to solve the above problem.
- the method shown in Fig. 2 may include step S210.
- Step S210 The first communication device determines whether the first channel data is valid or invalid.
- the first communication device may acquire one or more channel data, and the first channel data may be any one of the one or more channel data.
- the first channel data may also be referred to as a first channel sample.
- the first channel data can be used to train the first model. If the first channel data is invalid, the first channel data cannot be used to train the first model. It can be understood that if the first channel data is judged to be valid, the first channel data can be channel data of higher quality; if the first channel data is judged to be invalid, the first channel data can be channel data of lower quality. In other words, based on step S210, the first communication device can implement data cleaning of the first channel data.
- the data used to train the first model is screened, and the first channel data can be used to train the first model only when the first channel data is valid. It can be understood that for the training of the first model, the quality of valid channel data is higher than that of invalid channel data. Therefore, based on the method provided by the present application, the low-quality part of the channel data can be effectively filtered out, and the first model can be trained using the higher-quality channel data, thereby improving the training effect and performance of the first model.
- the first communication device may receive first indication information.
- the first indication information may be used to indicate whether the first communication device determines whether the first channel data is valid or invalid.
- the first indication information may be used to indicate whether the first communication device performs step S210.
- the first indication information may include an indication of "yes/no" or "on/off”. If step S210 does not need to be performed, the first indication information may indicate "off” or "no", and the first communication device may not perform a judgment on whether the first channel data is valid or invalid. If step S210 needs to be performed, the first indication information may indicate "on” or "yes”, and the first communication device may not perform a judgment on whether the first channel data is valid or invalid.
- step S210 actually cleans the first channel data. Therefore, in some embodiments, the first indication information may also be referred to as data cleaning indication information.
- the first indication information may be sent by the second communication device.
- the second communication device may be, for example, a network device.
- the second communication device may determine whether to require the first communication device based on aspects such as the usage mode of the first channel data and/or specific demand characteristics, thereby flexibly controlling the first communication device to perform data cleaning.
- the first indication information may be included in the first configuration information.
- the first channel data may be valid if the first channel data satisfies a first condition.
- the first condition may be related to one or more of the following information: a first indicator, and a power distribution of the first channel data.
- the first indicator may be determined based on the RS corresponding to the first channel data.
- the RS corresponding to the first channel data may be the RS measured to determine the first channel data.
- the first communication device may measure the first channel data and calculate the first indicator.
- the first indicator may be, for example, one or more of the following indicators: reference signal received power (reference signal received power, RSRP), reference signal received quality (reference signal receiving quality, RSRQ), and received signal strength indicator (received signal strength indicator, RSSI).
- reference signal received power reference signal received power
- RSRQ reference signal received quality
- RSSI received signal strength indicator
- the first indicator may reflect the channel condition and/or the reception effect of the reference signal. For example, the larger the first indicator is, the better the channel condition is and/or the better the reception effect of the reference signal is.
- the first condition may include that the first indicator is greater than or equal to the threshold value of the first indicator.
- the first channel data may be valid.
- the measured first channel data may be suitable for training the first model.
- the first indicator when the first indicator is less than or equal to the threshold value of the first indicator, it can be determined that the first channel data is invalid. That is, when the channel condition is poor and/or the reception effect of the reference signal is poor, the measured first channel data may be submerged in noise and is not suitable for training the first model.
- the present application does not limit the specific value of the threshold value of the first indicator.
- the threshold value of the first indicator can be: -80dBm, -70dBm or -60dBm, etc.
- the power distribution of the first channel data can be used to reflect the energy distribution on different signal transmission paths in the first channel data.
- the power distribution is the distribution of power in the delay domain.
- the delay domain can also be called the time domain.
- the first channel data may be in the frequency dimension, and the first channel data may be transformed from the frequency domain to the delay domain.
- the first channel data may be transformed to the delay domain by inverse fast Fourier transform (IFFT).
- IFFT inverse fast Fourier transform
- the first condition may include: the power distribution of the first channel data is relatively concentrated. That is, in the case where the power distribution or energy distribution of the first channel data is concentrated, the first channel data may be valid.
- Figures 3A and 3B are example diagrams of the power distribution of different channel data in the delay domain.
- the power distribution shown in Figure 3A is concentrated, and obvious rules can be seen, indicating that the channel data can clearly reflect the channel characteristics.
- the power distribution shown in Figure 3B is chaotic, which can reflect that the channel data is too affected by noise and has poor quality.
- the first channel data conforms to the basic distribution law, and the first channel data can be used for training the first model.
- the first channel data In the case where the power distribution of the first channel data is too dispersed, the first channel data lacks the basic distribution law, and the first channel data may be an invalid channel measurement data, and the first channel data cannot be used for training the first model.
- the following example illustrates how to determine whether the power distribution of the first channel data is concentrated.
- the first channel data may include multiple sampling points, and some of the sampling points in the first channel data may form a first group of sampling points.
- the power sum of the first group of sampling points may be the first power, that is, the sum of the powers of the sampling points in the first group of sampling points may be the first power.
- the proportion of the first power to the total power of the first channel data is greater than or equal to the first threshold, it can be determined that the power distribution of the first channel data is concentrated.
- the first condition may include: the proportion of the first power to the total power of the first channel data is greater than or equal to the first threshold. It can be understood that if the proportion of the first power is large, it can be explained that the power distribution of the first channel data is concentrated in the first group of sampling points, that is, it can be considered that the power distribution of the first channel data is concentrated.
- some sampling points in the first channel data may constitute a second group of sampling points.
- the sampling points in the second group of sampling points may be different from the sampling points in the first group of sampling points.
- the power sum of the second group of sampling points may be the second power, that is, the sum of the powers of the sampling points in the second group of sampling points may be the second power.
- the first condition may include: the proportion of the second power to the total power of the first channel data is less than or equal to the second threshold. It can be understood that if the proportion of the second power is small, it can be explained that the power distribution of the first channel data is concentrated on other sampling points except the second group of sampling points, that is, the power distribution of the first channel data is concentrated.
- the present application does not limit the specific value of the first threshold or the second threshold.
- the first threshold or the second threshold can be one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99, etc.
- the power of the first group of sampling points may be greater than or equal to the power of the sampling points other than the first group of sampling points in the first channel data. That is, in the delay dimension, if the sampling points in the first channel data are sorted from large to small according to power size, the first group of sampling points may be the first one or more sampling points in the reordered sampling points in the first channel data.
- the number of sampling points in the first group of sampling points may satisfy, in the delay dimension, that the number is M or the proportion of all sampling points in the first channel data is N. Wherein, both M and N may be numbers greater than 0. Taking the ordering of the sampling points in the first channel data from large to small according to power as an example, the first group of sampling points may be the first M or the first N proportion of the reordered sampling points in the first channel data.
- the power of the second group of sampling points may be less than or equal to the power of the sampling points other than the second group of sampling points in the first channel data. That is, in the delay dimension, if the sampling points in the first channel data are sorted from large to small according to power size, the second group of sampling points may be the latter one or more sampling points in the reordered sampling points in the first channel data.
- the number of sampling points in the second group of sampling points may satisfy, in the delay dimension, that the number is P or the proportion of all sampling points in the first channel data is Q. Wherein, P and Q may both be numbers greater than 0.
- the second group of sampling points may be the last P or the last Q proportion of the reordered sampling points in the first channel data.
- M, N, P or Q can be one of 32, 64, 96, 128, 160, etc.
- N or Q can be one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99, etc.
- the present application does not limit the method for obtaining the first group of sampling points and the second group of sampling points.
- the sampling points in the first channel data can be sorted according to the power size to determine the first group of sampling points and/or the second group of sampling points.
- the sorting method can be, for example, from large to small as described above, or from small to large.
- the method for determining the first group of sampling points and/or the second group of sampling points in a small to large order is similar to that in a large to small order, and the present application will not repeat them.
- the sampling point can also be called a delay sampling point.
- the method shown in FIG. 2 may further include step S205 .
- Step S205 The first communication device may receive first configuration information.
- the first configuration information can be used to configure the content and/or parameters of the first condition.
- the first configuration information can be used to configure the conditions and/or indicators related to data cleaning.
- the content of the first condition may include, for example, the information related to the first condition described above.
- the first configuration information may be used to configure the first condition to be related to the power distribution of the first indicator and/or the first channel data.
- the content of the first condition may include: the first indicator is greater than or equal to the threshold of the first indicator; and/or, the power distribution of the first channel data is concentrated.
- the parameters of the first condition may include any one or more parameters related to the first condition described above.
- the parameters of the first condition may include: a threshold of the first indicator, a first threshold, a second threshold, one or more of M, N, P, and Q.
- the first configuration information may be used to indicate that the configuration of the first condition is related to the first indicator, and the first condition may be configured to be related to which or which specific first indicator.
- the first configuration information may also be further used to configure the threshold value of the first indicator.
- the first configuration information may be sent by the second communication device described above.
- the content and/or parameters of the first condition may be configured by the second communication device.
- the second communication device may flexibly control the degree of data cleaning according to the usage mode of the first channel data, actual needs, etc.
- the first configuration information can be carried in one or more of the following messages: radio resource control (RRC) message, broadcast message, medium access control control element (MAC CE), downlink control information (DCI), etc.
- RRC radio resource control
- MAC CE medium access control control element
- DCI downlink control information
- the present application does not limit the operation of the first communication device on the first channel data after data cleaning.
- the first communication device may send the first channel data.
- the recipient of the first channel data may train the first model based on the first channel data.
- the first communication device may not send the first channel data. In this case, the first communication device may not need to upload invalid channel data, thereby avoiding wasting uplink transmission resources.
- the first channel data can be carried by RRC signaling and/or physical uplink shared channel (PUSCH).
- PUSCH physical uplink shared channel
- the first communication device may train the first model based on the first channel data.
- the training of the first model by the first communication device may be a fine-tuning of the first model.
- the first communication device may not train the first model based on the first channel data. Training the first model locally based on valid first channel data can effectively improve the performance of the first model, thereby avoiding the adverse effects of invalid data on the performance of the first model.
- the present application does not limit the processing method for the first channel data.
- the first communication device may discard or delete the invalid first channel data, that is, not use the first channel data to perform the operation performed when the first channel data is valid.
- the first communication device may replace the invalid first channel data.
- the first communication device may process the invalid first channel data so that the processed first channel data meets the first condition.
- the first channel data can be acquired by the first communication device. That is, the first communication device can perform data collection to obtain the first communication data.
- the second communication device can send second configuration information to the first communication device, and the second configuration information can be used to instruct the first communication device to perform channel measurement.
- the second configuration information can be used to configure RS.
- the first communication device can perform a channel measurement process to collect the first channel data.
- FIG4 takes the first communication device as a terminal device and the second communication device as a network device as an example to illustrate the collection process of the first channel data.
- the method shown in FIG. 4 may include step S410 and step S420 .
- Step S410 The terminal device receives the second configuration information.
- the network device sends the second configuration information.
- the second configuration information can be used to configure the RS.
- the network device configures the RS through the second configuration information so that the terminal device can collect the first channel data.
- Step S420 The terminal device receives the RS.
- the network device sends the RS.
- the network device may send the RS according to the second configuration information.
- the terminal device may receive or detect the RS according to the second configuration information.
- Step S430 The terminal device completes channel measurement based on the detected RS. Based on the channel measurement process in step S430, the terminal device can collect first channel data.
- the first communication device may be the terminal device in Figure 5
- the second communication device may be the network device in Figure 5.
- the method shown in Figure 5 may include steps S510 to S560.
- Step S510 The terminal device receives first configuration information sent by the network device.
- the first configuration information can be used to configure the content and/or parameters of the first condition.
- the first condition is related to data cleaning.
- the first configuration information can be used to configure data cleaning related conditions and/or indicators.
- the first configuration information may include data cleaning indication information.
- the data cleaning indication information is used to indicate whether the terminal device performs data cleaning.
- Step S520 The terminal device receives second configuration information sent by the network device.
- the second configuration information can be used to configure the RS.
- Step S530 the network device sends RS according to the second configuration.
- the RS is used for the terminal device to complete the collection and cleaning of the first channel data.
- Step S540 The terminal device completes channel measurement based on the detected RS, thereby collecting first channel data.
- the terminal device can determine whether to perform data cleaning according to the data cleaning indication information. If data cleaning is not required, the terminal device can directly send the first channel data to the network device and/or use the first channel data to fine-tune the first model. If data cleaning is required, the terminal device can determine whether the channel data or sample is valid or invalid for each channel data or sample according to the first condition indicated by the network device. For channel data that meets the first condition, the channel data can be judged to be valid; for channel data that does not meet the first condition, the channel data can be judged to be invalid.
- the first condition may include, for example, one or more of the following conditions: the first indicator is greater than or equal to the threshold value of the first indicator; the power distribution of the first channel data meets the condition.
- the first configuration information may configure one or more of the above conditions to belong to the first condition and the corresponding threshold value.
- the first indicator may include: one or more of RSRP, RSRQ, and RSSI.
- the network device may specify a specific threshold value X of the first indicator in the first configuration information. X may be, for example: -80dBm, -70dBm, or -60dBm, etc.
- X may be, for example: -80dBm, -70dBm, or -60dBm, etc.
- FIG. 6 exemplarily shows the steps of determining whether the power distribution of the first channel data satisfies the conditions.
- Step 1 Convert the first channel data from the frequency domain to the delay domain through IFFT. There is no strict restriction on whether to perform additional mathematical processing on the antenna dimension.
- Step 2 Rearrange the samples in the delay domain according to the energy size.
- the following is an example of arrangement from large to small. It is understandable that the arrangement from small to large can also be performed, and the first condition can be adjusted accordingly, which will not be repeated in this application.
- Step 3 For the reordered first channel data, determine whether the first channel data is valid according to the first condition content and indicator parameters configured in the first configuration information.
- the content of the first condition may include, for example, one or more of conditions 1 to 4.
- Conditions 1 to 4 are all related to the power proportion of some sampling points in the first channel data.
- N and Y can be configured by the network device. N and Y are used to indicate the proportion.
- the values of N and Y can be, for example, one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, and 0.99.
- Condition 2 In the delay dimension, the power of the first M sampling points of the first channel data and the proportion of the total power of the first channel data are greater than the first threshold Y.
- M and Y can be configured by the network device.
- M can be used to indicate the number of sampling points.
- the value of M can be, for example, one of 32, 64, 96, 128, 160, etc.
- Y can be used to indicate the ratio.
- the value of Y can be, for example, one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99, etc.
- Condition 3 In the delay dimension, the power of the Q part corresponding to the first channel data and the proportion of the total power of the first channel data are less than the second threshold Z.
- Both Q and Z can be configured by the network device. Both Q and Z can be used to indicate the ratio.
- the values of Q and Z can be, for example, one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99, etc.
- Condition 4 In the delay dimension, the power of the last P sampling points on the first channel data and the proportion of the total energy of the first channel data are less than the second threshold Z.
- P and Z can be configured by the network device.
- P can be used to indicate the number of sampling points.
- the value of P can be, for example, one of 32, 64, 96, 128, 160...
- Z can be used to indicate the ratio.
- the value of Z can be, for example, one of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99.
- the method shown in FIG5 may include step S560.
- Step S560 may include step S561 and/or step S562.
- Step S561 The terminal device fine-tunes the first model based on valid first channel data.
- Step S562 The terminal device sends valid first channel data to the network device.
- the first channel data may be carried by RRC signaling or PUSCH.
- the first model described in the present application may be a model for communication.
- the first model may include one or more of a channel state information feedback model, a beam management model, and a high-precision positioning model.
- the first model may be an AI model.
- the first model may include a machine learning model.
- the first model may include a neural network model.
- FIG7 is a schematic structural diagram of a communication device 700 provided in an embodiment of the present application.
- the communication device 700 is a first communication device.
- the communication device 700 includes a determination unit 710 .
- the judgment unit 710 is used to judge whether the first channel data is valid or invalid; wherein, when the first channel data is valid, the first channel data can be used to train the first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- the first channel data is valid if the first channel data satisfies a first condition, and the first condition is related to one or more of the following information: a first indicator, which is determined based on a reference signal corresponding to the first channel data; and power distribution of the first channel data.
- the first indicator includes one or more of the following indicators: RSRP, RSRQ, RSSI.
- the power distribution is the distribution of power in the delay domain.
- the first condition when the first condition is related to the power distribution, includes one or more of the following: the proportion of the first power to the total power of the first channel data is greater than or equal to a first threshold; the proportion of the second power to the total power of the first channel data is less than or equal to a second threshold; wherein the first power is the sum of the powers of a first group of sampling points in the first channel data, and the second power is the sum of the powers of a second group of sampling points in the first channel data.
- the power of the first group of sampling points is greater than or equal to the power of the sampling points other than the first group of sampling points in the first channel data, and the number of the first group of sampling points satisfies in the delay dimension: the number is M or the proportion of all sampling points in the first channel data is N; the power of the second group of sampling points is less than or equal to the power of the sampling points other than the second group of sampling points in the first channel data, and the number of the second group of sampling points satisfies in the delay dimension: the number is P or the proportion of all sampling points in the first channel data is Q.
- the communication device 700 further includes: a first receiving unit, configured to receive first configuration information; wherein the first configuration information is used to configure the content and/or parameters of the first condition.
- the communication device 700 when the first channel data is valid, the communication device 700 further includes: a first sending unit, configured to send the first channel data; and/or a training unit, configured to train the first model based on the first channel data.
- the communication device 700 further includes: a second receiving unit, configured to receive first indication information, wherein the first indication information is configured to indicate whether the first communication device determines whether the first channel data is valid or invalid.
- the first model is an AI model.
- FIG8 is a schematic structural diagram of a communication device 800 provided in an embodiment of the present application.
- the communication device 800 is a second communication device.
- the communication device 800 may include a second sending unit 810 .
- the second sending unit 810 is used to send first configuration information to the first communication device; wherein the first configuration information is used to configure the content and/or parameters of the first condition, and when the first channel data meets the first condition, the first channel data is valid, and when the first channel data is valid, the first channel data can be used to train the first model, and when the first channel data is invalid, the first channel data cannot be used to train the first model.
- the first condition is related to one or more of the following information: a first indicator, the first indicator is determined based on a reference signal corresponding to the first channel data; and power distribution of the first channel data.
- the first indicator includes one or more of the following indicators: RSRP, RSRQ, RSSI.
- the power distribution is the distribution of power in the delay domain.
- the first condition when the first condition is related to the power distribution, includes one or more of the following: the proportion of the first power to the total power of the first channel data is greater than or equal to a first threshold; the proportion of the second power to the total power of the first channel data is less than or equal to a second threshold; wherein the first power is the sum of the powers of a first group of sampling points in the first channel data, and the second power is the sum of the powers of a second group of sampling points in the first channel data.
- the power of the first group of sampling points is greater than or equal to the power of the sampling points other than the first group of sampling points in the first channel data, and the number of the first group of sampling points satisfies in the delay dimension: the number is M or the proportion of all sampling points in the first channel data is N; the power of the second group of sampling points is less than or equal to the power of the sampling points other than the second group of sampling points in the first channel data, and the number of the second group of sampling points satisfies in the delay dimension: the number is P or the proportion of all sampling points in the first channel data is Q.
- the communication device when the first channel data is valid, the communication device further includes: a third receiving unit, configured to receive the first channel data.
- the communication device 800 further includes: a third sending unit, configured to send first indication information to the first communication device, wherein the first indication information is configured to indicate whether the first communication device determines whether the first channel data is valid or invalid.
- the first model is an AI model.
- the second sending unit 810 may be a transceiver 930, and the determining unit 720 may be a processor 910.
- the communication device 700 or the communication device 800 may further include a memory 920, as specifically shown in FIG9 .
- FIG9 is a schematic structural diagram of a device for communication according to an embodiment of the present application.
- the dotted lines in FIG9 indicate that the unit or module is optional.
- the device 900 may be used to implement the method described in the above method embodiment.
- the device 900 may be a chip, a terminal device, or a network device.
- the device 900 may include one or more processors 910.
- the processor 910 may support the device 900 to implement the method described in the method embodiment above.
- the processor 910 may be a general-purpose processor or a special-purpose processor.
- the processor may be a central processing unit (CPU).
- the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- DSP digital signal processor
- ASIC application-specific integrated circuits
- FPGA field programmable gate arrays
- a general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
- the apparatus 900 may further include one or more memories 920.
- the memory 920 stores a program, which can be executed by the processor 910, so that the processor 910 executes the method described in the above method embodiment.
- the memory 920 may be independent of the processor 910 or integrated in the processor 910.
- the apparatus 900 may further include a transceiver 930.
- the processor 910 may communicate with other devices or chips through the transceiver 930.
- the processor 910 may transmit and receive data with other devices or chips through the transceiver 930.
- the present application also provides a computer-readable storage medium for storing a program.
- the computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.
- the embodiment of the present application also provides a computer program product.
- the computer program product includes a program.
- the computer program product can be applied to the terminal or network device provided in the embodiment of the present application, and the program enables the computer to execute the method performed by the terminal or network device in each embodiment of the present application.
- the embodiment of the present application also provides a computer program.
- the computer program can be applied to the terminal or network device provided in the embodiment of the present application, and the computer program enables a computer to execute the method executed by the terminal or network device in each embodiment of the present application.
- the "indication" mentioned can be a direct indication, an indirect indication, or an indication of an association relationship.
- a indicates B which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, B can be obtained through C; it can also mean that there is an association relationship between A and B.
- B corresponding to A means that B is associated with A, and B can be determined according to A.
- determining B according to A does not mean determining B only according to A, and B can also be determined according to A and/or other information.
- the term "corresponding" may indicate that there is a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship of indication and being indicated, configuration and being configured, etc.
- pre-definition or “pre-configuration” can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and the present application does not limit the specific implementation method.
- pre-definition can refer to what is defined in the protocol.
- the “protocol” may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.
- the term "and/or" is only a description of the association relationship of the associated objects, indicating that there can be three relationships.
- a and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone.
- the character "/" in this article generally indicates that the associated objects before and after are in an "or" relationship.
- the size of the serial numbers of the above-mentioned processes does not mean the order of execution.
- the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
- the disclosed systems, devices and methods can be implemented in other ways.
- the device embodiments described above are only schematic.
- the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
- Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
- the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
- each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the computer program product includes one or more computer instructions.
- the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
- the computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
- the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.
- the computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated.
- the available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.
- a magnetic medium e.g., a floppy disk, a hard disk, a magnetic tape
- an optical medium e.g., a digital video disc (DVD)
- DVD digital video disc
- SSD solid state disk
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Electromagnetism (AREA)
- Cable Transmission Systems, Equalization Of Radio And Reduction Of Echo (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
提供了一种通信方法以及通信设备。所述方法包括:第一通信设备判断第一信道数据有效或无效;其中,在第一信道数据有效的情况下,第一信道数据能够用于训练第一模型,在第一信道数据无效的情况下,第一信道数据不能用于训练第一模型。用于训练第一模型的数据是经过筛选的,在第一信道数据有效的情况下,第一信道数据才可以用于训练第一模型。可以理解的是,对于第一模型的训练,有效的信道数据的质量比无效的信道数据的高。因此,基于本申请提供的方法,可以有效滤除信道数据中低质量的部分,使用较高质量的信道数据对第一模型进行训练,从而提高第一模型的训练效果及性能。
Description
本申请涉及通信技术领域,并且更为具体地,涉及一种通信方法以及通信设备。
无线通信领域的人工智能(artificial intelligence,AI)技术需要的不仅仅是数据,更是干净的、高质量的数据。而无线通信系统本身,特别是物理层,又是受到外界环境影响最大的。直接收集到的物理层数据,例如信道数据,往往包含着大量噪声,质量参差不齐。如果用包含质量低的信道数据直接训练或调优模型可能会影响模型性能的提升。
发明内容
本申请提供一种通信方法以及通信设备。下面对本申请涉及的各个方面进行介绍。
第一方面,提供了一种通信方法,所述方法包括:第一通信设备判断第一信道数据有效或无效;其中,在第一信道数据有效的情况下,第一信道数据能够用于训练第一模型,在第一信道数据无效的情况下,第一信道数据不能用于训练第一模型。
第二方面,提供了一种通信方法,所述方法包括:第二通信设备向第一通信设备发送第一配置信息;其中,所述第一配置信息用于配置第一条件的内容和/或参数,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
第三方面,提供了一种通信设备,所述通信设备为第一通信设备,所述通信设备包括:判断单元,用于判断第一信道数据有效或无效;其中,在第一信道数据有效的情况下,第一信道数据能够用于训练第一模型,在第一信道数据无效的情况下,第一信道数据不能用于训练第一模型。
第四方面,提供了一种通信设备,所述通信设备为第二通信设备,所述通信设备包括:第二发送单元,用于向第一通信设备发送第一配置信息;其中,第一配置信息用于配置第一条件的内容和/或参数,在第一信道数据满足第一条件的情况下,第一信道数据有效,在第一信道数据有效的情况下,第一信道数据能够用于训练第一模型,在第一信道数据无效的情况下,第一信道数据不能用于训练第一模型。
第五方面,提供一种通信设备,包括处理器以及存储器,所述存储器用于存储一个或多个计算机程序,所述处理器用于调用所述存储器中的计算机程序使得所述终端设备执行上述各个方面的方法中的部分或全部步骤。
第六方面,本申请实施例提供了一种通信系统,该系统包括上述的通信设备。在另一种可能的设计中,该系统还可以包括本申请实施例提供的方案中与该通信设备进行交互的其他设备。
第七方面,本申请实施例提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序使得通信设备执行上述各个方面的方法中的部分或全部步骤。
第八方面,本申请实施例提供了一种计算机程序产品,其中,所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质,所述计算机程序可操作来使通信设备执行上述各个方面的方法中的部分或全部步骤。在一些实现方式中,该计算机程序产品可以为一个软件安装包。
第九方面,本申请实施例提供了一种芯片,该芯片包括存储器和处理器,处理器可以 从存储器中调用并运行计算机程序,以实现上述各个方面的方法中所描述的部分或全部步骤。
用于训练第一模型的数据是经过筛选的,在第一信道数据有效的情况下,第一信道数据才可以用于训练第一模型。可以理解的是,对于第一模型的训练,有效的信道数据的质量比无效的信道数据的高。因此,基于本申请提供的方法,可以有效滤除信道数据中低质量的部分,使用较高质量的信道数据对第一模型进行训练,从而提高第一模型的训练效果及性能。
图1是本申请实施例应用的无线通信系统的示意图。
图2是本申请实施例提供的一种通信方法的示意性流程图。
图3A和图3B分别是不同的信道数据的功率在时延域上的分布情况示例图。
图4是本申请实施例提供的另一种通信方法的示意性流程图。
图5是本申请实施例提供的另一种通信方法的示意性流程图。
图6是本申请提供的一种第一信道数据的功率分布情况是否满足条件的判断方法的示例图。
图7是本申请实施例提供的一种通信设备的示意性结构图。
图8是本申请实施例提供的另一种通信设备的示意性结构图。
图9是本申请实施例提供的一种用于通信的装置的示意性结构图。
下面将结合附图,对本申请中的技术方案进行描述。
通信系统
图1是本申请实施例应用的无线通信系统100。该无线通信系统100可以包括通信设备。通信设备例如可以包括网络设备110或终端设备120。网络设备110可以是与终端设备120通信的设备。网络设备110可以为特定的地理区域提供通信覆盖,并且可以与位于该覆盖区域内的终端设备120进行通信。
图1示例性地示出了一个网络设备和两个终端,可选地,该无线通信系统100可以包括多个网络设备并且每个网络设备的覆盖范围内可以包括其它数量的终端设备,本申请实施例对此不做限定。
可选地,该无线通信系统100还可以包括网络控制器、移动管理实体等其他网络实体,本申请实施例对此不作限定。
应理解,本申请实施例的技术方案可以应用于各种通信系统,例如:第五代(5th generation,5G)系统或新无线(new radio,NR)、长期演进(long term evolution,LTE)系统、LTE频分双工(frequency division duplex,FDD)系统、LTE时分双工(time division duplex,TDD)等。本申请提供的技术方案还可以应用于未来的通信系统,如第六代移动通信系统,又如卫星通信系统,等等。
本申请实施例中的终端设备也可以称为用户设备(user equipment,UE)、接入终端、用户单元、用户站、移动站、移动台(mobile station,MS)、移动终端(mobile terminal,MT)、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置。本申请实施例中的终端设备可以是指向用户提供语音和/或数据连通性的设备,可以用于连接人、物和机,例如具有无线连接功能的手持式设备、车载设备等。本申请的实施例中的终端设备可以是手机(mobile phone)、平板电脑(Pad)、笔记本电脑、掌上电脑、移动互联网设备(mobile internet device,MID)、可穿戴设备,虚拟现实(virtual reality,VR)设备、增强现实(augmented reality,AR)设备、工业控制(industrial control)中的无线终端、无人驾驶(self driving)中的无线终端、远程手术(remote medical surgery)中的 无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端等。可选地,UE可以用于充当基站。例如,UE可以充当调度实体,其在车辆外联(vehicle-to-everything,V2X)或设备到设备(device to device,D2D)等中的UE之间提供侧行链路信号。比如,蜂窝电话和汽车利用侧行链路信号彼此通信。蜂窝电话和智能家居设备之间通信,而无需通过基站中继通信信号。
本申请实施例中的网络设备可以是用于与终端设备通信的设备,该网络设备也可以称为接入网设备或无线接入网设备,如网络设备可以是基站。本申请实施例中的网络设备可以是指将终端设备接入到无线网络的无线接入网(radio access network,RAN)节点(或设备)。基站可以广义的覆盖如下中的各种名称,或与如下名称进行替换,比如:节点B(NodeB)、演进型基站(evolved NodeB,eNB)、下一代基站(next generation NodeB,gNB)、中继站、接入点、传输点(transmitting and receiving point,TRP)、发射点(transmitting point,TP)、主站(master eNB,MeNB)、辅站(secondary eNB,SeNB)、多标准无线(multi-standard radio,MSR)节点、家庭基站、网络控制器、接入节点、无线节点、接入点(access point,AP)、传输节点、收发节点、基带单元(base band unit,BBU)、射频拉远单元(remote radio unit,RRU)、有源天线单元(active antenna unit,AAU)、射频头(remote radio head,RRH)、中心单元(central unit,CU)、分布式单元(distributed unit,DU)、定位节点等。基站可以是宏基站、微基站、中继节点、施主节点或类似物,或其组合。基站还可以指用于设置于前述设备或装置内的通信模块、调制解调器或芯片。基站还可以是移动交换中心以及D2D、V2X、机器到机器(machine-to-machine,M2M)通信中承担基站功能的设备、6G网络中的网络侧设备、未来的通信系统中承担基站功能的设备等。基站可以支持相同或不同接入技术的网络。本申请的实施例对网络设备所采用的具体技术和具体设备形态不做限定。
基站可以是固定的,也可以是移动的。例如,直升机或无人机可以被配置成充当移动基站,一个或多个小区可以根据该移动基站的位置移动。在其他示例中,直升机或无人机可以被配置成用作与另一基站通信的设备。
在一些部署中,本申请实施例中的网络设备可以是指CU或者DU,或者,网络设备包括CU和DU。gNB还可以包括AAU。
网络设备和终端设备可以部署在陆地上,包括室内或室外、手持或车载;也可以部署在水面上;还可以部署在空中的飞机、气球和卫星上。本申请实施例中对网络设备和终端设备所处的场景不做限定。
应理解,本申请中的通信设备的全部或部分功能也可以通过在硬件上运行的软件功能来实现,或者通过平台(例如云平台)上实例化的虚拟化功能来实现。
人工智能
近年来,人工智能(artificial intelligence,AI)技术正在人类社会中掀起一轮技术革新。作为AI技术的一个重要的研究方向,深度学习技术利用深度人工神经网络模型的强大非线性拟合能力,成功地解决了一系列从前难以处理的问题。特别地,在计算机视觉和自然语言处理领域,深度学习技术成功应用,甚至表现出了强于人类的性能。然而,与工程领域的传统技术方案主要依赖于算法不同,AI技术高度依赖于数据。是否有足量数据、数据质量如何等问题,很大程度上将影响AI算法最终的性能效果。举例而言,卷积神经网络的概念在二十世纪八、九十年代就已经被提出,但后续很长时间并没有引起特别大的关注。直到2012年,依托于大规模图像数据集ImageNet,卷积神经网络才在图像识别领域取得了引人注目的突破。如今,在任何领域应用AI技术,大规模、高质量数据集的获取和构建都是十分关键的问题。可以说,数据是AI的源泉。数据越多,数据质量越高,AI的潜力越大。
数据清洗可以对收集到的原始数据进行规范化处理,从而提高数据质量,进而提升AI模型训练效果。具体而言,数据清洗最基本的逻辑是从原始数据中识别出异常样本,并进行例如删除、替换等处理。例如,在计算机视觉领域,可以通过人眼进行主观判断或是基于图像质量的一些客观评判指标来识别异常数据并进行清洗。客观评判指标例如可以包括:图像的模糊度、亮度、色差等。与计算机视觉领域类似,在自然语言领域,可以基于主观判断或语法、格式等客观规则,来筛选、识别异常数据。
基于AI技术的无线通信系统
未来无线通信系统将向更大吞吐、更低时延、更高可靠性、更大连接数、更高频谱利用率等方向演进。而近年的研究工作表明,AI技术在复杂环境建模和学习、复杂信号处理和预测等很多方面具有重要的应用潜力,有望促进未来通信范式的演进和变革,由此催生了无线AI技术的蓬勃发展。例如,在第三代合作伙伴计划(3rd generation partnership project,3GPP)的R18(release 18)标准化中,也设立了研究项目(study item)专门进行关于在无线通信系统物理层中引入AI技术的研究与讨论。该研究主要聚焦于信道状态信息(channel state information,CSI)反馈、波束管理和高精度定位等用例。与在其他应用AI技术的领域类似,数据集的数量和质量是影响无线通信领域AI性能效果的关键因素。毫无疑问,无线通信系统本身是蕴含大量数据的。数以百万计的系统设备、数十亿的手机终端以及未来数百亿的物联网终端,每时每刻都在产生着海量的数据。直接将这些数据用于模型的训练,会产生诸多问题。
采集的物理层数据的质量受到数据采集设备所处无线环境影响。以物理层数据由终端设备直接采集为例,这些物理层数据的质量是受终端设备所处无线环境所大幅影响的。例如,对于部分信道质量很差的终端设备而言,其采集到的数据中可能含有大量的噪声。如果用包含大量噪声的数据直接训练或调优模型可能会影响其性能的提升。
由此可知,无线通信领域的AI技术需要的不仅仅是数据,更是干净的、高质量的数据。而无线通信系统本身,特别是物理层,又是受到外界环境影响最大的。直接收集到的物理层数据,例如无线信道数据(或称为信道数据或信道样本),往往包含着大量噪声,质量参差不齐。
无线信道数据中隐式包含了丰富的环境信息,因而在使用AI解决诸多无线通信物理层问题中都会被用到。例如CSI反馈、信道估计、定位等潜在AI用例都有可能在模型训练过程中使用信道数据。对于下行信道的测量,往往需要由网络设备配置并发送参考信号(reference signal,RS),再由终端设备实现RS的检测从而完成信道的测量,得到无线信道数据。然而,在终端设备测量得到的信道数据中,可能由于诸如测量位置、角度、RS检测效果不佳等原因,存在部分质量不佳的信道数据。由于信道数据的形态本身千变万化、杂乱无章,这些质量不佳的信道数据不具备显式的物理意义。
图2为本申请实施例提供的一种通信方法的示意性流程图,以解决上述问题。图2所示的方法可以包括步骤S210。
步骤S210,第一通信设备判断第一信道数据有效或无效。
第一通信设备可以获取一个或多个信道数据,第一信道数据可以为一个或多个信道数据中的任意一个。在一些实施例中,第一信道数据也可以称为第一信道样本。
在第一信道数据有效的情况下,第一信道数据能够用于训练第一模型。在第一信道数据无效的情况下,第一信道数据不能用于训练第一模型。可以理解的是,如果判断第一信道数据是有效的,则第一信道数据可以是质量较高的信道数据;如果判断第一信道数据是无效的,则第一信道数据可以是质量较低的信道数据,换句话说,基于步骤S210,第一通信设备可以实现第一信道数据的数据清洗。
用于训练第一模型的数据是经过筛选的,在第一信道数据有效的情况下,第一信道数据才可以用于训练第一模型。可以理解的是,对于第一模型的训练,有效的信道数据的质 量比无效的信道数据的高。因此,基于本申请提供的方法,可以有效滤除信道数据中低质量的部分,使用较高质量的信道数据对第一模型进行训练,从而提高第一模型的训练效果及性能。
在一些实施例中,第一通信设备可以接收第一指示信息。第一指示信息可以用于指示第一通信设备是否判断第一信道数据有效或无效。换句话说,第一指示信息可以用于指示第一通信设备是否执行步骤S210。例如,第一指示信息可以包括“是/否”或“开/关(on/off)”的指示。若不需要执行步骤S210,则第一指示信息可以指示“关”或“否”,则第一通信设备可以不对第一信道数据进行有效或无效进行判断。若需要执行步骤S210,则第一指示信息可以指示“开”或“是”,则第一通信设备可以不对第一信道数据进行有效或无效的判断。
如上文所述,步骤S210实际上是对第一信道数据进行了数据清洗,因此,在一些实施例中,第一指示信息也可以称为数据清洗指示信息。
第一指示信息可以是第二通信设备发送的。第二通信设备例如可以为网络设备。第二通信设备可以根据第一信道数据的使用方式和/或具体需求特点等方面,确定是否要求第一通信设备,从而灵活地控制第一通信设备进行数据清洗。在一些实施例中,第一指示信息可以包含于第一配置信息中。
不同于计算机视觉和自然语言处理等领域,无线物理层数据是难以通过主观判断来识别异常的。另外,也没有成熟、规范的客观评判指标判断数据是否有效。本申请提出,可以基于第一条件确定第一信道数据有效或无效。
在一些实施例中,在第一信道数据满足第一条件的情况下,第一信道数据可以为有效的。第一条件可以与以下信息中的一项或多项相关:第一指标、第一信道数据的功率分布情况。
第一指标可以基于第一信道数据对应的RS确定。第一信道数据对应的RS可以是确定第一信道数据所测量的RS。通过RS,第一通信设备可以测量得到第一信道数据,并且可以计算得到第一指标。
第一指标例如可以以下指标中的一项或多项:参考信号接收功率(reference signal received power,RSRP)、参考信号接收质量(reference signal receiving quality,RSRQ)、接收信号强度指示(received signal strength indicator,RSSI)。
第一指标可以反映信道状况和/或参考信号的接收效果。例如,第一指标越大,信道状况越好和/或参考信号的接收效果越好。
在一些实施例中,在第一指标大于或等于第一指标的门限值的情况下,可以确定第一信道数据是有效的,即第一条件可以包括第一指标大于或等于第一指标的门限值。也就是说,在信道状况较好和/或参考信号的接收效果较佳的情况下,第一信道数据可以是有效的。在这种情况下,测量得到的第一信道数据可以是适宜用于第一模型的训练的。
在一些实施例中,在第一指标小于或等于第一指标的门限值的情况下,可以确定第一信道数据是无效的。也就是说,在信道状况较差和/或参考信号的接收效果不佳的情况下,测量得到的第一信道数据可能会淹没在噪声中,而不适宜用于第一模型的训练。
本申请不限制第一指标的门限值的具体大小。例如,第一指标的门限值可以为:-80dBm、-70dBm或-60dBm等。
第一信道数据的功率(power)分布情况可以用于反映第一信道数据中不同信号传输径上的能量分布。例如,功率分布情况为功率在时延(delay)域上的分布情况。在一些实施例中,时延域也可以称为时域。
在一些实施例中,第一信道数据可能是属于频率维度的,可以将第一信道数据由频率域转化至时延域。例如,可以通过快速傅里叶逆变换(inverse fast fourier transform,IFFT)将第一信道数据转化至时延域。
对于传输环境简单的情况,如存在视距(line of sight,LOS)传输径的情况,功率分布 将较为集中。而对于传输环境复杂的情况,如只存在非视距(none line of sight,NLOS)传输径的情况,功率分布将相对分散。第一条件可以包括:第一信道数据的功率分布较集中。也就是说,在第一信道数据的功率分布或能量分布集中的情况下,第一信道数据可以是有效的。
图3A和图3B分别为不同的信道数据的功率在时延域上的分布情况示例图。图3A所示的功率分布集中,可以看出明显的规律,说明该信道数据可以明确体现信道特征。图3B所示的功率分布杂乱无章,可以反映出该信道数据受到噪声的影响过大,质量不佳。
在第一信道数据的功率分布较集中的情况下,第一信道数据符合基本分布规律,则第一信道数据可以用于第一模型的训练。在第一信道数据的功率分布过于分散的情况下,第一信道数据缺乏基本分布规律,则第一信道数据可能是一个无效的信道测量数据,则第一信道数据不能用于训练第一模型。下面举例说明,如何判断第一信道数据的功率分布是否是集中的。
在一些实施例中,第一信道数据中可以包括多个采样点,第一信道数据中的部分采样点可以组成第一组采样点。第一组采样点的功率和可以为第一功率,即第一组采样点中的采样点的功率的总和可以为第一功率。在第一功率对于第一信道数据的总功率的占比大于或等于第一门限的情况下,可以确定第一信道数据的功率分布是集中的。也就是说,第一条件可以包括:第一功率对于第一信道数据的总功率的占比大于或等于第一门限。可以理解的是,如果第一功率的占比较大,则可以说明第一信道数据的功率分布集中于第一组采样点,即可以认为第一信道数据的功率分布是集中的。
在一些实施例中,第一信道数据中的部分采样点可以组成第二组采样点。第二组采样点中的采样点可以与第一组采样点中的采样点不同。第二组采样点的功率和可以为第二功率,即第二组采样点中的采样点的功率的总和可以为第二功率。在第二功率对于第一信道数据的总功率的占比小于或等于第二门限的情况下,可以确定第一信道数据的功率分布是集中的。也就是说,第一条件可以包括:第二功率对于第一信道数据的总功率的占比小于或等于第二门限。可以理解的是,如果第二功率的占比较小,则可以说明第一信道数据的功率分布集中于除第二组采样点的其他采样点,即第一信道数据的功率分布是集中的。
本申请不限制第一门限或第二门限的具体取值。例如,第一门限或第二门限可以为0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99等值中的一个。
作为一种实现方式,第一组采样点的功率可以均大于或等于第一信道数据中除第一组采样点以外的采样点的功率。也就是说,在时延维度上,如果将第一信道数据中的采样点按照功率大小进行由大到小的排序,第一组采样点可以为第一信道数据中重新排序的采样点中的前一个或多个采样点。
第一组采样点中采样点的数量在时延维度上可以满足:数量为M或对于第一信道数据中所有采样点的占比为N。其中,M和N均可以为大于0的数。以第一信道数据中的采样点按照功率大小进行由大到小的排序为例,第一组采样点可以为第一信道数据中重新排序的采样点中的前M个或前N占比的采样点。
作为一种实现方式,第二组采样点的功率可以均小于或等于第一信道数据中除第二组采样点以外的采样点的功率。也就是说,在时延维度上,如果将第一信道数据中的采样点按照功率大小进行由大到小的排序,第二组采样点可以为第一信道数据中重新排序的采样点中的后一个或多个采样点。
第二组采样点中采样点的数量在时延维度上可以满足:数量为P或对于第一信道数据中所有采样点的占比为Q。其中,P和Q均可以为大于0的数。以第一信道数据中的采样点按照功率大小进行由大到小的排序后,第二组采样点可以为第一信道数据中重新排序的采样点中的后P个或后Q占比的采样点。
本申请不限制M、N、P或Q的具体取值。例如,M或P的取值可以为32、64、96、 128、160等值中的一个。例如,N或Q的取值可以为0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99等值中的一个。
本申请不限制第一组采样点和第二组采样点的获取方式。例如,在时延维度上,可以将第一信道数据中的采样点按照功率大小进行排序,从而确定第一组采样点和/或第二组采样点。排序的方式例如可以为上文所述的有大到小,也可以是由小到大。按照由小到大的排序方式确定第一组采样点和/或第二组采样点的方法与按照由大到小的方式确定类似,本申请不再赘述。
需要说明的是,在时延维度上,采样点也可以称为时延采样点。
在一些实施例中,图2所示的方法还可以包括步骤S205。
步骤S205,第一通信设备可以接收第一配置信息。
第一配置信息可以用于配置第一条件的内容和/或参数。换句话说,第一配置信息可以用于配置数据清洗相关的条件和/或指标。
第一条件的内容例如可以包括上文所述的与第一条件相关的信息。作为一种实现方式,第一配置信息可以用于配置第一条件与第一指标和/或第一信道数据的功率分布情况相关。例如,第一条件的内容可以包括:第一指标大于或等于第一指标的门限;和/或,第一信道数据的功率分布是集中的。
第一条件的参数可以包括上文所述的任意一个或多个与第一条件相关的参数。例如,第一条件的参数可以包括:第一指标的门限、第一门限、第二门限、M、N、P、Q中的一项或多项。作为一种实现方式,第一配置信息可以用于指示配置第一条件与第一指标相关,并且可以配置第一条件与哪些或哪个具体的第一指标相关。另外,第一配置信息也可以进一步用于配置第一指标的门限值。
第一配置信息可以是上文所述的第二通信设备发送的。换句话说,第一条件的内容和/或参数可以由第二通信设备配置。第二通信设备可以根据第一信道数据的使用方式、实际需求等,灵活地控制数据清洗的程度。
第一配置信息可以承载在以下消息中的一项或多项中:无线资源控制(radio resource control,RRC)消息、广播消息、媒体接入层控制单元(medium access control control element,MAC CE)、下行控制信息(downlink control information,DCI)等。
本申请不限制第一通信设备对进行数据清理后的第一信道数据的操作。
作为一种实现方式,在第一信道数据有效的情况下,第一通信设备可以发送第一信道数据。第一信道数据的接收方可以基于第一信道数据对第一模型进行训练。在第一信道数据无效的情况下,第一通信设备可以不发送第一信道数据。在这种情况下,第一通信设备可以不需要上传无效的信道数据,从而可以避免浪费上行传输资源。
本申请不限制承载第一信道数据的消息。例如,第一信道数据可以通过RRC信令和/或物理上行共享信道(physical uplink shared channel,PUSCH)承载。
作为一种实现方式,在第一信道数据有效的情况下,第一通信设备可以基于第一信道数据对第一模型进行训练。在一些情况下,例如第一通信设备为终端设备的情况下,第一通信设备对第一模型的训练可以是对第一模型的微调。在第一信道数据无效的情况下,第一通信设备可以不基于第一信道数据对第一模型进行训练。基于有效的第一信道数据在本地对第一模型进行训练可以有效提升第一模型的性能,从而避免无效的数据对第一模型性能的不利影响。
需要说明的是,在第一信道数据无效的情况下,本申请不限制针对第一信道数据的处理方式。例如,第一通信设备可以将无效的第一信道数据丢弃或删除,即不用第一信道数据执行第一信道数据有效时执行的操作。或者,第一通信设备可以将无效的第一信道数据进行替换。或者,第一通信设备可以将无效的第一信道数据进行处理,以使得处理后的第一信道数据满足第一条件。
第一信道数据可以由第一通信设备获取。即第一通信设备可以进行数据采集,以获取第一通信数据。在一些实施例中,第二通信设备可以向第一通信设备发送第二配置信息,第二配置信息可以用于指示第一通信设备进行信道测量。例如,第二配置信息可以用于配置RS。基于RS,第一通信设备可以进行信道测量过程,从而采集第一信道数据。图4以第一通信设备为终端设备,第二通信设备为网络设备为例,对第一信道数据的采集过程进行说明。
图4所示的方法可以包括步骤S410和步骤S420。
步骤S410,终端设备接收第二配置信息。对应地,网络设备发送第二配置信息。
第二配置信息可以用于配置RS。网络设备通过第二配置信息配置RS以供终端设备采集第一信道数据。
步骤S420,终端设备接收RS。对应地,网络设备发送RS。
网络设备可以按照第二配置信息下发RS。终端设备可以根据第二配置信息接收或检测RS。
步骤S430,终端设备基于检测到的RS完成信道测量。基于步骤S430中的信道测量过程,终端设备可以采集到第一信道数据。
为便于理解,下面通过图5对本申请实施例提供的通信方法进行说明。第一通信设备可以为图5中的终端设备,第二通信设备可以为图5中的网络设备。图5所示的方法可以包括步骤S510~步骤S560。
步骤S510,终端设备接收网络设备发送的第一配置信息。
第一配置信息可以用于配置第一条件的内容和/或参数。第一条件与数据清洗相关。换句话说,第一配置信息可以用于配置数据清洗相关条件和/或指标。
第一配置信息可以包括数据清洗指示信息。数据清洗指示信息用于指示终端设备是否进行数据清洗。
步骤S520,终端设备接收网络设备发送的第二配置信息。第二配置信息可以用于配置RS。
步骤S530,网络设备按照第二配置下发RS。该RS用于供终端设备完成第一信道数据的采集以及清洗。
步骤S540,终端设备基于检测到的RS完成信道测量,从而采集到第一信道数据。
终端设备可以根据数据清洗指示信息判断是否进行数据清洗。若不需要进行数据清洗,则终端设备可以直接将第一信道数据发送给网络设备和/或使用第一信道数据微调第一模型。若需要进行数据清洗,则终端设备可以对于每一个信道数据或样本,按照网络设备指示的第一条件判断信道数据或样本有效或无效。对于满足第一条件的信道数据,可以判断该信道数据有效;对于不满足第一条件的信道数据,可以判断该信道数据无效。
第一条件例如可以包括下面的条件中的一项或多项:第一指标大于或等于第一指标的门限值;第一信道数据的功率分布情况满足条件。第一配置信息可以配置上述条件中的一项或多项属于第一条件以及对应的门限值。
第一指标可以包括:RSRP、RSRQ、RSSI中的一项或多项。当信道状况太差或RS接收效果不佳时,测量到的第一信道数据可能会淹没在噪声当中而不适宜用作第一模型的训练。网络设备可以在第一配置信息中指定第一指标的具体的门限值X。X例如可以为:-80dBm、-70dBm或-60dBm等。当第一信道数据对应的第一指标均大于或等于X时,可以判定第一信道数据有效。在第一信道数据对应的第一指标存在小于或等于X的情况下,可以丢弃第一信道数据。
图6示例性地示出了第一信道数据的功率分布情况是否满足条件的判断步骤。
步骤1:通过IFFT将第一信道数据由频域转换至时延域。对于天线维度是否做额外的数学处理不做严格约束。
步骤2:在时延域维度上按照能量大小在样本内进行重新排序。下面以由大到小排列为例进行说明。可以理解的是,也可以进行由小到大的排列,第一条件可以进行相应的调整,本申请不再赘述。
步骤3:对于重新排序后的第一信道数据,遵照第一配置信息配置的第一条件内容和指标参数,判断第一信道数据是否有效。第一条件的内容例如可以包括条件一~条件四中的一项或多项。条件一~条件四均与第一信道数据中部分采样点的功率占比相关。
条件一:在时延维度上,第一信道数据对应前N部分采样点的功率和相对于该样本总功率的占比大于第一门限Y。这里N和Y均可以由网络设备配置。N和Y用于指示比例。N和Y的取值例如可以是0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99中的一个。
条件二:在时延维度上,第一信道数据的前M个采样点的功率和相对于该第一信道数据的总功率的占比大于第一门限Y。这里M和Y均可以由网络设备配置。M可以用于指示采样点的数目。M的取值例如可以是32、64、96、128、160等中的一个。Y可以用于指示比例。Y的取值例如可以是0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99等中的一个。
条件三:在时延维度上,第一信道数据对应后Q部分的功率和相对于第一信道数据总功率的占比小于第二门限Z。Q和Z均可以由网络设备配置。Q和Z均可以用于指示比例。Q和Z的取值例如可以是0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99等中的一个。
条件四:在时延维度上,第一信道数据上后P个采样点的功率和相对于第一信道数据总能量的占比小于第二门限Z。这里P和Z均可以由网络设备配置。P可以用于指示采样点数目。P的取值例如可以是32、64、96、128、160…中的一个。Z可以用于指示比例。Z的取值例如可以是0.1、0.2、0.3、0.4、0.5、0.6、0.7、0.8、0.9、0.95、0.99中的一个。
在确定第一信道数据有效的情况下,图5所示的方法可以包括步骤S560。
步骤S560可以包括步骤S561和/或步骤S562。
步骤S561,终端设备基于有效的第一信道数据,微调第一模型。
步骤S562,终端设备将有效的第一信道数据发送到网络设备。例如可以通过RRC信令或PUSCH承载第一信道数据。
需要说明的是,本申请所述的第一模型可以为用于通信的模型。例如,第一模型可以包括信道状态信息反馈模型、波束管理模型、高精度定位模型中的一项或多项。在一些实施例中,第一模型可以为AI模型。例如,第一模型可以包括机器学习模型。或者,第一模型可以包括神经网络模型。
上文结合图1至图6,详细描述了本申请的方法实施例,下面结合图7至图9,详细描述本申请的装置实施例。应理解,方法实施例的描述与装置实施例的描述相互对应,因此,未详细描述的部分可以参见前面方法实施例。
图7为本申请实施例提供的一种通信设备700的示意性结构图。通信设备700为第一通信设备。通信设备700包括判断单元710。
判断单元710用于判断第一信道数据有效或无效;其中,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
在一些实施例中,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,所述第一条件与以下信息中的一项或多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
在一些实施例中,所述第一指标包括以下指标中的一项或多项:RSRP、RSRQ、RSSI。
在一些实施例中,所述功率分布情况为功率在时延域上的分布情况。
在一些实施例中,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率为所述第一信道数据中的第二组采样点的功率和。
在一些实施例中,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
在一些实施例中,通信设备700还包括:第一接收单元,用于接收第一配置信息;其中,所述第一配置信息用于配置所述第一条件的内容和/或参数。
在一些实施例中,在所述第一信道数据有效的情况下,所述通信设备700还包括:第一发送单元,用于发送所述第一信道数据;和/或,训练单元,用于基于所述第一信道数据,训练所述第一模型。
在一些实施例中,通信设备700还包括:第二接收单元,用于接收第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有效或无效。
在一些实施例中,所述第一模型为AI模型。
图8为本申请实施例提供的一种通信设备800的示意性结构图。通信设备800为第二通信设备。通信设备800可以包括第二发送单元810。
第二发送单元810,用于向第一通信设备发送第一配置信息;其中,所述第一配置信息用于配置第一条件的内容和/或参数,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
在一些实施例中,所述第一条件与以下信息中的一项或多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
在一些实施例中,所述第一指标包括以下指标中的一项或多项:RSRP、RSRQ、RSSI。
在一些实施例中,所述功率分布情况为功率在时延域上的分布情况。
在一些实施例中,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率为所述第一信道数据中的第二组采样点的功率和。
在一些实施例中,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
在一些实施例中,在所述第一信道数据有效的情况下,所述通信设备还包括:第三接收单元,用于接收所述第一信道数据。
在一些实施例中,通信设备800还包括:第三发送单元,用于向所述第一通信设备发送第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有 效或无效。
在一些实施例中,所述第一模型为AI模型。
在可选的实施例中,所述第二发送单元810可以为收发器930,判断单元720可以为处理器910。通信设备700或通信设备800还可以包括存储器920,具体如图9所示。
图9是本申请实施例的用于通信的装置的示意性结构图。图9中的虚线表示该单元或模块为可选的。该装置900可用于实现上述方法实施例中描述的方法。装置900可以是芯片、终端设备或网络设备。
装置900可以包括一个或多个处理器910。该处理器910可支持装置900实现前文方法实施例所描述的方法。该处理器910可以是通用处理器或者专用处理器。例如,该处理器可以为中央处理单元(central processing unit,CPU)。或者,该处理器还可以是其他通用处理器、数字信号处理器(digital signal processor,DSP)、专用集成电路(application specific integrated circuit,ASIC)、现成可编程门阵列(field programmable gate array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
装置900还可以包括一个或多个存储器920。存储器920上存储有程序,该程序可以被处理器910执行,使得处理器910执行前文方法实施例所描述的方法。存储器920可以独立于处理器910也可以集成在处理器910中。
装置900还可以包括收发器930。处理器910可以通过收发器930与其他设备或芯片进行通信。例如,处理器910可以通过收发器930与其他设备或芯片进行数据收发。
本申请实施例还提供一种计算机可读存储介质,用于存储程序。该计算机可读存储介质可应用于本申请实施例提供的终端或网络设备中,并且该程序使得计算机执行本申请各个实施例中的由终端或网络设备执行的方法。
本申请实施例还提供一种计算机程序产品。该计算机程序产品包括程序。该计算机程序产品可应用于本申请实施例提供的终端或网络设备中,并且该程序使得计算机执行本申请各个实施例中的由终端或网络设备执行的方法。
本申请实施例还提供一种计算机程序。该计算机程序可应用于本申请实施例提供的终端或网络设备中,并且该计算机程序使得计算机执行本申请各个实施例中的由终端或网络设备执行的方法。
应理解,本申请中术语“系统”和“网络”可以被可互换使用。另外,本申请使用的术语仅用于对本申请的具体实施例进行解释,而非旨在限定本申请。本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象,而不是用于描述特定顺序。此外,术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。
在本申请的实施例中,提到的“指示”可以是直接指示,也可以是间接指示,还可以是表示具有关联关系。举例说明,A指示B,可以表示A直接指示B,例如B可以通过A获取;也可以表示A间接指示B,例如A指示C,B可以通过C获取;还可以表示A和B之间具有关联关系。
在本申请实施例中,“与A相应的B”表示B与A相关联,根据A可以确定B。但还应理解,根据A确定B并不意味着仅仅根据A确定B,还可以根据A和/或其它信息确定B。
在本申请实施例中,术语“对应”可表示两者之间具有直接对应或间接对应的关系,也可以表示两者之间具有关联关系,也可以是指示与被指示、配置与被配置等关系。
本申请实施例中,“预定义”或“预配置”可以通过在设备(例如,包括终端设备和网络设备)中预先保存相应的代码、表格或其他可用于指示相关信息的方式来实现,本申请对于其具体的实现方式不做限定。比如预定义可以是指协议中定义的。
本申请实施例中,所述“协议”可以指通信领域的标准协议,例如可以包括LTE协议、NR协议以及应用于未来的通信系统中的相关协议,本申请对此不做限定。
本申请实施例中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
在本申请的各种实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够读取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,数字通用光盘(digital video disc,DVD))或者半导体介质(例如,固态硬盘(solid state disk,SSD))等。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。
Claims (44)
- 一种通信方法,其特征在于,所述方法包括:第一通信设备判断第一信道数据有效或无效;其中,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
- 根据权利要求1所述的方法,其特征在于,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,所述第一条件与以下信息中的一项或多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
- 根据权利要求2所述的方法,其特征在于,所述第一指标包括以下指标中的一项或多项:参考信号接收功率RSRP、参考信号接收质量RSRQ、接收信号强度指示RSSI。
- 根据权利要求2或3所述的方法,其特征在于,所述功率分布情况为功率在时延域上的分布情况。
- 根据权利要求2-4中任一项所述的方法,其特征在于,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率为所述第一信道数据中的第二组采样点的功率和。
- 根据权利要求5所述的方法,其特征在于,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
- 根据权利要求2-6中任一项所述的方法,其特征在于,还包括:所述第一通信设备接收第一配置信息;其中,所述第一配置信息用于配置所述第一条件的内容和/或参数。
- 根据权利要求1-7中任一项所述的方法,其特征在于,在所述第一信道数据有效的情况下,所述方法还包括:所述第一通信设备发送所述第一信道数据;和/或,基于所述第一信道数据,所述第一通信设备训练所述第一模型。
- 根据权利要求1-8中任一项所述的方法,其特征在于,还包括:所述第一通信设备接收第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有效或无效。
- 根据权利要求1-9中任一项所述的方法,其特征在于,所述第一模型为人工智能AI模型。
- 一种通信方法,其特征在于,所述方法包括:第二通信设备向第一通信设备发送第一配置信息;其中,所述第一配置信息用于配置第一条件的内容和/或参数,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
- 根据权利要求11所述的方法,其特征在于,所述第一条件与以下信息中的一项或 多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
- 根据权利要求12所述的方法,其特征在于,所述第一指标包括以下指标中的一项或多项:参考信号接收功率RSRP、参考信号接收质量RSRQ、接收信号强度指示RSSI。
- 根据权利要求12或13所述的方法,其特征在于,所述功率分布情况为功率在时延域上的分布情况。
- 根据权利要求12-14中任一项所述的方法,其特征在于,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率为所述第一信道数据中的第二组采样点的功率和。
- 根据权利要求15所述的方法,其特征在于,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
- 根据权利要求11-16中任一项所述的方法,其特征在于,在所述第一信道数据有效的情况下,所述方法还包括:所述第二通信设备接收所述第一信道数据。
- 根据权利要求11-17中任一项所述的方法,其特征在于,还包括:所述第二通信设备向所述第一通信设备发送第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有效或无效。
- 根据权利要求11-18中任一项所述的方法,其特征在于,所述第一模型为人工智能AI模型。
- 一种通信设备,其特征在于,所述通信设备为第一通信设备,所述通信设备包括:判断单元,用于判断第一信道数据有效或无效;其中,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
- 根据权利要求20所述的通信设备,其特征在于,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,所述第一条件与以下信息中的一项或多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
- 根据权利要求21所述的通信设备,其特征在于,所述第一指标包括以下指标中的一项或多项:参考信号接收功率RSRP、参考信号接收质量RSRQ、接收信号强度指示RSSI。
- 根据权利要求21或22所述的通信设备,其特征在于,所述功率分布情况为功率在时延域上的分布情况。
- 根据权利要求21-23中任一项所述的通信设备,其特征在于,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率 为所述第一信道数据中的第二组采样点的功率和。
- 根据权利要求24所述的通信设备,其特征在于,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
- 根据权利要求21-25中任一项所述的通信设备,其特征在于,还包括:第一接收单元,用于接收第一配置信息;其中,所述第一配置信息用于配置所述第一条件的内容和/或参数。
- 根据权利要求20-26中任一项所述的通信设备,其特征在于,在所述第一信道数据有效的情况下,所述通信设备还包括:第一发送单元,用于发送所述第一信道数据;和/或,训练单元,用于基于所述第一信道数据,训练所述第一模型。
- 根据权利要求20-27中任一项所述的通信设备,其特征在于,还包括:第二接收单元,用于接收第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有效或无效。
- 根据权利要求20-28中任一项所述的通信设备,其特征在于,所述第一模型为人工智能AI模型。
- 一种通信设备,其特征在于,所述通信设备为第二通信设备,所述通信设备包括:第二发送单元,用于向第一通信设备发送第一配置信息;其中,所述第一配置信息用于配置第一条件的内容和/或参数,在所述第一信道数据满足第一条件的情况下,所述第一信道数据有效,在所述第一信道数据有效的情况下,所述第一信道数据能够用于训练第一模型,在所述第一信道数据无效的情况下,所述第一信道数据不能用于训练所述第一模型。
- 根据权利要求30所述的通信设备,其特征在于,所述第一条件与以下信息中的一项或多项相关:第一指标,所述第一指标基于所述第一信道数据对应的参考信号确定;所述第一信道数据的功率分布情况。
- 根据权利要求31所述的通信设备,其特征在于,所述第一指标包括以下指标中的一项或多项:参考信号接收功率RSRP、参考信号接收质量RSRQ、接收信号强度指示RSSI。
- 根据权利要求31或32所述的通信设备,其特征在于,所述功率分布情况为功率在时延域上的分布情况。
- 根据权利要求31-33中任一项所述的通信设备,其特征在于,在所述第一条件与所述功率分布情况相关的情况下,所述第一条件包括以下中的一项或多项:第一功率对于所述第一信道数据的总功率的占比大于或等于第一门限;第二功率对于所述第一信道数据的总功率的占比小于或等于第二门限;其中,所述第一功率为所述第一信道数据中的第一组采样点的功率和,所述第二功率为所述第一信道数据中的第二组采样点的功率和。
- 根据权利要求34所述的通信设备,其特征在于,所述第一组采样点的功率均大于或等于所述第一信道数据中除所述第一组采样点以外的采样点的功率,并且所述第一组采样点的数量在时延维度上满足:数量为M或对于所述第一信道数据中所有采样点的占比为N;所述第二组采样点的功率均小于或等于所述第一信道数据中除所述第二组采样点以 外的采样点的功率,并且所述第二组采样点的数量在时延维度上满足:数量为P或对于所述第一信道数据中所有采样点的占比为Q。
- 根据权利要求30-35中任一项所述的通信设备,其特征在于,在所述第一信道数据有效的情况下,所述通信设备还包括:第三接收单元,用于接收所述第一信道数据。
- 根据权利要求30-36中任一项所述的通信设备,其特征在于,还包括:第三发送单元,用于向所述第一通信设备发送第一指示信息,所述第一指示信息用于指示所述第一通信设备是否判断第一信道数据有效或无效。
- 根据权利要求30-37中任一项所述的通信设备,其特征在于,所述第一模型为人工智能AI模型。
- 一种通信设备,其特征在于,包括存储器和处理器,所述存储器用于存储程序,所述处理器用于调用所述存储器中的程序,以使所述通信设备执行如权利要求1-19中任一项所述的方法。
- 一种装置,其特征在于,包括处理器,用于从存储器中调用程序,以使所述装置执行如权利要求1-19中任一项所述的方法。
- 一种芯片,其特征在于,包括处理器,用于从存储器调用程序,使得安装有所述芯片的设备执行如权利要求1-19中任一项所述的方法。
- 一种计算机可读存储介质,其特征在于,其上存储有程序,所述程序使得计算机执行如权利要求1-19中任一项所述的方法。
- 一种计算机程序产品,其特征在于,包括程序,所述程序使得计算机执行如权利要求1-19中任一项所述的方法。
- 一种计算机程序,其特征在于,所述计算机程序使得计算机执行如权利要求1-19中任一项所述的方法。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2023/071739 WO2024148528A1 (zh) | 2023-01-10 | 2023-01-10 | 通信方法以及通信设备 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2023/071739 WO2024148528A1 (zh) | 2023-01-10 | 2023-01-10 | 通信方法以及通信设备 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024148528A1 true WO2024148528A1 (zh) | 2024-07-18 |
Family
ID=91897630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/071739 WO2024148528A1 (zh) | 2023-01-10 | 2023-01-10 | 通信方法以及通信设备 |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2024148528A1 (zh) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11075929B1 (en) * | 2018-02-20 | 2021-07-27 | Facebook, Inc. | Machine learning assisted anomaly detection on a millimeter-wave communications network |
US20220051139A1 (en) * | 2018-12-28 | 2022-02-17 | Telefonaktiebolaget Lm Ericsson (Publ) | Wireless device, a network node and methods therein for training of a machine learning model |
CN115099354A (zh) * | 2022-07-06 | 2022-09-23 | 中国农业银行股份有限公司 | 训练样本的构建方法、装置、设备及存储介质 |
CN115280682A (zh) * | 2020-01-19 | 2022-11-01 | Oppo广东移动通信有限公司 | 通信方法及装置 |
CN115329954A (zh) * | 2021-05-11 | 2022-11-11 | 维沃移动通信有限公司 | 训练数据集获取方法、无线传输方法、装置及通信设备 |
-
2023
- 2023-01-10 WO PCT/CN2023/071739 patent/WO2024148528A1/zh unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11075929B1 (en) * | 2018-02-20 | 2021-07-27 | Facebook, Inc. | Machine learning assisted anomaly detection on a millimeter-wave communications network |
US20220051139A1 (en) * | 2018-12-28 | 2022-02-17 | Telefonaktiebolaget Lm Ericsson (Publ) | Wireless device, a network node and methods therein for training of a machine learning model |
CN115280682A (zh) * | 2020-01-19 | 2022-11-01 | Oppo广东移动通信有限公司 | 通信方法及装置 |
CN115329954A (zh) * | 2021-05-11 | 2022-11-11 | 维沃移动通信有限公司 | 训练数据集获取方法、无线传输方法、装置及通信设备 |
CN115099354A (zh) * | 2022-07-06 | 2022-09-23 | 中国农业银行股份有限公司 | 训练样本的构建方法、装置、设备及存储介质 |
Non-Patent Citations (1)
Title |
---|
OPPO: "Discussion on R18 study on AIML-based 5G enhancements", 3GPP DRAFT; RP-212927, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. TSG RAN, no. Electronic Meeting; 20211206 - 20211217, 29 November 2021 (2021-11-29), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052097068 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220279341A1 (en) | Radio resource control procedures for machine learning | |
US11388778B2 (en) | Time configuration method, network device, and UE | |
US11146372B2 (en) | Reference signal transmission method and apparatus | |
WO2020244644A1 (zh) | 一种网络系统分级方法及装置 | |
TW201101870A (en) | Geographic-based measurement and logging of radio coverage related information by mobile devices | |
US20230262490A1 (en) | Data transmission method and apparatus | |
WO2016000491A1 (zh) | 确定拉远射频单元rru的方法与设备 | |
CN111436061A (zh) | 用于在无线通信系统中配置回程链路的装置和方法 | |
WO2021218820A1 (zh) | 测量方法、装置及系统 | |
WO2021134496A1 (zh) | 通信方法及装置 | |
TWI531271B (zh) | 執行無線資源管理之方法及其使用相同方法之網路節點、行動裝置、基地台以及無線通訊系統 | |
Aguilar-Garcia et al. | Location-aware self-organizing methods in femtocell networks | |
WO2022206328A1 (zh) | 一种通信协作方法及装置 | |
WO2024148528A1 (zh) | 通信方法以及通信设备 | |
CN113905385B (zh) | 无线电资源参数配置 | |
WO2022086406A1 (en) | Method and nodes for handling beam measurements | |
WO2024138611A1 (zh) | 通信方法和通信设备 | |
WO2024130602A1 (zh) | 通信方法、装置、设备、存储介质、芯片、产品及程序 | |
CN113518355B (zh) | 准共址关系管理方法及装置 | |
WO2022082516A1 (zh) | 数据传输方法及通信装置 | |
WO2024138653A1 (zh) | 用于通信的方法、终端设备以及网络设备 | |
US11115986B2 (en) | Reference signal sending method and apparatus | |
WO2022253001A1 (zh) | 一种切换方法及装置 | |
EP4415403A1 (en) | Data collection method and communication apparatus | |
US20240031865A1 (en) | Machine learning-based pcell and scell throughput distribution |