WO2023201668A1 - 导频位置确定模型的获取、导频位置确定方法及其装置 - Google Patents

导频位置确定模型的获取、导频位置确定方法及其装置 Download PDF

Info

Publication number
WO2023201668A1
WO2023201668A1 PCT/CN2022/088321 CN2022088321W WO2023201668A1 WO 2023201668 A1 WO2023201668 A1 WO 2023201668A1 CN 2022088321 W CN2022088321 W CN 2022088321W WO 2023201668 A1 WO2023201668 A1 WO 2023201668A1
Authority
WO
WIPO (PCT)
Prior art keywords
channel state
pilot
state information
target pilot
target
Prior art date
Application number
PCT/CN2022/088321
Other languages
English (en)
French (fr)
Inventor
池连刚
刘昊翔
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to CN202280001148.XA priority Critical patent/CN117280662A/zh
Priority to PCT/CN2022/088321 priority patent/WO2023201668A1/zh
Publication of WO2023201668A1 publication Critical patent/WO2023201668A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems
    • H04L27/26—Systems using multi-frequency codes

Definitions

  • the present application relates to the field of communication technology, and in particular, to a method of obtaining a pilot position determination model and a device thereof, a pilot position determination method and a device thereof.
  • eMBB Enhanced Mobile Broadband
  • URLLC Ultra Reliable Low Latency Communication
  • mMTC Massive Machine Type of Communication
  • RIS Reconfigurable Intelligence Surface
  • RIS can be deployed on the surfaces of various objects in wireless transmission environments, which is expected to break through the uncontrollability of traditional wireless channels, build an intelligent programmable wireless environment, and introduce future wireless communications. new paradigm.
  • RIS can actively enrich channel scattering conditions and enhance the multiplexing gain of wireless communication systems; on the other hand, RIS can realize signal propagation direction control and in-phase superposition in three-dimensional space, increase received signal strength, and improve communication equipment. transmission performance between. Therefore, RIS has great potential to be used to enhance the coverage and capacity of future wireless networks and eliminate local coverage holes. How to efficiently select effective array elements on RIS has become a major issue.
  • Embodiments of the present application provide a method and device for obtaining a pilot position determination model, a pilot position determination method and a device thereof, which can be applied in the field of communication technology and used to generate a pilot position determination model through training to improve the determination of RIS.
  • the efficiency of the channel state information of the upper pilot array element is a method and device for obtaining a pilot position determination model, a pilot position determination method and a device thereof, which can be applied in the field of communication technology and used to generate a pilot position determination model through training to improve the determination of RIS.
  • embodiments of the present disclosure provide a method for obtaining a pilot position determination model, which is performed by a communication device.
  • the method includes: obtaining a training sample set, and the training sample set includes multiple sample groups, each sample The group includes the first sample channel state information and the tag channel state information of the first sample channel state information; input the sample group into the initial pilot position determination model to output the first pilot position information; based on the first pilot position information to obtain predicted channel state information; based on the tag channel state information and predicted channel state information, the model parameters of the initial pilot position determination model are adjusted, and the next sample group is used to continue training the adjusted initial pilot position determination model. Until the end of training, the target pilot position determination model is obtained.
  • the efficiency of determining the channel state information of the pilot array elements on the RIS can be improved.
  • the communication equipment can be saved for channel estimation. time cost and can improve accuracy.
  • the predicted channel state information is obtained, including:
  • the method further includes:
  • test sample set which includes channel state information for the second sample
  • the target pilot position determination model is tested based on the test sample set.
  • the model parameters of the initial pilot position determination model are adjusted based on the tag channel state information and the predicted channel state information, including:
  • the model parameters of the initial pilot position determination model are adjusted based on the loss function.
  • Embodiments of the present disclosure provide a method for determining pilot location information, which is characterized in that it is executed by a communication device, and the method includes:
  • the target pilot position determination model is trained by the acquisition method of the pilot position determination model.
  • the target pilot position information after obtaining the target pilot position information, it also includes:
  • activating the target pilot element on the RIS indicated by the target pilot location information includes:
  • the communication device is a network device, and the network device activates the target pilot array element based on the target pilot position.
  • the network device activates the target pilot element based on the target pilot position, including:
  • the target pilot array element is determined based on the target pilot position information, and an activation instruction is sent to the RIS.
  • the activation instruction is used to instruct the activation of the target pilot array element.
  • activating the target pilot element on the RIS indicated by the target pilot location information includes:
  • the communication device is a terminal device.
  • the terminal device sends the target pilot position information to the network device through the second signaling.
  • the target pilot position information is used to instruct the network device to activate the target pilot array element based on the target pilot position.
  • the method further includes:
  • the method further includes: determining the target full array element channel state information of the RIS based on the second channel state information.
  • embodiments of the present disclosure provide a method for determining pilot location information, which is characterized in that it is executed by RIS, and the method includes:
  • the initial pilot signal is used for channel estimation by the communication device to obtain the first channel state information.
  • the first channel state information is used to input into the trained target pilot position determination model to obtain the RIS. target pilot location information.
  • sending an initial pilot signal to the communication device includes:
  • the initial pilot signal is sent to the communication device through the initial pilot array element activated on the RIS.
  • the method further includes:
  • activating the target pilot array element indicated by the target pilot location information includes:
  • the target pilot array element indicated by the target pilot location information after activating the target pilot array element indicated by the target pilot location information, it also includes:
  • the target pilot signal is sent to the communication device based on the target pilot array element, where the target pilot signal is used for channel estimation to obtain the second channel state information.
  • inventions of the present application provide a communication device.
  • the device includes: a processing module configured to obtain a training sample set.
  • the training sample set includes multiple sample groups, and each sample group includes a first sample channel state information and a third sample group.
  • Tag channel state information of a sample channel state information and input the sample group into the initial pilot position determination model to output the first pilot position information.
  • the predicted channel state information is obtained, and based on Tag channel state information and predicted channel state information, adjust the model parameters of the initial pilot position determination model, and use the next sample group to continue training the adjusted initial pilot position determination model until the end of the training to determine the target pilot position.
  • Model is
  • embodiments of the present application provide a communication device that has some or all of the functions of the terminal device in the method example of the first aspect.
  • the functions of the communication device may include some or all of the implementations in this application.
  • the functions in the examples can also be used to independently implement any of the embodiments in this application.
  • Functions can be implemented by hardware, or by hardware executing corresponding software.
  • Hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device in performing corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may also include a storage module coupled to the transceiver module and the processing module, which stores computer programs and data necessary for the communication device.
  • the processing module may be a processor
  • the transceiver module may be a transceiver or a communication interface
  • the storage module may be a memory
  • embodiments of the present application provide another communication device that has some or all of the functions of the network equipment in the method example of the second aspect.
  • the functions of the communication device may have some or all of the functions in this application.
  • the functions in the embodiments may also be used to independently implement any of the embodiments in this application.
  • Functions can be implemented by hardware, or by hardware executing corresponding software.
  • Hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device to perform corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may also include a storage module coupled to the transceiver module and the processing module, which stores computer programs and data necessary for the communication device.
  • the processing module may be a processor
  • the transceiver module may be a transceiver or a communication interface
  • the storage module may be a memory
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method of the first aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method of the second aspect.
  • the processing module may be a processor
  • the transceiver module may be a transceiver or a communication interface
  • the storage module may be a memory
  • inventions of the present application provide a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method of the first aspect.
  • inventions of the present application provide a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method of the second aspect.
  • inventions of the present application provide a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory.
  • the processor executes the computer program stored in the memory, so that the communication device executes the above-mentioned first aspect.
  • One way approach One way approach.
  • inventions of the present application provide a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory.
  • the processor executes the computer program stored in the memory, so that the communication device executes the above-mentioned first step.
  • inventions of the present application provide a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to cause the device to execute The method of the first aspect above.
  • inventions of the present application provide a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to enable the device.
  • embodiments of the present application provide a communication system, which includes the communication device of the third aspect and the communication device of the fourth aspect, or the system includes the communication device of the fifth aspect and the communication device of the sixth aspect. , or the system includes the communication device of the seventh aspect and the communication device of the eighth aspect, or the system includes the communication device of the ninth aspect and the communication device of the tenth aspect.
  • embodiments of the present invention provide a computer-readable storage medium for storing instructions used by the above-mentioned receiving device. When the instructions are executed, the receiving device performs the method of the first aspect.
  • embodiments of the present invention provide a readable storage medium for storing instructions used by the above-mentioned sending device. When the instructions are executed, the sending device is caused to perform the method of the second aspect.
  • the present application also provides a computer program product including a computer program, which when run on a computer causes the computer to execute the method of the first aspect.
  • the present application also provides a computer program product including a computer program, which when run on a computer causes the computer to execute the method of the second aspect.
  • the present application provides a chip system, which includes at least one processor and an interface for supporting the receiving device to implement the functions involved in the first aspect, for example, determining or processing the data involved in the above method. and information.
  • the chip system also includes a memory, which is used to save necessary computer programs and data for the receiving device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the present application provides a chip system, which includes at least one processor and an interface for supporting the sending device to implement the functions involved in the second aspect, for example, determining or processing the data involved in the above method. and information.
  • the chip system also includes a memory, which is used to save necessary computer programs and data for the sending device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • this application provides a computer program that, when run on a computer, causes the computer to execute the method of the first aspect.
  • the present application provides a computer program that, when run on a computer, causes the computer to execute the method of the second aspect.
  • Figure 1 is a schematic architectural diagram of a communication system provided by an embodiment of the present application.
  • Figure 2 is a schematic flowchart of a method for obtaining a pilot position determination model provided by an embodiment of the present application
  • Figure 3 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application
  • Figure 4 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application
  • Figure 5 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application
  • Figure 6 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application
  • Figure 7 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application.
  • Figure 8 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application.
  • Figure 9 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application.
  • Figure 10 is a schematic flowchart of a method for obtaining another pilot position determination model provided by an embodiment of the present application
  • Figure 11 is a schematic structural diagram of a communication device of a pilot position determination model provided by an embodiment of the present application
  • Figure 12 is a schematic structural diagram of a communication device of a pilot position determination model provided by an embodiment of the present application
  • FIG. 13 is a schematic structural diagram of a chip of a pilot position determination model provided by an embodiment of the present application.
  • first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.
  • first information may also be called second information, and similarly, the second information may also be called first information.
  • word “if” as used herein may be interpreted as "when” or “when” or “in response to determining”
  • the terms used in this article are “greater than” or “less than”, “higher than” or “lower than” when characterizing size relationships. But for those skilled in the art, it can be understood that: the term “greater than” also covers the meaning of “greater than or equal to”, and “less than” also covers the meaning of “less than or equal to”; the term “higher than” covers the meaning of “higher than or equal to”. “The meaning of “less than” also covers the meaning of "less than or equal to”.
  • RIS information metamaterial
  • Metamaterials refer to a type of man-made materials with special properties that do not exist in nature. They have some special properties, such as allowing light and electromagnetic waves to change their normal properties, and such effects cannot be achieved with traditional materials.
  • RIS can actively enrich channel scattering conditions and enhance the multiplexing gain of wireless communication systems; on the other hand, RIS can realize signal propagation direction control and in-phase superposition in three-dimensional space, increase received signal strength, and improve communication equipment. Transmission performance.
  • Figure 1 is a schematic architectural diagram of a communication system provided by an embodiment of the present application.
  • the communication system may include but is not limited to one network device and one terminal device.
  • the number and form of devices shown in Figure 1 are only for examples and do not constitute a limitation on the embodiments of the present application. In actual applications, two or more devices may be included.
  • the communication system shown in Figure 1 includes a network device 101 and a terminal device 102 as an example.
  • LTE long term evolution
  • 5th generation 5th generation
  • NR 5th generation new radio
  • side link in the embodiment of the present application may also be called a side link or a through link.
  • the network device 101 in the embodiment of this application is an entity on the network side that is used to transmit or receive signals.
  • the network device 101 may be an access network device, and the access network device may be an evolved base station (evolved nodeb, enb), a transmission point (transmission reception point, TRP), or a next generation base station (next generation nodeb) in an NR system. , gnb), base stations in other future mobile communication systems or access nodes in wireless fidelity (wifi) systems, etc.
  • the network device 101 may be a core network device.
  • the core network device in the embodiment of the present application may be a device that communicates with an access network device.
  • the core network device may be a 5G core network device, such as an access and mobility management function (Access and Mobility Management Function (AMF), or it can be an evolved packet core (EPC) device, such as a mobility management entity (Mobility Management Entity, MME).
  • AMF Access and Mobility Management Function
  • EPC evolved packet core
  • MME mobility management entity
  • the embodiments of this application do not limit the specific technology and specific equipment form used by the network equipment.
  • the network equipment provided by the embodiments of this application may be composed of a centralized unit (central unit, CU) and a distributed unit (DU).
  • the CU may also be called a control unit (control unit).
  • CU-DU is used.
  • the structure can separate the protocol layers of network equipment, such as base stations, and place some protocol layer functions under centralized control on the CU. The remaining part or all protocol layer functions are distributed in the DU, and the CU centrally controls the DU.
  • the terminal device 102 in the embodiment of this application is an entity on the user side that is used to receive or transmit signals, such as a mobile phone.
  • Terminal equipment can also be called terminal equipment (terminal), user equipment (user equipment, UE), mobile station (mobile station, MS), mobile terminal equipment (mobile terminal, MT), etc.
  • the terminal device can be a car with communication functions, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an augmented reality (augmented reality (AR) terminal equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in remote medical surgery, smart grid ( Wireless terminal equipment in smart grid, wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, wireless terminal equipment in smart home, etc.
  • the embodiments of this application do not limit the specific technology and specific equipment form used by the terminal equipment.
  • Figure 2 is a schematic flowchart of a method for obtaining a pilot position determination model provided by an embodiment of the present application. As shown in Figure 2, the method is executed by the communication device and may include but is not limited to the following steps:
  • the training sample set includes multiple sample groups, and each sample group includes the first sample channel state information and the label channel state information of the first sample channel state information.
  • the communication device referred to in the embodiment of the present disclosure may be a network device or a terminal device.
  • the terminal device may be a mobile phone, a handheld computer, etc.
  • the network device may be a base station, etc.
  • RIS can be set up between network equipment and terminal equipment, and has the functions of sending pilot signals, receiving pilot signals, and estimating pilot signals.
  • RIS can actively enrich channel scattering conditions and enhance wireless communications.
  • the multiplexing gain of the system; on the other hand, RIS can realize signal propagation direction control and in-phase superposition in three-dimensional space, increase the received signal strength, and improve the transmission performance between communication equipment. Therefore, RIS has great potential to be used to enhance the coverage and capacity of future wireless networks and eliminate local coverage holes.
  • the RIS can contain multiple pilot array elements.
  • the array elements on the RIS are arranged in a certain order. There are no restrictions here. The specific settings can be based on actual needs or functions that need to be implemented.
  • the array elements on the RIS can be arranged in the form of a matrix.
  • the pilot array element can be an active array element, a passive array element, or a combination of active and passive array elements, which needs to be set according to actual needs.
  • the active array elements on the RIS can send pilot signals, and the pilot signals can be estimated to obtain channel state information (CSI), that is, in the field of wireless communications, the channel attributes of the communication link. It describes the fading factor of the signal on each transmission path, that is, the value of each element in the channel gain matrix, such as signal scattering (Scattering), environmental fading (fading, multipath fading or shadowing fading), distance attenuation (power decay of distance) and other information. It should be noted that the CSI corresponding to each array element may be the same or different.
  • the communication equipment can estimate the channel state information H 1 k based on the pilot signal, and obtain the sample set based on the channel state information H 1 k .
  • the channel state information H 1 k samples can be enhanced based on linear interpolation to obtain the first sample channel state information H 1 all as multiple samples in the training phase.
  • the tag channel state information can be obtained under a set communication environment.
  • some channel state information can be obtained under an ideal transmission environment with less interference as the tag channel state information H real .
  • each first sample channel state information corresponds to a label channel state information
  • the first sample channel state information and its corresponding label channel state information serve as a sample group.
  • the initial pilot position determination model may be an artificial intelligence (Artificial Intelligence, AI)/machine learning (Machine Learning, ML) model.
  • AI/ML models have important application potential in many aspects such as complex unknown environment modeling and learning, channel prediction, intelligent signal generation and processing, network status tracking and intelligent scheduling, network optimization deployment, etc., and are expected to promote the evolution of future communication paradigms and networks.
  • the change of architecture is of great significance and value to 5G-Advanced/6G technology research.
  • the communication device After obtaining the training sample set, the communication device inputs the training sample set sample group (H 1 all , H real ) into the initial pilot position determination model in batches, and gradually extracts important features during the iterative process, that is, selects the pilot information
  • the position with the largest amount is taken as the first pilot position information (x k , y k ) and saved.
  • k ⁇ 1, 2, ..., K ⁇
  • K is the number of sample groups selected in each batch, and is also the number of pilot array elements on the RIS that need to be activated.
  • x k and y k respectively indicate the time domain resource and frequency domain resource positions allocated to the RIS or the pilot array elements on it. Therefore, after obtaining the pilot position information (x k , y k ), the corresponding RIS or pilot array element can be known based on the position information.
  • the electronic device After obtaining the first pilot position information, the electronic device notifies the RIS of the obtained first pilot position information (x k , y k ) through signaling, and the RIS activates the pilot signal of the pilot array element, and communicates with The device estimates the channel information at the selected pilot position to determine the predicted channel state information H pilot .
  • the training of the model is an iterative process, and the network parameters of the model are continuously adjusted for training until the overall loss function value of the model is less than the preset value, or the overall loss function value of the model no longer changes or changes in magnitude. Slowly, the model converges and the trained model is obtained.
  • the model parameters can be adjusted based on the tag channel state information and predicted channel state information, and then the next sample group is used to continue training the adjusted initial pilot position determination model. until the desired effect is achieved.
  • the loss value can be obtained and compared with a set threshold to determine whether the expected effect is achieved.
  • the set threshold can be set in advance.
  • the accuracy of the predicted channel state information output by the model can also be determined through actual testing.
  • the accuracy threshold can be set in advance.
  • a training sample set is first obtained.
  • the training sample set includes multiple sample groups, each sample group includes first sample channel state information and label channel state information of the first sample channel state information, and then
  • the sample group is input into the initial pilot position determination model to output the first pilot position information, and then the predicted channel state information is obtained based on the first pilot position information.
  • the initial pilot is calculated based on the tag channel state information and the predicted channel state information. Adjust the model parameters of the frequency position determination model, and use the next sample group to continue training the adjusted initial pilot position determination model until the end of the training to obtain the target pilot position determination model. Therefore, by training the initial pilot position determination model, the efficiency of determining the channel state information of the pilot array elements on the RIS can be improved. Especially when there are a large number of pilot array elements on the RIS, the communication equipment can be saved for channel estimation. time cost and can improve accuracy.
  • Figure 4 is a schematic flowchart of a method for obtaining a pilot position determination model provided by an embodiment of the present application. As shown in Figure 3, the method is executed by the communication device and may include but is not limited to the following steps:
  • the training sample set includes multiple sample groups, and each sample group includes the first sample channel state information and the label channel state information of the first sample channel state information.
  • the communication device referred to in the embodiment of the present disclosure may be a network device or a terminal device.
  • the terminal device may be a mobile phone, a handheld computer, etc.
  • the network device may be a base station, etc.
  • S42 Input the sample group into the initial pilot position determination model to output the first pilot position information.
  • step S42 the implementation provided in any embodiment of this application may be adopted, and details will not be described again here.
  • S43 Obtain predicted channel state information based on the first pilot location information.
  • the first pilot array element after obtaining the first pilot location information, activate the first pilot array element on the RIS indicated by the first pilot location information, and receive the first pilot signal sent by the first pilot array element. , and perform channel estimation based on the first pilot signal to obtain predicted channel state information.
  • the communication device in the uplink transmission scenario is a network device, and the network device activates the first pilot array element based on the first pilot position.
  • the network device sends the first pilot location information to the RIS through signaling to instruct the RIS to activate the first pilot array element; or, the network device determines the first pilot array element based on the first pilot location information. , and sends an activation instruction to the RIS, where the activation instruction is used to instruct activation of the first pilot array element.
  • the communication device in the downlink transmission scenario is a terminal device.
  • the terminal device sends the first pilot position information to the network device through uplink signaling, and the network device activates the first pilot array element based on the first pilot position. .
  • the active array element on the RIS can be determined based on the predicted channel information. After the active array element is determined, the active array element can be determined based on the position of the active array element on the RIS. , to determine the channel status information of other array elements. It should be noted that the determination method can be multiple. For example, it can be determined through traditional difference algorithm, or it can be determined through screening using neural network algorithm. There is no limitation here.
  • the loss function of the initial pilot position determination model can be calculated based on the first full array element channel state information and the tag channel state information to generate a loss value.
  • the loss function in this embodiment is set in advance and can be set according to actual needs.
  • the loss function can be a hinge loss function, a cross-entropy loss function, an exponential loss function, etc.
  • the specific loss function can be selected according to actual needs without any restrictions here.
  • the initial pilot position determination model is adjusted through the loss value.
  • the adjusted initial pilot position determination model is trained according to the above steps until the training is completed, and a target pilot position determination model is generated.
  • the loss threshold can be set according to the actual situation.
  • the channel state information H 3 k can be estimated based on the pilot signal, the test sample set is obtained through linear interpolation, and the second sample channel state information is obtained.
  • test sample set and the above-mentioned test sample set may contain duplicate samples, or may include completely different duplicate samples. There may be a certain ratio between the two. There is no limit here, and the details can be determined according to actual needs. set up.
  • the loss function in this embodiment is set in advance and can be set according to actual needs.
  • the loss function can be a hinge loss function, a cross-entropy loss function, an exponential loss function, etc.
  • the specific loss function can be selected according to actual needs without any restrictions here.
  • test sample set After obtaining the test sample set and the second sample channel status information, the test sample set is used to check the target pilot position to determine the performance of the model, the weights are continuously adjusted through data and labels, and the model is saved locally on the network device after updating the parameters.
  • a test sample set is first obtained, the test sample set includes channel state information for the second sample, and then the target pilot position determination model is tested based on the test sample set. Therefore, by testing the target pilot position determination model, the accuracy and practicality of the target pilot position determination model can be improved.
  • a training sample set is first obtained.
  • the training sample set includes multiple sample groups, each sample group includes first sample channel state information and label channel state information of the first sample channel state information, and then
  • the sample group is input into the initial pilot position determination model to output the first pilot position information, and then based on the first pilot position information, the predicted channel state information is obtained, and then based on the predicted channel state information, the first full array of the RIS is determined meta-channel state information, and then based on the first full-array meta-channel state information and tag channel state information, determine the loss function of the initial pilot position determination model, adjust the model parameters of the initial pilot position determination model based on the loss function, and adopt the following
  • a sample group continues to train the adjusted initial pilot position determination model until the training is completed to obtain the target pilot position determination model, and then obtains a test sample set.
  • the test sample set includes channel state information for the second sample, and finally based on the test
  • the sample set tests the target pilot location determination model. Therefore, the target pilot position determination model is generated through training, and the target pilot positions of all array elements on the RIS can be obtained by inputting data, which greatly improves the efficiency of determining the channel status information of the pilot array elements on the RIS, saves time and costs, and improves accuracy. Rate.
  • FIG. 5 is a schematic flowchart of a method for determining a pilot position provided by an embodiment of the present disclosure. As shown in Figure 5, the method is executed by the communication device and may include but is not limited to the following steps:
  • S51 Obtain an initial pilot signal, and determine first channel state information based on the initial pilot signal.
  • the communication device referred to in the embodiment of the present disclosure may be a network device or a terminal device.
  • the terminal device may be a mobile phone, a handheld computer, etc.
  • the network device may be a base station, etc.
  • the first channel state information H 2 k may be that the communication device receives the initial pilot signal sent by the initial pilot array element activated on the RIS in the actual environment, and estimates the actual pilot signal, To obtain the first channel status information.
  • the initial pilot array elements can be determined in real time, or can be predefined or preconfigured.
  • the first channel status information may be received in real time or may be received previously.
  • S52 Input the first channel state information into the trained target pilot position determination model to obtain the target pilot position information of the RIS.
  • the network device or the terminal device inputs the first channel state information H 2 k into the target pilot position determination model, and the target pilot position determination model outputs the target pilot position information (x m , y m ).
  • x m and y m respectively indicate the time domain resource and frequency domain resource positions allocated to the RIS or the pilot array elements on it. Therefore, after obtaining the pilot position information (x m , y m ), the corresponding RIS or pilot array element can be known based on the position information.
  • the training method of the target pilot position determination model may refer to the content in the above embodiments, and will not be described again here.
  • the first channel state information is determined, and then the first channel state information is input into the trained target pilot position determination model to obtain the target pilot position information of the RIS. Therefore, by inputting the first channel state information into the target pilot position determination model to obtain the target pilot position information of the RIS, the accuracy and efficiency of obtaining the target pilot position information can be improved and the acquisition time cost can be reduced.
  • FIG. 6 is a schematic flowchart of a method for determining a pilot position provided by an embodiment of the present disclosure. As shown in Figure 6, the method is executed by the communication device and may include but is not limited to the following steps:
  • S61 Obtain the initial pilot signal, and determine the first channel state information based on the initial pilot signal.
  • the communication device referred to in the embodiment of the present disclosure may be a network device or a terminal device.
  • the terminal device may be a mobile phone, a handheld computer, etc.
  • the network device may be a base station, etc.
  • S62 Input the first channel state information into the trained target pilot position determination model to obtain the target pilot position information of the RIS.
  • steps S61 to S62 the implementation provided in any embodiment of this application may be adopted, and details will not be described again here.
  • S63 Activate the target pilot array element on the RIS indicated by the target pilot location information.
  • the target pilot array element on the RIS indicated by the target pilot location information can be activated, so that the target pilot signal is sent to the communication device through the target pilot array element.
  • the communication device is a network device, and the network device can directly activate the target pilot array element based on the target pilot location information.
  • the communication device is a terminal device. The terminal device needs to report the target pilot location information to the network device, and the network device deactivates the target pilot array element on the RIS indicated by the target pilot location information.
  • S64 Receive the target pilot signal sent by the target pilot array element, and perform channel estimation based on the target pilot signal to obtain the second channel state information.
  • the communication device after receiving the target pilot signal sent by the target pilot array element, the communication device can obtain the second channel state information by performing channel estimation on the target pilot signal.
  • the active array element on the RIS can be determined based on the second channel state information. After determining the active array element, the active array element can be located on the RIS based on the second channel state information. The position on the RIS is used to determine the channel status information of other array elements, thereby determining the channel status information of the target entire array element.
  • the target pilot array element on the RIS indicated by the target pilot location information can also be activated.
  • the pilot position determination method provided by the embodiment of the present application will be explained below respectively in the uplink transmission scenario and the downlink transmission scenario.
  • FIG. 7 is a schematic flowchart of a method for determining a pilot position provided by an embodiment of the present disclosure.
  • this method is executed by the network device and may include but is not limited to the following steps:
  • the network device obtains the initial pilot signal and determines the first channel state information based on the initial pilot signal.
  • the network device inputs the first channel state information into the trained target pilot position determination model to obtain the target pilot position information of the RIS.
  • steps S71 to S72 the implementation provided in any embodiment of the present application may be adopted, and will not be described again here.
  • the network device activates the target pilot array element based on the target pilot position.
  • the network device sends the target pilot location information to the RIS through the first signaling to instruct the RIS to activate the target pilot array element.
  • the network device determines the target pilot array element based on the target pilot location information, and sends an activation instruction to the RIS, where the activation instruction is used to instruct the activation of the target pilot array element.
  • the network device receives the target pilot signal sent by the target pilot array element, and performs channel estimation based on the target pilot signal to obtain the second channel state information.
  • the network device determines the target full array element channel state information of the RIS based on the second channel state information.
  • determining the target channel state information of the entire array element of the RIS can be found in the relevant records in the above embodiments, and will not be described again here.
  • the base station determines the first channel state information, inputs the first channel state information into the trained target pilot position determination model to obtain the target pilot position information of the RIS, and then activates based on the target pilot position Target pilot array element, the network equipment receives the target pilot signal sent by the target pilot array element, and performs channel estimation based on the target pilot signal to obtain the second channel status information.
  • the network equipment determines the RIS based on the second channel status information. Target all-array element channel status information, and reconfigure all array elements of the RIS based on the target all-array element channel status information.
  • FIG. 8 is a schematic flowchart of a method for determining a pilot position provided by an embodiment of the present disclosure.
  • this method is executed by the terminal device and may include but is not limited to the following steps:
  • the terminal device obtains an initial pilot signal and determines the first channel state information based on the initial pilot signal.
  • the terminal device inputs the first channel state information into the trained target pilot position determination model to obtain the target pilot position information of the RIS.
  • the terminal device sends the target pilot location information to the network device through the second signaling.
  • the target pilot location information is used to instruct the network device to activate the target pilot array element based on the target pilot location.
  • the terminal device cannot directly communicate with the RIS. After the target pilot position information is obtained through the target pilot position determination model, the target pilot position information is sent to the network device through the second signaling, and the network device communicates with the RIS to activate the target pilot array element.
  • the terminal device receives the target pilot signal sent by the target pilot array element, and performs channel estimation based on the target pilot signal to obtain the second channel state information.
  • the terminal device determines the target full array element channel state information of the RIS based on the second channel state information.
  • determining the target channel state information of the entire array element of the RIS can be found in the relevant records in the above embodiments, and will not be described again here.
  • FIG. 9 is a schematic flowchart of a method for determining pilot location information provided by an embodiment of the present disclosure. As shown in Figure 9, this method is executed by RIS and may include but is not limited to the following steps:
  • S91 Send an initial pilot signal to the communication device.
  • the initial pilot signal is used for channel estimation by the communication device to obtain the first channel state information.
  • the first channel state information is used to input into the trained target pilot position determination model to determine the target pilot position.
  • the training method of the target pilot position determination model may refer to the content in the above embodiment, and will not be described again here.
  • the RIS sends an initial pilot signal to the network device through the initially activated pilot array element, and the network device performs initial pilot signal estimation to obtain the first channel state information. Then, the first channel state information is input into the trained target pilot position determination model to obtain the target pilot position information of the RIS.
  • the network device may be a base station.
  • the initial pilot signal can be sent to the communication device through the initial pilot array element activated on the RIS.
  • the activation configuration information can be generated based on the target pilot location information, and based on the activation configuration information, the RIS active array elements can be reconfigured, and the designated RIS pilot array elements can be activated to send pilot signals to the base station.
  • the target pilot signal is sent to the communication device based on the target pilot array element, where the target pilot signal is used for channel estimation to obtain the second channel state information.
  • FIG. 10 is a schematic flowchart of a method for determining pilot location information provided by an embodiment of the present disclosure. As shown in Figure 10, this method is executed by RIS and may include but is not limited to the following steps:
  • S101 sends an initial pilot signal to the communication device through the initial pilot array element activated on the RIS, where the initial pilot signal is used for channel estimation by the communication device to obtain the first channel state information, and the first channel state information is used for input training
  • a good target pilot position determination model is used to obtain the target pilot position information of RIS.
  • the communication device in the uplink transmission scenario is a network device, and the network device activates the target pilot array element based on the target pilot position.
  • the communication device is a terminal device, and the terminal device sends the target pilot location information to the network device through the second signaling.
  • the target pilot location information is used to instruct the network device to activate the target pilot based on the target pilot location.
  • Frequency array element is used to instruct the network device to activate the target pilot based on the target pilot location.
  • the target pilot signal is sent to the communication device based on the target pilot array element.
  • the target pilot signal is used for channel estimation to obtain the second channel state information. Please refer to the relevant content in the above embodiments and will not be described again here.
  • the methods provided by the embodiments of the present application are introduced from the perspectives of terminal equipment and network equipment respectively.
  • the terminal device and the network device may include a hardware structure and a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module.
  • a certain function among the above functions can be executed by a hardware structure, a software module, or a hardware structure plus a software module.
  • FIG. 11 is a schematic structural diagram of a communication device 1100 provided by an embodiment of the present application, which is executed by the communication device.
  • the communication device 1100 shown in FIG. 11 may include a processing module 111 and a transceiver module 112.
  • the communication device 1100 may be a terminal device, a device in a terminal device, a RIS, or a device that can be used in conjunction with a terminal device or a network device.
  • Communication device 1100 including:
  • the processing module 111 is used to obtain a training sample set.
  • the training sample set includes multiple sample groups. Each sample group includes first sample channel state information and label channel state information of the first sample channel state information, and combines the sample group with Enter the initial pilot position determination model to output the first pilot position information, obtain the predicted channel state information based on the first pilot position information, and determine the initial pilot position based on the tag channel state information and the predicted channel state information.
  • the model adjusts the model parameters, and uses the next sample group to continue training the adjusted initial pilot position determination model until the target pilot position determination model is obtained after the training.
  • the processing module 111 is also configured to: activate the first pilot array element on the smart metasurface RIS indicated by the first pilot location information; receive the first pilot signal sent by the first pilot array element, And perform channel estimation based on the first pilot signal to obtain predicted channel state information.
  • the processing module 111 is also configured to: obtain a test sample set, which includes channel state information for the second sample; and test the target pilot position determination model based on the test sample set.
  • the processing module 111 is also configured to: determine the first full array element channel state information of the RIS based on the predicted channel state information; determine the initial pilot position based on the first full array element channel state information and the tag channel state information. Determine the loss function of the model; adjust the initial pilot position based on the loss function to determine the model parameters of the model.
  • the processing module 111 is also configured to: a processing module to obtain the initial pilot signal, determine the first channel state information based on the initial pilot signal, and convert the first A channel state information is input into the trained target pilot position determination model to obtain the target pilot position information of the RIS; wherein, the target pilot position determination model is trained by the acquisition method in any of the above embodiments.
  • the processing module 111 is also configured to activate the target pilot array element on the RIS indicated by the target pilot location information.
  • the processing module 111 is also configured to: in the uplink transmission scenario, the communication device is a network device, and the network device activates the target pilot element based on the target pilot position.
  • the processing module 111 is also configured to: send the target pilot location information to the RIS through the first signaling to instruct the RIS to activate the target pilot array element; or determine the target pilot array element based on the target pilot location information. , and sends an activation command to the RIS.
  • the activation command is used to instruct the activation of the target pilot array element.
  • the processing module 111 is also configured to: receive the target pilot signal sent by the target pilot array element, and perform channel estimation based on the target pilot signal to obtain the second channel state information.
  • the processing module 111 is also configured to determine the target full array element channel state information of the RIS based on the second channel state information.
  • the communication device 1100 may also be a RIS (such as the RIS in the foregoing method embodiment).
  • the transceiver module 112 is also used to: send an initial pilot signal to the terminal device or network device.
  • the initial pilot signal is used for channel estimation by the communication device to obtain the first channel state information.
  • the first channel state information is used for input training.
  • a good target pilot position determination model is used to obtain the target pilot position information of RIS.
  • the transceiver module 112 is also configured to send an initial pilot signal to the terminal device or network device through the initial pilot array element activated on the RIS.
  • the processing module 111 is also configured to activate the target pilot array element indicated by the target pilot location information.
  • the transceiver module 112 is also used to: receive activation configuration information, reconfigure the active array elements of the RIS based on the activation configuration information, and activate the target pilot array element.
  • the transceiver module 112 is also configured to send a target pilot signal to the communication device based on the target pilot array element, where the target pilot signal is used for channel estimation to obtain the second channel state information.
  • the efficiency of determining the channel state information of the pilot array elements on the RIS can be improved. Especially when there are a large number of pilot array elements on the RIS, communication equipment can be saved. The time cost of channel estimation can be improved and the accuracy can be improved.
  • FIG 12 is a schematic structural diagram of another communication device 1200 provided by an embodiment of the present application.
  • the communication device 1200 may be a network device, a terminal device, a RIS, a chip, a chip system, a processor, etc. that supports a network device to implement the above method, or a chip that supports a terminal device to implement the above method. , chip system, or processor, etc.
  • the device can be used to implement the method described in the above method embodiment. For details, please refer to the description in the above method embodiment.
  • Communication device 1200 may include one or more processors 121.
  • the processor 121 may be a general-purpose processor or a special-purpose processor, or the like. For example, it can be a baseband processor or a central processing unit.
  • the baseband processor can be used to process communication protocols and communication data.
  • the central processor can be used to control communication devices (such as base stations, baseband chips, terminal equipment, terminal equipment chips, DU or CU, etc.) and execute computer programs. , processing data for computer programs.
  • the communication device 1200 may also include one or more memories 122, on which a computer program 124 may be stored.
  • the processor 121 executes the computer program 124, so that the communication device 1200 executes the method described in the above method embodiment.
  • data may also be stored in the memory 122 .
  • the communication device 1200 and the memory 122 can be provided separately or integrated together.
  • the communication device 1200 may also include a transceiver 127 and an antenna 126.
  • the transceiver 127 may be called a transceiver unit, a transceiver, a transceiver circuit, etc., and is used to implement transceiver functions.
  • the transceiver 127 may include a receiver and a transmitter.
  • the receiver may be called a receiver or a receiving circuit, etc., used to implement the receiving function;
  • the transmitter may be called a transmitter, a transmitting circuit, etc., used to implement the transmitting function.
  • the communication device 1200 may also include one or more interface circuits 127.
  • the interface circuit 127 is used to receive code instructions and transmit them to the processor 121 .
  • the processor 121 executes code instructions to cause the communication device 1200 to perform the method described in the above method embodiment.
  • the processor 121 may include a transceiver for implementing receiving and transmitting functions.
  • the transceiver may be a transceiver circuit, an interface, or an interface circuit.
  • the transceiver circuits, interfaces or interface circuits used to implement the receiving and transmitting functions can be separate or integrated together.
  • the above-mentioned transceiver circuit, interface or interface circuit can be used for reading and writing codes/data, or the above-mentioned transceiver circuit, interface or interface circuit can be used for signal transmission or transfer.
  • the processor 121 may store a computer program 123, and the computer program 123 runs on the processor 121, causing the communication device 1200 to perform the method described in the above method embodiment.
  • the computer program 123 may be solidified in the processor 121, in which case the processor 121 may be implemented by hardware.
  • the communication device 1200 may include a circuit, and the circuit may implement the sending or receiving or communication functions in the foregoing method embodiments.
  • the processor and transceiver described in this application can be implemented in integrated circuits (ICs), analog ICs, radio frequency integrated circuits RFICs, mixed signal ICs, application specific integrated circuits (ASICs), printed circuit boards ( printed circuit board (PCB), electronic equipment, etc.
  • the processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide-semiconductor (NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (bicmos), silicon germanium (sige), gallium arsenide (gaas), etc.
  • CMOS complementary metal oxide semiconductor
  • NMOS N-type metal oxide-semiconductor
  • PMOS P-type Metal oxide semiconductor
  • BJT bipolar junction transistor
  • bipolar CMOS bicmos
  • silicon germanium sige
  • gallium arsenide gallium arsenide
  • the communication device described in the above embodiments may be a network device or a terminal device (such as the terminal device in the foregoing method embodiment), but the scope of the communication device described in this application is not limited thereto, and the structure of the communication device may not be limited to Limitations of Figure 12.
  • the communication device may be a stand-alone device or may be part of a larger device.
  • the communication device may be:
  • the IC collection may also include storage components for storing data and computer programs;
  • the communication device may be a chip or a chip system
  • the schematic structural diagram of the chip shown in FIG. 13 refer to the schematic structural diagram of the chip shown in FIG. 13 .
  • the chip shown in FIG. 13 includes a processor 131 and an interface 132.
  • the number of processors 131 may be one or more, and the number of interfaces 132 may be multiple.
  • the chip is used to implement any method provided in the embodiments of this application.
  • the chip also includes a memory 133, which is used to store necessary computer programs and data.
  • This application also provides a readable storage medium on which instructions are stored. When the instructions are executed by a computer, the functions of any of the above method embodiments are implemented.
  • This application also provides a computer program product, which, when executed by a computer, implements the functions of any of the above method embodiments.
  • a computer program product includes one or more computer programs.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • the computer program may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program may be transmitted from a website, computer, server or data center via a wireline (e.g.
  • Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless means to transmit to another website, computer, server or data center.
  • Computer-readable storage media can be any available media that can be accessed by a computer, or a data storage device such as a server, data center, or other integrated media that contains one or more available media. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVD)), or semiconductor media (e.g., solid state disks (SSD)) )wait.
  • magnetic media e.g., floppy disks, hard disks, tapes
  • optical media e.g., high-density digital video discs (DVD)
  • semiconductor media e.g., solid state disks (SSD)
  • At least one in this application can also be described as one or more, and the plurality can be two, three, four or more, which is not limited by this application.
  • the technical feature is distinguished by “first”, “second”, “third”, “A”, “B”, “C” and “D”, etc.
  • the technical features described in “first”, “second”, “third”, “A”, “B”, “C” and “D” are in no particular order or order.
  • the corresponding relationships shown in each table in this application can be configured or predefined.
  • the values of the information in each table are only examples and can be configured as other values, which are not limited by this application.
  • the corresponding relationships shown in some rows may not be configured.
  • appropriate deformation adjustments can be made based on the above table, such as splitting, merging, etc.
  • the names of the parameters shown in the titles of the above tables may also be other names understandable by the communication device, and the values or expressions of the parameters may also be other values or expressions understandable by the communication device.
  • other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables. wait.
  • Predefinition in this application can be understood as definition, pre-definition, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-burning.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Power Engineering (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种导频位置确定模型的获取方法，可应用于通信技术领域，其中，由通信设备执行的方法包括：获取训练样本集，训练样本集中包括多个样本组；将样本组输入初始导频位置确定模型中，以输出第一导频位置信息（22）；基于第一导频位置信息，得到预测信道状态信息（23）；基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型（24）。通过对初始导频位置确定模型进行训练，可以提升确定RIS上导频阵元的信道状态信息的效率，尤其是在RIS上存在大量导频阵元，可以节省通信设备进行信道估计的时间成本，并且可以提升准确率。

Description

导频位置确定模型的获取、导频位置确定方法及其装置 技术领域
本申请涉及通信技术领域，尤其涉及一种导频位置确定模型的获取的方法及其装置、导频位置确定方法及其装置。
背景技术
由于不同的业务类型对于无线通信技术有不同的要求，如增强移动宽带(Enhanced Mobile Broadband，eMBB)业务的需求侧重在大带宽，高速率等方面；超高可靠低时延通信(Ultra Reliable Low Latency Communication，URLLC)业务的需求侧重在较高的可靠性以及低的时延方面；海量机器类通信(massive Machine Type of Communication，mMTC)业务的需求侧重在海量的连接数方面。因此新一代的无线通信系统需要灵活、可配置的设计来支持多种业务类型的传输需求。
当前技术中，可通过将智能超表面(Reconfigurable Intelligence Surface，RIS)部署在无线传输环境中各类物体的表面，有望突破传统无线信道的不可控性，构建智能可编程无线环境，引入未来无线通信的新范式。一方面，RIS可以主动地丰富信道散射条件，增强无线通信系统的复用增益；另一方面，RIS可以在三维空间中实现信号传播方向调控及同相位叠加，增大接收信号强度，提高通信设备之间的传输性能。因此，RIS有很大潜力用于未来无线网络的覆盖增强和容量提升，消除局部覆盖空洞。如何高效选取RIS上的有效阵元成为了主要问题。
发明内容
本申请实施例提供一种导频位置确定模型的获取的方法及其装置、导频位置确定方法及其装置，可以应用于通信技术领域，用于通过训练生成导频位置确定模型，提升确定RIS上导频阵元的信道状态信息的效率。
第一方面，本公开实施例提供了一种导频位置确定模型的获取方法，其特征在于，由通信设备执行，方法包括：获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息；将样本组输入初始导频位置确定模型中，以输出第一导频位置信息；基于第一导频位置信息，得到预测信道状态信息；基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。由此，通过对初始导频位置确定模型进行训练，可以提升确定RIS上导频阵元的信道状态信息的效率，尤其是在RIS上存在大量导频阵元，可以节省通信设备进行信道估计的时间成本，并且可以提升准确率。
在一种可能实现的方式中，基于第一导频位置信息，得到预测信道状态信息，包括：
激活第一导频位置信息所指示的智能超表面RIS上的第一导频阵元；
接收第一导频阵元发送第一导频信号，并基于第一导频信号进行信道估计，得到预测信道状态信息。
在一种可能实现的方式中，得到目标导频位置确定模型之后，方法还包括：
获取测试样本集，测试样本集中包括用于第二样本信道状态信息；
基于测试样本集对目标导频位置确定模型进行测试。
在一种可能实现的方式中，基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，包括：
基于预测信道状态信息，确定RIS的第一全阵元信道状态信息；
基于第一全阵元信道状态信息和标签信道状态信息，确定初始导频位置确定模型的损失函数；
基于损失函数调整初始导频位置确定模型的模型参数。
在一种可能实现的方式中，
本公开实施例提供了一种导频位置信息确定方法，其特征在于，由通信设备执行，方法包括：
获取初始导频信号，并基于初始导频信号确定第一信道状态信息；
将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息；
其中，目标导频位置确定模型为导频位置确定模型的获取方法训练得到。
在一种可能实现的方式中，得到目标导频位置信息之后，还包括：
激活目标导频位置信息所指示的RIS上的目标导频阵元。
在一种可能实现的方式中，激活目标导频位置信息所指示的RIS上的目标导频阵元，包括：
上行传输场景下通信设备为网络设备，网络设备基于目标导频位置激活目标导频阵元。
在一种可能实现的方式中，网络设备基于目标导频位置激活目标导频阵元，包括：
通过第一信令将目标导频位置信息发送给RIS，以指示RIS激活目标导频阵元；或者
基于目标导频位置信息确定目标导频阵元，并向RIS发送激活指令，激活指令用于指示激活目标导频阵元。
在一种可能实现的方式中，激活目标导频位置信息所指示的RIS上的目标导频阵元，包括：
下行传输场景下通信设备为终端设备，终端设备通过第二信令将目标导频位置信息发送给网络设备，目标导频位置信息用于指示网络设备基于目标导频位置激活目标导频阵元。
在一种可能实现的方式中，激活第一导频位置信息所指示的RIS上的目标导频阵元之后，还包括：
接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息。
在一种可能实现的方式中，得到第二信道状态信息之后，还包括：基于第二信道状态信息，确定RIS的目标全阵元信道状态信息。
第二方面，本公开实施例提供了一种导频位置信息确定方法，其特征在于，由RIS执行，方法包括：
向通信设备发送初始导频信号，初始导频信号用于由通信设备进行信道估计得到第一信道状态信息，第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
在一种可能实现的方式中，向通信设备发送初始导频信号，包括：
通过RIS上激活的初始导频阵元，向通信设备发送初始导频信号。
在一种可能实现的方式中，向通信设备发送第一信道状态信息之后，还包括：
激活目标导频位置信息所指示的目标导频阵元。
在一种可能实现的方式中，激活目标导频位置信息所指示的目标导频阵元，包括：
接收激活配置信息，并基于激活配置信息重新配置RIS的有源阵元，并激活目标导频阵元。
在一种可能实现的方式中，激活目标导频位置信息所指示的目标导频阵元之后，还包括：
基于目标导频阵元向通信设备发送目标导频信号，其中目标导频信号用于进行信道估计得到第二信道状态信息。
第三方面，本申请实施例提供一种通信设备，设备包括：处理模块，用于获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息，并将样本组输入初始导频位置确定模型中，以输出第一导频位置信息，基于第一导频位置信息，得到预测信道状态信息，以及基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。
第四方面，本申请实施例提供一种通信装置，该通信装置具有实现上述第一方面的方法示例中终端设备的部分或全部功能，比如通信装置的功能可具备本申请中的部分或全部实施例中的功能，也可以具备单独实施本申请中的任一个实施例的功能。功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中，该通信装置的结构中可包括收发模块和处理模块，处理模块被配置为支持通信装置执行上述方法中相应的功能。收发模块用于支持通信装置与其他设备之间的通信。通信装置还可以包括存储模块，存储模块用于与收发模块和处理模块耦合，其保存通信装置必要的计算机程序和数据。
作为示例，处理模块可以为处理器，收发模块可以为收发器或通信接口，存储模块可以为存储器。
第六方面，本申请实施例提供另一种通信装置，该通信装置具有实现上述第二方面的方法示例中网络设备的部分或全部功能，比如通信装置的功能可具备本申请中的部分或全部实施例中的功能，也可以具备单独实施本申请中的任一个实施例的功能。功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中，该通信装置的结构中可包括收发模块和处理模块，该处理模块被配置为支持通信装置执行上述方法中相应的功能。收发模块用于支持通信装置与其他设备之间的通信。通信装置还可以包括存储模块，存储模块用于与收发模块和处理模块耦合，其保存通信装置必要的计算机程序和数据。
作为示例，处理模块可以为处理器，收发模块可以为收发器或通信接口，存储模块可以为存储器。
第七方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第一方面的方法。
第八方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的 计算机程序时，执行上述第二方面的方法。
作为示例，处理模块可以为处理器，收发模块可以为收发器或通信接口，存储模块可以为存储器。
第六方面，本申请实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第一方面的方法。
第七方面，本申请实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第二方面的方法。
第八方面，本申请实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第一方面的方法。
第九方面，本申请实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第二方面的方法。
第十方面，本申请实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行代码指令以使该装置执行上述第一方面的方法。
第十一方面，本申请实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行代码指令以使该装置执行上述第二方面的方法。
第十二方面，本申请实施例提供一种通信系统，该系统包括第三方面的通信装置以及第四方面的通信装置，或者，该系统包括第五方面的通信装置以及第六方面的通信装置，或者，该系统包括第七方面的通信装置以及第八方面的通信装置，或者，该系统包括第九方面的通信装置以及第十方面的通信装置。
第十三方面，本发明实施例提供一种计算机可读存储介质，用于储存为上述接收设备所用的指令，当指令被执行时，使接收设备执行上述第一方面的方法。
第十四方面，本发明实施例提供一种可读存储介质，用于储存为上述发送设备所用的指令，当指令被执行时，使发送设备执行上述第二方面的方法。
第十五方面，本申请还提供一种包括计算机程序的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第一方面的方法。
第十六方面，本申请还提供一种包括计算机程序的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第二方面的方法。
第十七方面，本申请提供一种芯片系统，该芯片系统包括至少一个处理器和接口，用于支持接收设备实现第一方面所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中，芯片系统还包括存储器，存储器，用于保存接收设备必要的计算机程序和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十八方面，本申请提供一种芯片系统，该芯片系统包括至少一个处理器和接口，用于支持发送设备实现第二方面所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中，芯片系统还包括存储器，存储器，用于保存发送设备必要的计算机程序和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十九方面，本申请提供一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面 的方法。
第二十方面，本申请提供一种计算机程序，当其在计算机上运行时，使得计算机执行上述第二方面的方法。
附图说明
为了更清楚地说明本申请实施例或背景技术中的技术方案，下面将对本申请实施例或背景技术中所需要使用的附图进行说明。
图1是本申请实施例提供的一种通信系统的架构示意图；
图2是本申请实施例提供的一种导频位置确定模型的获取的方法的流程示意图；
图3是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图4是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图5是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图6是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图7是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图8是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图9是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
[根据细则91更正 09.05.2022]
图10是本申请实施例提供的另一种导频位置确定模型的获取的方法流程示意图；
图11是本申请实施例提供的一种导频位置确定模型的通信设备的结构示意图；
图12是本申请实施例提供的一种导频位置确定模型的通信装置的结构示意图；
图13是本申请实施例提供的一种导频位置确定模型的一种芯片的结构示意图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
在本公开实施例使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本公开实施例。在本公开实施例和所附权利要求书中所使用的单数形式的“一种”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本公开实施例可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本公开实施例范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”
出于简洁和便于理解的目的，本文在表征大小关系时，所使用的术语为“大于”或“小于”、“高于”或“低于”。但对于本领域技术人员来说，可以理解：术语“大于”也涵盖了“大于等于”的含义，“小于”也涵盖了“小于等于”的含义；术语“高于”涵盖了“高于等于”的含义，“低于”也涵盖了“低于等于”的含义。
为了便于理解，首先介绍本申请涉及的术语。
1、智能超表面(Reconfigurable Intelligence Surface，RIS)
RIS的技术基础，则是一种被叫做“信息超材料”的人工材料。超材料是指一类自然界中不存在的， 具有特殊性质的人造材料。它们拥有一些特别的性质，比如让光、电磁波改变它们的通常性质，而这样的效果是传统材料无法实现的。RIS可以主动地丰富信道散射条件，增强无线通信系统的复用增益；另一方面，RIS可以在三维空间中实现信号传播方向调控及同相位叠加，增大接收信号强度，提高通信设备之间的传输性能。
为了更好的理解本申请实施例公开的一种导频位置确定模型的获取的方法机及其装置，下面首先对本申请实施例适用的通信系统进行描述。
请参见图1，图1为本申请实施例提供的一种通信系统的架构示意图。该通信系统可包括但不限于一个网络设备和一个终端设备，图1所示的设备数量和形态仅用于举例并不构成对本申请实施例的限定，实际应用中可以包括两个或两个以上的网络设备，两个或两个以上的终端设备。图1所示的通信系统以包括一个网络设备101和一个终端设备102为例。
需要说明的是，本申请实施例的技术方案可以应用于各种通信系统。例如：长期演进(long term evolution，LTE)系统、第五代(5th generation，5G)移动通信系统、5G新空口(new radio，NR)系统，或者其他未来的新型移动通信系统等。还需要说明的是，本申请实施例中的侧链路还可以称为侧行链路或直通链路。
本申请实施例中的网络设备101是网络侧的一种用于发射或接收信号的实体。例如，网络设备101可以为接入网设备，该接入网设备可以为演进型基站(evolved nodeb，enb)、传输点(transmission reception point，TRP)、NR系统中的下一代基站(next generation nodeb，gnb)、其他未来移动通信系统中的基站或无线保真(wireless fidelity，wifi)系统中的接入节点等。网络设备101可以为核心网设备，本申请实施例中的核心网设备可以是与接入网设备通信的设备，该核心网设备可以是5G核心网设备，例如接入与移动性管理功能(Access and Mobility Management Function，AMF)，也可以是分组核心演进(evolvedpacket Core，EPC)设备，例如移动性管理实体(Mobility Management Entity，MME)。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。本申请实施例提供的网络设备可以是由集中单元(central unit，CU)与分布式单元(distributed unit，DU)组成的，其中，CU也可以称为控制单元(control unit)，采用CU-DU的结构可以将网络设备，例如基站的协议层拆分开，部分协议层的功能放在CU集中控制，剩下部分或全部协议层的功能分布在DU中，由CU集中控制DU。
本申请实施例中的终端设备102是用户侧的一种用于接收或发射信号的实体，如手机。终端设备也可以称为终端设备(terminal)、用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端设备(mobile terminal，MT)等。终端设备可以是具备通信功能的汽车、智能汽车、手机(mobile phone)、穿戴式设备、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self-driving)中的无线终端设备、远程手术(remote medical surgery)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备、智慧家庭(smart home)中的无线终端设备等等。本申请的实施例对终端设备所采用的具体技术和具体设备形态不做限定。
可以理解的是，本申请实施例描述的通信系统是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着系统架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
下面结合附图对本申请所提供的导频位置确定模型方法及其装置进行详细地介绍。
请参见图2，图2是本申请实施例提供的一种导频位置确定模型的获取方法的流程示意图。如图2所示，该方法由通信设备执行，可以包括但不限于如下步骤：
S21，获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息。
需要说明的是，本公开实施例中的所指的通信设备可为网络设备，也可为终端设备，举例来说，终端设备可为手机、掌上电脑等，网络设备可为基站等。
需要说明的是，RIS可设置在网络设备和终端设备之间，具有发送导频信号、接收导频信号和估计导频信号的功能，一方面，RIS可以主动地丰富信道散射条件，增强无线通信系统的复用增益；另一方面，RIS可以在三维空间中实现信号传播方向调控及同相位叠加，增大接收信号强度，提高通信设备之间的传输性能。因此，RIS有很大潜力用于未来无线网络的覆盖增强和容量提升，消除局部覆盖空洞。
RIS上可包含多个导频阵元，RIS上的阵元按照一定的顺序进行排列,此处不作任何限定，具体可根据实际需要或者需要实现的功能进行设定。举例来说，如图3所示，RIS上的阵元可按照矩阵的形式进行排列。导频阵元可为有源阵元，也可为无源阵元，也可为有源与无源之间相结合的组合，具体需要根据实际需要进行设定。
RIS上的有源阵元可以发送导频信号，通过该导频信号能够进行估计，得到信道状态信息(Channel State Information，CSI)，即在无线通信领域中，通信链路的信道属性。它描述了信号在每条传输路径上的衰弱因子，即信道增益矩阵中每个元素的值，如信号散射(Scattering),环境衰弱(fading，multipath fading or shadowing fading),距离衰减(power decay of distance)等信息。需要说明的是，每个阵元对应的CSI可以为相同的，也可为不同的。
通信设备在接收到RIS上的导频阵元发送的导频信号后，可基于导频信号估计出信道状态信息H 1 k，基于信道状态信息H 1 k可以得到样本集。可选地，可以基于线性插值的方式，对信道状态信息H 1 k对样本进行增强，得到第一样本信道状态信息H 1 all，作为训练阶段的多个样本。
本申请实施例中，可以在设定通信环境下获取标签信道状态信息，例如可以干扰较小的理想传输环境下获取一些信道状态信息，作为标签信道状态信息H real。
需要说明的是，每个第一样本信道状态信息对应有一个标签信道状态信息，第一样本信道状态信息和其对应的标签信道状态信息，作为一个样本组。
S22，将样本组输入初始导频位置确定模型中，以输出第一导频位置信息。
在本公开实施例中，初始导频位置确定模型可为人工智能(Artificial Intelligence，AI)/机器学习(Machine Learning，ML)模型。AI/ML模型在复杂未知环境建模、学习，信道预测，智能信号生成与处理，网络状态跟踪与智能调度，网络优化部署等许多方面具有重要的应用潜力，有望促进未来通信范 式的演变和网络架构的变革，对5G-Advanced/6G技术研究具有十分重要的意义和价值。
在获取到训练样本集后，通信设备将训练样本集中样本组(H 1 all，H real)分批次输入初始导频位置确定模型中，在迭代过程中逐渐提取重要特征，即选取导频信息量最大的位置，作为第一导频位置信息(x k，y k)并保存。其中k＝{1，2，…，K}，K为选取每个批次中样本组的数量，也是需要激活的RIS上导频阵元的数量。
在一种实施例中，x k和y k分别指示给RIS或者其上的导频阵元所分配的时域资源和频域资源位置。因此，在得到了导频位置信息(x k，y k)后，可以根据该位置信息得知对应的RIS或导频阵元。
S23，基于第一导频位置信息，得到预测信道状态信息。
在得到第一导频位置信息后，电子设备将得到的第一导频位置信息(x k，y k)通过信令通知给RIS，由RIS激活导频阵元的导频信号，并由通信设备对选取的导频位置处的信道信息进行估计，以确定预测信道状态信息H pilot。
S24，基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。
能够理解的是，模型的训练是个重复迭代的过程，通过不断地调整模型的网络参数进行训练，直到模型整体的损失函数值小于预设值，或者模型整体的损失函数值不再变化或变化幅度缓慢，模型收敛，得到训练好的模型。
在获取到标签信道状态信息和预测信道状态信息后，可基于标签信道状态信息和预测信道状态信息对模型参数进行调整，然后采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至达到预期的效果。
可选地，可通过获取损失值来，并将损失值与设定阈值进行比较，以确定是否达到预期效果。需要说明的是，设定阈值可为提前设定好的。
可选地，还可通过实际的测试，确定模型输出预测信道状态信息的准确性，当准确性大于准确性阈值时，则可认为达到预期效果。需要说明的是，准确性阈值可为提前设定好的。
在本公开实施例中，首先获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息，然后将样本组输入初始导频位置确定模型中，以输出第一导频位置信息，而后基于第一导频位置信息，得到预测信道状态信息，最后基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。由此，通过对初始导频位置确定模型进行训练，可以提升确定RIS上导频阵元的信道状态信息的效率，尤其是在RIS上存在大量导频阵元，可以节省通信设备进行信道估计的时间成本，并且可以提升准确率。
请参见图4，图4是本申请实施例提供的一种导频位置确定模型的获取方法的流程示意图。如图3所示，该方法由通信设备执行，可以包括但不限于如下步骤：
S41，获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和 第一样本信道状态信息的标签信道状态信息。
需要说明的是，本公开实施例中的所指的通信设备可为网络设备，也可为终端设备，举例来说，终端设备可为手机、掌上电脑等，网络设备可为基站等。
关于训练样本集的介绍可参见上述实施例中相关内容的记载，此处不再赘述。
S42，将样本组输入初始导频位置确定模型中，以输出第一导频位置信息。
关于步骤S42的实现方式，可采用本申请任一实施例中提供的实现方式，此处不再赘述。
S43，基于第一导频位置信息，得到预测信道状态信息。
可选地，在获取到第一导频位置信息后，激活第一导频位置信息所指示的RIS上的第一导频阵元，并接收第一导频阵元发送的第一导频信号，并基于第一导频信号进行信道估计，得到预测信道状态信息。
可选地，上行传输场景下通信设备为网络设备，网络设备基于第一导频位置激活第一导频阵元。
在一些实现中，网络设备通过信令将第一导频位置信息发送给RIS，以指示RIS激活第一导频阵元；或者，网络设备基于第一导频位置信息确定第一导频阵元，并向RIS发送激活指令，该激活指令用于指示激活第一导频阵元。
可选地，下行传输场景下所述通信设备为终端设备，终端设备通过上行信令将第一导频位置信息发送给网络设备，由网络设备基于第一导频位置激活第一导频阵元。
S44，基于预测信道状态信息，确定RIS的第一全阵元信道状态信息。
在本公开实施例中，在获取到预测信道信息后，可基于预测信道信息确定RIS上的有源阵元，在确定该有源阵元以后，可基于该有源阵元在RIS上的位置，来确定其他阵元的信道状态信息。需要说明的是，确定方法可为多种，举例来说，可通过传统的差值算法来确定，也可以通过神经网络算法进行筛选确定，此处不作任何限定。
S45，基于第一全阵元信道状态信息和标签信道状态信息，确定初始导频位置确定模型的损失函数，基于损失函数调整初始导频位置确定模型的模型参数，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。
可以根据第一全阵元信道状态信息和标签信道状态信息，对初始导频位置确定模型的损失函数进行计算，生成损失值。例如，该实施例中的损失函数为提前设定好的，并可根据实际需要进行设定。例如，该损失函数可为铰链损失函数、交叉熵损失函数和指数损失函数等，具体可根据实际需要进行选定，此处不做任何限制。
进一步地，通过损失值对初始导频位置确定模型进行调整。将调整后的初始导频位置确定模型再按照上述步骤进行训练，直至训练结束，生成目标导频位置确定模型。可选地，当损失值到达损失阈值后，训练完成，生成目标导频位置确定模型，该损失阈值可根据实际情况进行设定。
S46，获取测试样本集，测试样本集中包括用于第二样本信道状态信息。
在本公开实施例中，可基于导频信号估计信道状态信息H 3 k，通过线性插值的方式得到测试样本集，并获取第二样本信道状态信息。
需要说明的是，测试样本集与上述测试样本集可以存在重复样本，也可以包括完全不同重复的样本二者之间的数量可存在一定的比例，此处不作任何限定，具体可根据实际需要进行设定。
该实施例中的损失函数为提前设定好的，并可根据实际需要进行设定。例如，该损失函数可为铰链损失函数、交叉熵损失函数和指数损失函数等，具体可根据实际需要进行选定，此处不做任何限制。
S47，基于测试样本集对目标导频位置确定模型进行测试。
在获取到测试样本集和第二样本信道状态信息后，通过测试样本集检验目标导频位置确定模型的性能，通过数据和标签不断调整权重，更新参数后将模型保存至网络设备本地。
在本公开实施例中，首先获取测试样本集，测试样本集中包括用于第二样本信道状态信息，然后基于测试样本集对目标导频位置确定模型进行测试。由此通过对目标导频位置确定模型进行测试，可以提升目标导频位置确定模型的准确性和实用性。
在本公开实施例中，首先获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息，然后将样本组输入初始导频位置确定模型中，以输出第一导频位置信息，而后基于第一导频位置信息，得到预测信道状态信息，再之后基于预测信道状态信息，确定RIS的第一全阵元信道状态信息，再之后基于第一全阵元信道状态信息和标签信道状态信息，确定初始导频位置确定模型的损失函数，基于损失函数调整初始导频位置确定模型的模型参数，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型，再之后获取测试样本集，测试样本集中包括用于第二样本信道状态信息，最后基于测试样本集对目标导频位置确定模型进行测试。由此，通过训练生成目标导频位置确定模型，可以通过输入数据获取RIS上所有阵元的目标导频位置，大大提升确定RIS上导频阵元的信道状态信息的效率，节省时间成本提升准确率。
请参见图5，图5是本公开实施例提供的一种导频位置确定方法的流程示意图。如图5示，该方法由通信设备执行，可以包括但不限于如下步骤：
S51，获取初始导频信号，并基于所述初始导频信号确定第一信道状态信息。
需要说明的是，本公开实施例中的所指的通信设备可为网络设备，也可为终端设备，举例来说，终端设备可为手机、掌上电脑等，网络设备可为基站等。
在本公开实施例中，第一信道状态信息H 2 k可为在实际环境中通信设备接收RIS上激活的初始导频阵元发送的初始导频信号，并对实际的导频信号进行估计，以获取第一信道状态信息。可选地，初始导频阵元可以实时确定，也可以为预先定义或者预先配置。可选地，第一信道状态信息可为实时接收到的，也可能是之前接收到的。
S52，将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
在本公开实施例中，网络设备或者终端设备将第一信道状态信息H 2 k输入目标导频位置确定模型中，目标导频位置确定模型输出目标导频位置信息(x m，y m)。
在一种实施例中，x m和y m分别指示给RIS或者其上的导频阵元所分配的时域资源和频域资源位置。 因此，在得到了导频位置信息(x m，y m)后，可以根据该位置信息得知对应的RIS或导频阵元。
其中，目标导频位置确定模型的训练方法可参照上述实施例中的内容，此处不再赘述。
在本公开实施例中，确定第一信道状态信息，然后将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。由此，通过将第一信道状态信息输入至目标导频位置确定模型中以得到RIS的目标导频位置信息，可以提升获取目标导频位置信息的准确性和效率，降低获取时间成本。
请参见图6，图6是本公开实施例提供的一种导频位置确定方法的流程示意图。如图6示，该方法由通信设备执行，可以包括但不限于如下步骤：
S61，获取初始导频信号，并基于初始导频信号确定第一信道状态信息。
需要说明的是，本公开实施例中的所指的通信设备可为网络设备，也可为终端设备，举例来说，终端设备可为手机、掌上电脑等，网络设备可为基站等。
S62，将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
关于步骤S61～步骤S62的实现方式，可采用本申请任一实施例中提供的实现方式，此处不再赘述。
S63，激活目标导频位置信息所指示的RIS上的目标导频阵元。
在确定了目标导频位置信息后，可以激活目标导频位置信息所指示的RIS上的目标导频阵元，以便于通过该目标导频阵元向通信设备发送目标导频信号。
上行传输场景中，通信设备为网络设备，网络设备可以基于目标导频位置信息，直接激活激活目标导频阵元。下行传输场景中，通信设备为终端设备，终端设备需要将目标导频位置信息上报给网络设备，由网络设备去激活目标导频位置信息所指示的RIS上的目标导频阵元。
S64，接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息。
在本公开实施例中，通信设备在接收目标导频阵元发送的目标导频信号后，可通过对目标导频信号进行信道估计，得到第二信道状态信息。
S65，基于第二信道状态信息，确定RIS的目标全阵元信道状态信息。
在本公开实施例中，在获取到第二信道状态信息后，可基于第二信道状态信息确定RIS上的有源阵元，在确定该有源阵元以后，可基于该有源阵元在RIS上的位置，来确定其他阵元的信道状态信息，从而确定目标全阵元信道状态信息。
需要说明的是，将目标导频位置处的信道信息恢复成RIS全部阵元对应的信道信息的方法可为多种，举例来说，可以通过传统的差值算法进行恢复，也可以通过神经网络算法进行过滤，此处不作任何限定。
在本公开实施例中，在得到目标导频位置信息之后，还可激活目标导频位置信息所指示的RIS上的目标导频阵元。
下面分别在上行传输场景和下行传输场景对本申请实施例提供的导频位置确定方法进行解释说明。
请参见图7，图7是本公开实施例提供的一种导频位置确定方法的流程示意图。在上行传输场景中，如图7示，该方法由网络设备执行，可以包括但不限于如下步骤：
S71，网络设备获取初始导频信号，并基于所述初始导频信号确定第一信道状态信息。
S72，网络设备将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
关于步骤S71～步骤S72的实现方式，可采用本申请任一实施例中提供的实现方式，此处不再赘述。
S73，网络设备基于目标导频位置激活目标导频阵元。
可选地，网络设备通过第一信令将目标导频位置信息发送给RIS，以指示RIS激活目标导频阵元。可选地，网络设备基于目标导频位置信息确定目标导频阵元，并向RIS发送激活指令，其中激活指令用于指示激活目标导频阵元。
S74，网络设备接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息。
基于目标导频信号进行信道估计，得到第二信道状态信息可参见上述实施例中相关内容的记载，此处不再赘述。
S75，网络设备基于第二信道状态信息，确定RIS的目标全阵元信道状态信息。
基于第二信道状态信息，确定RIS的目标全阵元信道状态信息可参见上述实施例中相关内容的记载，此处不再赘述。
在上行传输场景中，基站在确定第一信道状态信息，将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息，然后基于目标导频位置激活目标导频阵元，网络设备接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息，网络设备基于第二信道状态信息，确定RIS的目标全阵元信道状态信息，并基于目标全阵元信道状态信息重新配置RIS的所有阵元。
请参见图8，图8是本公开实施例提供的一种导频位置确定方法的流程示意图。在下行传输场景中，如图8示，该方法由终端设备执行，可以包括但不限于如下步骤：
S81，终端设备获取初始导频信号，并基于所述初始导频信号确定第一信道状态信息。
S82，终端设备将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
S83，终端设备通过第二信令将目标导频位置信息发送给网络设备，目标导频位置信息用于指示网络设备基于目标导频位置激活目标导频阵元。
在本公开实施例中，终端设备无法直接通信RIS。在通过目标导频位置确定模型得到目标导频位置信息后，通过第二信令将目标导频位置信息发送给网络设备，并由网络设备通信RIS激活目标导频阵元。
S84，终端设备接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息。
基于目标导频信号进行信道估计，得到第二信道状态信息可参见上述实施例中相关内容的记载，此处不再赘述。
S85，终端设备基于第二信道状态信息，确定RIS的目标全阵元信道状态信息。
基于第二信道状态信息，确定RIS的目标全阵元信道状态信息可参见上述实施例中相关内容的记载，此处不再赘述。
请参见图9，图9是本公开实施例提供的一种导频位置信息确定方法的流程示意图。如图9示，该方法由RIS执行，可以包括但不限于如下步骤：
S91，向通信设备发送初始导频信号，初始导频信号用于由通信设备进行信道估计得到第一信道状态信息，第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
目标导频位置确定模型的训练方法可参照上述实施例中的内容，此处不再赘述。
在本公开实施例中，RIS通过初始激活的导频阵元发送初始导频信号至网络设备，并由网络设备进行初始导频信号估计，以得到第一信道状态信息。然后将第一信道状态信息输入至输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。需要说明的是，网络设备可为基站。
需要说明的是，可通过RIS上激活的初始导频阵元，向通信设备发送初始导频信号。
在获取到目标导频位置信息后，可基于目标导频位置信息生成激活配置信息，并基于激活配置信息，重新配置RIS有源阵元，激活指定的RIS导频阵元向基站导频信号，基于目标导频阵元向通信设备发送目标导频信号，其中目标导频信号用于进行信道估计得到第二信道状态信息。
请参见图10，图10是本公开实施例提供的一种导频位置信息确定方法的流程示意图。如图10示，该方法由RIS执行，可以包括但不限于如下步骤：
S101通过RIS上激活的初始导频阵元，向通信设备发送初始导频信号，其中初始导频信号用于由通信设备进行信道估计得到第一信道状态信息，第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
通过初始导频信号得到RIS的目标导频位置信息可参见上述实施例中相关内容的记载，此处不再赘述。S102，激活目标导频位置信息所指示的目标导频阵元。
可选地，接收激活配置信息，并基于激活配置信息重新配置RIS的有源阵元，并激活目标导频阵元
可选地，上行传输场景下通信设备为网络设备，网络设备基于目标导频位置激活目标导频阵元。
可选地，下行传输场景下通信设备为终端设备，终端设备通过第二信令将目标导频位置信息发送给网络设备，目标导频位置信息用于指示网络设备基于目标导频位置激活目标导频阵元。
S103，基于目标导频阵元向通信设备发送目标导频信号，其中目标导频信号用于进行信道估计得到 第二信道状态信息。
基于目标导频阵元向通信设备发送目标导频信号，其中目标导频信号用于进行信道估计得到第二信道状态信息可参见上述实施例中相关内容的记载，此处不再赘述。
上述本申请提供的实施例中，分别从终端设备和网络设备的角度对本申请实施例提供的方法进行了介绍。为了实现上述本申请实施例提供的方法中的各功能，终端设备和网络设备可以包括硬件结构、软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能可以以硬件结构、软件模块、或者硬件结构加软件模块的方式来执行。
请参见图11，为本申请实施例提供的一种通信设备1100的结构示意图，被通信设备执行。图11所示的通信设备1100可包括处理模块111和收发模块112。
通信设备1100可以是终端设备，也可以是终端设备中的设备，也可以是RIS，还可以是能够与终端设备或者网络设备匹配使用的设备。
通信设备1100，包括：
处理模块111，用于获取训练样本集，训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和第一样本信道状态信息的标签信道状态信息，并将样本组输入初始导频位置确定模型中，以输出第一导频位置信息，基于第一导频位置信息，得到预测信道状态信息，以及基于标签信道状态信息和预测信道状态信息，对初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到目标导频位置确定模型。
可选地，处理模块111，还用于：激活第一导频位置信息所指示的智能超表面RIS上的第一导频阵元；接收第一导频阵元发送的第一导频信号，并基于第一导频信号进行信道估计，得到预测信道状态信息。
可选地，处理模块111，还用于：获取测试样本集，测试样本集中包括用于第二样本信道状态信息；基于测试样本集对目标导频位置确定模型进行测试。
可选地，处理模块111，还用于：基于预测信道状态信息，确定RIS的第一全阵元信道状态信息；基于第一全阵元信道状态信息和标签信道状态信息，确定初始导频位置确定模型的损失函数；基于损失函数调整初始导频位置确定模型的模型参数。
在确定了目标导频位置确定模型之后，可选地，处理模块111，还用于：处理模块，用于获取初始导频信号，并基于初始导频信号确定第一信道状态信息，并将第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息；其中，目标导频位置确定模型为上述任一实施例获取方法训练得到。
可选地，处理模块111，还用于：激活目标导频位置信息所指示的RIS上的目标导频阵元。
可选地，处理模块111，还用于：上行传输场景下通信设备为网络设备，网络设备基于目标导频位置激活目标导频阵元。
可选地，处理模块111，还用于：通过第一信令将目标导频位置信息发送给RIS，以指示RIS激活 目标导频阵元；或者基于目标导频位置信息确定目标导频阵元，并向RIS发送激活指令，激活指令用于指示激活目标导频阵元。
可选地，处理模块111，还用于：接收目标导频阵元发送的目标导频信号，并基于目标导频信号进行信道估计，得到第二信道状态信息。
可选地，处理模块111，还用于：基于第二信道状态信息，确定RIS的目标全阵元信道状态信息。
通信设备1100也可以是RIS(如前述方法实施例中的RIS)。
收发模块112，还用于：用于向终端设备或网络设备发送初始导频信号，初始导频信号用于由通信设备进行信道估计得到第一信道状态信息，第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息。
可选地，收发模块112，还用于：通过RIS上激活的初始导频阵元，向终端设备或网络设备发送初始导频信号。
可选地，处理模块111，还用于：激活目标导频位置信息所指示的目标导频阵元。
收发模块112，还用于：接收激活配置信息，并基于激活配置信息重新配置RIS的有源阵元，并激活目标导频阵元。
可选地，收发模块112，还用于：基于目标导频阵元向通信设备发送目标导频信号，其中目标导频信号用于进行信道估计得到第二信道状态信息。
通过本公开实施例，通过对初始导频位置确定模型进行训练，可以提升确定RIS上导频阵元的信道状态信息的效率，尤其是在RIS上存在大量导频阵元，可以节省通信设备进行信道估计的时间成本，并且可以提升准确率。
请参见图12，图12是本申请实施例提供的另一种通信装置1200的结构示意图。通信装置1200可以是网络设备，也可以是终端设备，也可以是RIS，也可以是支持网络设备实现上述方法的芯片、芯片系统、或处理器等，还可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等。该装置可用于实现上述方法实施例中描述的方法，具体可以参见上述方法实施例中的说明。
通信装置1200可以包括一个或多个处理器121。处理器121可以是通用处理器或者专用处理器等。例如可以是基带处理器或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对通信装置(如，基站、基带芯片，终端设备、终端设备芯片，DU或CU等)进行控制，执行计算机程序，处理计算机程序的数据。
可选的，通信装置1200中还可以包括一个或多个存储器122，其上可以存有计算机程序124，处理器121执行计算机程序124，以使得通信装置1200执行上述方法实施例中描述的方法。可选的，存储器122中还可以存储有数据。通信装置1200和存储器122可以单独设置，也可以集成在一起。
可选的，通信装置1200还可以包括收发器127、天线126。收发器127可以称为收发单元、收发机、或收发电路等，用于实现收发功能。收发器127可以包括接收器和发送器，接收器可以称为接收机或接收电路等，用于实现接收功能；发送器可以称为发送机或发送电路等，用于实现发送功能。
可选的，通信装置1200中还可以包括一个或多个接口电路127。接口电路127用于接收代码指令并传输至处理器121。处理器121运行代码指令以使通信装置1200执行上述方法实施例中描述的方法。
在一种实现方式中，处理器121中可以包括用于实现接收和发送功能的收发器。例如该收发器可以是收发电路，或者是接口，或者是接口电路。用于实现接收和发送功能的收发电路、接口或接口电路可以是分开的，也可以集成在一起。上述收发电路、接口或接口电路可以用于代码/数据的读写，或者，上述收发电路、接口或接口电路可以用于信号的传输或传递。
在一种实现方式中，处理器121可以存有计算机程序123，计算机程序123在处理器121上运行，可使得通信装置1200执行上述方法实施例中描述的方法。计算机程序123可能固化在处理器121中，该种情况下，处理器121可能由硬件实现。
在一种实现方式中，通信装置1200可以包括电路，电路可以实现前述方法实施例中发送或接收或者通信的功能。本申请中描述的处理器和收发器可实现在集成电路(integrated circuit，IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit，ASIC)、印刷电路板(printed circuit board，PCB)、电子设备等上。该处理器和收发器也可以用各种IC工艺技术来制造，例如互补金属氧化物半导体(complementary metal oxide semiconductor，CMOS)、N型金属氧化物半导体(nmetal-oxide-semiconductor，NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor，PMOS)、双极结型晶体管(bipolar junction transistor，BJT)、双极CMOS(bicmos)、硅锗(sige)、砷化镓(gaas)等。
以上实施例描述中的通信装置可以是网络设备或者终端设备(如前述方法实施例中的终端设备)，但本申请中描述的通信装置的范围并不限于此，而且通信装置的结构可以不受图12的限制。通信装置可以是独立的设备或者可以是较大设备的一部分。例如通信装置可以是：
(1)独立的集成电路IC，或芯片，或，芯片系统或子系统；
(2)具有一个或多个IC的集合，可选的，该IC集合也可以包括用于存储数据，计算机程序的存储部件；
(3)ASIC，例如调制解调器(Modem)；
(4)可嵌入在其他设备内的模块；
(5)接收机、终端设备、智能终端设备、蜂窝电话、无线设备、手持机、移动单元、车载设备、网络设备、云设备、人工智能设备等等；
(6)其他等等。
对于通信装置可以是芯片或芯片系统的情况，可参见图13所示的芯片的结构示意图。图13所示的芯片包括处理器131和接口132。其中，处理器131的数量可以是一个或多个，接口132的数量可以是多个。
对于芯片用于实现本申请实施例提供的任一方法。
可选的，芯片还包括存储器133，存储器133用于存储必要的计算机程序和数据。
本领域技术人员还可以了解到本申请实施例列出的各种说明性逻辑块(illustrative logical block)和 步骤(step)可以通过电子硬件、电脑软件，或两者的结合进行实现。这样的功能是通过硬件还是软件来实现取决于特定的应用和整个系统的设计要求。本领域技术人员可以对于每种特定的应用，可以使用各种方法实现的功能，但这种实现不应被理解为超出本申请实施例保护的范围。
本申请还提供一种可读存储介质，其上存储有指令，该指令被计算机执行时实现上述任一方法实施例的功能。
本申请还提供一种计算机程序产品，该计算机程序产品被计算机执行时实现上述任一方法实施例的功能。
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。计算机程序产品包括一个或多个计算机程序。在计算机上加载和执行计算机程序时，全部或部分地产生按照本申请实施例的流程或功能。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。计算机程序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，计算机程序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。计算机可读存储介质可以是计算机能够存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。可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解：本申请中涉及的第一、第二等各种数字编号仅为描述方便进行的区分，并不用来限制本申请实施例的范围，也表示先后顺序。
本申请中的至少一个还可以描述为一个或多个，多个可以是两个、三个、四个或者更多个，本申请不做限制。在本申请实施例中，对于一种技术特征，通过“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”等区分该种技术特征中的技术特征，该“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”描述的技术特征间无先后顺序或者大小顺序。
本申请中各表所示的对应关系可以被配置，也可以是预定义的。各表中的信息的取值仅仅是举例，可以配置为其他值，本申请并不限定。在配置信息与各参数的对应关系时，并不一定要求必须配置各表中示意出的所有对应关系。例如，本申请中的表格中，某些行示出的对应关系也可以不配置。又例如，可以基于上述表格做适当的变形调整，例如，拆分，合并等等。上述各表中标题示出参数的名称也可以采用通信装置可理解的其他名称，其参数的取值或表示方式也可以通信装置可理解的其他取值或表示方式。上述各表在实现时，也可以采用其他的数据结构，例如可以采用数组、队列、容器、栈、线性表、指针、链表、树、图、结构体、类、堆、散列表或哈希表等。
本申请中的预定义可以理解为定义、预先定义、存储、预存储、预协商、预配置、固化、或预烧制。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行， 取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上，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权利要求的保护范围为准。

Claims (28)

  1. 一种导频位置确定模型的获取方法，其特征在于，由通信设备执行，所述方法包括：
    获取训练样本集，所述训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和所述第一样本信道状态信息的标签信道状态信息；
    将所述样本组输入初始导频位置确定模型中，以输出第一导频位置信息；
    基于所述第一导频位置信息，得到预测信道状态信息；
    基于所述标签信道状态信息和所述预测信道状态信息，对所述初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到所述目标导频位置确定模型。
  2. 根据权利要求1所述的方法，其特征在于，所述基于所述第一导频位置信息，得到预测信道状态信息，包括：
    激活所述第一导频位置信息所指示的智能超表面RIS上的第一导频阵元；
    接收所述第一导频阵元发送的第一导频信号，并基于所述第一导频信号进行信道估计，得到所述预测信道状态信息。
  3. 根据权利要求1或2所述的方法，其特征在于，得到所述目标导频位置确定模型之后，所述方法还包括：
    获取测试样本集，所述测试样本集中包括用于第二样本信道状态信息；
    基于所述测试样本集对所述目标导频位置确定模型进行测试。
  4. 根据权利要求1所述的方法，其特征在于，所述基于所述标签信道状态信息和所述预测信道状态信息，对所述初始导频位置确定模型进行模型参数调整，包括：
    基于所述预测信道状态信息，确定所述RIS的第一全阵元信道状态信息；
    基于所述第一全阵元信道状态信息和所述标签信道状态信息，确定所述初始导频位置确定模型的损失函数；
    基于所述损失函数调整所述初始导频位置确定模型的模型参数。
  5. 一种导频位置信息确定方法，其特征在于，由通信设备执行，所述方法包括：
    获取初始导频信号，并基于所述初始导频信号确定第一信道状态信息；
    将所述第一信道状态信息输入训练好的目标导频位置确定模型中，以得到所述RIS的目标导频位置信息；
    其中，所述目标导频位置确定模型为采用如权利要求1-4中任一项所述的导频位置确定模型的获取方法训练得到。
  6. 根据权利要求5所述的方法，其特征在于，所述得到目标导频位置信息之后，还包括：
    激活所述目标导频位置信息所指示的所述RIS上的目标导频阵元。
  7. 根据权利要求6所述的方法，其特征在于，所述激活所述目标导频位置信息所指示的所述RIS上的目标导频阵元，包括：
    上行传输场景下所述通信设备为网络设备，所述网络设备基于所述目标导频位置激活所述目标导频阵元。
  8. 根据权利要求7所述的方法，其特征在于，所述网络设备基于所述目标导频位置激活所述目标导频阵元，包括：
    通过第一信令将所述目标导频位置信息发送给所述RIS，以指示所述RIS激活所述目标导频阵元；或者
    基于所述目标导频位置信息确定所述目标导频阵元，并向所述RIS发送激活指令，所述激活指令用于指示激活所述目标导频阵元。
  9. 根据权利要求6所述的方法，其特征在于，所述激活所述目标导频位置信息所指示的所述RIS上的目标导频阵元，包括：
    下行传输场景下所述通信设备为终端设备，所述终端设备通过第二信令将所述目标导频位置信息发送给网络设备，所述目标导频位置信息用于指示所述网络设备基于所述目标导频位置激活所述目标导频阵元。
  10. 根据权利要求6所述的方法，其特征在于，所述激活所述第一导频位置信息所指示的所述RIS上的目标导频阵元之后，还包括：
    接收所述目标导频阵元发送的目标导频信号，并基于所述目标导频信号进行信道估计，得到第二信道状态信息。
  11. 根据权利要求10所述的方法，其特征在于，所述得到第二信道状态信息之后，还包括：
    基于所述第二信道状态信息，确定所述RIS的目标全阵元信道状态信息。
  12. 一种导频位置信息确定方法，其特征在于，由RIS执行，所述方法包括：
    向通信设备发送初始导频信号，所述初始导频信号用于由所述通信设备进行信道估计得到第一信道状态信息，所述第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到所述RIS的目标导频位置信息。
  13. 根据权利要求12所述的方法，其特征在于，所述向通信设备发送初始导频信号，包括：
    通过所述RIS上激活的初始导频阵元，向所述通信设备发送所述初始导频信号。
  14. 根据权利要求12所述的方法，其特征在于，所述向通信设备发送第一信道状态信息之后，还包括：
    激活所述目标导频位置信息所指示的目标导频阵元。
  15. 根据权利要求14所述的方法，其特征在于，所述激活所述目标导频位置信息所指示的目标导频阵元，包括：
    接收激活配置信息，并基于所述激活配置信息重新配置所述RIS的有源阵元，并激活所述目标导频阵元。
  16. 根据权利要求14或15任一项所述的方法，其特征在于，所述激活所述目标导频位置信息所指示的目标导频阵元之后，还包括：
    基于所述目标导频阵元向所述通信设备发送目标导频信号，其中所述目标导频信号用于进行信道估计得到第二信道状态信息。
  17. 一种通信设备，其特征在于，所述设备包括：
    处理模块，用于获取训练样本集，所述训练样本集中包括多个样本组，每个样本组包括第一样本信道状态信息和所述第一样本信道状态信息的标签信道状态信息，并将所述样本组输入初始导频位置确定模型中，以输出第一导频位置信息，基于所述第一导频位置信息，得到预测信道状态信息，以及基于所述标签信道状态信息和所述预测信道状态信息，对所述初始导频位置确定模型进行模型参数调整，并采用下一样本组继续对调整后初始导频位置确定模型进行训练，直至训练结束得到所述目标导频位置确定模型。
  18. 一种通信设备，其特征在于，所述设备包括：
    处理模块，用于获取初始导频信号，并基于所述初始导频信号确定第一信道状态信息，并将所述第一信道状态信息输入训练好的目标导频位置确定模型中，以得到RIS的目标导频位置信息；
    其中，所述目标导频位置确定模型为采用如权利要求1-4中任一项所述的导频位置确定模型的获取方法训练得到。
  19. 一种通信设备，其特征在于，所述设备包括：
    收发模块，用于向终端设备或网络设备发送初始导频信号，所述初始导频信号用于由所述通信设备进行信道估计得到第一信道状态信息，所述第一信道状态信息用于输入训练好的目标导频位置确定模型中，以得到所述RIS的目标导频位置信息。
  20. 一种通信设备，其特征在于，所述设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述设备执行如权利要求1至4中任一项所述的方法。
  21. 一种通信设备，其特征在于，所述设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述设备执行如权利要求5至11中任一项所述的方法。
  22. 一种通信设备，其特征在于，所述设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述设备执行如权利要求12至16中任一项所述的方法。
  23. 一种通信装置，其特征在于，包括：处理器和接口电路；
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求1至4中的任一项所述的方法。
  24. 一种通信装置，其特征在于，包括：处理器和接口电路；
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求5至11中的任一项所述的方法。
  25. 一种通信装置，其特征在于，包括：处理器和接口电路；
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求12至16中的任一项所述的方法。
  26. 一种计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如权利要求1至4中任一项所述的方法被实现。
  27. 一种计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如权利要求5至11中任一项所述的方法被实现。
  28. 一种计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如权利要求12至16中任一项所述的方法被实现。
PCT/CN2022/088321 2022-04-21 2022-04-21 导频位置确定模型的获取、导频位置确定方法及其装置 WO2023201668A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280001148.XA CN117280662A (zh) 2022-04-21 2022-04-21 导频位置确定模型的获取、导频位置确定方法及其装置
PCT/CN2022/088321 WO2023201668A1 (zh) 2022-04-21 2022-04-21 导频位置确定模型的获取、导频位置确定方法及其装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/088321 WO2023201668A1 (zh) 2022-04-21 2022-04-21 导频位置确定模型的获取、导频位置确定方法及其装置

Publications (1)

Publication Number Publication Date
WO2023201668A1 true WO2023201668A1 (zh) 2023-10-26

Family

ID=88418774

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/088321 WO2023201668A1 (zh) 2022-04-21 2022-04-21 导频位置确定模型的获取、导频位置确定方法及其装置

Country Status (2)

Country Link
CN (1) CN117280662A (zh)
WO (1) WO2023201668A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111131096A (zh) * 2019-12-03 2020-05-08 东南大学 基于可编程超表面的无线中继系统及其一种信道估计方法
CN114124173A (zh) * 2020-08-25 2022-03-01 华为技术有限公司 信道信息获取的方法、设备和存储介质
EP3962006A1 (en) * 2020-09-01 2022-03-02 Vestel Elektronik Sanayi ve Ticaret A.S. Channel estimation for configurable surfaces

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111131096A (zh) * 2019-12-03 2020-05-08 东南大学 基于可编程超表面的无线中继系统及其一种信道估计方法
CN114124173A (zh) * 2020-08-25 2022-03-01 华为技术有限公司 信道信息获取的方法、设备和存储介质
EP3962006A1 (en) * 2020-09-01 2022-03-02 Vestel Elektronik Sanayi ve Ticaret A.S. Channel estimation for configurable surfaces

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HEWANG WENG: "An Efficient Pilot Design of Sparse Channel Estimation for OFDM System ", JOURNAL OF HUNAN CITY UNIVERSITY(NATURAL SCIENCE), vol. 26, no. 5, 15 September 2017 (2017-09-15), pages 56 - 60, XP093102651, ISSN: 1672-7304, DOI: 10.3969/j.issn.1672-7304.2017.05.0012 *
MEHRAN S. ET AL.: "Pilot Pattern Design for Deep Learning-Based Channel Estimation in OFDM Systems", IEEE WIRELESS COMMUNICATIONS LETTERS, vol. 9, no. 12, 13 August 2020 (2020-08-13), XP011823718, DOI: 10.1109/LWC.2020.3016603 *
QUALCOMM INCORPORATED: "CSI enhancements: MTRP and FR1 FDD reciprocity", 3GPP DRAFT; R1-2103156, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG1, no. e-Meeting; 20210412 - 20210420, 7 April 2021 (2021-04-07), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052177956 *

Also Published As

Publication number Publication date
CN117280662A (zh) 2023-12-22

Similar Documents

Publication Publication Date Title
WO2023197226A1 (zh) 波束选择方法和装置
CN108604950A (zh) 数据传输方法及装置
CN115336191B (zh) 一种最大传输层数的调整的方法及其装置
CN114208354A (zh) 物理下行共享信道pdsch配置方法及装置
WO2023201668A1 (zh) 导频位置确定模型的获取、导频位置确定方法及其装置
WO2024098208A1 (zh) 波束指示方法及装置
WO2024050776A1 (zh) 一种信息确定方法/装置/设备及存储介质
WO2023184372A1 (zh) 上行信道的发送和接收的方法及装置
WO2023184451A1 (zh) 一种基于非码本的pusch发送、接收信息的方法及其装置
WO2023168575A1 (zh) 一种天线切换能力上报方法及其装置
WO2023184448A1 (zh) 一种基于非码本的pusch发送/接收信息的方法及其装置
WO2023184449A1 (zh) 一种发送tri的方法及其装置、接收tri的方法及其装置
WO2023168574A1 (zh) 一种天线切换能力上报方法及其装置
WO2024036570A1 (zh) 基于智能超表面的预编码方法及装置
WO2023168611A1 (zh) 一种附加解调参考信号dmrs的发送方法及其装置
WO2023077311A1 (zh) 一种智能超表面ris的预编码方法及其装置
WO2024027011A1 (zh) 系数指示方法及其装置
CN114503658B (zh) 一种测量报告上报方法和装置
WO2023201503A1 (zh) Mimo上行传输预编码码本的确定方法及其装置
WO2023201501A1 (zh) Mimo上行传输部分天线相干传输码字的确定方法及其装置
CN114026907B (zh) 一种上行波束的测量方法及其装置
WO2023184435A1 (zh) 一种确定波束信息的方法及装置
WO2024031719A1 (zh) 支持8Tx的基于码本的PUSCH传输的预编码指示方法及装置
WO2023150918A1 (zh) 一种波束管理的方法及其装置
WO2023115579A1 (zh) 一种人工智能ai服务提供方法和装置

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280001148.X

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22937904

Country of ref document: EP

Kind code of ref document: A1