WO2025246715A1 - 一种感知方法及相应装置 - Google Patents

一种感知方法及相应装置

Info

Publication number
WO2025246715A1
WO2025246715A1 PCT/CN2025/089464 CN2025089464W WO2025246715A1 WO 2025246715 A1 WO2025246715 A1 WO 2025246715A1 CN 2025089464 W CN2025089464 W CN 2025089464W WO 2025246715 A1 WO2025246715 A1 WO 2025246715A1
Authority
WO
WIPO (PCT)
Prior art keywords
sensing
quality
data
perception
communication device
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
PCT/CN2025/089464
Other languages
English (en)
French (fr)
Inventor
彭燕
罗嘉金
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of WO2025246715A1 publication Critical patent/WO2025246715A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information

Definitions

  • This application relates to the field of communication technology, specifically to a sensing method and corresponding device.
  • sensing nodes can detect targets in the environment by receiving and analyzing echo signals.
  • Echo signals refer to signals that are reflected, diffracted, or scattered by the target.
  • a perception process based on DL/large models typically includes: data collection nodes collecting perception data, then training a perception model based on the collected perception data, and the trained perception model can be applied to the perception process, such as analyzing echo signals.
  • This application provides a perception method for filtering high-quality perception data, thereby improving the efficiency and effectiveness of perception model training.
  • This application also provides corresponding apparatus, computer-readable storage media, and computer program products.
  • a first aspect of this application provides a sensing method applied to a first communication device, the method comprising:
  • the second sensing data is part or all of the first sensing data whose sensing quality meets the sensing quality requirements.
  • the sensing quality of the first sensing data is determined by the sensing quality strategy information.
  • the first communication device can be a sensing node, such as a receiver of the echo signal of the sensing signal, and/or a transmitter of the sensing signal.
  • This first communication device can be an access network device, a terminal device, or a chip within the access network device or the terminal device.
  • the second communication device can be a data collection node, used to collect sensing data for training the sensing model.
  • This data collection node can be an access network device, a terminal device, or a chip within the access network device or the terminal device; it can also be a server.
  • first sensing data there may be one or more first sensing data.
  • first sensing data When there are multiple first sensing data, the same sensing quality-related processing procedure can be performed on each first sensing data.
  • second sensing data There may also be one or more second sensing data.
  • the second sensing data can be a subset of the first sensing data. Of course, if each first sensing data satisfies the sensing quality requirements, then the second sensing data is the complete set of the first sensing data.
  • the processing related to perceived quality may include: determining the perceived quality of the first perceived data, determining whether the perceived quality of the first perceived data meets the perceived quality requirements, or determining at least one of the first parameters used to determine the perceived quality of the first perceived data; wherein the first parameter is used to determine the perceived quality of the first perceived data.
  • the perceived quality requirement can be one or more perceived quality thresholds. For example, if the perceived quality of the perceived data is greater than the perceived quality threshold, then the perceived quality of the perceived data meets the perceived quality requirement.
  • the strategy information for perceived quality refers to the strategy used to determine the perceived quality of perceived data. It can be represented by a function or given in a table. This application does not limit the specific form of the strategy for perceived quality.
  • the first communication device can, based on the first information sent by the second communication device, filter out second perceptual data from the first perceptual data that meets the perceptual quality requirements. In this way, using the second perceptual data to train the perceptual model can improve the efficiency and effectiveness of the perceptual model training, thereby also improving the accuracy of the perceptual model's inference.
  • the first information includes strategy information for perceived quality, which is used by the first communication device to determine the perceived quality of the first perceived data.
  • the perception quality of the first perception data is determined by the first communication device. Since there are usually multiple first communication devices and only one second communication device serving as a data collection node, having the first communication device determine the perception quality of the first perception data can distribute the computational burden on the second communication device.
  • the policy information includes data fields related to the training of the perceptual model, as well as the quality assessment policy corresponding to the data fields.
  • the quality assessment strategy can be a quality assessment relation, such as a relation expressed by a function; the quality assessment strategy can also be a series of pre-configured values or ranges of values, which can be linked in a table to determine the relationship between the parameters used to determine the perceived quality and the corresponding perceived quality.
  • describing the strategy information through data fields and the corresponding quality assessment strategies can improve the speed of determining perceived quality.
  • the data field includes at least one of the fields used to indicate input information, output information, time information, or configuration parameters related to the training of the perceptual model.
  • Input information refers to the information that needs to be input into the perception model during model training, such as the sampling information of the echo signal, which may include one or more information such as amplitude, time delay, angle, and distance.
  • Output information typically refers to the output information of the perception model. However, during model training, output information refers to the ground-truth label.
  • the ground-truth label and the input information form sample pairs, which are used as training samples during model training to adjust the gradient in the perception model.
  • the output information of the echo signal typically includes one or more of the following: scattering point information (e.g., at least one of the following: the location, amplitude, energy, or velocity of the scattering point), geometric information (at least one of the following: the shape or center of a polygon or polyhedron), or object material information (e.g., at least one of the following: material, texture, color, or electromagnetic parameters).
  • Time information is usually in the form of timestamps. Time information is often used to mark the time when the perception data was collected, and can be used to select perception data for appropriate time periods as training samples for perception models.
  • Configuration parameters typically include one or more of the following: transceiver antenna location, number of transceiver antennas, imaging area, bandwidth, or frequency band.
  • the content indicated by the data fields is different, and the associated quality assessment strategies are also different, which can perform targeted perceptual quality calculations on different dimensions of the first perceptual data.
  • the strategy information also includes the weights corresponding to the data fields, which are used to indicate the proportion of the perceived quality of the data field in the perceived quality of the first perceived data.
  • the proportion of perceived quality of data fields with higher importance in the total perceived quality can be increased, which is conducive to improving the reliability of the perceived quality of the first perceived data.
  • the first information further includes a perception quality requirement, which is used by the first communication device to determine whether the perception quality of the first perception data meets the perception quality requirement.
  • the first communication device can filter the first perception data to determine the second perception data that meets the perception quality requirements. This reduces the computational burden on the second communication device.
  • the method before sending the second sensing data to the second communication device, the method further includes:
  • the perception quality of the first perception data is sent to the second communication device.
  • the perception quality of the first perception data is used by the second communication device to determine whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is received from a second communication device, the sensing data request being used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first communication device sends the perception quality of the first perception data to the second communication device, which then determines whether the perception quality requirements are met.
  • This approach is more conducive to managing perception quality requirements and reduces the risk of leakage of perception quality requirements during transmission.
  • the first information includes parameter indication information, which indicates a first parameter for determining the perception quality of the first perception data; correspondingly, before sending perception data that meets the perception quality requirements to the second communication device, the method further includes:
  • the first parameter is used by the second communication device to determine the perception quality of the first perception data and whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request from a second communication device, the sensing data request being used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first information includes parameter indication information
  • the first parameter is a subset of the parameters required to determine the perceived quality of the first perceived data.
  • the second communication device records a set of parameters used to determine the sensing quality. These parameters no longer need to be obtained from the first communication device. In this way, the second communication device sends parameter indication information as needed, and the first communication device provides the first parameters according to the second communication device's requirements. This satisfies the second communication device's need to determine the sensing quality while reducing the amount of data transmitted between the two communication devices.
  • the output information is collected by an active reflector or obtained by estimating the first sensed data.
  • Collecting output information through an active reflector offers higher accuracy, but using the active reflector as the sensing target limits the source of the initial sensing data.
  • Estimating the initial sensing data yields slightly lower accuracy compared to collecting it through an active reflector, but the source of the initial sensing data is more diverse.
  • the configuration parameters include multiple types, wherein the probability density of the first type of configuration parameters is negatively correlated with the perceived quality of the first type of configuration parameters, and the probability density of the first type of configuration parameters is used to indicate the proportion of the first type of configuration parameters among the multiple types of configuration parameters, and the first type can be any one of the multiple types.
  • configuration parameters typically include one or more of the following: transceiver antenna location, number of transceiver antennas, imaging area, bandwidth, or frequency band, where each item represents a type.
  • the number of configuration parameters of different types is usually different.
  • the probability density of the first type of configuration parameter can be the ratio of the number of the first type of configuration parameter to the total number of configuration parameters of all types. If the probability density of the first type of configuration parameter is small, it indicates that the number of the first type of configuration parameter is small, and a higher sensing quality can be configured for that first type of configuration parameter. This is beneficial for subsequent collection of configuration parameters, increasing the amount of first type of configuration parameters collected, thereby achieving data balance among various types of configuration parameters.
  • a second aspect of this application provides a sensing method, the method comprising:
  • the system receives second sensing data from a first communication device.
  • the second sensing data is part or all of the first sensing data whose sensing quality meets the sensing quality requirements.
  • the sensing quality of the first sensing data is determined by sensing quality strategy information.
  • the second communication device can send first information to the first communication device, causing the first communication device to perform processing related to perception quality, thereby filtering out second perception data from the first perception data that meets the perception quality requirements.
  • training the perception model using the second perception data can improve the efficiency and effectiveness of the perception model training, and consequently improve the accuracy of the perception model's inference.
  • the first information includes strategy information for perceived quality, which is used by the first communication device to determine the perceived quality of the first perceived data.
  • the policy information includes data fields related to the training of the perceptual model, as well as the quality assessment policy corresponding to the data fields.
  • the data field includes at least one of the fields used to indicate input information, output information, time information, or configuration parameters related to the training of the perceptual model.
  • the strategy information also includes the weights corresponding to the data fields, which are used to indicate the proportion of the perceived quality of the data field in the perceived quality of the first perceived data.
  • the first information further includes a perception quality requirement, which is used by the first communication device to determine whether the perception quality of the first perception data meets the perception quality requirement.
  • the method before receiving the second sensing data from the first communication device, the method further includes:
  • the perception quality of the first perception data received from the first communication device is used by the second communication device to determine whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is sent to the first communication device.
  • the sensing data request is used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first information includes parameter indication information, which indicates a first parameter for determining the perception quality of the first sensing data; before receiving the second sensing data from the first communication device, the method further includes:
  • the device receives a first parameter from a first communication device.
  • the first parameter is used by the second communication device to determine the perception quality of the first perception data and whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is sent to the first communication device.
  • the sensing data request is used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first parameter is a subset of the parameters required to determine the perceived quality of the first perceived data.
  • the output information is collected by an active reflector or obtained by estimating the first sensed data.
  • the configuration parameters include multiple types, wherein the probability density of the first type of configuration parameters is negatively correlated with the perceived quality of the first type of configuration parameters, and the probability density of the first type of configuration parameters is used to indicate the proportion of the first type of configuration parameters among the multiple types of configuration parameters, and the first type can be any one of the multiple types.
  • a third aspect of this application provides a communication device, which can be a first communication device, including: a transceiver module and a processing module;
  • the transceiver module is used to receive first information from the second communication device, the first information being used to instruct the first communication device to perform processing related to the sensing quality on the first sensing data;
  • the processing module is used to perform processing related to the perception quality on the first perception data
  • the transceiver module is also used to send second sensing data to the second communication device.
  • the second sensing data is part or all of the first sensing data whose sensing quality meets the sensing quality requirements.
  • the sensing quality of the first sensing data is determined by the sensing quality strategy information.
  • the first information includes strategy information for perceived quality, which is used by the first communication device to determine the perceived quality of the first perceived data.
  • the policy information includes data fields related to the training of the perceptual model, as well as the quality assessment policy corresponding to the data fields.
  • the data field includes at least one of the fields used to indicate input information, output information, time information, or configuration parameters related to the training of the perceptual model.
  • the strategy information also includes the weights corresponding to the data fields, which are used to indicate the proportion of the perceived quality of the data field in the perceived quality of the first perceived data.
  • the first information further includes a perception quality requirement, which is used by the first communication device to determine whether the perception quality of the first perception data meets the perception quality requirement.
  • the transceiver module is also used for:
  • the perception quality of the first perception data is sent to the second communication device.
  • the perception quality of the first perception data is used by the second communication device to determine whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is received from a second communication device, the sensing data request being used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first information includes parameter indication information, which is used to indicate a first parameter for determining the perception quality of the first perception data; correspondingly, the transceiver module is also used for:
  • the first parameter is used by the second communication device to determine the perception quality of the first perception data and whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is received from a second communication device, the sensing data request being used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first parameter is a subset of the parameters required to determine the perceived quality of the first perceived data.
  • the output information is collected by an active reflector or obtained by estimating the first sensed data.
  • the configuration parameters include multiple types, wherein the probability density of the first type of configuration parameters is negatively correlated with the perceived quality of the first type of configuration parameters, and the probability density of the first type of configuration parameters is used to indicate the proportion of the first type of configuration parameters among the multiple types of configuration parameters, and the first type can be any one of the multiple types.
  • a fourth aspect of this application provides a communication device, which can be a second communication device that communicates with a first communication device, the communication device comprising: a transceiver module and a processing module;
  • the processing module is used to determine the first piece of information
  • the transceiver module is used for:
  • the system receives second sensing data from a first communication device.
  • the second sensing data is part or all of the first sensing data whose sensing quality meets the sensing quality requirements.
  • the sensing quality of the first sensing data is determined by sensing quality strategy information.
  • the first information includes strategy information for perceived quality, which is used by the first communication device to determine the perceived quality of the first perceived data.
  • the policy information includes data fields related to the training of the perceptual model, as well as the quality assessment policy corresponding to the data fields.
  • the data field includes at least one of the fields used to indicate input information, output information, time information, or configuration parameters related to the training of the perceptual model.
  • the strategy information also includes the weights corresponding to the data fields, which are used to indicate the proportion of the perceived quality of the data field in the perceived quality of the first perceived data.
  • the first information further includes a perception quality requirement, which is used by the first communication device to determine whether the perception quality of the first perception data meets the perception quality requirement.
  • the transceiver module is also used for:
  • the perception quality of the first perception data received from the first communication device is used by the second communication device to determine whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is sent to the first communication device.
  • the sensing data request is used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first information includes parameter indication information, which is used to indicate a first parameter for determining the perceived quality of the first perceived data; correspondingly, the transceiver module is also used to:
  • the device receives a first parameter from a first communication device.
  • the first parameter is used by the second communication device to determine the perception quality of the first perception data and whether the perception quality of the first perception data meets the perception quality requirements.
  • a sensing data request is sent to the first communication device.
  • the sensing data request is used to indicate that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the first parameter is a subset of the parameters required to determine the perceived quality of the first perceived data.
  • the output information is collected by an active reflector or obtained by estimating the first sensed data.
  • the configuration parameters include multiple types, wherein the probability density of the first type of configuration parameters is negatively correlated with the perceived quality of the first type of configuration parameters, and the probability density of the first type of configuration parameters is used to indicate the proportion of the first type of configuration parameters among the multiple types of configuration parameters, and the first type can be any one of the multiple types.
  • a fifth aspect of this application provides a communication device including a processor.
  • the processor is configured to call and run a computer program stored in a memory, causing the processor to implement as described in the first aspect or any of the implementations of the first aspect.
  • the communication device also includes a transceiver; the processor is also used to control the transceiver to send and receive signals.
  • the communication device includes a memory in which a computer program is stored.
  • the communication device mentioned in the fifth aspect above can be a device or a chip (system) in a device.
  • a sixth aspect of this application provides a communication device including a processor.
  • the processor is configured to invoke and execute a computer program stored in a memory, such that the processor implements as described in the second aspect or any of the implementations in the second aspect.
  • the communication device also includes a transceiver; the processor is also used to control the transceiver to send and receive signals.
  • the communication device includes a memory in which a computer program is stored.
  • the communication device described in the sixth aspect above can be a device or a chip (system) in a device.
  • the seventh aspect of this application provides a communication device, which may be a first communication device or a module or unit (e.g., a chip, a chip system, or a circuit) in the first communication device that corresponds to the execution of the methods/operations/steps/actions described in the first aspect.
  • a communication device which may be a first communication device or a module or unit (e.g., a chip, a chip system, or a circuit) in the first communication device that corresponds to the execution of the methods/operations/steps/actions described in the first aspect.
  • the eighth aspect of this application provides a communication device, which may be a second communication device or a module or unit (e.g., a chip, a chip system, or a circuit) in the second communication device that corresponds to the execution of the methods/operations/steps/actions described in the second aspect.
  • a communication device which may be a second communication device or a module or unit (e.g., a chip, a chip system, or a circuit) in the second communication device that corresponds to the execution of the methods/operations/steps/actions described in the second aspect.
  • the ninth aspect of this application provides a computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform an implementation as described in the first aspect or any of the first aspects.
  • the tenth aspect of this application provides a computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform an implementation as described in the second aspect or any of the second aspects.
  • the eleventh aspect of this application provides a computer program product including instructions that, when run on a computer, cause the computer to perform an implementation as described in the first aspect or any of the first aspects.
  • the twelfth aspect of this application provides a computer program product including instructions that, when run on a computer, cause the computer to perform an implementation as described in the second aspect or any of the second aspects.
  • the thirteenth aspect of this application provides a chip device including a processor for calling a program stored in a memory, such that the processor executes the first aspect or any implementation thereof.
  • the memory may be located inside or outside the chip device.
  • the fourteenth aspect of this application provides a chip device including a processor for calling a program stored in a memory, such that the processor executes the second aspect or any implementation thereof described above.
  • the memory may be located inside or outside the chip device.
  • the fifteenth aspect of this application provides a communication system, which includes a first communication device and a second communication device.
  • the first communication device is used to execute the first aspect or any one of the implementations of the first aspect
  • the second communication device is used to execute the second aspect or any one of the implementations of the second aspect.
  • Figure 1A is a schematic diagram of a communication system provided in an embodiment of this application.
  • Figure 1B is another structural schematic diagram of the communication system provided in an embodiment of this application.
  • Figure 2A is a schematic diagram of an example of a perception scenario provided in an embodiment of this application.
  • Figure 2B is another example schematic diagram of the perception scenario provided in the embodiments of this application.
  • Figure 3 is a schematic diagram of an embodiment of the sensing method provided in this application.
  • Figure 4A is a schematic diagram illustrating the relationship between signal-to-noise ratio and accuracy provided in an embodiment of this application;
  • Figure 4B is a schematic diagram showing the relationship between the position error and accuracy of the sensing node provided in an embodiment of this application.
  • Figure 5 is a schematic diagram of a scenario using an active reflector as a sensing target, provided in an embodiment of this application.
  • Figure 6 is a schematic diagram of another embodiment of the sensing method provided in this application.
  • Figure 7 is a schematic diagram of another embodiment of the sensing method provided in this application.
  • Figure 8 is a schematic diagram of another embodiment of the sensing method provided in this application.
  • Figure 9 is a structural schematic diagram of a communication device provided in an embodiment of this application.
  • Figure 10 is another structural schematic diagram of the communication device provided in an embodiment of this application.
  • Figure 11 is another structural schematic diagram of the communication device provided in an embodiment of this application.
  • This application provides a perception method for filtering high-quality perception data, thereby improving the efficiency and effectiveness of perception model training.
  • This application also provides corresponding apparatus, computer-readable storage media, and computer program products. These are described in detail below.
  • the technical solutions of this application embodiment can be applied to various communication systems, such as: satellite communication, 5th generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, universal mobile communication system (UMTS), mobile communication systems after 5G network (e.g., 6G mobile communication system), vehicle to everything (V2X) communication system, etc.
  • 5G 5th generation
  • NR new radio
  • LTE long term evolution
  • FDD frequency division duplex
  • TDD LTE time division duplex
  • UMTS universal mobile communication system
  • 6G mobile communication system vehicle to everything communication system, etc.
  • the aforementioned communication system also possesses sensing capabilities, making it a communication system with integrated sensing and communication (ISAC).
  • An integrated sensing and communication system means that the communication system can communicate through communication signals (which can also be described as communication channels) and perform sensing and measurement through sensing signals (which can also be described as sensing channels).
  • “perception” refers to using the transmission, reflection, and scattering of radio waves (radio frequency signals) to sense the surrounding environment and detect targets.
  • radio waves radio frequency signals
  • sensing signals are used to detect other vehicles or objects around vehicles
  • imaging systems sensing signals are used to image target points (buildings, vehicles, and other tangible objects) in the environment.
  • the communication system in this application can also be an industrial automation system or other communication systems that require sensing.
  • the communication system described in this application can be a communication system based on orthogonal frequency division multiplexing (OFDM) and/or time division multiplexing (TDM), or a communication system or communication and sensing system based on frequency modulated continuous wave (FMCW).
  • OFDM orthogonal frequency division multiplexing
  • TDM time division multiplexing
  • FMCW frequency modulated continuous wave
  • Sensing Node A communication device used for sensing, which may include a transmitter (Tx), a receiver (Rx), or a transceiver integrated communication device.
  • Transmitter A communication device that transmits communication signals and/or sensing signals (SS), also known as a transmitting node or transmitting device.
  • SS communication signals and/or sensing signals
  • Receiver A communication device that receives the echo signal of communication signals and/or sensing signals; it may also be called a receiving node or receiving device.
  • Sensing Signal This refers to the radio frequency signal used to sense the environment or target.
  • SS can be a sensing reference signal (SERS), a positioning reference signal (PRS), or a sounding reference signal (SRS), etc.
  • Sensing signals can be transmitted in the form of beams.
  • Echo signal (ES) refers to the signal after the sensing signal has been transmitted, reflected or scattered. The sensing result can be determined by measuring the echo signal, which can be received by beamforming.
  • a beam is a communication resource.
  • a beam can be wide, narrow, or other types of beams.
  • the technology used to form a beam can be beamforming technology or other techniques. Beamforming technology can specifically be digital beamforming technology, analog beamforming technology, and hybrid digital or analog beamforming technology. Different beams can be considered different resources.
  • the beam used to transmit signals can be called a transmission beam (Tx beam), and the beam used to receive signals can be called a reception beam (Rx beam).
  • the transmission beam refers to the distribution of signal strength in different directions in space after the signal is transmitted through the antenna, while the reception beam refers to the distribution of signal strength in different directions in space of the wireless signal received from the antenna.
  • Perceived target refers to the target object in the environment, such as buildings, vehicles or other objects.
  • Sensing data refers to data determined through echo signals.
  • AI Artificial Intelligence
  • AI is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.
  • AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence.
  • AI studies the design principles and implementation methods of various intelligent machines, enabling them to have the functions of perception, reasoning, and decision-making.
  • Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, and the fundamental theories of AI.
  • the application of artificial intelligence typically involves pre-designing AI models, then training these models with large amounts of data to obtain reasoning models suitable for different scenarios.
  • a perception model can be understood as an AI model applied to a perception scenario. It is trained using perception data and then used to perform inference processes within that scenario.
  • the data used for training the perception model typically needs to meet four criteria: accuracy, diversity, timeliness, and completeness. Accuracy measures the error of the training data; diversity measures the richness of the data features and distribution; timeliness determines the time the training data was generated and the time it was used to determine training data that fits a reasonable time interval; and completeness measures whether it can cover the feature fields required for training the perception model.
  • Figure 1A is a schematic diagram of the communication system provided in an embodiment of this application.
  • the communication system applicable to this application includes a first communication device and a second communication device.
  • the first communication device can be a sensing node, such as a receiver of the echo signal of the sensing signal, and/or a transmitter of the sensing signal.
  • This first communication device can be an access network device, a terminal device, or a chip within the access network device or a chip within the terminal device.
  • the second communication device can be a data collection node, used to collect sensing data for training the sensing model.
  • This data collection node can be an access network device, a terminal device, or a chip within the access network device or a chip within the terminal device; it can also be a server.
  • the perception method provided in this application can be applied to the process of collecting perception data during perception model training or inference.
  • Figure 1B is a schematic diagram of the scene during the training process of the perception model.
  • the communication system includes sensing nodes and data collection nodes. There can be multiple sensing nodes, and there can also be multiple data collection nodes. Figure 1B only shows one as an example.
  • the data collection node can send data collection instructions to the perception node, which can receive and process the echo signals to obtain perception data. The perception node can then send the perception data back to the data collection node.
  • the data collection node After receiving a large amount of sensory data, the data collection node can use this data as training samples to train the sensory model. Alternatively, the data collection node can send the received sensory data to the model training node, which can then use the sensory data to train the sensory model.
  • the trained perception model can be configured on perception nodes, and the perception nodes can use the perception model to perform perception data reasoning to obtain perception results.
  • the format of the sensing data can be understood by referring to Table 1 below.
  • measurement parameters can be fields used to indicate input information related to the training of the perception model
  • truth labels can be fields used to indicate input and output information related to the training of the perception model
  • quality accuracy indicators can be accuracy indicator fields related to measurement parameters and/or truth labels
  • timestamps are usually timestamps, and time information is usually used to mark the time of perception data collection, which can be used to select perception data within a suitable time period as training samples for the perception model.
  • Configuration parameters are fields used to indicate configurations related to the perception data.
  • the perception model in this application embodiment may include one or more AI modules, which are used to implement corresponding AI functions.
  • the AI modules deployed in different perception nodes may be the same or different.
  • Different AI modules can implement different functions based on different parameter configurations.
  • the model of an AI module may be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and/or dimension of input parameters), or output parameters (e.g., type and/or dimension of output parameters).
  • the bias in the activation function may also be referred to as the bias of the neural network.
  • An AI module can have one or more models.
  • a model can infer an output, which includes one or more parameters.
  • the learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.
  • the neural network of an AI model can be a neural network composed of an embedding layer and a multi-layer perceptron (MLP), or it can be a deep neural network (DNN), a convolutional neural network (CNN), recurrent neural networks (RNN), residual networks, or other neural networks.
  • DNN deep neural network
  • CNN convolutional neural network
  • RNN recurrent neural networks
  • residual networks or other neural networks.
  • a dual-base sensing scenario refers to a sensing scenario where the transmitter and receiver are separate, meaning the transmitter of the sensing signal and the receiver of the echo signal are not the same communication device.
  • a single-base sensing scenario refers to a sensing scenario where the transmitter of the sensing signal and the receiver of the echo signal belong to the same communication device.
  • a single-base sensing scenario can also be called a self-sensing scenario.
  • the dual-base sensing scenario can be understood by referring to Figure 2A.
  • this dual-base sensing scenario includes two transmitters, four receivers, a sensing target, and a data collection node.
  • the two transmitters are transmitter Tx201 and transmitter Tx202;
  • the four receivers are receiver Rx203, receiver Rx204, receiver Rx205, and receiver Rx206;
  • the sensing target can be various types of buildings or other objects;
  • the data collection node 207 can send data collection instructions to the receivers and receive sensing data from the receivers.
  • the transmitter Tx201 transmits a sensing signal SS1, and the echo signal ES1 generated by SS1 after passing through the building is received by the receiver Rx203.
  • Transmitter Tx202 transmits SS2, and SS2 generates ES2 after passing through a building, which is received by receiver Rx203; Transmitter Tx202 transmits SS3, and SS3 generates ES3 after passing through a building, which is received by receiver Rx204; Transmitter Tx202 transmits SS4, and SS4 generates ES4 after passing through a building, which is received by receiver Rx205; ES5 is received by receiver Rx206.
  • SS2, SS3, and SS4 can be sensing signals emitted from the same transmitting beam. However, sensing signals within the range of this transmitting beam will produce echo signals in different directions when encountering buildings at different locations, such as ES2, ES3, ES4, and ES5. Echo signals in different directions can be received by different receiving terminals.
  • SS2, SS3, and SS4 can also be sensing signals in different beams of the transmitting terminal Tx202.
  • echo signals generated by sensing signals transmitted from the same transmitter can be received by different receivers.
  • ES2 is received by receiver Rx203, ES3 by receiver Rx204, ES4 by receiver Rx205, and ES5 by receiver Rx206.
  • Echo signals generated by sensing signals transmitted from different transmitters can also be received by the same receiver, such as ES1 and ES2 being received by receiver Rx203.
  • echo signals generated by sensing signals transmitted from the same transmitter can also be received by only one receiver.
  • This application does not limit the correspondence between transmitters and receivers; it is related to the number of transmitters or receivers within a certain area.
  • the receiver can determine the sensing data based on its received echo signals.
  • the receiver can send relevant data from the received echo signals to other communication devices for them to determine the sensing data.
  • the receiving end will send the determined sensing data SD to the data collection node 207.
  • the receiving end Rx203 sends SD1 to the data collection node
  • the receiving end Rx204 sends SD2 to the data collection node
  • the receiving end Rx205 sends SD3 to the data collection node
  • the receiving end Rx206 sends SD4 to the data collection node.
  • the data collection node 207 can train the sensing model based on SD1, SD2, SD3 and SD4, or it can send SD1, SD2, SD3 and SD4 to other nodes or devices specifically used for training the sensing model.
  • the single-base sensing scenario can be understood by referring to Figure 2B.
  • the single-base sensing scenario can include four measurement nodes, a data collection node 207, and a sensing target.
  • the four measurement nodes are measurement node 211, measurement node 212, measurement node 213, and measurement node 214.
  • the measurement nodes can both transmit sensing signals and receive echo signals.
  • a measurement node When a measurement node senses a target in a measurement environment, it can transmit one or more beams. The sensing signals SS on these beams can detect different locations of the target. The measurement node then receives the corresponding echo signals ES, and can determine the sensing data based on the ES. Alternatively, the measurement node can also transmit relevant data from the received echo signals to other communication devices for them to determine the sensing data.
  • measurement node 211 transmits SS1, receives ES1, and determines the sensing data SD1 based on ES1;
  • measurement node 212 transmits SS2, receives ES21, and determines the sensing data SD2 based on ES2;
  • measurement node 213 transmits SS3, receives ES31, and determines the sensing data SD3 based on ES3;
  • measurement node 214 transmits SS4, receives ES41, and determines the sensing data SD4 based on ES4.
  • data collection node 207 can train a sensing model based on SD1, SD2, SD3, and SD4, or send SD1, SD2, SD3, and SD4 to other nodes or devices specifically used for training sensing models.
  • the receiving end, transmitting end, or measuring node can all be referred to as a sensing node.
  • the receiving end, transmitting end, and measuring node can all be terminal devices or access network devices, and the data collection node can also be a terminal device, access network device, or server.
  • This application does not limit the specific forms of the receiving end, transmitting end, measuring node, and data collection node shown in Figures 2A and 2B above.
  • the terminal equipment and access network equipment of this application are described below.
  • the terminal device can be a wireless terminal device capable of receiving scheduling and instruction information from access network devices.
  • the wireless terminal device can be a device that provides voice and/or data connectivity to the user, a handheld device with wireless connectivity, another processing device connected to a wireless modem, or a device with sensing capabilities.
  • Terminal equipment also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc.
  • UE user equipment
  • MS mobile station
  • MT mobile terminal
  • terminal devices include: mobile phones, tablets, laptops, PDAs, drones, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in vehicle-to-everything (V2X) communication, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes.
  • MIDs mobile internet devices
  • VR virtual reality
  • AR augmented reality
  • V2X vehicle-to-everything
  • wireless terminals in V2X can be in-vehicle equipment, vehicle-mounted equipment, in-vehicle modules, and vehicles themselves.
  • Wireless terminals in industrial control can be cameras, robots, etc.
  • Wireless terminals in smart homes can be televisions, air conditioners, robot vacuums, speakers, set-top boxes, etc.
  • Access network equipment is a device deployed in a radio access network (RAN) that provides wireless communication and/or sensing functions to terminal devices.
  • RAN radio access network
  • an access network device can be a RAN node that connects terminal devices to a wireless network.
  • Access network equipment can also be a device deployed in a RAN that can communicate with other access network devices and provide wireless communication and/or sensing functions between access network devices.
  • Access network equipment includes, but is not limited to: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), baseband unit (BBU), access point (AP), wireless relay node, wireless backhaul node, transmission point (TP), or transmission and reception point (TRP) in a wireless fidelity (WIFI) system, and can also be access network equipment in a 5G mobile communication system.
  • eNB evolved Node B
  • RNC radio network controller
  • NB Node B
  • BSC base station controller
  • BTS base transceiver station
  • home base station e.g., home evolved Node B, or home Node B, HNB
  • BBU baseband unit
  • AP access point
  • TP transmission point
  • TRP transmission and reception point
  • WIFI wireless fidelity
  • a next-generation NodeB gNB
  • transmission reception point TRP
  • transmission point TP
  • NR new radio
  • access network equipment can also be network nodes constituting a gNB or transmission point.
  • a baseband unit BBU
  • DU distributed unit
  • a gNB may include a centralized unit (CU) and a DU.
  • the gNB may also include an active antenna unit (AAU).
  • the CU implements some of the gNB's functions, and the DU implements others.
  • the CU handles non-real-time protocols and services, implementing the functions of the radio resource control (RRC) and packet data convergence protocol (PDCP) layers.
  • RRC radio resource control
  • PDCP packet data convergence protocol
  • the DU handles physical layer protocols and real-time services, implementing the functions of the radio link control (RLC), media access control (MAC), and physical (PHY) layers.
  • the AAU implements some physical layer processing functions, radio frequency processing, and related functions of the active antenna.
  • RRC layer Information from the RRC layer ultimately becomes information from the PHY layer, or is derived from information from the PHY layer. Therefore, in this architecture, higher-layer signaling (such as RRC layer signaling) can be considered to be sent by the DU, or by both the DU and the AAU.
  • access network equipment can be one or more of CU nodes, DU nodes, and AAU nodes.
  • a CU can be classified as an access network device in the radio access network (RAN) or as an access network device in the core network (CN); this application does not limit this classification.
  • the sensing method provided in this application embodiment includes:
  • the second communication device sends first information to the first communication device.
  • the first communication device receives the first information from the second communication device.
  • the first information is used to instruct the first communication device to perform processing related to perception quality on the first sensing data.
  • the processing related to perception quality may include: determining the perception quality of the first sensing data, determining whether the perception quality of the first sensing data meets the perception quality requirements, or determining at least one of the first parameters used to determine the perception quality of the first sensing data; wherein, the first parameter is used to determine the perception quality of the first sensing data.
  • the same sensing quality-related processing procedure can be performed on each first sensing data.
  • the first communication device performs processing related to the sensing quality on the first sensing data based on the first information.
  • the first communication device sends second sensing data to the second communication device.
  • the second communication device receives the second sensing data from the first communication device.
  • the second perception data is part or all of the first perception data whose perception quality meets the perception quality requirements.
  • the perception quality of the first perception data is determined by the perception quality strategy information.
  • the second sensing data may be a subset of the first sensing data.
  • the second sensing data is the complete set of the first sensing data.
  • the perceived quality requirement can be one or more perceived quality thresholds. For example, if the perceived quality of the perceived data is greater than the perceived quality threshold, then the perceived quality of the perceived data meets the perceived quality requirement.
  • the strategy information for perceived quality refers to the strategy used to determine the perceived quality of perceived data. It can be represented by a function or given in a table. This application does not limit the specific form of the strategy for perceived quality.
  • the perceived quality strategy information may include data fields related to the training of the perceived model, as well as the quality assessment strategies corresponding to those data fields.
  • the perceived quality strategy information can be understood by referring to Table 2 below, which is presented in tabular form.
  • each data field in Table 2 can be understood by referring to the corresponding explanations in Table 1. Specifically, the measurement parameters and truth labels are related to accuracy, time information is related to timeliness, and configuration parameters are related to diversity. Table 2 as a whole also reflects completeness.
  • v acc1 represents the sensing quality corresponding to the measurement parameter field
  • snr represents the signal-to-noise ratio (SNR) of the echo signal
  • the first communication device can determine the perceived quality vacc2 of the truth label field.
  • vtim represents the timeliness of the perceived data.
  • vdiv is related to the imaging area, which can also be called the region of interest (ROI), the location and/or number of receiving antennas (Rx), the location and/or number of transmitting antennas (Tx), the bandwidth (B), and the frequency band (f).
  • the perceived quality of the configuration parameter field is not limited to the one representation shown in Table 2.
  • the quality assessment strategy corresponding to the configuration parameters can be given in the form of a relationship between a single configuration parameter, a relationship between multiple configuration parameters, or other methods. As shown in Table 3, taking bandwidth as an example...
  • the perceived quality corresponding to different bandwidths can be determined by referring to Table 3.
  • this application is not limited to the method of determining perceived quality given for a single configuration parameter, such as in Table 3. It can also give the corresponding joint perceived quality for multiple configuration parameters. In this case, please refer to Table 4 for understanding.
  • the accuracy of the sensing data is related to SNR and the position error of the sensing node.
  • the relationship between the accuracy of the sensing data and SNR, and between the accuracy of the sensing data and the position error of the sensing node, can be understood by referring to Figures 4A and 4B.
  • the functional relationship between the accuracy of the sensing data and the SNR is basically an increasing function.
  • the accuracy of the sensing data increases with the increase of SNR.
  • the accuracy of the sensing data tends to stabilize.
  • the functional relationship between the accuracy of the sensing data and the position error of the sensing node is basically a decreasing function.
  • the accuracy of the sensing data decreases as the position error of the sensing node increases.
  • the accuracy of the sensing data is basically zero.
  • the ground-truth labels in Table 2 above can be collected by active reflectors or obtained by estimating the first sensing data.
  • the scenario collected by active reflectors can be understood by referring to Figure 5.
  • the collected ground-truth labels are based on information about the scattering point (at least one of the following: position, amplitude, energy, or velocity of the scattering point); geometric information (at least one of the following: shape or center of a polygon or polyhedron); and object material information (at least one of the following: material, texture, color, or electromagnetic parameters).
  • Information about scattering points, geometry, or object material can also be estimated by processing the first-sensor data.
  • the accuracy of the ground truth labels obtained through estimation is lower than that obtained by active reflectors, but the sources of first-sensor data are wide-ranging, which can improve the collection range of first-sensor data.
  • the timestamps in Table 2 are used to assess timeliness. When the time when the sensed data is generated meets the time requirements of the data collection node, the timeliness is high.
  • configuration parameters in Table 2 are used to assess diversity. As shown in Table 2, configuration parameters can include multiple types, and the number of configuration parameters of different types is usually different. To achieve a balance between different types of data, the collection volume of one or more data types can be adjusted by adjusting the perceived quality of different types of configuration parameters.
  • the probability density of the first type of configuration parameter can be determined first.
  • the probability density of the first type of configuration parameter can be the ratio of the number of first type configuration parameters to the total number of configuration parameters of various types.
  • the probability density of the first type of configuration parameter can be configured to be negatively correlated with its perceived quality.
  • a lower probability density of the first type of configuration parameter indicates a smaller number of first type configuration parameters, which can lead to a higher perceived quality for that first type of configuration parameter. This is beneficial for subsequent collection of configuration parameters, increasing the amount of first type configuration parameters collected, thereby achieving data balance among various types of configuration parameters.
  • This strategy information can be used to determine the perceived quality of the first perceived data. After determining the perceived quality, the perceived quality of the first perceived data and the perceived quality requirements can be used to filter out the second perceived data that meets the perceived quality requirements.
  • the perceived quality requirement can be one or more perceived quality thresholds.
  • This perceived quality requirement can be a requirement for the perceived quality of the aggregated data fields, or it can be a requirement for the perceived quality of each data field individually; this application does not limit this.
  • the perceived quality of the aggregated data fields can be referred to as the perceived quality of the perceived data.
  • v represents the perceived quality of the first sensing data
  • v acc1 represents the perceived quality of the measurement parameter data field
  • m acc1 represents the weight of the measurement parameter data field
  • v acc2 represents the perceived quality of the truth label data field
  • m acc2 represents the weight of the truth label data field
  • v div represents the perceived quality of the configuration parameter data field
  • m div represents the weight of the configuration parameter data field
  • v tim represents the perceived quality of the timestamp data field
  • m tim represents the weight of the timestamp data field; where the weight is used to indicate the proportion of the perceived quality of the data field in the perceived quality of the first sensing data.
  • the weights of each data field can be carried in the strategy information or be default values set by the first communication device.
  • the sensing quality only requires configuring a threshold value v_th .
  • the first sensing data where v > v_th can be determined as the second sensing data.
  • the perception quality requirements may need to be configured with multiple threshold values. Then, the perceived quality of each data field is compared with the corresponding threshold value. Then, the first perception data in which the perceived quality of one or more data fields is greater than the corresponding threshold value can be selected as the second perception data.
  • the first communication device can filter out second perception data that meets the perception quality requirements from the first perception data based on the first information sent by the second communication device. In this way, using the second perception data to train the perception model can improve the efficiency and effectiveness of the perception model training, and consequently improve the accuracy of the perception model's inference.
  • the primary information includes strategic information on perceived quality plus perceived quality requirements
  • the methods for sensing this situation include:
  • the data collection node sends the perception quality strategy information and perception quality requirements to the perception node.
  • the perception node receives the perception quality strategy information and perception quality requirements from the data collection node.
  • the strategy information for perceived quality can be understood by referring to Table 5.
  • Table 5 adds a third column, which is the weight of each data field.
  • the sensing node determines the sensing quality of the first sensing data based on the sensing quality strategy information.
  • the sensing node determines whether the sensing quality of the first sensing data meets the sensing quality requirements. If it does, then execute S604; otherwise, execute S605.
  • the process can involve the sensing node comparing v with v_th . If v > v_th , it can be determined that the sensing quality of the first sensing data meets the sensing quality requirements; if v ⁇ v_th , it can be determined that the sensing quality of the first sensing data does not meet the sensing quality requirements.
  • the sensing node sends second sensing data to the data collection node.
  • the data collection node receives the second sensing data from the sensing node.
  • the second perception data is part or all of the first perception data that meets the perception quality requirements.
  • the sensing node deletes the first sensing data whose sensing quality does not meet the sensing quality requirements.
  • the timely deletion of the first sensing data that does not meet the sensing quality requirements by the sensing node can free up the memory of the sensing node.
  • the data collection node After receiving the second sensing data, the data collection node can execute S606 or S607.
  • the data collection node uses the second sensing data to train the sensing model.
  • the data collection node sends the second sensing data to the model training node.
  • the model training node receives the second sensing data from the data collection node.
  • the model training node uses the second perception data to train the perception model.
  • the model training node can send the trained perception model to the perception node, so that the perception node can use the trained perception model to process the subsequent echo signal.
  • the second sensing data is selected from the first sensing data based on sensing quality strategy information and sensing quality requirements, resulting in higher-quality first sensing data. Therefore, the sensing model trained using the second sensing data can improve the training efficiency and quality of the sensing model.
  • the weights of each data field can be defaulted to 1 when determining the perception quality of the first perception data in S602.
  • the first information includes strategic information on perceived quality, but does not include perceived quality requirements
  • the sensing methods for this situation include:
  • the data collection node sends the perception quality policy information to the perception node.
  • the perception node receives the perception quality policy information from the data collection node.
  • the sensing node determines the sensing quality of the first sensing data based on the sensing quality strategy information.
  • the sensing node sends the sensing quality of the first sensing data to the data collection node.
  • the data collection node receives the sensing quality of the first sensing data from the sensing node.
  • the data collection node determines whether the perception quality of the first sensing data meets the perception quality requirements. If the perception quality of some or all of the first sensing data meets the perception quality requirements, then S705 is executed.
  • the process can involve the data collection node comparing v with v_th . If v > v_th , it can be determined that the perception quality of the first sensing data meets the perception quality requirements; if v ⁇ v_th , it can be determined that the perception quality of the first sensing data does not meet the perception quality requirements.
  • the data collection node can send an indication message to the sensing node.
  • This indication message indicates that the perception quality of the first sensing data does not meet the requirements.
  • the sensing node can then delete the first sensing data based on this indication message.
  • the data collection node sends a sensing data request to the sensing node, the sensing data request indicating that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the sensing node receives the sensing data request from the data collection node.
  • the data collection node sends a second sensing data request, carrying information such as the identifier and index of the second sensing data, to instruct the sensing data to send the second sensing data.
  • the sensing node selects the second sensing data from the first sensing data according to the sensing data request.
  • the sensing node sends second sensing data to the data collection node.
  • the data collection node receives the second sensing data from the sensing node.
  • S708 to S710 can be understood by referring to S606 to S608 above.
  • the sensing scheme provided in this application embodiment sends the sensing quality of the first sensing data to the data collection node, which then determines whether the sensing quality requirements are met. This is more conducive to managing the sensing quality requirements and reduces the risk of leakage of the sensing quality requirements during transmission.
  • the first information includes parameter indication information, which is used to indicate the first parameter for determining the perceived quality of the first perceived data.
  • the sensing methods for this situation include:
  • the data collection node sends parameter indication information to the sensing node.
  • the sensing node receives parameter indication information from the data collection node.
  • the first parameter indicated by this parameter indication information is a subset of the parameters required to determine the sensing quality of the first sensing data.
  • the parameters required to determine the sensing quality of the first sensing data typically include SNR, sensing node location error, ROI, location and number of receiving antennas, location and number of transmitting antennas, bandwidth, and frequency, etc. Some of these parameters may already be known to the data collection node. For example, the data collection node may already know the location, bandwidth, and frequency of the sensing node. Therefore, when issuing the parameter indication information, the data collection node only needs to send requests for unknown parameters, such as unknown SNR and ROI. This satisfies the data collection node's need to determine sensing quality while reducing the amount of data transmitted between the sensing node and the data collection node.
  • the sensing node determines the first parameter based on the parameter indication information.
  • the sensing node sends the first parameter to the data collection node.
  • the data collection node receives the first parameter from the sensing node.
  • the data collection node determines the perception quality of the first perception data based on the first parameter and the perception quality strategy information.
  • This step can be understood by referring to the description in section S602 above.
  • the data collection node determines whether the perception quality of the first sensing data meets the perception quality requirements. If it does, or if the perception quality of some or all of the first sensing data meets the perception quality requirements, then execute S806.
  • the data collection node sends a sensing data request to the sensing node, the sensing data request indicating that the sensing quality of the second sensing data meets the sensing quality requirements.
  • the sensing node receives the sensing data request from the data collection node.
  • the sensing node selects the second sensing data from the first sensing data according to the sensing data request.
  • the sensing node sends second sensing data to the data collection node.
  • the data collection node receives the second sensing data from the sensing node.
  • S809 to S811 can be understood by referring to S606 to S608 above.
  • the sensing scheme provided in this application embodiment when the first information includes parameter indication information, does not need to send the sensing quality strategy information and sensing quality requirements to the sensing node, which can reduce the risk of leakage of the sensing quality strategy information and sensing quality requirements during transmission.
  • FIG. 9 is a schematic diagram of the structure of the communication device in an embodiment of this application.
  • the communication device 900 can be used to execute the steps in the embodiments shown in Figures 3 to 8. Please refer to the relevant descriptions in the above method embodiments for details.
  • the communication device 900 includes a transceiver module 901 and a processing module 902.
  • the transceiver module 901 can implement the corresponding communication functions, and the processing module 902 is used for data processing.
  • the transceiver module 901 can also be referred to as a communication interface or a communication unit.
  • the communication device 900 may further include a storage unit, which can be used to store instructions and/or data.
  • the processing module 902 can read the instructions and/or data in the storage unit so that the communication device can implement the aforementioned method embodiments.
  • the communication device 900 can be used to perform the actions in the method embodiments described above.
  • the communication device 900 can be a terminal device or an access network device, or a component or module configurable in a terminal device or access network device.
  • the transceiver module 901 is used to perform the receiving-related operations in the method embodiments described above, and the processing module 902 is used to perform the processing-related operations in the method embodiments described above.
  • the transceiver module 901 may include a sending module and a receiving module.
  • the sending module is used to perform the sending operation in the above method embodiments.
  • the receiving module is used to perform the receiving operation in the above method embodiments.
  • the communication device 900 may include a transmitting module but not a receiving module.
  • the communication device 900 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the communication device 900 includes both transmitting and receiving actions.
  • the communication device 900 is used to perform the actions shown in the embodiment of Figure 3 above.
  • the transceiver module 901 is used to receive first information from the second communication device, the first information being used to instruct the first communication device to perform processing related to the sensing quality on the first sensing data;
  • Processing module 902 is used to perform processing related to perception quality on the first perception data
  • the transceiver module 901 is also used to send second sensing data to the second communication device.
  • the second sensing data is part or all of the first sensing data whose sensing quality meets the sensing quality requirements.
  • the sensing quality of the first sensing data is determined by the sensing quality strategy information.
  • the processing module 902 in the above embodiments can be implemented by at least one processor or processor-related circuitry.
  • the transceiver module 901 can be implemented by a transceiver or transceiver-related circuitry.
  • the transceiver module 901 can also be referred to as a communication unit or communication interface.
  • the storage unit can be implemented by at least one memory.
  • the communication device 1000 includes a processor 1010, the processor 1010 being coupled to a memory 1020, the memory 1020 being used to store computer programs or instructions and/or data, and the processor 1010 being used to execute the computer programs or instructions and/or data stored in the memory 1020, so that the methods in the above method embodiments are executed.
  • the communication device 1000 may include one or more processors 1010.
  • the communication device 1000 may further include a memory 1020.
  • the communication device 1000 may include one or more memory 1020.
  • the memory 1020 may be integrated with the processor 1010 or set separately.
  • the communication device 1000 may further include a transceiver 1030, which is used for receiving and/or transmitting signals.
  • the processor 1010 is used to control the transceiver 1030 to receive and/or transmit signals.
  • the communication device 1000 is used to implement the operations described in the above method embodiments.
  • processor 1010 is used to implement processing-related operations in the above method embodiments
  • transceiver 1030 is used to implement receiving-related operations in the above method embodiments.
  • This application also provides a communication device 1000, which can be a terminal device, an access network device, or a chip or module in a core network device.
  • This communication device 1000 can be used to perform the operations described in the above method embodiments.
  • FIG 11 shows a simplified structural diagram of the communication device.
  • the communication device includes a processor, a memory, and a transceiver.
  • the memory can store computer program code and may also store an AI module, which is used to implement AI-related functions.
  • the AI module can be implemented through software, hardware, or a combination of both.
  • the AI module can be a near real-time access network intelligent controller (RIC) or a non-real-time RIC.
  • the transceiver includes a transmitter 1031, a receiver 1032, an RF circuit (not shown in the figure), an antenna 1033, and input/output devices (not shown in the figure).
  • the processor is mainly used to process communication protocols and communication data, control the communication device, execute software programs, and process data from the software programs.
  • the memory is mainly used to store software programs and data.
  • the RF circuit is mainly used for the conversion between baseband signals and RF signals and for processing RF signals.
  • the antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves.
  • Input/output devices such as touch screens, displays, and keyboards, are mainly used to receive user input data and output data to the user. It should be noted that some types of communication devices may not have input/output devices.
  • the processor When data needs to be transmitted, the processor performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency (RF) circuit.
  • the RF circuit then processes the baseband signal and transmits it outward as an electromagnetic wave through the antenna.
  • the RF circuit receives the RF signal through the antenna, converts it into a baseband signal, and outputs the baseband signal to the processor.
  • the processor converts the baseband signal back into data and processes it.
  • Figure 11 only shows one memory, processor, and transceiver. In actual communication device products, there may be one or more processors and one or more memories.
  • the memory can also be called a storage medium or storage device, etc.
  • the memory can be set up independently of the processor or integrated with the processor; this application embodiment does not impose any limitations on this.
  • the antenna and radio frequency circuit with transceiver function can be regarded as the transceiver unit of the communication device, and the processor with processing function can be regarded as the processing unit of the communication device.
  • the communication device includes a processor 1010, a memory 1020, and a transceiver 1030.
  • the processor 1010 can also be called a processing unit, processing board, processing module, processing device, etc.
  • the transceiver 1030 can also be called a transceiver unit, transceiver, transceiver device, etc.
  • transceiver 1030 includes a receiver and a transmitter.
  • a transceiver may also be called a transceiver unit, transceiver circuit, etc.
  • a receiver may also be called a receiver unit, receiving circuit, etc.
  • a transmitter may also be called a transmitter, transmitting unit, or transmitting circuit, etc.
  • processor 1010 is used to execute the processing actions in the embodiment shown in FIG3, and transceiver 1030 is used to execute the transmit and receive actions in FIG3.
  • transceiver 1030 is used to execute the transmit and receive operation of step S301 in the embodiment shown in FIG3.
  • Processor 1010 is used to execute the processing operations of steps S302 and S303 in the embodiment shown in FIG3.
  • Figure 11 is merely an example and not a limitation, and the communication device described above, including the transceiver unit and the processing unit, may not depend on the structure shown in Figure 11.
  • the chip When the communication device 1000 is a chip, the chip includes a processor, a memory, and a transceiver.
  • the transceiver can be an input/output circuit or a communication interface;
  • the processor can be a processing unit integrated on the chip, a microprocessor, or an integrated circuit.
  • the transmitting operation of the communication device can be understood as the chip's output, and the receiving operation of the communication device in the above method embodiments can be understood as the chip's input.
  • This application also provides a computer-readable storage medium storing computer instructions for implementing the methods in the above-described method embodiments.
  • the computer program when executed by a computer, it enables the computer to implement the methods performed in the above method embodiments.
  • This application also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the method described in the above method embodiments.
  • This application also provides a communication system, which includes the access network device and terminal device described in the above embodiments.
  • This application also provides a chip device, including a processor, for calling computer programs or computer instructions stored in a memory to cause the processor to execute the methods of the embodiments shown in Figures 3 to 8 above.
  • the input of the chip device corresponds to the receiving operation in the embodiments shown in Figures 3 to 8
  • the output of the chip device corresponds to the transmitting operation in the embodiments shown in Figures 3 to 8.
  • the processor is coupled to the memory via an interface.
  • the chip device may also include a memory that stores computer programs or computer instructions.
  • the processor mentioned above can be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of a program for controlling the methods of the embodiments shown in Figures 3 to 8.
  • the memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM).
  • the disclosed systems, apparatuses, and methods can be implemented in other ways.
  • the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods.
  • multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
  • the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.
  • the units described as separate components may or may not be physically separate.
  • the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
  • the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
  • the integrated unit can be implemented in hardware or as a software functional unit.
  • the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or an access network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
  • the aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

Landscapes

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

Abstract

本申请提供一种感知方法，可以应用于通信感知一体化ISAC的通信系统，该方法包括：感知节点可以依据数据收集节点的指示，对第一感知数据执行与感知质量相关的处理。这样，感知节点和数据收集节点配合可以从第一感知数据中筛选出感知质量满足感知质量要求的第二感知数据。这样，使用第二感知数据训练感知模型，就可以提高感知模型训练的效率和效果，进而也能提高感知模型推理的准确度。

Description

一种感知方法及相应装置
本申请要求于2024年05月28日提交国家知识产权局、申请号为202410681726.X、申请名称为“一种感知方法及相应装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，具体涉及一种感知方法及相应装置。
背景技术
无线感知技术中，感知节点可以通过接收回波信号，并分析回波信号来实现对环境中感知目标的感知。回波信号指的是感知信号被感知目标反射、衍射或散射的信号。
随着人工智能(artificial intelligence，AI)技术的发展，深度学习(deep learning，DL)/大模型在各个领域都展现出了较强的能力，在感知领域也得到较多关注。基于DL/大模型的感知过程通常包括：数据收集节点收集感知数据，然后根据收集到的感知数据进行感知模型的训练，训练好的感知模型可以应用于感知过程，如：分析回波信号。
目前用于感知模型训练的感知数据的来源多样，这些感知数据往往存在噪声、时效性等问题，质量较低。
发明内容
本申请提供一种感知方法，用于筛选出高质量的感知数据，进而可以提高感知模型训练的效率和效果。本申请还提供了相应装置、计算机可读存储介质和计算机程序产品等。
本申请第一方面提供感知方法，该方法应用于第一通信装置，该方法包括：
接收来自第二通信装置的第一信息，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理；
向第二通信装置发送第二感知数据，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
本申请中，第一通信装置可以是感知节点，如：感知信号的回波信号的接收端，或/和，感知信号的发射端等。该第一通信装置可以是接入网设备、终端设备或者接入网设备中的芯片、终端设备中的芯片。第二通信装置可以是数据收集节点，数据收集节点用于收集感知模型训练的感知数据的节点。该数据收集节点可以是接入网设备、终端设备或者接入网设备中的芯片、终端设备中的芯片，该数据收集节点可以是也可以是服务器。
本申请中，第一感知数据可以有一个或多个，当第一感知数据有多个时，对每个第一感知数据都可以执行相同的感知质量相关的处理过程。第二感知数据可以有一个或多个，第二感知数据可以为第一感知数据的子集，当然，若每个第一感知数据都满足感知质量要求，则第二感知数据为第一感知数据的全集。
本申请中，与感知质量相关的处理可以包括：确定第一感知数据的感知质量、确定第一感知数据的感知质量是否满足感知质量要求、或者，确定用于确定第一参数中的至少一项；其中，第一参数用于确定第一感知数据的感知质量。
本申请中，感知质量要求可以是一个或多个感知质量的门限值，如：感知数据的感知质量大于感知质量的门限值，即为该感知数据的感知质量满足感知质量要求。
本申请中，感知质量的策略信息指的是用于确定感知数据的感知质量的策略，可以通过函数的方式表示，也可以通过表格的方式给出，本申请不限定感知质量的策略的具体形式。
该第一方面中，第一通信装置可以基于第二通信装置发送的第一信息，从第一感知数据中筛选出感知质量满足感知质量要求的第二感知数据。这样，使用第二感知数据训练感知模型，就可以提高感知模型训练的效率和效果，进而也能提高感知模型推理的准确度。
一种可能的实现方式中，第一信息包括感知质量的策略信息，策略信息用于第一通信装置确定第一感知数据的感知质量。
该种可能的实现方式中，若第一信息中包括感知质量的策略信息，则第一感知数据的感知质量由第一通信装置确定。因为第一通信装置通常有多个，作为数据收集节点的第二通信装置通常有一个，由第一通信装置确定第一感知数据的感知质量，可以分散第二通信装置的计算压力。
一种可能的实现方式中，策略信息包括感知模型训练相关的数据字段，以及数据字段对应的质量评估策略。
本申请中，质量评估策略可以是质量评估关系式，如：通过函数的方式表示的关系式；质量评估策略也可以预配置好的一些列数值或数值范围，可以通过表格的形式来关联用于确定感知质量的参数与对应的感知质量之间的关系。
该种可能的实现方式中，通过数据字段，以及数据字段对应的质量评估策略的方式描述策略信息，可以提高确定感知质量的速度。
一种可能的实现方式中，数据字段包括用于指示感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
本申请中，数据字段可以有一个或多个，不同的数据字段指示的内容不同。
输入信息指的是模型训练过程中要输入到感知模型中的信息，如：回波信号的采样信息，可以包括幅度、时延、角度等信息、距离像中的一个或多个。
输出信息通常指的是感知模型的输出信息，但在模型训练过程中，输出信息指的是真值标签(Ground-truth label)，真值标签与输入信息构成样本对，在模型训练的过程中都作为训练样本，用于调整感知模型中的梯度。回波信号的输出信息通常包括散射点信息(如：散射点的位置、幅度、能量或速度等至少一项)、几何信息(多边形或多面体的形状或中心等中的至少一项)或物体材质信息(如：材料、纹理、颜色或电磁参数等中的至少一项)中的一项或多项。
时间信息通常为时间戳，时间信息通常用于标记感知数据收集的时间，可以用于筛选合适时间段的感知数据作为感知模型的训练样本。
配置参数通常可以包括收发天线位置，收发天线数目、成像区域、带宽或频段中的一项或多项。
该种可能的实现方式中，数据字段所指示的内容不同，所关联的质量评估策略也不同，可以对第一感知数据的不同维度进行针对性的感知质量计算。
一种可能的实现方式中，策略信息还包括数据字段对应的权重，权重用于指示数据字段的感知质量在第一感知数据的感知质量中的占比。
该种可能的实现方式中，通过权重指示不同数据字段的感知质量占比，可以提高重要性较高的数据字段的感知质量在总的感知质量中的占比，有利于提高第一感知数据的感知质量的可靠性。
一种可能的实现方式中，第一信息还包括感知质量要求，感知质量要求用于第一通信装置确定第一感知数据的感知质量是否满足感知质量要求。
该种可能的实现方式中，第一信息还包括感知质量要求时，可以由第一通信装置对第一感知数据进行筛选，从而确定满足感知质量要求的第二感知数据。这样，可以分散第二通信装置的计算压力。
一种可能的实现方式中，在向第二通信装置发送第二感知数据之前，该方法还包括：
向第二通信装置发送第一感知数据的感知质量，第一感知数据的感知质量用于第二通信装置确定第一感知数据的感知质量是否满足感知质量要求；
接收来自第二通信装置的感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
该种可能的实现方式中，第一通信装置将第一感知数据的感知质量发送给第二通信装置，由第二通信装置判断是否满足感知质量要求，更有利于管理感知质量要求，降低感知质量要求在传输过程中泄露的风险。
一种可能的实现方式中，第一信息包括参数指示信息，参数指示信息用于指示确定第一感知数据的感知质量的第一参数；对应地，在向第二通信装置发送满足感知质量要求的感知数据之前，该方法还包括：
向第二通信装置发送第一参数，第一参数用于第二通信装置确定第一感知数据的感知质量，并确定第一感知数据的感知质量是否满足感知质量要求；
接收来自第二通信装置的感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
该种可能的实现方式中，第一信息包括参数指示信息时，不需要将感知质量的策略信息和感知质量要求发送给第一通信装置，可以降低感知质量的策略信息和感知质量要求在传输过程中泄露的风险。
一种可能的实现方式中，第一参数为用于确定第一感知数据的感知质量所需参数的子集。
该种可能的实现方式中，第二通信装置中会记录有一部分用于确定感知质量的参数，针对这部分参数，不再需要从第一通信装置获取。这样，第二通信装置按需求发送参数指示信息，第一通信装置按照第二通信装置的需求提供第一参数，既可以满足第二通信装置确定感知质量的需求，又可以减少第一通信装置与第二通信装置之间的传输的数据量。
一种可能的实现方式中，输出信息通过有源反射器收集或者通过估计第一感知数据得到。
该种可能的实现方式中，针对输出信息的收集可以有多种方式得到，通过有源反射器收集的输出信息的准确度较高，但将有源反射器作为感知目标，相对限定了第一感知数据的来源。通过估计第一感知数据的准确度相比于通过有源反射器收集的方式低一些，但第一感知数据的来源广泛。
一种可能的实现方式中，配置参数包括多种类型，其中，第一类型的配置参数的概率密度与第一类型的配置参数的感知质量负相关，第一类型的配置参数的概率密度用于指示第一类型的配置参数在多种类型的配置参数中的占比，第一类型为多种类型中的任意一种。
该种可能的实现方式中，配置参数通常可以包括收发天线位置，收发天线数目、成像区域、带宽或频段中的一项或多项，其中，每项都为一种类型。不同类型的配置参数的数量通常不同。第一类型的配置参数的概率密度可以是第一类型的配置参数的数量在多种类型的配置参数的总数量的比值。若第一类型的配置参数的概率密度小表示第一类型的配置参数的数量少，则可以为该第一类型的配置参数配置较高的感知质量。这样，有利于后续收集配置参数，提高第一类型的配置参数的收集量，从而实现各种类型的配置参数的数据均衡。
本申请第二方面提供一种感知方法，该方法包括：
向第一通信装置发送第一信息，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理；
接收来自第一通信装置的第二感知数据，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
该第二方面中，第二通信装置可以通过给第一通信装置发送的第一信息，使得第一通信装置执行与感知质量相关的处理，进而从第一感知数据中筛选出感知质量满足感知质量要求的第二感知数据。这样，使用第二感知数据训练感知模型，就可以提高感知模型训练的效率和效果，进而也能提高感知模型推理的准确度。
一种可能的实现方式中，第一信息包括感知质量的策略信息，策略信息用于第一通信装置确定第一感知数据的感知质量。
一种可能的实现方式中，策略信息包括感知模型训练相关的数据字段，以及数据字段对应的质量评估策略。
一种可能的实现方式中，数据字段包括用于指示感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
一种可能的实现方式中，策略信息还包括数据字段对应的权重，权重用于指示数据字段的感知质量在第一感知数据的感知质量中的占比。
一种可能的实现方式中，第一信息还包括感知质量要求，感知质量要求用于第一通信装置确定第一感知数据的感知质量是否满足感知质量要求。
一种可能的实现方式中，在接收来自第一通信装置的第二感知数据之前，该方法还包括：
接收来自第一通信装置的第一感知数据的感知质量，第一感知数据的感知质量用于第二通信装置确定第一感知数据的感知质量是否满足感知质量要求；
向第一通信装置发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一信息包括参数指示信息，参数指示信息用于指示确定第一感知数据的感知质量的第一参数；在接收来自第一通信装置的第二感知数据之前，该方法还包括：
接收来自第一通信装置的第一参数，第一参数用于第二通信装置确定第一感知数据的感知质量，并确定第一感知数据的感知质量是否满足感知质量要求；
向第一通信装置发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一参数为用于确定第一感知数据的感知质量所需参数的子集。
一种可能的实现方式中，输出信息通过有源反射器收集或者通过估计第一感知数据得到。
一种可能的实现方式中，配置参数包括多种类型，其中，第一类型的配置参数的概率密度与第一类型的配置参数的感知质量负相关，第一类型的配置参数的概率密度用于指示第一类型的配置参数在多种类型的配置参数中的占比，第一类型为多种类型中的任意一种。
本申请第三方面提供一种通信装置，该通信装置可以为第一通信装置，包括：收发模块和处理模块；
收发模块，用于接收来自第二通信装置的第一信息，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理；
处理模块，用于对第一感知数据执行与感知质量相关的处理；
收发模块，还用于向第二通信装置发送第二感知数据，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
一种可能的实现方式中，第一信息包括感知质量的策略信息，策略信息用于第一通信装置确定第一感知数据的感知质量。
一种可能的实现方式中，策略信息包括感知模型训练相关的数据字段，以及数据字段对应的质量评估策略。
一种可能的实现方式中，数据字段包括用于指示感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
一种可能的实现方式中，策略信息还包括数据字段对应的权重，权重用于指示数据字段的感知质量在第一感知数据的感知质量中的占比。
一种可能的实现方式中，第一信息还包括感知质量要求，感知质量要求用于第一通信装置确定第一感知数据的感知质量是否满足感知质量要求。
一种可能的实现方式中，收发模块还用于：
向第二通信装置发送第一感知数据的感知质量，第一感知数据的感知质量用于第二通信装置确定第一感知数据的感知质量是否满足感知质量要求；
接收来自第二通信装置的感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一信息包括参数指示信息，参数指示信息用于指示确定第一感知数据的感知质量的第一参数；对应地，收发模块还用于：
向第二通信装置发送第一参数，第一参数用于第二通信装置确定第一感知数据的感知质量，并确定第一感知数据的感知质量是否满足感知质量要求；
接收来自第二通信装置的感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一参数为用于确定第一感知数据的感知质量所需参数的子集。
一种可能的实现方式中，输出信息通过有源反射器收集或者通过估计第一感知数据得到。
一种可能的实现方式中，配置参数包括多种类型，其中，第一类型的配置参数的概率密度与第一类型的配置参数的感知质量负相关，第一类型的配置参数的概率密度用于指示第一类型的配置参数在多种类型的配置参数中的占比，第一类型为多种类型中的任意一种。
本申请第四方面提供一种通信装置，该通信装置可以为与第一通信装置通信的第二通信装置，该通信装置包括：收发模块和处理模块；
处理模块，用于确定第一信息；
收发模块用于：
向第一通信装置发送第一信息，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理；
接收来自第一通信装置的第二感知数据，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
一种可能的实现方式中，第一信息包括感知质量的策略信息，策略信息用于第一通信装置确定第一感知数据的感知质量。
一种可能的实现方式中，策略信息包括感知模型训练相关的数据字段，以及数据字段对应的质量评估策略。
一种可能的实现方式中，数据字段包括用于指示感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
一种可能的实现方式中，策略信息还包括数据字段对应的权重，权重用于指示数据字段的感知质量在第一感知数据的感知质量中的占比。
一种可能的实现方式中，第一信息还包括感知质量要求，感知质量要求用于第一通信装置确定第一感知数据的感知质量是否满足感知质量要求。
一种可能的实现方式中，收发模块还用于：
接收来自第一通信装置的第一感知数据的感知质量，第一感知数据的感知质量用于第二通信装置确定第一感知数据的感知质量是否满足感知质量要求；
向第一通信装置发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一信息包括参数指示信息，参数指示信息用于指示确定第一感知数据的感知质量的第一参数；对应地，收发模块还用于：
接收来自第一通信装置的第一参数，第一参数用于第二通信装置确定第一感知数据的感知质量，并确定第一感知数据的感知质量是否满足感知质量要求；
向第一通信装置发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。
一种可能的实现方式中，第一参数为用于确定第一感知数据的感知质量所需参数的子集。
一种可能的实现方式中，输出信息通过有源反射器收集或者通过估计第一感知数据得到。
一种可能的实现方式中，配置参数包括多种类型，其中，第一类型的配置参数的概率密度与第一类型的配置参数的感知质量负相关，第一类型的配置参数的概率密度用于指示第一类型的配置参数在多种类型的配置参数中的占比，第一类型为多种类型中的任意一种。
本申请第五方面提供一种通信装置，该通信装置包括处理器。该处理器用于调用并运行存储器中存储的计算机程序，使得处理器实现如第一方面或第一方面中的任意一种实现方式。
可选的，该通信装置还包括收发器；该处理器还用于控制该收发器收发信号。
可选的，该通信装置包括存储器，该存储器中存储有计算机程序。
上述第五方面的通信装置可以为设备或设备中的芯片(系统)。
本申请第六方面提供一种通信装置，该通信装置包括处理器。该处理器用于调用并运行存储器中存储的计算机程序，使得处理器实现如第二方面或第二方面中的任意一种实现方式。
可选的，该通信装置还包括收发器；该处理器还用于控制该收发器收发信号。
可选的，该通信装置包括存储器，该存储器中存储有计算机程序。
上述第六方面所述的通信装置可以为设备或设备中的芯片(系统)。
本申请第七方面提供一种通信装置，该通信装置可以为第一通信装置，也可以是第一通信装置中执行第一方面中所描述的方法/操作/步骤/动作所一一对应的模块或单元(例如，芯片，或者芯片系统，或者电路)。
本申请第八方面提供一种通信装置，该通信装置可以为第二通信装置，也可以是第二通信装置中执行第二方面中所描述的方法/操作/步骤/动作所一一对应的模块或单元(例如，芯片，或者芯片系统，或者电路)。
本申请第九方面提供一种计算机可读存储介质，包括计算机指令，当该计算机指令在计算机上运行时，使得计算机执行如第一方面或第一方面中的任意一种实现方式。
本申请第十方面提供一种计算机可读存储介质，包括计算机指令，当该计算机指令在计算机上运行时，使得计算机执行如第二方面或第二方面中的任意一种实现方式。
本申请第十一方面提供一种包括指令的计算机程序产品，当其在计算机上运行时，使得该计算机执行如第一方面或第一方面中的任意一种实现方式。
本申请第十二方面提供一种包括指令的计算机程序产品，当其在计算机上运行时，使得该计算机执行如第二方面或第二方面中的任意一种实现方式。
本申请第十三方面提供一种芯片装置，包括处理器，用于调用存储器中存储的程序，以使得该处理器执行上述第一方面或第一方面中的任意一种实现方式。
可选的，上述存储器位于芯片装置内部或外部。
本申请第十四方面提供一种芯片装置，包括处理器，用于调用存储器中存储的程序，以使得该处理器执行上述第二方面或第二方面中的任意一种实现方式。
可选的，上述存储器位于芯片装置内部或外部。
本申请第十五方面提供一种通信系统，该通信系统包括第一通信装置和第二通信装置，该第一通信装置用于执行上述第一方面或第一方面中的任意一种实现方式，该第二通信装置用于执行上述第二方面或第二方面中的任意一种实现方式。
其中，第二方面、第三方面或第四方面，或第二方面、第三方面或第四方面任一可能的实现方式，以及第五方面至第十五方面所带来的技术效果可参见第一方面或第一方面不同可能实现方式所带来的技术效果，此处不再赘述。
附图说明
图1A是本申请实施例提供的通信系统的一结构示意图；
图1B是本申请实施例提供的通信系统的另一结构示意图；
图2A是本申请实施例提供的感知场景的一示例示意图；
图2B是本申请实施例提供的感知场景的另一示例示意图；
图3是本申请实施例提供的感知方法的一实施例示意图；
图4A是本申请实施例提供的信噪比与准确性的一关系示意图；
图4B是本申请实施例提供的感知节点的位置误差与准确性的一关系示意图；
图5是本申请实施例提供的通过有源反射器作为感知目标的一场景示意图；
图6是本申请实施例提供的感知方法的另一实施例示意图；
图7是本申请实施例提供的感知方法的另一实施例示意图；
图8是本申请实施例提供的感知方法的另一实施例示意图；
图9是本申请实施例提供的通信装置的一结构示意图；
图10是本申请实施例提供的通信装置的另一结构示意图；
图11是本申请实施例提供的通信装置的另一结构示意图。
具体实施方式
下面结合附图，对本申请的实施例进行描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。本领域普通技术人员可知，随着技术发展和新场景的出现，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。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本申请实施例提供一种感知方法，用于筛选出高质量的感知数据，进而可以提高感知模型训练的效率和效果。本申请还提供了相应装置、计算机可读存储介质和计算机程序产品等。以下分别进行详细说明。
本申请实施例的技术方案可以应用于各种通信系统，例如：卫星通信、第五代(5th generation，5G)系统或新无线(new radio，NR)、长期演进(long term evolution，LTE)系统、LTE频分双工(frequency division duplex，FDD)系统、LTE时分双工(time division duplex，TDD)、通用移动通信系统(universal mobile telecommunication system，UMTS)、5G网络之后的移动通信系统(例如，6G移动通信系统)、车联网(vehicle to everything，V2X)通信系统等。
上述通信系统除了具有更强的通信能力，也具备感知的能力，是具有通信感知一体化(integrated sensing and communication，ISAC)的通信系统，通信感知一体化的通信系统指的是该通信系统既可以通过通信信号(通信信号也可以描述为通信信道)进行通信，还可以通过感知信号(感知信号也可以描述为感知信道)进行感知测量。
本申请中，“感知”指的是利用无线电波(射频信号)的传输、反射，散射来感知周围环境，探测目标等，例如：在车联网中通过感知信号来感知其他车辆或者车辆周围的物体；在成像系统中，利用感知信号来对环境中的目标点(建筑物、车辆等有形物体)成像。当然，本申请的通信系统还可以是工业自动化的系统等会涉及到需要感知的通信系统。
本申请的通信系统可以是基于正交频分复用(orthogonal frequency division multiplexing，OFDM)和/或时分复用(time division multiplexing，TDM)的通信系统，也可以是基于频率调制连续波(frequency modulated continuous waveform，FMCW)的通信系统或通信和感知系统。
为便于理解，下面对本申请实施例涉及到的技术术语做简单介绍：
1.感知节点：用于感知的通信装置，可以包括发射端(transmission，Tx)、接收端(receiving，Rx)或者收发一体的通信装置。
2.发射端：发射通信信号或/和感知信号(sensing signal，SS)的通信装置，也可以称为发射节点或发射装置。
3.接收端：接收通信信号和/或感知信号的回波信号的通信装置，也可以称为接收节点或接收装置。
4.感知信号：指的是用于感知环境或感知目标的射频信号。SS可以是感知参考信号(sensing reference signal，SERS)、定位参考信号(positioning reference signal，PRS)或者探测参考信号(sounding reference signal，SRS)等，感知信号可以以波束的形式发送。
5.回波信号(echo signal，ES)：指的是感知信号被传输、反射或散射后的信号，可以通过对回波信号的测量确定感知结果，回波信号可以通过波束接收。
6.波束(beam)：波束是一种通信资源。波束可以是宽波束，或者窄波束，或者其他类型波束，形成波束的技术可以是波束成形技术或者其他技术手段。波束成形技术可以具体为数字波束成形技术、模拟波束成形技术和混合数字或模拟波束成形技术。不同的波束可以认为是不同的资源。用于发射信号的波束可以称为发射波束(transmission beam，Tx beam)，用于接收信号的波束可以称为接收波束(reception beam，Rx beam)，发射波束可以是指信号经天线发射出去后在空间不同方向上形成的信号强度的分布，接收波束可以是指从天线上接收到的无线信号在空间不同方向上的信号强度分布。
7.感知目标：指的是环境中的目标物，如：建筑物、车辆或其他物体等。
8.感知数据(sensing data，SD)：指的是通过回波信号确定出的数据。
9.人工智能(artificial intelligence，AI)：AI是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，AI是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式作出反应的智能机器。AI也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。人工智能领域的研究包括机器人，自然语言处理，计算机视觉，决策与推理，人机交互，推荐与搜索，AI基础理论等。人工智能的应用通常通过预先设计AI模型，然后采用大量数据对模型进行训练，进而得到适用于不同场景的推理模型。
10.智能感知模型：也可以简称为感知模型，后文统一用感知模型表述。感知模型可以理解为是应用在感知场景中的AI模型。感知模型通过感知数据训练得到，训练好感知模型用于在感知场景中执行推理过程。用于感知模型训练的数据通常需要满足准确性(accuracy)、多样性(diversity)、时效性(timeliness)和完整性(completeness)。其中，准确性用于衡量训练数据的误差；多样性用于衡量训练数据的数据特征和分布的丰富程度；时效性用于确定训练数据产生时间，以及使用时间确定符合合理时间间隔的训练数据；完整性用于衡量是否能够覆盖感知模型训练需要使用的特征字段。
图1A为本申请实施例提供的通信系统的一结构示意图。
如图1A所示，本申请适用的通信系统包括第一通信装置和第二通信装置。第一通信装置可以是感知节点，如：感知信号的回波信号的接收端，或/和，感知信号的发射端等。该第一通信装置可以是接入网设备、终端设备或者接入网设备中的芯片、终端设备中的芯片。第二通信装置可以是数据收集节点，数据收集节点用于收集感知模型训练的感知数据的节点。该数据收集节点可以是接入网设备、终端设备或者接入网设备中的芯片、终端设备中的芯片，该数据收集节点可以是也可以是服务器。
本申请实施例提供的感知方法可以应用于感知模型训练或推理时收集感知数据的过程。
图1B为感知模型训练过程中的场景示意图。
如图1B所示，该通信系统包括感知节点和数据收集节点，其中，感知节点可以有多个，当然，数据收集节点也可以有多个，图1B中只是以一个为例进行说明。
在感知模型训练过程中，数据收集节点可以向感知节点下发数据收集指示，感知节点可以接收并处理回波信号，从而获得感知数据。感知节点可以将感知数据发送给数据收集节点。
数据收集节点接收到大量的感知数据后，可以将这些感知数据作为训练样本，对感知模型进行训练。当然，该数据收集节点也可以将接收到的感知数据发送给模型训练节点，该模型训练节点可以使用感知数据训练感知模型。
训练好的感知模型可以配置在感知节点上，感知节点可以使用感知模型进行感知数据推理，以得到感知结果。
本申请实施例中，感知数据的格式可以参阅下表1进行理解。
表1：感知数据的格式
表1中，测量参数可以是用于指示感知模型训练相关的输入信息的字段；真值标签可以是用于指示感知模型训练相关的输入输出信息的字段；质量精度指示可以是与测量参数或者/和真值标签相关的精度指示字段；时间戳通常为时间戳，时间信息通常用于标记感知数据收集的时间，可以用于筛选合适时间段的感知数据作为感知模型的训练样本。配置参数为用于指示感知数据相关的配置的字段。
本申请实施例中的感知模型可以包括一个或多个AI模块，AI模块用以实现相应的AI功能。不同感知节点中部署的AI模块可以相同或不同。不同AI模块的模型根据不同的参数配置，AI模块可以实现不同的功能。AI模块的模型可以是基于以下一项或多项参数配置的：结构参数(例如神经网络层数、神经网络宽度、层间的连接关系、神经元的权值、神经元的激活函数、或激活函数中的偏置中的至少一项)、输入参数(例如输入参数的类型和/或输入参数的维度)、或输出参数(例如输出参数的类型和/或输出参数的维度)。其中，激活函数中的偏置还可以称为神经网络的偏置。
一个AI模块可以具有一个或多个模型。一个模型可以推理得到一个输出，该输出包括一个参数或者多个参数。不同模型的学习过程、训练过程、或推理过程可以部署在不同的节点或设备中，或者可以部署在相同的节点或设备中。
AI模型的神经网络可以是嵌入层(Embedding layer)和多层感知机(multi layer perception，MLP)组成的神经网络，也可以是深度神经网络(deep neural network，DNN)、卷积神经网络(convolutional neural network，CNN)、循环神经网络(recurrent neural networks，RNN)、残差网络或其他神经网络等。
另外，本申请实施例提供的感知方法可以应用于双基感知场景或单基感知场景。双基感知场景指的是收发分离的感知场景，发射感知信号的发射端与接收回波信号的接收端不是同一通信装置。单基感知场景指的是收发一体的感知场景，发射感知信号的发射端与接收回波信号的接收端属于同一通信装置。单基感知场景也可以称为自感知场景。
双基感知场景可以参阅图2A进行理解。如图2A所示，该双基感知场景包括两个发射端，四个接收端、感知目标和数据收集节点。其中，两个发射端分别为发射端Tx201和发射端Tx202；四个接收端分别为接收端Rx203、接收端Rx204、接收端Rx205和接收端Rx206；感知目标可以为各类型建筑或者其他物体；数据收集节点207可以向接收端发送数据收集指示，并接收来自接收端的感知数据。
发射端Tx201发射感知信号SS1，SS1经过建筑物产生的回波信号ES1被接收端Rx203接收。
发射端Tx202发射SS2，SS2经过建筑物产生的ES2被接收端Rx203接收；发射端Tx202发射SS3，SS3经过建筑物产生的ES3被接收端Rx204接收；发射端Tx202发射SS4，SS4经过建筑物产生的ES4被接收端Rx205，ES5被接收端Rx206接收。
需要说明的是，SS2、SS3和SS4可以是同一发射波束发出的感知信号，只是该发射波束范围内的感知信号遇到不同位置的建筑物会产生不同方向的回波信号，如：ES2、ES3、ES4和ES5，不同方向的回波信号可以被不同的接送端接收。当然，SS2、SS3和SS4也可以是发射端Tx202不同波束中的感知信号。
在双基感知场景中，同一发射端发射的感知信号产生的回波信号可以被不同的接收端接收，如：ES2被接收端Rx203接收、ES3被接收端Rx204接收、ES4被接收端Rx205，ES5被接收端Rx206接收。不同发射端发射的感知信号产生的回波信号也可以被同一接收端接收，如：ES1和ES2都被接收端Rx203接收。当然，同一发射端发射的感知信号产生的回波信号也可以只被同一个接收端接收，对于发射端与接收端的对应关系本申请不做限定，与一定区域范围内的发射端或接收端的数量相关。无论是哪种情形，接收端可以根据各自接收的回波信号确定感知数据，当然，接收端也可以将接收的回波信号中的相关数据发送给其他通信装置，由其他通信装置来确定感知数据。
接收端会将确定的感知数据SD发送给数据收集节点207，如：接收端Rx203将SD1发送给数据收集节点，接收端Rx204将SD2发送给数据收集节点，接收端Rx205将SD3发送给数据收集节点，接收端Rx206将SD4发送给数据收集节点，数据收集节点207可以根据SD1、SD2、SD3和SD4训练感知模型，也可以将SD1、SD2、SD3和SD4发送给其他专门用于训练感知模型的节点或设备。
单基感知场景可以参阅图2B进行理解。如图2B所示，该单基感知场景可以包括四个测量节点、数据收集节点207和感知目标。四个测量节点分别为测量节点211、测量节点212、测量节点213和测量节点214，测量节点既可以发射感知信号，也可以接收回波信号。
测量节点在测量环境中的感知目标时，可以发射一个或多个波束，一个或多个波束上的感知信号SS可以探测感知目标的不同位置，然后测量节点会接收对应的回波信号ES，进而可以根据ES确定感知数据。当然，测量节点也可以将接收的回波信号中的相关数据发送给其他通信装置，由其他通信装置来确定感知数据。
如图2B所示，测量节点211发射SS1，接收ES1，并根据ES1确定感知数据SD1；测量节点212发射SS2，接收ES21，并根据ES2确定感知数据SD2；测量节点213发射SS3，接收ES31，并根据ES3确定感知数据SD3；测量节点214发射SS4，接收ES41，并根据ES4确定感知数据SD4；四个测量节点计算出感知数据后，会将各自的感知数据SD1、SD2、SD3和SD4都发送给数据收集节点207，然后数据收集节点207可以根据SD1、SD2、SD3和SD4训练感知模型，也可以将SD1、SD2、SD3和SD4发送给其他专门用于训练感知模型的节点或设备。
另外，需要说明的事，上述图2A和图2B所介绍的场景中，接收端、发射端或测量节点都有多个，实际上，接收端、发射端或测量节点都可以有一个，可以通过调整接收端、发射端或测量节点的角度来实现对感知目标不同位置的测量，因此，本申请中对接收端、发射端或测量节点的数量不做限定，可以为一个或多个。
上述图2A和图2B所介绍的场景中，接收端、发射端或测量节点都可以称为感知节点。接收端、发射端、测量节点都可以为终端设备或接入网设备，数据收集节点也可以为终端设备、接入网设备或服务器。本申请中并不限定上述图2A和图2B中所示出的接收端、发射端、测量节点、数据收集节点的具体形态。
下面对本申请的终端设备和接入网设备进行介绍。
终端设备可以是能够接收接入网设备调度和指示信息的无线终端设备。无线终端设备可以是指向用户提供语音和/或数据连通性的设备，或具有无线连接功能的手持式设备、或连接到无线调制解调器的其他处理设备或具有感知功能的设备。
终端设备，又称之为用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端(mobile terminal，MT)等，是包括无线通信功能和/或感知功能(向用户提供语音或数据连通性)的设备，例如，具有无线连接功能的手持式设备、或车载设备等。目前，一些终端设备的举例为：手机(mobile phone)、平板电脑、笔记本电脑、掌上电脑、无人机、移动互联网设备(mobile internet device，MID)、可穿戴设备，虚拟现实(virtual reality，VR)设备、增强现实(augmented reality，AR)设备、工业控制(industrial control)中的无线终端、车联网中的无线终端、无人驾驶(self driving)中的无线终端、远程手术(remote medical surgery)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、或智慧家庭(smart home)中的无线终端等。例如，车联网中的无线终端可以为车载设备、整车设备、车载模块、车辆等。工业控制中的无线终端可以为摄像头、机器人等。智慧家庭中的无线终端可以为电视、空调、扫地机、音箱、机顶盒等。
接入网设备是部署在无线接入网中为终端设备提供无线通信功能和/或感知功能的设备。例如，接入网设备可以为将终端设备接入到无线网络的无线接入网(radio access network，RAN)节点。接入网设备也可以是部署在无线接入网中能够与其它接入网设备通信，可以为接入网设备间提供无线通信功能和/或感知功能的设备。
接入网设备包括但不限于：演进型节点B(evolved Node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(Node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station，BTS)、家庭基站(例如，home evolved NodeB，或home Node B，HNB)、基带单元(baseband unit，BBU)，无线保真(wireless fidelity，WIFI)系统中的接入点(access point，AP)、无线中继节点、无线回传节点、传输点(transmission point，TP)或者发送接收点(transmission and reception point，TRP)等，还可以为5G移动通信系统中的接入网设备。例如，新空口(new radio，NR)系统中的下一代基站(next generation NodeB，gNB)，传输接收点(transmission reception point，TRP)，传输点(transmission point，TP)；或者，5G移动通信系统中的基站的一个或一组(包括多个天线面板)天线面板；或者，接入网设备还可以为构成gNB或传输点的网络节点。例如，基带单元(baseband unit，BBU)，或，分布式单元(distributed unit，DU)等。
在一些部署中，gNB可以包括集中式单元(centralized unit，CU)和DU。gNB还可以包括有源天线单元(active antenna unit，AAU)。CU实现gNB的部分功能，DU实现gNB的部分功能。比如，CU负责处理非实时协议和服务，实现无线资源控制(radio resource control，RRC)，分组数据汇聚层协议(packet data convergence protocol，PDCP)层的功能。DU负责处理物理层协议和实时服务，实现无线链路控制(radio link control，RLC)层、媒体接入控制(media access control，MAC)层和物理(physical，PHY)层的功能。AAU实现部分物理层处理功能、射频处理及有源天线的相关功能。RRC层的信息最终会变成PHY层的信息，或者，由PHY层的信息转变而来。因此在该架构下，高层信令(如RRC层信令)也可以认为是由DU发送的，或者，由DU和AAU发送的。可以理解的是，接入网设备可以为包括CU节点、DU节点、AAU节点中一个或多个的设备。此外，可以将CU划分为接入网(radio access network，RAN)中的接入网设备，也可以将CU划分为核心网(core network，CN)中的接入网设备，本申请对此不做限定。
以上介绍了本申请方案的通信系统和应用场景，下面结合第一通信装置和第二通信装置的交互过程介绍本申请实施例提供的感知方法。关于第一通信装置和第二通信装置可以参阅前面的介绍进行理解。
如图3所示，本申请实施例提供的感知方法包括：
S301.第二通信装置向第一通信装置发送第一信息。对应地，第一通信装置接收来自第二通信装置的第一信息。
其中，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理。其中，与感知质量相关的处理可以包括：确定第一感知数据的感知质量、确定第一感知数据的感知质量是否满足感知质量要求、或者，确定用于确定第一参数中的至少一项；其中，第一参数用于确定第一感知数据的感知质量。
本申请中，第一感知数据可以有一个或多个，当第一感知数据有多个时，对每个第一感知数据都可以执行相同的感知质量相关的处理过程。
S302.第一通信装置根据第一信息，对第一感知数据执行与感知质量相关的处理。
S303.第一通信装置向第二通信装置发送第二感知数据。对应地，第二通信装置接收来自第一通信装置的第二感知数据。
其中，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
本申请中，第二感知数据可以有一个或多个，第二感知数据可以为第一感知数据的子集，当然，若每个第一感知数据都满足感知质量要求，则第二感知数据为第一感知数据的全集。
本申请中，感知质量要求可以是一个或多个感知质量的门限值，如：感知数据的感知质量大于感知质量的门限值，即为该感知数据的感知质量满足感知质量要求。
本申请中，感知质量的策略信息指的是用于确定感知数据的感知质量的策略，可以通过函数的方式表示，也可以通过表格的方式给出，本申请不限定感知质量的策略的具体形式。
其中，感知质量的策略信息可以包括感知模型训练相关的数据字段，以及所述数据字段对应的质量评估策略。感知质量的策略信息若用表格的形式来表示可以参阅下表2进行理解。
表2：感知质量的策略信息
表2中各数据字段的含义可以参阅表1部分对应的介绍进行理解。其中，测量参数和真值标签这两个数据字段与准确性相关，时间信息与时效性相关，配置参数与多样性相关。而表2这个整体也体现了完整性。
表2中，vacc1为测量参数字段对应的感知质量，snr表示回波信号的信噪比(signal to noise rate，SNR)，Le表示感知节点的位置误差；从vacc1＝F(snr,Le)的关系式可知，第一通信装置获取第一感知数据的信噪比和对应的感知节点的位置误差后，就可以确定测量参数这个字段的感知质量vacc1。
同理，通过vacc2＝F(lable)，第一通信装置就可以确定出真值标签这个字段的感知质量vacc2。表2中，vtim表示感知数据的时效性。vdiv与成像区域，成像区域也可以称为感兴趣区域(region of interest，ROI)、接收天线位置和/或接收天线数(Rx)、发射天线位置和/或发射天线数(Tx)、带宽(B)和频段(f)相关，第一通信装置通过vdiv＝F(ROI,Rx,Tx,B,f)就可以确定配置参数这个字段的感知质量vdiv。
当然，配置参数这个字段的感知质量不限于表2中的一种表示方式，还可以不同的配置参数分别有对应的感知质量关系式，如：
vdiv，ROI＝F(ROI)；
vdiv，Rx＝F(Rx)；
vdiv，Tx＝F(Tx)；
vdiv，B＝F(B)；
vdiv，f＝F(f)。
另外，需要说明的是，配置参数对应的质量评估策略可以通过上述单个配置参数的关系式的形式给出，也可以通过多个配置参数联合的关系式的形式给出，还可以通过其他方式给出。如表3所示，以带宽为例，
表3：带宽的感知质量表
表3中，当带宽为B0时，带宽的感知质量为vdiv，0，当带宽为B1时，带宽的感知质量为vdiv，1，…当带宽为Bm时，带宽的感知质量为vdiv，m。也就是说，通过查表3可以确定不同带宽对应的感知质量。当然，此处只是以带宽为例进行说明，其他配置参数，如：ROI、Tx、Rx或f等都可以参考表3的形式给出ROI、Tx、Rx或f在不同取值时对应的感知质量。
当然，本申请中，不限于是针对单个配置参数给出的例如表3的确定感知质量的方式，还可以是针对多个配置参数给出对应的联合的感知质量，这种情况可以参阅表4进行理解。
表4：多个配置参数联合的感知质量表
表4中，以第一行为例，当ROI属于R0，Rx位置属于RL0，Tx位置属于TL0，Rx天线数为Rn0，Tx天线数为Tn0，带宽为B0，频段为{f00,f01,….f0n}时，配置参数这个字段的感知质量为vdiv，0。同理，其他每一行都表示对应的多个配置参数联合的感知质量。
本申请中，针对表2中的测量参数，需要评估感知数据的准确性，感知数据的准确性与SNR和感知节点的位置误差相关，关于感知数据的准确性与SNR、感知数据的准确性与感知节点的位置误差的关系可以参阅图4A和图4B进行理解。
如图4A所示，感知数据的准确性与SNR之间的函数关系基本为增函数，感知数据的准确性随着SNR的增大而增大，当SNR达到一定程度时，感知数据的准确性也趋于稳定。
如图4B所示，感知数据的准确性与感知节点的位置误差之间的函数关系基本为减函数，感知数据的准确性随着感知节点的位置误差的增大而减小，当感知节点的位置误差达到一定程度时，感知数据的准确性基本为0。
由上述图4A和图4B的关系可知，在获取SNR和感知节点的位置误差时，可以尽量获取准确性较高点的SNR和感知节点的位置误差。
关于上述表2中的真值标签(ground-truth label)可以通过有源反射器收集或者通过估计第一感知数据得到。其中，通过有源反射器收集的场景可以参阅图5进行理解，如图5所示，将有源反射器作为感知目标，这样收集到的关于散射点的信息(散射点的位置、幅度、能量或速度等至少一项)；几何信息(多边形或多面体的形状或中心等中的至少一项)；物体材质信息(如：材料、纹理、颜色或电磁参数等中的至少一项)这些真值标签基于接近于真实值，提高了真值标签的准确度。
通过处理第一感知数据也可以估计出散射点的信息、几何信息，或物体材质信息。但通过估计的方式得到的真值标签相对于有源反射器收集的方式的准确度低一些，但第一感知数据的来源广泛，可以提高第一感知数据的收集范围。
表2中的时间戳用于评估时效性，当感知数据产生的时间满足数据收集节点的时间要求时，时效性高。
表2中的配置参数用于评估多样性，由表2可知配置参数可以包括多种类型，不同类型的配置参数的数量通常不同。为了实现不同类型数据的均衡性，可以通过调整不同类型的配置参数的感知质量的方式来调整某一个或多种类型的数据的收集量。
本申请中，针对第一类型的配置参数，可以先确定第一类型的配置参数的概率密度，第一类型的配置参数的概率密度可以是第一类型的配置参数的数量在多种类型的配置参数的总数量的比值。本申请中，可以将第一类型的配置参数的概率密度配置为与第一类型的配置参数的感知质量负相关。这样，若第一类型的配置参数的概率密度小表示第一类型的配置参数的数量少，则可以为该第一类型的配置参数的配置较高感知质量。这样，有利于后续收集配置参数，提高第一类型的配置参数的收集量，从而实现各种类型的配置参数的数据均衡。
以上介绍了感知质量的策略信息，感知质量的策略信息可以用于确定第一感知数据的感知质量，确定感知质量后，可以利用第一感知数据的感知质量，以及感知质量要求从第一感知数据中筛选出感知质量满足感知质量要求的第二感知数据。
本申请实施例中，感知质量要求可以是一个或多个感知质量的门限值，该感知质量要求可以是对感知数据各个数据字段汇总后的感知质量的要求，也可以是对各个数据字段对应的感知质量的要求，本申请对此不做限定。其中，各个数据字段汇总后的感知质量可以称为感知数据的感知质量。
本申请实施例中，第一感知数据的感知质量可以表示为：
v＝macc1*vacc1+macc2*vacc2+mdiv*vdiv+mtim*vtim；
其中，v表示第一感知数据的感知质量；vacc1表示测量参数的数据字段的感知质量，macc1表示测量参数的数据字段的权重；vacc2表示真值标签的数据字段的感知质量，macc2表示真值标签的数据字段的权重；vdiv表示配置参数的数据字段的感知质量，mdiv表示配置参数的数据字段的权重；vtim表示时间戳的数据字段的感知质量，mtim表示时间戳的数据字段的权重；其中，权重用于指示数据字段的感知质量在第一感知数据的感知质量中的占比。
其中，各个数据字段的权重可以是在策略信息中携带的，也可以是第一通信装置取的默认值。
若通过第一感知数据的感知质量来筛选第二感知数据，则感知质量要求配置一个门限值vth即可，可以将v＞vth的第一感知数据确定为第二感知数据。
若通过数据字段的感知质量来筛选第二感知数据，则感知质量要求可能需要配置多个门限值，然后将各数据字段的感知质量与对应的门限值进行比较，然后可以选择其中有一个或多个数据字段的感知质量大于对应门限值的第一感知数据为第二感知数据。
请实施例提供的方案中，第一通信装置可以基于第二通信装置发送的第一信息，从第一感知数据中筛选出感知质量满足感知质量要求的第二感知数据。这样，使用第二感知数据训练感知模型，就可以提高感知模型训练的效率和效果，进而也能提高感知模型推理的准确度。
当第一信息的内容不同时，S302所执行的对第一感知数据执行与感知质量相关的处理不同，下面分不同情况分别进行介绍。
一、第一信息包括感知质量的策略信息+感知质量要求；
如图6所示，该种情况的感知方法包括：
S601.数据收集节点向感知节点送感知质量的策略信息和感知质量要求。对应地，感知节点接收来自数据收集节点的感知质量的策略信息和感知质量要求。
其中，感知质量的策略信息可以参阅表5进行理解。
表5：感知质量的策略信息
表5相对于表2，增加了第三列，即各数据字段对应的权重。
S602.感知节点根据感知质量的策略信息确定第一感知数据的感知质量。
本申请实施例中，感知节点确定第一感知数据的感知质量可以是先确定各数据字段对应的感知质量，如：参阅表5中各数据字段对应的质量评估策略，先分别确定vacc1、vacc2、vtim，以及vdiv。然后通过如下关系式确定第一感知数据的感知质量。
v＝macc1*vacc1+macc2*vacc2+mdiv*vdiv+mtim*vtim；
关于定vacc1、vacc2、vtim，以及vdiv的确定过程，以及v中各参数的含义，可以参阅前面图3对应的实施例中的相应内容进行理解，此处不再重复介绍。
S603.感知节点确定第一感知数据的感知质量是否满足感知质量要求。若满足，则执行S604，若不满足，可以执行S605。
该过程可以是感知节点将v与vth进行比较，若v＞vth，则可以确定第一感知数据的感知质量满足感知质量要求；若v＜vth，则可以确定第一感知数据的感知质量不满足感知质量要求。
S604.感知节点向数据收集节点发送第二感知数据。对应地，数据收集节点接收来自感知节点的第二感知数据。
第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据。
S605.感知节点删除感知质量不满足感知质量要求的第一感知数据。
感知节点及时删除感知质量不满足感知质量要求的第一感知数据，可以释放感知节点的内存。
数据收集节点接收第二感知数据后，可以执行S606，或者执行S607。
S606.数据收集节点使用第二感知数据训练感知模型。
S607.数据收集节点向模型训练节点发送第二感知数据。对应地，模型训练节点接收来自数据收集节点的第二感知数据。
S608.模型训练节点使用第二感知数据训练感知模型。
感知模型训练好后，模型训练节点可以将训练好的感知模型发送给感知节点，这样，感知节点就可以使用训练好的感知模型处理后续的回波信号。
本申请实施例中，因为第二感知数据是根据感知质量的策略信息和感知质量要求从第一感知数据中筛选出来的质量较好的第一感知数据。所以，使用第二感知数据训练的感知模型可以提高感知模型的训练效率和质量。
另外，该图6所示的实施例的过程，若表5中不包括第三列，即不包括权重，在S602确定第一感知数据的感知质量时，可以将各数据字段的权重都默认为1。
二、第一信息包括感知质量的策略信息，不包括感知质量要求；
如图7所示，该种情况的感知方法包括：
S701.数据收集节点向感知节点送感知质量的策略信息。对应地，感知节点接收来自数据收集节点的感知质量的策略信息。
S702.感知节点根据感知质量的策略信息确定第一感知数据的感知质量。
该过程可以参阅上述S602部分的介绍进行理解。
S703.感知节点向数据收集节点发送第一感知数据的感知质量。对应地，数据收集节点接收来自感知节点的第一感知数据的感知质量。
S704.数据收集节点确定第一感知数据的感知质量是否满足感知质量要求。若部分或全部的第一感知数据的感知质量满足感知质量要求，则执行S705。
该过程可以是数据收集节点将v与vth进行比较，若v＞vth，则可以确定第一感知数据的感知质量满足感知质量要求；若v＜vth，则可以确定第一感知数据的感知质量不满足感知质量要求。
若全部第一感知数据的感知质量都不满足感知质量要求，则数据收集节点可以向感知节点发送指示信息，指示信息用于指示第一感知数据的感知质量不满足感知质量要求。这样，感知节点就可以根据该指示信息删除第一感知数据。
S705.数据收集节点向感知节点发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。对应地，感知节点接收来自数据收集节点的感知数据请求。
数据收集节点通过感知数据请求，携带第二感知数据的标识、索引等信息，以指示感知数据发送第二感知数据。
S706.感知节点根据感知数据请求，从第一感知数据中筛选出第二感知数据。
S707.感知节点向数据收集节点发送第二感知数据。对应地，数据收集节点接收来自感知节点的第二感知数据。
S708至S710可以参阅上述S606至S608进行理解。
本申请实施例提供的感知方案，感知节点将第一感知数据的感知质量发送给数据收集节点，由数据收集节点判断是否满足感知质量要求，更有利于管理感知质量要求，降低感知质量要求在传输过程中泄露的风险。
三、第一信息包括参数指示信息，参数指示信息用于指示确定第一感知数据的感知质量的第一参数。
如图8所示，该种情况的感知方法包括：
S801.数据收集节点向感知节点送参数指示信息。对应地，感知节点接收来自数据收集节点的参数指示信息。
该参数指示信息所指示的第一参数为用于确定第一感知数据的感知质量所需参数的子集。如前面所介绍的，用于确定第一感知数据的感知质量所需参数通常包括SNR、感知节点的位置误差、ROI、接收天线的位置、数量、发射天线的位置、数量、带宽和频率等参数等。其中部分参数可能数据收集节点已经获知，如：数据收集节点可能已知感知节点的位置、带宽和频率等参数，那么在下发参数指示信息时，数据收集节点只需要发送未知的参数请求，如：未知的SNR和ROI等。这样既可以满足数据收集节点确定感知质量的需求，又可以减少感知节点与数据收集节点之间的传输的数据量。
S802.感知节点根据参数指示信息，确定第一参数。
S803.感知节点向数据收集节点发送第一参数。对应地，数据收集节点接收来自感知节点的第一参数。
S804.数据收集节点根据第一参数和感知质量的策略信息确定第一感知数据的感知质量。
该步骤可以参阅上述S602部分的介绍进行理解，将第一参数，如：SNR和ROI等以及已知的感知节点的位置、带宽和频率等参数代入表5中的对应关系式，先分别确定vacc1、vacc2、vtim，以及vdiv。然后通过关系式v＝macc1*vacc1+macc2*vacc2+mdiv*vdiv+mtim*vtim确定出第一感知数据的感知质量。
S805.数据收集节点确定第一感知数据的感知质量是否满足感知质量要求。若满足，若部分或全部的第一感知数据的感知质量满足感知质量要求，则执行S806。
S806.数据收集节点向感知节点发送感知数据请求，感知数据请求用于指示第二感知数据的感知质量满足感知质量要求。对应地，感知节点接收来自数据收集节点的感知数据请求。
S807.感知节点根据感知数据请求，从第一感知数据中筛选出第二感知数据。
S808.感知节点向数据收集节点发送第二感知数据。对应地，数据收集节点接收来自感知节点的第二感知数据。
S809至S811可以参阅上述S606至S608进行理解。
本申请实施例提供的感知方案，第一信息包括参数指示信息时，不需要将感知质量的策略信息和感知质量要求发送给感知节点，可以降低感知质量的策略信息和感知质量要求在传输过程中泄露的风险。
以上介绍了本申请实施例中的通信系统，以及感知方法，下面对本申请实施例提供的通信装置进行描述。请参阅图9，图9为本申请实施例通信装置的一个结构示意图。通信装置900可以用于执行图3至图8中所示的实施例中的步骤，具体请参考上述方法实施例中的相关介绍。
通信装置900包括收发模块901和处理模块902。收发模块901可以实现相应的通信功能，处理模块902用于进行数据处理。收发模块901还可以称为通信接口或通信单元。
可选地，该通信装置900还可以包括存储单元，该存储单元可以用于存储指令和/或数据，处理模块902可以读取存储单元中的指令和/或数据，以使得通信装置实现前述方法实施例。
该通信装置900可以用于执行上文方法实施例中的动作。该通信装置900可以为终端设备或接入网设备或者可配置于终端设备或接入网设备的部件或模块。收发模块901用于执行上文方法实施例中的接收相关的操作，处理模块902用于执行上文方法实施例中的处理相关的操作。
可选的，收发模块901可以包括发送模块和接收模块。发送模块用于执行上述方法实施例中的发送操作。接收模块用于执行上述方法实施例中的接收操作。
需要说明的是，通信装置900可以包括发送模块，而不包括接收模块。或者，通信装置900可以包括接收模块，而不包括发送模块。具体可以视通信装置900执行的上述方案中是否包括发送动作和接收动作。
作为一种示例，该通信装置900用于执行上文图3所示的实施例中的动作。
收发模块901，用于接收来自第二通信装置的第一信息，第一信息用于指示第一通信装置对第一感知数据执行与感知质量相关的处理；
处理模块902，用于对第一感知数据执行与感知质量相关的处理；
收发模块901，还用于向第二通信装置发送第二感知数据，第二感知数据为感知质量满足感知质量要求的部分或全部第一感知数据，第一感知数据的感知质量通过感知质量的策略信息确定。
应理解，各模块执行上述相应步骤的具体过程在上述方法实施例中已经详细说明，为了简洁，在此不再赘述。
上文实施例中的处理模块902可以由至少一个处理器或处理器相关电路实现。收发模块901可以由收发器或收发器相关电路实现。收发模块901还可称为通信单元或通信接口。存储单元可以通过至少一个存储器实现。
本申请实施例还提供另一种通信装置1000。如图10所示，该通信装置1000包括处理器1010，处理器1010与存储器1020耦合，存储器1020用于存储计算机程序或指令和/或数据，处理器1010用于执行存储器1020存储的计算机程序或指令和/或数据，使得上文方法实施例中的方法被执行。
可选地，该通信装置1000包括的处理器1010为一个或多个。
可选地，如图10所示，该通信装置1000还可以包括存储器1020。
可选地，该通信装置1000包括的存储器1020可以为一个或多个。
可选地，该存储器1020可以与该处理器1010集成在一起，或者分离设置。
可选地，如图10所示，该通信装置1000还可以包括收发器1030，收发器1030用于信号的接收和/或发送。例如，处理器1010用于控制收发器1030进行信号的接收和/或发送。
作为一种方案，该通信装置1000用于实现上文方法实施例中的操作。
例如，处理器1010用于实现上文方法实施例中处理相关的操作，收发器1030用于实现上文方法实施例中由收发相关的操作。
本申请实施例还提供一种通信装置1000，该通信装置1000可以是终端设备或接入网设备也可以是终端设备或接入网设备或核心网的设备中的芯片或模块。该通信装置1000可以用于执行上述方法实施例中的操作。
当该通信装置1000为通信装置时，图11示出了一种简化的通信装置的结构示意图。如图11所示，通信装置包括处理器、存储器、收发器，其中存储器可以存储计算机程序代码，存储器中还可以存储有AI模块，AI模块用于实现AI相关的功能。AI模块可以是通过软件，硬件，或软硬结合的方式实现。例如，AI模块可以是近实时接入网智能控制(ran intelligent controller，RIC)或者非实时RIC。收发器包括发射机1031、接收机1032、射频电路(图中未示出)、天线1033以及输入输出装置(图中未示出)。处理器主要用于对通信协议以及通信数据进行处理，以及对通信装置进行控制，执行软件程序，处理软件程序的数据等。存储器主要用于存储软件程序和数据。射频电路主要用于基带信号与射频信号的转换以及对射频信号的处理。天线主要用于收发电磁波形式的射频信号。输入输出装置，例如触摸屏、显示屏，键盘等主要用于接收用户输入的数据以及对用户输出数据。需要说明的是，有些种类的通信装置可以不具有输入输出装置。
当需要发送数据时，处理器对待发送的数据进行基带处理后，输出基带信号至射频电路，射频电路将基带信号进行射频处理后将射频信号通过天线以电磁波的形式向外发送。当有数据发送到通信装置时，射频电路通过天线接收到射频信号，将射频信号转换为基带信号，并将基带信号输出至处理器，处理器将基带信号转换为数据并对该数据进行处理。为便于说明，图11中仅示出了一个存储器、处理器和收发器，在实际的通信装置产品中，可以存在一个或多个处理器和一个或多个存储器。存储器也可以称为存储介质或者存储设备等。存储器可以是独立于处理器设置，也可以是与处理器集成在一起，本申请实施例对此不做限制。
在本申请实施例中，可以将具有收发功能的天线和射频电路视为通信装置的收发单元，将具有处理功能的处理器视为通信装置的处理单元。
如图11所示，通信装置包括处理器1010、存储器1020和收发器1030。处理器1010也可以称为处理单元，处理单板，处理模块、处理装置等，收发器1030也可以称为收发单元、收发机、收发装置等。
可选地，可以将收发器1030中用于实现接收功能的器件视为接收单元，将收发器1030中用于实现发送功能的器件视为发送单元，即收发器1030包括接收器和发送器。收发器有时也可以称为收发机、收发单元、或收发电路等。接收器有时也可以称为接收机、接收单元、或接收电路等。发送器有时也可以称为发射机、发射单元或者发射电路等。
例如，在一种实现方式中，处理器1010用于执行图3所示的实施例中处理动作，收发器1030用于执行图3中收发动作。例如，收发器1030用于执行图3所示的实施例中的步骤S301的收发操作。处理器1010用于执行图3所示的实施例中的步骤S302和S303的处理操作。
应理解，图11仅为示例而非限定，上述包括收发单元和处理单元的通信装置可以不依赖于图11所示的结构。
当该通信装置1000为芯片时，该芯片包括处理器、存储器和收发器。其中，收发器可以是输入输出电路或通信接口；处理器可以为该芯片上集成的处理单元或者微处理器或者集成电路。上述方法实施例中通信装置的发送操作可以理解为芯片的输出，上述方法实施例中通信装置的接收操作可以理解为芯片的输入。
本申请实施例还提供一种计算机可读存储介质，其上存储有用于实现上述方法实施例中的方法的计算机指令。
例如，该计算机程序被计算机执行时，使得该计算机可以实现上述方法实施例中执行的方法。
本申请实施例还提供一种包含指令的计算机程序产品，该指令被计算机执行时使得该计算机实现上述方法实施例中执行的方法。
本申请实施例还提供一种通信系统，该通信系统包括上文实施例中的接入网设备与终端设备。
本申请实施例还提供一种芯片装置，包括处理器，用于调用存储器中存储的计算机程度或计算机指令，以使得该处理器执行上述图3至图8所示的实施例的方法。
一种可能的实现方式中，该芯片装置的输入对应上述图3至图8所示的实施例中的接收操作，该芯片装置的输出对应上述图3至图8所示的实施例中的发送操作。
可选的，该处理器通过接口与存储器耦合。
可选的，该芯片装置还包括存储器，该存储器中存储有计算机程度或计算机指令。
其中，上述任一处提到的处理器，可以是一个通用中央处理器，微处理器，特定应用集成电路(application-specific integrated circuit，ASIC)，或一个或多个用于控制上述图3至图8所示的实施例的方法的程序执行的集成电路。上述任一处提到的存储器可以为只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)等。
所属领域的技术人员可以清楚地了解到，为描述方便和简洁，上述提供的任一种通信装置中相关内容的解释及有益效果均可参考上文提供的对应的方法实施例，此处不再赘述。
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。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者接入网设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器、随机存取存储器、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (26)

  1. 一种感知方法，其特征在于，所述方法应用于第一通信装置，所述方法包括：
    接收来自第二通信装置的第一信息，所述第一信息用于指示所述第一通信装置对第一感知数据执行与感知质量相关的处理；
    向所述第二通信装置发送第二感知数据，所述第二感知数据为感知质量满足感知质量要求的部分或全部所述第一感知数据，所述第一感知数据的感知质量通过感知质量的策略信息确定。
  2. 根据权利要求1所述的方法，其特征在于，所述第一信息包括所述感知质量的策略信息，所述策略信息用于所述第一通信装置确定所述第一感知数据的感知质量。
  3. 根据权利要求2所述的方法，其特征在于，所述策略信息包括感知模型训练相关的数据字段，以及所述数据字段对应的质量评估策略。
  4. 根据权利要求3所述的方法，其特征在于，所述数据字段包括用于指示所述感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
  5. 根据权利要求3或4所述的方法，其特征在于，所述策略信息还包括所述数据字段对应的权重，所述权重用于指示所述数据字段的感知质量在所述第一感知数据的感知质量中的占比。
  6. 根据权利要求2-5任一项所述的方法，其特征在于，所述第一信息还包括所述感知质量要求，所述感知质量要求用于所述第一通信装置确定所述第一感知数据的感知质量是否满足所述感知质量要求。
  7. 根据权利要求2-5任一项所述的方法，其特征在于，在向所述第二通信装置发送第二感知数据之前，所述方法还包括：
    向所述第二通信装置发送所述第一感知数据的感知质量，所述第一感知数据的感知质量用于所述第二通信装置确定所述第一感知数据的感知质量是否满足所述感知质量要求；
    接收来自所述第二通信装置的感知数据请求，所述感知数据请求用于指示所述第二感知数据的感知质量满足所述感知质量要求。
  8. 根据权利要求1所述的方法，其特征在于，所述第一信息包括参数指示信息，所述参数指示信息用于指示确定第一感知数据的感知质量的第一参数；
    对应地，在向所述第二通信装置发送满足感知质量要求的感知数据之前，所述方法还包括：
    向所述第二通信装置发送所述第一参数，所述第一参数用于所述第二通信装置确定所述第一感知数据的感知质量，并确定所述第一感知数据的感知质量是否满足感知质量要求；
    接收来自所述第二通信装置的感知数据请求，所述感知数据请求用于指示所述第二感知数据的感知质量满足所述感知质量要求。
  9. 根据权利要求8所述的方法，其特征在于，所述第一参数为用于确定所述第一感知数据的感知质量所需参数的子集。
  10. 根据权利要求4所述的方法，其特征在于，所述输出信息通过有源反射器收集或者通过估计所述第一感知数据得到。
  11. 根据权利要求4所述的方法，其特征在于，所述配置参数包括多种类型，其中，第一类型的配置参数的概率密度与所述第一类型的配置参数的感知质量负相关，所述第一类型的配置参数的概率密度用于指示所述第一类型的配置参数在所述多种类型的配置参数中的占比，所述第一类型为所述多种类型中的任意一种。
  12. 一种感知方法，其特征在于，所述方法包括：
    向所述第一通信装置发送第一信息，所述第一信息用于指示所述第一通信装置对第一感知数据执行与感知质量相关的处理；
    接收来自所述第一通信装置的第二感知数据，所述第二感知数据为感知质量满足感知质量要求的部分或全部所述第一感知数据，所述第一感知数据的感知质量通过感知质量的策略信息确定。
  13. 根据权利要求12所述的方法，其特征在于，所述第一信息包括所述感知质量的策略信息，所述策略信息用于所述第一通信装置确定所述第一感知数据的感知质量。
  14. 根据权利要求13所述的方法，其特征在于，所述策略信息包括感知模型训练相关的数据字段，以及所述数据字段对应的质量评估策略。
  15. 根据权利要求14所述的方法，其特征在于，所述数据字段包括用于指示所述感知模型训练相关的输入信息、输出信息、时间信息或配置参数的字段中的至少一项。
  16. 根据权利要求14或15所述的方法，其特征在于，所述策略信息还包括所述数据字段对应的权重，所述权重用于指示所述数据字段的感知质量在所述第一感知数据的感知质量中的占比。
  17. 根据权利要求13-16任一项所述的方法，其特征在于，所述第一信息还包括所述感知质量要求，所述感知质量要求用于所述第一通信装置确定所述第一感知数据的感知质量是否满足所述感知质量要求。
  18. 根据权利要求13-16任一项所述的方法，其特征在于，在接收来自所述第一通信装置的第二感知数据之前，所述方法还包括：
    接收来自所述第一通信装置的所述第一感知数据的感知质量，所述第一感知数据的感知质量用于确定所述第一感知数据的感知质量是否满足所述感知质量要求；
    向所述第一通信装置发送感知数据请求，所述感知数据请求用于指示所述第二感知数据的感知质量满足所述感知质量要求。
  19. 根据权利要求12所述的方法，其特征在于，所述第一信息包括参数指示信息，所述参数指示信息用于指示确定第一感知数据的感知质量的第一参数；在接收来自所述第一通信装置的第二感知数据之前，所述方法还包括：
    接收来自所述第一通信装置的所述第一参数，所述第一参数用于确定所述第一感知数据的感知质量，并确定所述第一感知数据的感知质量是否满足感知质量要求；
    向所述第一通信装置发送感知数据请求，所述感知数据请求用于指示所述第二感知数据的感知质量满足所述感知质量要求。
  20. 根据权利要求19所述的方法，其特征在于，所述第一参数为用于确定所述第一感知数据的感知质量所需参数的子集。
  21. 一种通信装置，其特征在于，包括：收发模块和处理模块，
    所述收发模块用于执行上述权利要求1-20任一项所述的方法中的发送步骤或接收步骤；
    所述处理模块用于执行上述权利要求1-20任一项所述的方法中的除发送步骤和接收步骤之外的步骤。
  22. 一种通信装置，其特征在于，包括至少一个处理器，与存储器耦合；
    所述存储器用于存储程序或指令；
    所述至少一个处理器用于执行所述程序或指令，以使所述装置实现如权利要求1至20中任一项所述的方法。
  23. 一种芯片装置，其特征在于，包括处理器，用于调用存储器中存储的程序，以使得该处理器执行如权利要求1至20中任一项所述的方法。
  24. 根据权利要求23所述的芯片装置，其特征在于，所述芯片装置还包括所述存储器。
  25. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储程序指令，当所述程序指令运行时，使得如权利要求1至20任一项所述的方法被执行。
  26. 一种包含程序指令的计算机程序产品，其特征在于，当所述程序指令在计算机上运行时，使得所述计算机执行如权利要求1至20任一项所述的方法。
PCT/CN2025/089464 2024-05-28 2025-04-17 一种感知方法及相应装置 Pending WO2025246715A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410681726.X 2024-05-28
CN202410681726.XA CN121037895A (zh) 2024-05-28 2024-05-28 一种感知方法及相应装置

Publications (1)

Publication Number Publication Date
WO2025246715A1 true WO2025246715A1 (zh) 2025-12-04

Family

ID=97769437

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/089464 Pending WO2025246715A1 (zh) 2024-05-28 2025-04-17 一种感知方法及相应装置

Country Status (2)

Country Link
CN (1) CN121037895A (zh)
WO (1) WO2025246715A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115696370A (zh) * 2021-07-23 2023-02-03 维沃移动通信有限公司 感知方法、装置、终端及网络设备
WO2023198124A1 (zh) * 2022-04-15 2023-10-19 维沃移动通信有限公司 感知处理方法、装置、网络侧设备以及终端
CN117097494A (zh) * 2022-05-13 2023-11-21 华为技术有限公司 一种感知的方法、通信装置及计算机可读存储介质
CN117793767A (zh) * 2022-09-29 2024-03-29 华为技术有限公司 Ai模型训练中用于获取训练数据的方法以及通信装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115696370A (zh) * 2021-07-23 2023-02-03 维沃移动通信有限公司 感知方法、装置、终端及网络设备
WO2023198124A1 (zh) * 2022-04-15 2023-10-19 维沃移动通信有限公司 感知处理方法、装置、网络侧设备以及终端
CN117097494A (zh) * 2022-05-13 2023-11-21 华为技术有限公司 一种感知的方法、通信装置及计算机可读存储介质
CN117793767A (zh) * 2022-09-29 2024-03-29 华为技术有限公司 Ai模型训练中用于获取训练数据的方法以及通信装置

Also Published As

Publication number Publication date
CN121037895A (zh) 2025-11-28

Similar Documents

Publication Publication Date Title
US20240155394A1 (en) Sensing method and apparatus, terminal, and network device
EP4615014A1 (en) Method and apparatus for positioning
CN117202218A (zh) 感知方式切换方法、装置及通信设备
CN117544993A (zh) 信号确定方法、装置及通信设备
WO2023226826A1 (zh) 感知方法、装置及通信设备
CN117544992A (zh) 信号确定方法、装置及通信设备
CN117715128A (zh) 感知方式切换方法、装置及设备
CN118250712A (zh) 感知融合方法、装置及通信设备
WO2025246715A1 (zh) 一种感知方法及相应装置
WO2024131761A1 (zh) 感知协作方法、装置及通信设备
CN118250709A (zh) 感知融合方法、装置及通信设备
CN117715127A (zh) 感知方式切换方法、装置及设备
WO2025232207A9 (zh) 一种感知方法及相应装置
WO2025195407A1 (zh) 一种通信方法及装置
CN120812610A (zh) 一种感知方法及相应装置
WO2026092090A1 (zh) 一种通信方法及装置
WO2025241577A1 (zh) 一种感知方法及相应装置
WO2026011848A1 (zh) 一种通信方法及相应装置
WO2026040449A1 (zh) 一种感知方法及相应装置
CN121643832A (zh) 预编码信息确定方法、装置及相关设备
WO2025130792A1 (zh) 模型推理方法及装置
WO2025139991A1 (zh) 一种通信方法及通信装置
CN121645315A (zh) 一种感知方法、装置、系统、存储介质及程序产品
WO2026067379A1 (zh) 数据传输方法、装置、第一设备及第二设备
WO2026067394A1 (zh) 数据传输方法、装置及相关设备

Legal Events

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

Ref document number: 25814436

Country of ref document: EP

Kind code of ref document: A1