Communication method and related apparatus
Patent Information
- Application Number
- PCT/CN2026/082434
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-03-13
- Filing Date
- 2026-03-10
- Publication Date
- 2026-09-17
Smart Images

Figure CN2026082434_17092026_PF_FP_ABST
Abstract
Description
A communication method and related apparatus
[0001] This application claims priority to Chinese Patent Application No. 202510301346.3, filed on March 13, 2025, entitled “A Communication Method and Related Device”, the entire contents of which are incorporated herein by reference. Technical Field
[0002] This application relates to the field of communication technology, and in particular to a communication method and related apparatus. Background Technology
[0003] With the continuous evolution of communication technology, integrated sensing and communication (ISAC) systems are becoming increasingly widely used to improve the utilization of spectrum resources. In an ISAC system, sensing devices can use communication signals to sense targets and determine the target's location information, such as angle, speed, and distance, based on the echo signals without occupying additional spectrum resources.
[0004] In traditional sensing processing schemes, sensing devices perform inverse discrete fourier transform (IDFT), slow-time domain discrete fourier transform (DFT), and two-dimensional discrete fourier transform (2D-DFT) in the spatial domain on the echo signal of the sensed target to obtain a multi-dimensional sensing spectrum. Then, constant false alarm rate (CFAR) detection and peak search are applied to determine the scattering point parameters of the sensed target on the sensing spectrum, such as angle, velocity, and distance. Furthermore, based on the scattering point parameters, the centroid parameters of the sensed target, such as angle, velocity, and distance, are estimated to obtain the localization result of the sensed target. However, the accuracy of the localization result determined in this way depends on the resolution of the sensing spectrum. If the resolution of the sensing spectrum is low and the scattering points of the sensed target are dense, it is difficult to effectively distinguish these dense scattering points. Thus, the centroid parameters of the sensed target estimated based on the scattering point parameters may deviate from the actual centroid parameters of the sensed target, resulting in low accuracy of the localization result. Summary of the Invention
[0005] To address the aforementioned issues, this application provides a communication method and related apparatus that can correct scattering point parameters that significantly deviate from the centroid parameters of the perceived target, thereby improving the estimation accuracy and confidence level of the scattering point parameters of the perceived target and thus enhancing positioning accuracy.
[0006] The following sections introduce this application from multiple perspectives. It is easy to understand that the implementation methods of these multiple aspects can be referenced from each other.
[0007] In a first aspect, embodiments of this application provide a communication method applied to a first device. The method includes: the first device acquiring first parameters of a first scattering point of a sensed target, and then determining third parameters of the first scattering point of the sensed target based on the first parameters of the first scattering point and second parameters of the centroid of the sensed target. Further, the first device determines a positioning result of the sensed target based on the third parameters of the first scattering point of the sensed target. The first parameters include at least one of the following: the echo incident angle of the first scattering point of the sensed target, the velocity of the first scattering point of the sensed target, the distance of the first scattering point of the sensed target, and the coordinates of the first scattering point of the sensed target. The second parameter is determined based on a first model. The second parameter includes at least one of the following: the echo incident angle of the centroid of the sensed target, the velocity of the centroid of the sensed target, the distance of the centroid of the sensed target, and the coordinates of the centroid of the sensed target.
[0008] In this embodiment, the first device uses the second parameter of the centroid of the perceived target determined by the first model, and the first parameter of the first scattering point of the perceived target determined by a traditional sensing processing method, to determine the third parameter of the first scattering point of the perceived target. Compared to existing solutions that rely solely on the first parameter of the first scattering point of the perceived target determined by a traditional sensing processing method, this solution utilizes the more accurate second parameter of the centroid of the perceived target output by the first model to correct the first parameter of the first scattering point of the perceived target that deviates from the centroid parameter. This makes the third parameter of the first scattering point of the perceived target closer to the second parameter of the centroid of the perceived target with a smaller deviation, improving the estimation accuracy and confidence of the parameters of the scattering point of the perceived target, thereby enhancing the positioning accuracy of the perceived target.
[0009] In conjunction with the first aspect, in one possible implementation, determining a third parameter of the first scattering point of the perceived target based on the first parameter and a second parameter of the centroid of the perceived target includes: a first device determining the third parameter based on the first parameter, the second parameter, and a first threshold. Here, the first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference, or the first threshold includes a confidence value of the second parameter.
[0010] In the above implementation, when the first device determines the third parameter of the first scattering point of the perceived target based on the first parameter and the second parameter, it can also combine the first threshold to determine the difference between the first parameter and the second parameter, or the credibility of the second parameter, so as to determine the third parameter with higher accuracy, which is beneficial to improving the positioning accuracy.
[0011] In conjunction with the first aspect, in one possible implementation, the first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: if the first difference between the first parameter and the second parameter is greater than the first threshold, the first device determines the third parameter based on the second parameter. Here, the first difference includes at least one of a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid, a second velocity difference between the velocity of the first scattering point and the velocity of the centroid, a second distance difference between the distance of the first scattering point and the distance of the centroid, and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0012] In the above implementation, if the first difference between the first parameter and the second parameter is greater than the first threshold, it indicates that the first parameter of the first scattering point of the perceived target deviates significantly from the second parameter of the centroid of the perceived target. This can be understood as the first parameter having a large error and low accuracy. In this case, the first device can, based on the second parameter of the centroid of the perceived target output by the first model, assist in determining a third parameter of the first scattering point of the perceived target that has a smaller deviation from the second parameter and higher accuracy. This allows for the correction of the parameter of the first scattering point of the perceived target, improving the accuracy of the scattering point parameter and thus enhancing the positioning accuracy.
[0013] In conjunction with the first aspect, in one possible implementation, the first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: if the first difference between the first parameter and the second parameter is less than or equal to the first threshold, the first device determines the first parameter as the third parameter. Here, the first difference includes at least one of a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid, a second velocity difference between the velocity of the first scattering point and the velocity of the centroid, a second distance difference between the distance of the first scattering point and the distance of the centroid, and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0014] In the above implementation, if the first difference between the first parameter and the second parameter is less than or equal to the first threshold, it indicates that the deviation between the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target is small. This means the error of the first parameter is small, and its accuracy is high. In this case, the first device can directly determine the first parameter as the third parameter of the first scattering point of the perceived target, without needing to correct the parameters of the first scattering point. This eliminates the need to combine the second parameter of the centroid of the perceived target output by the first model to determine the third parameter, reducing the implementation complexity of the first device and making it simple and easy to implement.
[0015] In conjunction with the first aspect, in one possible implementation, the first threshold includes the confidence value of the second parameter. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: a first device determining a first difference between the first parameter and the second parameter, and then determining a second ratio based on a first ratio of the first difference to the second parameter. If the second ratio is less than the first threshold, the first device determines the third parameter based on the second parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. The sum of the first ratio and the second ratio equals 1. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid.
[0016] In the above implementation, if the second ratio is less than the first threshold, it indicates that the reliability of the first parameter of the first scattering point of the perceived target is lower than the second parameter of the centroid of the perceived target output by the first model. This can be understood as the first parameter having low accuracy and a significant deviation from the second parameter. In this case, the first device can, based on the second parameter of the centroid of the perceived target output by the first model, assist in determining a third parameter of the first scattering point of the perceived target that has a smaller deviation from the second parameter and higher accuracy. This allows for the correction of the parameters of the first scattering point of the perceived target, improving the accuracy of the scattering point parameters and thus enhancing the positioning accuracy.
[0017] In conjunction with the first aspect, in one possible implementation, the first threshold includes the confidence value of the second parameter. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: a first device determining a first difference between the first parameter and the second parameter, and then determining a second ratio based on a first ratio of the first difference to the second parameter. If the second ratio is greater than or equal to the first threshold, the first device determines the first parameter as the third parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid. The sum of the first ratio and the second ratio equals 1.
[0018] In the above implementation, if the second ratio is greater than or equal to the first threshold, it indicates that the reliability of the first parameter of the first scattering point of the perceived target is higher than the second parameter of the centroid of the perceived target output by the first model. This can be understood as the first parameter having higher accuracy and a smaller deviation from the second parameter. In this case, the first device can directly determine the first parameter as the third parameter of the first scattering point of the perceived target, without needing to correct the parameters of the first scattering point. This eliminates the need to combine the second parameter of the centroid of the perceived target output by the first model to determine the third parameter, reducing the implementation complexity of the first device and making it simple and easy to implement.
[0019] In conjunction with the first aspect, in one possible implementation, determining the third parameter based on the second parameter includes: the first device determining the second parameter as the third parameter, or the first device determining the third parameter based on the average of the first parameter and the second parameter. Here, the average of the first parameter and the second parameter includes at least one of the following: the average of the echo incident angle of the first scattering point and the echo incident angle of the centroid; the average of the velocity of the first scattering point and the velocity of the centroid; the average of the distance between the first scattering point and the distance between the centroid; and the average of the coordinates of the first scattering point and the coordinates of the centroid. Determining the third parameter of the first scattering point of the sensing target in this manner is simple and easy to implement.
[0020] In conjunction with the first aspect, in one possible implementation, the method further includes: a first device receiving first information. Here, the first information includes the network topology of the first model and the parameters of the neuron nodes.
[0021] In the above implementation, the first device can receive first information to indicate the first model, thereby generating the first model for subsequent determination of the second parameter of the centroid of the perceived target, and assisting in determining the third parameter of the first scattering point of the perceived target with higher accuracy.
[0022] In conjunction with the first aspect, in one possible implementation, the method further includes: a first device acquiring a first threshold.
[0023] In the above implementation, the first device can obtain a first threshold, which can be used to combine the first parameter of the first scattering point of the sensing target and the second parameter of the centroid of the sensing target to determine the third parameter of the first scattering point of the sensing target with higher accuracy.
[0024] In conjunction with the first aspect, in one possible implementation, the method further includes: the first device sending a first dataset to the second device. Here, the first dataset includes a first echo signal of the perceived target or a first signal obtained by performing a Fourier transform on the first echo signal of the perceived target. The first dataset is used for training a first model, and / or, the first dataset is used to determine a first threshold.
[0025] In the above implementation, the first device can send a first dataset to train a first model and determine a first threshold. Subsequently, based on the second parameter of the centroid of the perceived target output by the first model and the first threshold, the third parameter of the first scattering point of the perceived target can be determined.
[0026] In conjunction with the first aspect, in one possible implementation, the first dataset includes a validation set, and the validation set and the first model are used to determine the first threshold.
[0027] In conjunction with the first aspect, in one possible implementation, the second parameter is determined based on the first model, including: the first device acquiring a second echo signal of the perceived target, or the first device acquiring a second signal obtained by performing a Fourier transform on the second echo signal of the perceived target. Then, the first device determines the second parameter based on the first model and the second echo signal, or the first device determines the second parameter based on the first model and the second signal.
[0028] Secondly, this application provides a communication method applied to a second device. The method includes: the second device determining a first model and sending first information to the first device. The first model is used to determine a second parameter of the centroid of a sensing target. The first parameter of a first scattering point of the sensing target, along with the second parameter, is used to determine a third parameter of the first scattering point of the sensing target. The third parameter is used to determine the localization result of the sensing target. The first parameter includes at least one of the following: the echo incident angle of the first scattering point of the sensing target, the velocity of the first scattering point of the sensing target, the distance of the first scattering point of the sensing target, and the coordinates of the first scattering point. The second parameter includes at least one of the following: the echo incident angle of the centroid of the sensing target, the velocity of the centroid of the sensing target, the distance of the centroid of the sensing target, and the coordinates of the centroid of the sensing target. The first information includes the network topology of the first model and the parameters of the neuron nodes.
[0029] In the above implementation, after determining the first model, the second device can receive the first information indicating the first model, so that the second device can subsequently determine the second parameter of the centroid of the perceived target and the first parameter of the first scattering point of the perceived target based on the first model, and then determine the third parameter of the first scattering point of the perceived target. Compared with the existing scheme, which only relies on the first parameter of the first scattering point of the perceived target determined by traditional sensing processing methods, the above scheme utilizes the second parameter of the centroid of the perceived target output by the first model to correct the first parameter of the first scattering point of the perceived target that deviates significantly from the centroid parameter, thereby improving the estimation accuracy and confidence of the parameters of the scattering point of the perceived target and enhancing the positioning accuracy of the perceived target.
[0030] In conjunction with the second aspect, in one possible implementation, determining the first model includes: a second device receiving a first dataset and training the first model based on the first dataset. Here, the first dataset includes a first echo signal of the sensed target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensed target.
[0031] In conjunction with the second aspect, in one possible implementation, the first dataset includes a validation set, and the method further includes: a second device determining a first threshold based on the validation set and the first model. Here, the first threshold, the first parameter, and the second parameter are used to determine a third parameter. The first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference, or the first threshold includes a confidence value of the second parameter.
[0032] In conjunction with the second aspect, in one possible implementation, the method further includes: the second device sending a first threshold to the first device.
[0033] In the above implementation, the second device sends a first threshold to the first device, which can be used to determine the third parameter of the first scattering point of the sensing target with higher accuracy based on the first threshold, the first parameter and the second parameter, thereby improving the positioning accuracy.
[0034] It should be understood that the communication method provided in the second aspect above is used to cooperate with the communication method provided in the first aspect above, and thus can achieve the same beneficial effect. To avoid redundancy, it will not be explained again.
[0035] It should be understood that the communication method provided in the first aspect above is also applicable to functional components within the first device, such as processors, chips, chip systems, circuits, etc., within the first device, and this application does not specifically limit them. Similarly, the communication method provided in the second aspect above is also applicable to the corresponding functional components within the device, and to avoid redundancy, it will not be repeated here.
[0036] Thirdly, this application provides a communication device, which can be the first device mentioned in the first aspect. The communication device includes modules, units, or means that implement the above-described methods. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above-described functions.
[0037] In some possible designs, the communication device includes a transceiver unit (also called a transceiver module) and a processing unit (also called a processing module). The processing unit is used to acquire first parameters of a first scattering point of the sensed target. The first parameters include at least one of the following: the echo incident angle of the first scattering point of the sensed target, the velocity of the first scattering point of the sensed target, the distance of the first scattering point of the sensed target, and the coordinates of the first scattering point of the sensed target. The processing unit is also used to determine a third parameter of the first scattering point of the sensed target based on the first parameters of the first scattering point of the sensed target and a second parameter of the centroid of the sensed target. The second parameter is determined based on a first model. The second parameter includes at least one of the following: the echo incident angle of the centroid of the sensed target, the velocity of the centroid of the sensed target, the distance of the centroid of the sensed target, and the coordinates of the centroid of the sensed target. The processing unit is also used to determine the positioning result of the sensed target based on the third parameter of the first scattering point of the sensed target.
[0038] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine a third parameter based on the first parameter, the second parameter, and the first threshold. Here, the first threshold includes at least one of the first angle difference, the first velocity difference, the first distance difference, and the first coordinate difference, or the first threshold includes the confidence value of the second parameter.
[0039] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine a third parameter based on the second parameter if the first difference between the first parameter and the second parameter is greater than a first threshold. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0040] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine the first parameter as the third parameter if the first difference between the first parameter and the second parameter is less than or equal to a first threshold. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0041] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine a first difference between the first parameter and the second parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. The processing unit is further configured to determine a second ratio based on a first ratio of the first difference to the second parameter. Here, the sum of the first ratio and the second ratio is equal to 1. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid. The processing unit is further configured to determine a third parameter based on the second parameter if the second ratio is less than a first threshold.
[0042] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine a first difference between the first parameter and the second parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. The processing unit is further configured to determine a second ratio based on a first ratio of the first difference to the second parameter. Here, the sum of the first ratio and the second ratio is equal to 1. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid. The processing unit is further configured to determine the first parameter as a third parameter if the second ratio is greater than or equal to a first threshold.
[0043] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to determine the second parameter as the third parameter, or to determine the third parameter based on the average of the first parameter and the second parameter. Here, the average of the first parameter and the second parameter includes at least one of the following: the average of the echo incident angle of the first scattering point and the echo incident angle of the centroid, the average of the velocity of the first scattering point and the velocity of the centroid, the average of the distance between the first scattering point and the distance between the centroid, and the average of the coordinates of the first scattering point and the coordinates of the centroid.
[0044] In conjunction with the third aspect, in one possible implementation, a transceiver unit is used to receive first information. Here, the first information includes the network topology of the first model and the parameters of the neuron nodes.
[0045] In conjunction with the third aspect, in one possible implementation, the processing unit is also used to obtain the first threshold.
[0046] In conjunction with the third aspect, in one possible implementation, the transceiver unit is also used to transmit a first dataset. Here, the first dataset includes a first echo signal of the sensed target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensed target. The first dataset is used for training the first model, and / or, the first dataset is used to determine a first threshold.
[0047] In conjunction with the third aspect, in one possible implementation, the first dataset includes a validation set, and the validation set and the first model are used to determine the first threshold.
[0048] In conjunction with the third aspect, in one possible implementation, the processing unit is further configured to acquire a second echo signal of the perceived target, or the first device acquires a second signal obtained by performing a Fourier transform on the second echo signal of the perceived target. The processing unit is further configured to determine a second parameter based on the first model and the second echo signal, or the first device determines the second parameter based on the first model and the second signal.
[0049] Fourthly, this application provides a communication device, which can be the second device mentioned in the second aspect above. The communication device includes modules, units, or means that implement the above-described methods. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above-described functions.
[0050] In some possible designs, the communication device includes a transceiver unit (also called a transceiver module) and a processing unit (also called a processing module). The processing unit is used to determine a first model. The first model is used to determine a second parameter of the centroid of the perceived target. The first parameter of the first scattering point of the perceived target, along with the second parameter, is used to determine a third parameter of the first scattering point of the perceived target. The third parameter is used to determine the localization result of the perceived target. The first parameter includes at least one of the following: the echo incident angle of the first scattering point of the perceived target, the velocity of the first scattering point of the perceived target, the distance of the first scattering point of the perceived target, and the coordinates of the first scattering point. The second parameter includes at least one of the following: the echo incident angle of the centroid of the perceived target, the velocity of the centroid of the perceived target, the distance of the centroid of the perceived target, and the coordinates of the centroid of the perceived target. The transceiver unit is used to transmit first information. The first information includes the network topology of the first model and the parameters of the neuron nodes.
[0051] In conjunction with the fourth aspect, in one possible implementation, the transceiver unit is further configured to receive a first dataset. Here, the first dataset includes a first echo signal of the sensed target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensed target. The processing unit is further configured to train a first model based on the first dataset.
[0052] In conjunction with the fourth aspect, in one possible implementation, the processing unit is further configured to determine a first threshold based on the validation set and the first model. Here, the first threshold, the first parameter, and the second parameter are used to determine the third parameter. The first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference, or the first threshold includes the confidence value of the second parameter.
[0053] In conjunction with the fourth aspect, in one possible implementation, the transceiver unit is also used to send the first threshold.
[0054] Fifthly, this application provides a computer program product comprising instructions that, when executed on a computer, cause the computer to perform the method of any one of the first aspects or any possible implementations of the first aspect, or to perform the method of any one of the second aspects or any possible implementations of the second aspect.
[0055] Sixthly, this application provides a computer-readable storage medium storing a computer program that, when executed, performs the method described in any one of the first aspects or any possible implementations of the first aspect, or performs the method described in any one of the second aspects or any possible implementations of the second aspect.
[0056] Seventhly, this application provides a communication device including at least one processor. The at least one processor is configured to execute the method described in any of the preceding aspects or any possible implementation thereof. The communication device may be a first device as described in the first aspect, or a device including the first device, or a device included in the first device, such as a chip; or, the communication device may be a second device as described in the second aspect, or a device including the second device, or a device included in the second device, such as a chip.
[0057] In conjunction with the seventh aspect, in one possible implementation, the communication device further includes a memory for storing necessary program instructions and data (i.e., computer programs).
[0058] In conjunction with the seventh aspect, in one possible implementation, the memory can be coupled to the processor, or it can be independent of the processor.
[0059] Eighthly, this application provides a chip system that includes at least a processor. The processor is configured to execute computer execution instructions to cause a device mounted on the chip system to perform the method described in any one of the first aspects or any possible implementations of the first aspect, or to perform the method described in any one of the second aspects or any possible implementations of the second aspect.
[0060] In conjunction with aspect eight, in one possible implementation, the chip system may further include interface circuitry. This interface circuitry is used to receive computer execution instructions and transmit them to the processor.
[0061] Ninthly, this application provides a communication device comprising: a processor and an interface circuit. The interface circuit is configured to receive signals from other communication devices besides the communication device and transmit them to the processor, or to send signals from the processor to other communication devices besides the communication device. The processor is configured to implement the method described in any of the preceding aspects through logic circuits or by executing computer programs or instructions. The communication device may be the first device as described in the first aspect, or a device including the first device, or a device included in the first device, such as a chip system; or, the communication device may be the second device as described in the second aspect, or a device including the second device, or a device included in the second device.
[0062] Tenthly, this application provides a communication system. The communication system includes at least a first device and a second device, the first device being configured to perform the communication method provided by the first aspect or any possible implementation thereof, and the second device being configured to perform the communication method provided by the second aspect or any possible implementation thereof.
[0063] In summary, the communication method provided in this application can correct the scattering point parameters that are significantly deviated from the centroid parameters of the perceived target, thereby improving the estimation accuracy and confidence of the scattering point parameters of the perceived target and thus enhancing the positioning accuracy. Attached Figure Description
[0064] Figure 1 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;
[0065] Figure 2a is a schematic diagram of a scenario where a base station transmits and receives data independently, according to an embodiment of this application.
[0066] Figure 2b is a schematic diagram of a scenario where base stations mutually transmit and receive data, provided in an embodiment of this application;
[0067] Figure 2c is a schematic diagram of a UE transmitting and receiving scenario provided in an embodiment of this application;
[0068] Figure 3 is a flowchart illustrating a communication method provided in an embodiment of this application;
[0069] Figure 4 is a schematic diagram of a first model example provided in an embodiment of this application;
[0070] Figure 5 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;
[0071] Figure 6 is a schematic diagram of another communication device provided in an embodiment of this application;
[0072] Figure 7 is a schematic diagram of the structure of another communication device provided in an embodiment of this application. Detailed Implementation
[0073] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0074] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates an "or" relationship between the preceding and following related objects; in the formulas of this application, the character " / " indicates a "division" relationship between the preceding and following related objects. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.
[0075] The technical solutions provided in this application can be applied to various communication systems, such as Long Term Evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, 5th generation (5G) systems, or new radio (NR) systems. In addition, they can also be applied to future communication systems, such as 6th generation (6G) communication systems.
[0076] The system architecture used in the embodiments of this application is described below. It should be noted that the system architecture and business scenarios described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.
[0077] Please refer to Figure 1, which is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. As shown in Figure 1, the communication system 10 may include a first device and a second device. The first device and the second device cooperate with each other and can be used to implement the communication method provided in this application.
[0078] The first device can be a means, apparatus, or functional entity with sensing and computing capabilities. In some possible implementations, the first device can also be called a sensing device, which can be a terminal device or network device participating in the sensing process. It should be understood that in future communication systems, the first device can still be a terminal device or network device, or the first device can also be other means with sensing and computing capabilities, or the first device can have other names; this application does not impose specific limitations in this regard. It should be understood that this application does not impose specific limitations on the specific type of the first device.
[0079] Among them, terminal equipment can be referred to as: user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user equipment, etc.
[0080] Terminal devices can be devices that provide voice / data connectivity to users, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, 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, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in 5G networks, or terminal devices in future PLMNs, etc., and this application embodiment does not limit these.
[0081] As an example and not a limitation, in this application embodiment, wearable devices can also be called wearable smart devices. This is a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, and watches. Wearable devices are portable devices worn directly on the body or integrated into a user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable devices include those with comprehensive functions, large size, and the ability to achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those focused on a specific application function that require interaction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.
[0082] Furthermore, in this embodiment, the terminal device can also be a terminal device in an Internet of Things (IoT) system. IoT is an important component of future information technology development, and its main technical feature is connecting objects to networks through technology, thereby realizing an intelligent network for human-machine interconnection and object-to-object interconnection. In this embodiment, the terminal device can also include a relay. Alternatively, it can be understood that anything capable of data communication with a base station can be considered a terminal device.
[0083] A network device can be a base station, an access point, or an access network device, or it can refer to a device in an access network that communicates with a wireless terminal via one or more sectors on the air interface. A network device can be used to convert received air frames to and from Internet Protocol (IP) packets, and act as a router between the wireless terminal and the rest of the access network, which may include an IP network. The network device can also coordinate the attribute management of the air interface. For example, the network device can be an evolved node B (eNB or eNodeB) in an LTE system, a radio controller in a cloud radio access network (CRAN) or open radio access network (ORAN) scenario, or a relay station, access point, vehicle-mounted device, wearable device, access device in a 5G network, or a network device in a future evolved public land mobile network (PLMN), or an access point (AP) in a wireless local area network (WLAN), or a 5G radio base station (gNodeB or gNB) in an NR system. This application embodiment does not limit this.
[0084] In addition, in the embodiments of this application, the network device can be a device in the radio access network (RAN), or in other words, a RAN node that connects the terminal device to the wireless network. For example, by way of example and not limitation, network devices can include: gNB, transmission reception point (TRP), 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), base band unit (BBU), or wireless fidelity (WiFi) AP, etc.
[0085] For example, in an ORAN scenario, the RAN can communicate with the second device via a backhaul link and with the terminal via an air interface. Specifically, the BBU in the access network equipment communicates with the second device via the backhaul link, and the radio unit (RU) in the access network equipment communicates with at least one terminal device via an air interface. The BBU communicates with at least one RU via a fronthaul link; the BBU and RU can be co-located or non-co-located. The BBU includes at least one control unit (CU) and at least one distributed unit (DU), which can communicate via at least one midhaul link.
[0086] In some examples, the CU is a logical node carrying the radio resource control (RRC) layer, service data adaptation protocol (SDAP) layer, packet data convergence protocol (PDCP) layer, and other control functions of the access network equipment. The CU connects to network nodes such as the core network through interfaces, which can be interfaces such as E2 interfaces. Optionally, the CU may have some core network functions. The CU (e.g., the PDCP layer and higher layers) connects to the DU (e.g., the radio link control layer and lower layers) through interfaces, which can be interfaces such as the F1 interface. In some examples, these interfaces (e.g., the F1 interface) can provide control plane (C-Plane) and user plane (U-Plane) functions (e.g., interface management, system information management, UE context management, RRC message transmission, etc.). F1AP is the application protocol of the F1 interface, defining the F1 signaling procedures in some examples. The F1 interface supports control plane F1-C and user plane F1-U.
[0087] In some examples, the CU can be split into CU-CP (control unit-control plane) and CU-UP (control unit-user plane). CU-CP is a logical node carrying the RRC layer and PDCP-C (Control plane part of PDCP) layer, used to implement the CU's control plane functions. CU-CP can interact with network elements in the core network used to implement control plane functions. These network elements in the core network can be access and mobility function (AMF) elements, such as the access and mobility management function (AMF) in a 5G system. The AMF element is responsible for mobility management in the mobile network, such as terminal device location updates, terminal device registration with the network, and terminal device handover. CU-UP is a logical node carrying the SDAP layer and PDCP-U (user plane part of PDCP) layer, used to implement the CU's user plane functions. CU-UP can interact with network elements in the core network used to implement user plane functions. These network elements in the core network, such as the UPF (user plane function) in a 5G system, are responsible for data forwarding and receiving in terminal devices. The above CU and DU configurations are merely examples; the functions of the CU and DU can be configured as needed. For instance, the CU or DU can be configured to have more protocol layer functions, or only some protocol layer processing functions. For example, some functions of the radio link control (RLC) layer and protocol layer functions above the RLC layer can be placed in the CU, while the remaining RLC layer functions and protocol layer functions below the RLC layer can be placed in the DU. Furthermore, the functions of the CU or DU can be divided according to service type or other system requirements, such as by latency. Functions that require low latency can be placed in the DU, while functions that do not require low latency can be placed in the CU.
[0088] In some examples, a DU is a logical node that carries the RLC layer, medium access control (MAC) layer, higher physical layer (Higher PHY) layer, and other functions. In some examples, a DU can control at least one RU. The DU connects to the RU through interfaces, which can be fronthaul interfaces. In some examples, the Higher PHY layer includes the PHY layer processing, such as forward error correction (FEC) encoding and decoding, scrambling, modulation, and demodulation.
[0089] In some examples, the RU is a logical node that carries both lower physical layer (PHY) and radio frequency (RF) processing. In some examples, the RU can be a 3GPP TRP, a remote radio head (RRH), or other similar entity. In some examples, the Low-PHY includes PHY processing functions such as fast Fourier transform (FFT), inverse fast Fourier transform (IFFT), digital beamforming, and filtering. The RU communicates with one or more UEs via a radio link.
[0090] The DU and RU can be co-located or not. The DU and RU exchange control plane and user plane information via a lower-layer split-control, user, and synchronization (LLS-CUS) interface through a fronthaul link. LLS-CUS may include LLS-C and LLS-U interfaces that provide the control plane (C-Plane) and user plane (U-Plane), respectively. In some examples, the control plane (C-Plane) refers to real-time control between the DU and RU. The DU and RU exchange management information via an LLS-M interface on the fronthaul link; the management plane (M-Plane) refers to non-real-time management operations between the DU and RU.
[0091] DU and RU can cooperate to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of DU and RU can be configured in various ways depending on the design. For example, a DU can be configured to implement baseband functions, and an RU can be configured to implement mid-RF functions. Another example is that a DU can be configured to implement higher-level functions in the PHY layer, and an RU can be configured to implement lower-level functions in the PHY layer, or to implement both lower-level and RF functions. Higher-level functions in the physical layer can include a portion of the physical layer's functions that are closer to the MAC layer, while lower-level functions in the physical layer can include another portion of the physical layer's functions that are closer to the mid-RF side.
[0092] In different systems, CU (or CU-CP and CU-UP), DU, or RU can also have different names. For example, in the ORAN system, CU can also be called open CU (open CU, O-CU), DU can also be called open DU (open DU, O-DU), CU-CP can also be called open CU-CP (open CU-CP, O-CU-CP), CU-UP can also be called open CU-UP (open CU-UP, O-CU-UP), and RU can also be called open RU (open RU, O-RU).
[0093] It should be noted that the aforementioned network devices and terminal devices can be fixed in location or mobile. Specifically, network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted, on water, or in the air on airplanes, balloons, and satellites. This application does not impose specific limitations on the application scenarios of the network devices and terminal devices.
[0094] Network devices and terminal devices, as well as terminal devices communicating with each other, can communicate using licensed spectrum, unlicensed spectrum, or both simultaneously. Network devices and terminal devices, as well as terminal devices communicating with each other, can communicate using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. This application does not impose specific restrictions on the spectrum resources used between network devices and terminal devices.
[0095] Optionally, the second device can be used to acquire information such as the location and speed of the sensed object or target through sensing capabilities. Alternatively, the second device can be a device, network element, or functional entity that provides sensing functionality. The network element can also be referred to as an entity, device, apparatus, or module, etc., and this application does not specifically limit its usage. In some possible implementations, the second device can be a sensing function (SF) network element in a 5G network architecture, or it can be other network elements with sensing capabilities, or it can have other names; this application does not limit its usage. It should be understood that this application does not limit the specific type of the second device.
[0096] It should be understood that the communication system provided in this application can be applied in ISAC sensing scenarios. The first device can process the echo signal of the sensing target in different sensing modes to achieve target sensing. Furthermore, the first device can upload the echo signal or the intermediate sensing result obtained after preprocessing the echo signal (e.g., Fourier transform) to the second device for training the first model. In this way, the parameters of the sensing target output by the first model can be used to help determine the positioning result of the sensing target.
[0097] In other words, in the ISAC system, the second device can be responsible for the processing and interaction of sensing services within the ISAC system. Optionally, the second device can be placed in the core network to realize the processing and transfer of different sensing data, as well as the issuance and reception of sensing service-related instructions.
[0098] ISAC sensing can generally be divided into three modes: single-site sensing, dual-site sensing, and joint sensing at both sites.
[0099] In single-site sensing, the transmitting and receiving ends of the sensing signals are the same device. In terms of the sensing signal flow, this sensing station must both transmit sensing signals (e.g., a base station transmits a reference signal to achieve target sensing) and receive signals reflected from the surface of the sensing target. Therefore, single-site sensing mode is also known as self-transmitting and self-receiving mode.
[0100] Dual-station sensing involves two different devices that transmit and receive the sensing signal. In terms of the signal transmission flow, after sensing station A transmits the signal, the signal reflected from the surface of the target is received by sensing station B. Therefore, dual-station sensing is also known as the A-transmit, B-receive mode.
[0101] Joint sensing between the sensing station and the UE involves sensing together. Based on the different target of the signal transmission, it can be divided into uplink sensing signals and downlink sensing signals.
[0102] It should be noted that, when the first device mentioned above is a network device such as a base station, the communication method provided in this application is applicable to scenarios where the base station transmits and receives data independently, base stations transmit and receive data from each other (e.g., base station A transmits and base station B receives), and the UE transmits and the base station receives data. When the first device mentioned above is a UE, the communication method provided in this application is applicable to scenarios where the base station transmits and the UE receives data. This application does not impose specific limitations on the application scenarios.
[0103] The following examples, using Figures 2a, 2b, and 2c, illustrate scenarios of base station self-transmission and reception, base station mutual transmission and reception, and UE transmission and base station reception, respectively. It should be noted that the solid lines in Figures 2a, 2b, and 2c represent the transmission direction of signals transmitted by base station 1, while the dashed lines represent the transmission direction of signals transmitted by base station 2.
[0104] Please refer to Figure 2a, which is a schematic diagram of a self-transmitting and self-receiving scenario provided by an embodiment of this application. As shown in Figure 2a, for base station 1, the sensing signal it transmits can be received by base station 1 after being reflected or scattered by sensing target 1 and sensing target 2. Similarly, for base station 2, the sensing signal it transmits can be received by base station 2 after being reflected or scattered by sensing target 1 and sensing target 2.
[0105] Please refer to Figure 2b, which is a schematic diagram of a scenario where base stations mutually transmit and receive signals according to an embodiment of this application. As shown in Figure 2b, for base station 1, the sensing signal it transmits can be received by base station 2 after being reflected or scattered by sensing target 1 and sensing target 2. For base station 2, the sensing signal it transmits can be received by base station 1 after being reflected or scattered by sensing target 1 and sensing target 2.
[0106] Please refer to Figure 2c, which is a schematic diagram of a UE transmitting and receiving scenario provided in an embodiment of this application. As shown in Figure 2c, the sensing signal transmitted by the UE can be received by base station 1 and / or base station 2 after being reflected or scattered by sensing target 1. Similarly, the sensing signal transmitted by the UE can also be received by base station 1 and / or base station 2 after being reflected or scattered by sensing target 2.
[0107] To support artificial intelligence (AI) technology in wireless networks, AI nodes may also be introduced into the network.
[0108] Optionally, the AI node can be deployed in one or more of the following locations within the communication system: network devices, terminal devices, or core network devices. Alternatively, the AI node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as a host or cloud server in an over-the-top (OTT) system. The AI node can communicate with other devices in the communication system, which may be one or more of the following: network devices, terminal devices, or core network elements.
[0109] It should be noted that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, they can be divided based on function, such as different AI nodes being responsible for different functions.
[0110] It should also be noted that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (such as a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.
[0111] Among them, AI nodes can be AI network elements or AI models.
[0112] Optionally, referring to Figure 1, both the first and second devices in the communication system 10 shown in Figure 1 can include an AI module. That is, the AI module can be deployed in both the first and second devices.
[0113] The AI module can be used to implement corresponding AI functions. The AI modules deployed in the first and second devices can be the same or different. Depending on the parameter configuration, the AI module model can achieve different functions. The AI module model can 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 can also be referred to as the neural network bias.
[0114] An AI module can have one or more models. A model can infer an output that 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.
[0115] To facilitate understanding of this application, some terms or concepts used in this application will be explained below.
[0116] 1. Integrated communication and sensing
[0117] Communication-sensing integration is a key technology in next-generation wireless communication systems. It aims to integrate wireless communication and sensing functions into a single system, utilizing the various propagation characteristics of wireless signals to achieve sensing functions such as target localization, detection, imaging, and identification. This allows for the acquisition of information about the surrounding physical environment, improving communication performance and enhancing user experience. In communication-sensing integration technology, network devices can sense targets in the environment by sending sensing signals and receiving echo signals, thereby obtaining information such as the position and speed of the sensed targets.
[0118] The sensing signal can refer to a signal used to sense or detect a target, or in other words, a signal used to sense wake-up information or detect environmental information. For example, a sensing signal can be an electromagnetic wave sent by a network device to sense environmental information. Sensing signals can also be called radar signals, radar sensing signals, detection signals, radar detection signals, environmental sensing signals, etc., and this application does not limit the terminology.
[0119] The echo signal is the signal generated when the sensed signal is reflected by a sensed target in the environment. The time delay of the echo signal relative to the transmitted sensed signal reflects the distance of the sensed target, and the Doppler frequency shift of the echo signal relative to the transmitted sensed signal reflects the velocity of the sensed target.
[0120] 2. Perceiving the target
[0121] A sensing target refers to an object that a communication system or sensing device uses various technical means and algorithms to detect, identify, and acquire relevant information about. It can include various tangible objects on the ground that can be sensed, such as mountains, forests, or buildings, and can also include mobile objects such as vehicles, drones, pedestrians, and terminal devices. A sensing target can also be referred to as a target, a sensed target, a detected target, a sensed object, a sensed device, etc., and this application does not limit the terminology used.
[0122] For sensing targets, based on the number of echo signals generated after the sensing signal is reflected or scattered by the target, sensing targets can be divided into point targets and extended targets. It should be understood that the specific location on the sensing target where scattering occurs can be called the scattering point.
[0123] In this context, an extended target can generate multiple signal scattering points or signal measurements simultaneously. For example, a sensing station sends a sensing signal, which is reflected or scattered by a car, generating an echo signal. If the sensing station can simultaneously receive echo signals from different parts of the car, such as the front, rear, and wheels, then the car is considered an extended target. In other words, an extended target often generates scattering points at different locations, and the multiple echo signals corresponding to these points can be simultaneously received by the sensing station after being superimposed. It should be understood that the front, rear, and wheels of a car can all be scattering points.
[0124] The scattering characteristics of a point target are generally considered uniform in all directions, and its echo signal contains only one dominant scattering component. In other words, a point target can be considered to produce a single signal scattering point or signal measurement at any given time. For example, in satellite communications, some small satellites can be considered point targets.
[0125] 3. Perceptual spectrum and resolution
[0126] For echo signals from multiple carriers, multiple antennas, and multiple symbols, a joint time / frequency / spatial Fourier transform or beamforming is applied to convert them into a sensing spectrum in the beam domain. This sensing spectrum contains filtered signals from all velocity / delay / angle domain sampling points (which can be converted to Cartesian coordinates) within a specified sensing area. In other words, this sensing spectrum presents the scattered echo signal of the target point at the corresponding velocity / delay / angle position.
[0127] Resolution is the smallest unit of parameter used to describe the ability to distinguish between two different targets. Taking distance estimation as an example, a distance resolution of 1 meter (m) means that when the distance between two targets is greater than or equal to 1m, the sensing device can distinguish between the two targets, but when their distance is less than 1m, the sensing device cannot distinguish between the two targets.
[0128] 4. Constant false-alarm rate (CFAR) detection and peak search
[0129] After obtaining the multidimensional sensing spectrum, a constant false alarm rate (CFAR) detection algorithm is used to process the spectrum. The purpose of CFAR is to detect the presence of a target with a constant false alarm probability in noisy and cluttered environments. It performs statistical analysis on the spectral data and automatically adjusts the detection threshold based on a set false alarm probability threshold, thereby accurately identifying spectral regions where targets may exist under different noise and clutter backgrounds. During this process, regions in the spectrum exceeding the detection threshold are marked as areas where targets may exist, providing candidate regions for subsequent peak search.
[0130] Within the region where a target is likely to exist, as determined by constant false alarm rate (CFAR) detection, a peak search is performed. Since a target's multidimensional sensing spectrum typically exhibits concentrated energy peaks, searching for the peak positions in the spectrum reveals locations corresponding to the target's parameters. For example, in the spatial domain, the peak position might correspond to the target's angle; in the frequency domain, it might be related to the target's velocity. By precisely searching for peak positions, parameter information about the target in various dimensions can be obtained.
[0131] 5. Direction finding and positioning
[0132] Direction finding and positioning is a type of positioning technology that requires sensing technology to acquire various information about the target signal, such as signal strength, frequency, and time of arrival. This sensed information forms the basis for direction finding and positioning calculations. For example, in direction finding and positioning technology based on angle of arrival, the sensing device receives the target signal and calculates the angle of arrival by sensing features such as the signal phase, thereby determining the direction of the target.
[0133] 6. AI Models and Neural Networks
[0134] An AI model is an algorithm or computer program that enables AI functionality. It represents the mapping relationship between the model's input and output. Types of AI models include neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, and other machine learning (ML) models.
[0135] A neural network, or artificial neutral network (ANN), is an artificial intelligence method that consists of interconnected nodes or artificial neurons arranged in a hierarchical structure and transmitting and processing data through weighted connections.
[0136] In neural networks, datasets are fundamental for training and evaluating the network, playing a crucial role in the model's performance and generalization ability. Datasets can be categorized according to their purpose: training datasets (i.e., training sets), validation datasets (i.e., validation sets), and test datasets (i.e., test sets).
[0137] The training set is used to train the neural network model, allowing the model to learn patterns and rules in the data. For example, when training an image classifier, a large number of labeled images are used as the training set, enabling the model to learn to recognize image features of different categories.
[0138] The validation set is used to validate the model's performance and tune hyperparameters during training. By evaluating metrics such as accuracy and loss on the validation set, it's possible to determine if overfitting or underfitting has occurred, and thus adjust hyperparameters such as the model's structure and learning rate.
[0139] The test set is used to ultimately evaluate the generalization ability and performance of the trained model. After the model training is completed, the test set is used to calculate metrics such as accuracy and recall on unseen data to determine whether the model can be well applied to real-world scenarios.
[0140] In simple terms, training a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of deriving this mapping from existing data to random weight matrices and bias vectors is called neural network training.
[0141] The specific training method involves using a loss function to evaluate the output of the neural network and backpropagating the error. The weight matrix and bias vector can be iteratively optimized through gradient descent until the loss function reaches its minimum value.
[0142] During the training of a neural network, since the goal is for the network's output to be as close as possible to the desired predicted value, we can compare the current network's predicted value with the actual target value and update the weight vector of each layer based on the difference. Of course, there is usually an initialization process before the first update, where parameters are pre-configured for each layer in the deep neural network. If the network's predicted value is too high, the weight vector is adjusted to lower the prediction, and this adjustment is continued until the neural network can predict the actual target value or a value very close to it. Therefore, it is necessary to predefine "how to compare the difference between the predicted value and the target value," which is the loss function or objective function. These are important equations used to measure the difference between the predicted and target values. Taking the loss function as an example, the higher the output value (loss), the greater the difference, and training the neural network becomes a process of minimizing this loss as much as possible.
[0143] Neural networks can employ backpropagation (BP) to correct the parameters of the initial neural network model during training, thereby reducing the reconstruction error loss. Specifically, forward propagation of the input signal to the output generates error loss; this error loss information is then propagated back to update the parameters of the initial neural network model, leading to convergence of the error loss. The backpropagation algorithm is an error-loss-driven backpropagation process aimed at obtaining the optimal parameters of the neural network model, such as the weight matrix.
[0144] 7. Correction threshold
[0145] A correction threshold is a specific value used to judge and adjust the output of neurons or certain intermediate results during the training or inference process of a neural network. When the output of a neuron or related data exceeds or falls below this threshold, a corresponding correction operation is triggered to make the behavior or result of the neural network more in line with expectations.
[0146] In traditional sensing processing schemes, the sensing device performs IDFT, DFT, and 2D-DFT on the echo signal of the sensed target to obtain a multi-dimensional sensing spectrum. Then, constant false alarm rate (CFAR) detection and peak search are applied to determine the scattering point parameters of the sensed target on the sensing spectrum, such as angle, velocity, and distance. Furthermore, based on these scattering point parameters, the centroid parameters of the sensed target, such as angle, velocity, and distance, are estimated to obtain the positioning result of the sensed target. However, the accuracy of the positioning result determined in this way depends on the resolution of the sensing spectrum. If the resolution of the sensing spectrum is low and the scattering points of the sensed target are dense, it is difficult to effectively distinguish these dense scattering points. Thus, the centroid parameters of the sensed target estimated based on the scattering point parameters may deviate from the actual centroid parameters of the sensed target, resulting in low positioning accuracy. Therefore, the technical problem to be solved in this application is: how to improve positioning accuracy.
[0147] Based on the above, the communication method of this application embodiment will be described below by way of example.
[0148] Please refer to Figure 3, which is a flowchart illustrating a communication method provided in an embodiment of this application. It should be understood that the communication method shown in Figure 3 is applicable to the communication system 10 shown in Figure 1. Specifically, this communication method can be executed interactively by a first device and a second device. The first device can be a terminal device or a network device, or a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, chip system, functional module, control unit, circuit, processor, or integrated circuit that can be applied to the aforementioned device or apparatus. The second device can be an SF network element, or a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, chip system, functional module, control unit, circuit, processor, or integrated circuit that can be applied to the aforementioned device or apparatus. This application does not limit its scope. As shown in Figure 3, the communication method may specifically include the following steps:
[0149] S301, the second device determines the first model.
[0150] In some feasible implementations, the second device can determine the first model. The first model can be an AI model, for example, it can be obtained by constructing and training a neural network, i.e., an AI model based on a neural network.
[0151] Optionally, the neural network can be a deep neural network designed based on convolutional layers, residual connections, and complex networks. It can also be a neural network with added learning mechanisms, such as reinforcement learning, Transformer, and transfer learning. For example, the neural network can be a deep network based on architectures such as convolutional neural networks, multilayer perceptrons, Transformers, and residual networks.
[0152] In one optional implementation, the second device can acquire an echo signal dataset and train a first model based on the dataset. Specifically, each sensing device in at least one sensing device (e.g., a network device or a terminal device) of the communication system can receive an echo signal (hereinafter referred to as a third echo signal for easy distinction) of at least one sensing target and send at least one third echo signal to the second device. Optionally, each sensing device can perform a Fourier transform on the third echo signal of the at least one sensing target to obtain at least one signal (hereinafter referred to as a third signal for easy distinction) and send at least one third signal to the second device. Further, the second device can use the received at least one third echo signal or at least one third signal as an echo signal dataset and construct and train a neural network based on this dataset to obtain the first model.
[0153] It should be understood that the aforementioned at least one sensing device may include the first device of this application. A sensing device can be understood as a device capable of performing a sensing task, and the object being sensed when performing the sensing task can be called a sensing target. A sensing task refers to a series of operations that collect, detect, analyze, and understand various information in the surrounding environment through various technical means and algorithms.
[0154] It should be noted that, when any of the at least one sensing device is a network device, the third echo signal it receives can be an echo signal of a sensing signal transmitted by itself, or an echo signal of a sensing signal transmitted by another network device besides itself, or an echo signal of an uplink signal transmitted by a terminal device. When any of the at least one sensing device is a terminal device, the third echo signal it receives can be an echo signal of a downlink signal transmitted by a network device.
[0155] Optionally, the third signal can be a spatial signal obtained by performing a Fourier transform on the third echo signal. For example, the sensing device performs frequency and time domain Fourier transforms on the third echo signal, and further detects the target scattering point on the range-velocity spectrum. Then, the spatial signal can be obtained by extracting the signal at a specific range-velocity position.
[0156] In one optional implementation, after acquiring the echo signal dataset, the second device can use a portion of the dataset as a training set. Further, the second device constructs and trains an AI neural network based on the training set to obtain a first model. It should be understood that the second device inputs the training set into the AI neural network and iteratively trains the network's node parameters through gradient iteration until convergence; that is, the trained first model can be convergent.
[0157] It should be noted that the output of the first model can be parameters of the centroid of the perceived target, such as at least one of the following: the echo incident angle of the centroid, the velocity of the centroid, the distance of the centroid, and the coordinates of the centroid.
[0158] In this embodiment, the echo incidence angle of the centroid of the sensed target refers to the angle between the echo signal of the centroid of the sensed target and the antenna panel of the sensing device. The velocity of the centroid of the sensed target refers to the velocity of the centroid of the sensed target relative to the sensing device. The distance of the centroid of the sensed target refers to the straight-line distance between the centroid of the sensed target and the sensing device. The coordinates of the centroid of the sensed target refer to the position coordinates of the centroid of the sensed target with the sensing device as the origin.
[0159] For example, please refer to Figure 4, which is a schematic diagram of a first model example provided in an embodiment of this application. Here, it is assumed that the input of the first model is a spatial signal slice after range-velocity spectrum detection, which can be superimposed into a 40×4×16 tensor signal (i.e., a 40-time-frequency dimension slice and a 4×16 antenna dimension complex signal). As shown in Figure 4, after the spatial signal slice is input into the first model, it passes through a complex convolution layer, a complex maxpool, a complex residual block, and a complex fully connected layer in sequence. The output is the parameters of the centroid of the sensed target, i.e., at least one of the following: the echo incidence angle of the centroid, the distance of the centroid, the coordinates of the centroid, and the velocity of the centroid.
[0160] Optionally, after receiving the echo signal dataset, the second device can use a portion of the dataset other than the training set as a validation set. Furthermore, after training the first model, the second device can use the validation set to verify network performance, i.e., determine the correction threshold for the centroid parameter of the perceived target based on the output loss of the validation set.
[0161] The correction threshold for the centroid parameter can be a specific numerical value, such as an angle difference, velocity difference, distance difference, or coordinate difference. Alternatively, the correction threshold for the centroid parameter can also be a confidence value, or a probability value, which can characterize the confidence level of the second parameter of the centroid of the perceived target output by the first model.
[0162] S302, the second device sends the first information to the first device. Accordingly, the first device receives the first information.
[0163] In some feasible implementations, after determining the first model, the second device can generate first information and send the first information to the first device to indicate the first model. The first information may include the network topology of the first model and the parameters of its neuron nodes.
[0164] It should be noted that network topology refers to the arrangement of neurons, layers, and their connections within a neural network. Optionally, the network topology of the first model may include feedforward neural networks (FNNs), recurrent neural networks (RNNs), convolutional neural networks (CNNs), long short-term memory networks (LSTMs), generative adversarial networks (GANs), graph neural networks (GNNs), etc., and this application does not limit it.
[0165] It should also be noted that the parameters of a neuron node refer to the adjustable values used to control the neuron's behavior and output during information processing and transmission. These parameters are continuously adjusted during neural network training so that the neural network can learn patterns and rules in the input data, thereby achieving specific tasks such as classification and regression. Optionally, the parameters of the neuron nodes in the first model may include weights, biases, and activation function parameters.
[0166] Accordingly, the first device can receive first information from the second device and can obtain the network topology of the first model and the parameters of the neuron nodes included in the first information. Furthermore, the first device can determine the first model based on the network topology and the parameters of the neuron nodes, for use in subsequently determining the parameters of the centroid of the perceived target based on the first model.
[0167] S303, the first device determines the second parameter of the centroid of the perceived target based on the first model.
[0168] In some feasible implementations, after determining the first model based on the first information, the first device can determine the second parameter of the centroid of the perceived target based on the first model. The second parameter of the centroid of the perceived target may include at least one of the following: the echo incidence angle of the centroid of the perceived target, the velocity of the centroid of the perceived target, the distance to the centroid of the perceived target, and the coordinates of the centroid of the perceived target.
[0169] In one optional implementation, the first device can acquire a second echo signal of the perceived target. Further, the first device can determine a second parameter based on a first model and the second echo signal. Specifically, the first device can input the second echo signal into the first model, thereby obtaining the second parameter, which is the centroid of the perceived target, as the output of the first model.
[0170] In another alternative implementation, the first device can acquire a second signal obtained by performing a Fourier transform on the second echo signal of the sensed target. Further, the first device can determine a second parameter based on the first model and the second signal. Specifically, the first device can input the second signal into the first model, thereby obtaining the output of the first model, which is the second parameter representing the centroid of the sensed target.
[0171] Here, the process of the first device performing a Fourier transform on the second echo signal to obtain the second signal is similar to the process of the first device performing a Fourier transform on the third echo signal to obtain the third signal, as described above. For details, please refer to the content described in step S301 above, which will not be repeated here.
[0172] It should be noted that the sensing target corresponding to the second echo signal may or may not be the same as the sensing target corresponding to the third echo signal mentioned above. It should be understood that the sensing target corresponding to the second echo signal can be the object being sensed when the first device performs the current sensing task, while the sensing target corresponding to the third echo signal can be the object being sensed when the first device performs other sensing tasks before the current sensing task, or it can be the object being sensed when other sensing devices besides the first device perform sensing tasks. It should also be understood that the second echo signal is different from the third echo signal mentioned above. The source of the second echo signal is similar to the source of the third echo signal mentioned above; for details, please refer to the content described in step S301 above, which will not be repeated here.
[0173] S304, The first device acquires the first parameter of the first scattering point of the perceived target.
[0174] In some feasible implementations, the first device can acquire a first parameter of any scattering point (hereinafter referred to as the first scattering point) among at least one scattering point of the sensing target. The first parameter of the first scattering point of the sensing target may include at least one of the following: the echo incident angle of the first scattering point, the velocity of the first scattering point, the distance of the first scattering point, and the coordinates of the first scattering point.
[0175] In this embodiment, the echo incident angle of the scattering point of the sensing target refers to the angle between the echo signal of the scattering point and the antenna panel of the second device. The velocity of the scattering point of the sensing target refers to the velocity of the scattering point relative to the second device. The distance of the scattering point of the sensing target refers to the straight-line distance between the scattering point and the second device. The coordinates of the scattering point of the sensing target refer to the coordinates of the scattering point of the sensing target with the second device as the origin.
[0176] Based on the preceding content, it can be seen that the first parameter of the first scattering point of the perceived target and the second parameter of the target's centroid can have the same parameter type; that is, the parameter types of both the first and second parameters can include echo incident angle, velocity, distance, coordinates, etc. However, it should be understood that the values corresponding to the first and second parameters can be the same or different.
[0177] It should be understood that the sensing target corresponding to the first scattering point here is the object being sensed when the first device performs the current sensing task, that is, the sensing target corresponding to the centroid mentioned in step S303, or the sensing target corresponding to the second echo signal, is the same sensing target.
[0178] In one optional implementation, when performing a sensing task, the first device can perform signal processing and analysis on the received second echo signal of the sensing target to obtain the first parameter of the first scattering point of the sensing target. Exemplarily, the first device can obtain the first parameter of the first scattering point of the sensing target based on conventional sensing processing methods. Specifically, after acquiring the second echo signal of the sensing target, the first device can perform a Fourier transform on the second echo signal, such as IDFT, DFT, 2D-DFT, etc., to obtain a multidimensional sensing spectrum. Further, the first device can analyze and process the multidimensional sensing spectrum, such as using constant false alarm rate detection and peak search, to determine the first parameter of the first scattering point.
[0179] It should be noted that the first device may also obtain the first parameters of the first scattering point of the perceived target through other signal processing methods or algorithms, and this application does not limit this.
[0180] It should be understood that the preceding description refers to the process by which the first device acquires a single scattering point of the perceived target (i.e., the aforementioned first scattering point). In actual implementation, the perceived target may have multiple scattering points. The process by which the first device acquires the parameters of each of these multiple scattering points is similar to the process of acquiring the first parameter of the first scattering point, as described above. For details, please refer to the above content, which will not be repeated here.
[0181] S305, the first device determines the third parameter of the first scattering point of the perceived target based on the first parameter and the second parameter.
[0182] In some feasible implementations, after determining the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target, the first device can determine the third parameter of the first scattering point of the perceived target based on the first parameter and the second parameter.
[0183] The third parameter of the first scattering point of the perceived target can be understood as a new parameter (i.e., the third parameter) of the first scattering point of the perceived target, determined based on the first parameter of the first scattering point and the second parameter of the centroid of the perceived target. It should be understood that the third parameter of the first scattering point of the perceived target is of the same type as the first parameter; that is, the third parameter of the perceived target can also include at least one of the following: the echo incident angle of the first scattering point of the perceived target, the velocity of the first scattering point of the perceived target, the distance of the first scattering point of the perceived target, and the coordinates of the first scattering point of the perceived target. However, the values corresponding to the third parameter and the first parameter can be the same or different.
[0184] In one alternative implementation, the first device may determine the third parameter based on the first parameter, the second parameter, and the first threshold.
[0185] The first threshold can be a specific numerical value, which may include at least one of the following: a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference. For example, the first threshold may include a first distance difference of 2 meters (m). Alternatively, the first threshold may include the confidence value of the second parameter, such as 0.95.
[0186] Optionally, the first threshold may be the centroid parameter correction threshold determined based on the first model and validation set as described in step S301 above. This threshold may be determined by the second device based on the first model and validation set and sent to the first device, or it may be determined by the second device and sent to other devices in the communication system besides the first device (such as network devices or terminal devices), which then forward it to the first device. Alternatively, the first threshold may be a value predefined by the protocol. This application embodiment does not specifically limit the source of the first threshold.
[0187] The following is an example of how, when the first threshold includes at least one of the first angle difference, first velocity difference, first distance difference, and first coordinate difference, the first device determines the third parameter based on the first parameter, the second parameter, and the first threshold.
[0188] In one optional implementation, if the first difference between the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target is greater than a first threshold, the first device can determine the third parameter of the first scattering point of the perceived target based on the second parameter. It should be noted that the first difference in this application refers to the absolute value of the difference between the first parameter and the second parameter, i.e., the first difference is greater than or equal to 0.
[0189] In this embodiment, the first difference may include at least one of the following: a second angle difference between the echo incident angle of the first scattering point of the sensing target and the echo incident angle of the centroid of the sensing target; a second velocity difference between the velocity of the first scattering point of the sensing target and the velocity of the centroid of the sensing target; a second distance difference between the distance of the first scattering point of the sensing target and the distance of the centroid of the sensing target; and a second coordinate difference between the coordinates of the first scattering point of the sensing target and the coordinates of the centroid of the sensing target.
[0190] The following examples illustrate two possible implementations of a first device determining a third parameter based on a second parameter.
[0191] In one method, the first device can directly determine the second parameter of the centroid of the perceived target as the third parameter of the first scattering point of the perceived target. In other words, the first device can replace the first parameter of the first scattering point of the perceived target with the second parameter of the centroid of the perceived target output by the first model, and use it as the third parameter of the first scattering point of the perceived target.
[0192] For example, assuming the first parameter of the first scattering point of the perceived target includes a distance of 110m, the second parameter of the centroid of the perceived target includes a distance of 101m, and the first threshold includes a first distance difference of 2m, then the first device can determine that the first difference between the first parameter and the second parameter is 9m. Since this first difference of 9m is greater than the first threshold of 2m, the first device can determine the second parameter of the centroid of the perceived target, 101m, as the distance of the first scattering point of the perceived target.
[0193] Method 2: The first device can determine the third parameter of the first scattering point of the perceived target based on the average value of the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target.
[0194] The average value of the first parameter and the second parameter may include at least one of the following: the average value of the echo incident angle of the first scattering point of the sensing target and the echo incident angle of the centroid of the sensing target, the average value of the velocity of the first scattering point of the sensing target and the velocity of the centroid of the sensing target, the average value of the distance between the first scattering point of the sensing target and the distance between the centroid of the sensing target, and the average value of the coordinates of the first scattering point of the sensing target and the coordinates of the centroid of the sensing target.
[0195] Optionally, the first device may determine the third parameter of the first scattering point of the sensed target as the summation average of the first parameter of the first scattering point of the sensed target and the second parameter of the centroid of the sensed target.
[0196] Based on the example of Method 1 above, after determining that the difference between the first parameter and the second parameter is greater than the first threshold, the first device can determine that the average value of the first parameter and the second parameter is 105.5m, and determine 105.5m as the third parameter of the first scattering point of the sensing target.
[0197] Optionally, the first parameter of the first scattering point of the perceived target and the parameter of the second scattering point of the perceived target can each correspond to a weight (or weighting). Then, the first device can determine the third parameter of the first scattering point of the perceived target by the weighted average of the first parameter and the second parameter. Specifically, the first device can determine the product of the first parameter and its weight and the product of the second parameter and its weight, then sum these two products and take the average value, and determine this average value as the third parameter of the first scattering point of the perceived target.
[0198] It should be noted that if the first difference between the first parameter and the second parameter is greater than the first threshold, it indicates that the first parameter of the first scattering point of the perceived target deviates significantly from the second parameter of the centroid of the perceived target. This can be understood as the first parameter of the first scattering point obtained by the first device through signal processing and analysis of the second echo signal of the perceived target having a large error and low accuracy. In this case, the first device can use the second parameter of the centroid of the perceived target output by the first model to help determine a third parameter of the first scattering point of the perceived target that has a smaller deviation from the second parameter and higher accuracy. This can achieve the correction of the parameter of the first scattering point of the perceived target. In the embodiments of this application, the correction of parameters can also be understood as the correction, modification, or adjustment of parameters.
[0199] In another alternative implementation, if the first difference between the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target is less than or equal to a first threshold, the first device may determine the first parameter as the third parameter of the first scattering point of the perceived target.
[0200] For example, assuming that the first parameter of the first scattering point of the perceived target includes a distance of 100m from the first scattering point, the second parameter of the centroid of the perceived target includes a distance of 101m from the centroid, and the first threshold includes a first distance difference of 2m, then the first device can determine that the difference between the first parameter and the second parameter is 1m. Since the difference between the first parameter and the second parameter is less than the first threshold, the first device can determine the first parameter of the first scattering point of the perceived target as the third parameter of the first scattering point of the perceived target.
[0201] It should be noted that if the difference between the first parameter and the second parameter is less than or equal to the first threshold, it indicates that the deviation between the first parameter of the first scattering point of the perceived target and the second parameter of the centroid of the perceived target is small. This can be understood as the error of the first parameter of the first scattering point obtained by the first device through signal processing and analysis of the second echo signal of the perceived target being small, and its accuracy being high. In this case, the first device can directly determine the first parameter as the third parameter of the first scattering point of the perceived target, without needing to combine it with the second parameter of the centroid of the perceived target output by the first model to assist in determining the third parameter of the first scattering point of the perceived target. In other words, the first device can retain the first parameter of the first scattering point of the perceived target without needing to correct it, and can directly use it to determine the subsequent positioning result of the perceived target.
[0202] The following example illustrates the specific process by which the first device determines the third parameter based on the first parameter, the second parameter, and the first threshold, when the first threshold includes the confidence level of the second parameter.
[0203] In one optional implementation, the first device may first determine a first difference between a first parameter of a first scattering point of the perceived target and a second parameter of the centroid of the perceived target, and then determine a second ratio based on a first ratio of the first difference to the second parameter of the centroid of the perceived target. Here, the sum of the second ratio and the first ratio is equal to 1. Further, if the second ratio is less than a first threshold, the first device may determine a third parameter of the first scattering point of the perceived target based on the second parameter. It should be noted that the second ratio in this embodiment can be understood as the confidence level or credible probability of the first parameter of the first scattering point of the perceived target.
[0204] In this embodiment, the first ratio may include at least one of the following: the ratio of the second angle difference to the echo incident angle of the centroid of the sensed target, the ratio of the second velocity difference to the velocity of the centroid of the sensed target, the ratio of the second distance difference to the distance of the centroid of the sensed target, and the ratio of the second coordinate difference to the coordinates of the centroid of the sensed target.
[0205] Here, the specific process by which the first device determines the third parameter of the first scattering point of the perceived target based on the second parameter can be found in the above content, and will not be repeated here.
[0206] For example, assuming the distance of the first scattering point of the first scattering point of the perceived target is 110m, the distance of the centroid of the perceived target is 101m, and the confidence value of the second parameter included in the first threshold is 0.95, the first device can first determine that the first difference between the first parameter 110m and the second parameter 101m is 9m. Then, it can determine that the first ratio of the first difference 9m to the second parameter 101m is approximately 0.09, and the second ratio is 1 - 0.09 = 0.91. Since the second ratio 0.91 is less than the first threshold 0.95, the first device can determine the second parameter 101m as the third parameter of the first scattering point of the perceived target, or it can determine the average value of the first parameter and the second parameter, 105.5m, as the third parameter of the first scattering point of the perceived target.
[0207] It should be noted that if the second ratio is less than the first threshold, it indicates that the reliability of the first parameter of the first scattering point of the perceived target is lower than the second parameter of the centroid of the perceived target output by the first model. This can be understood as the accuracy of the first parameter of the first scattering point obtained by the first device through signal processing and analysis of the second echo signal of the perceived target being low, and its deviation from the second parameter of the centroid of the perceived target being significant. In this case, the first device can use the second parameter of the centroid of the perceived target output by the first model to help determine a third parameter of the first scattering point of the perceived target that is less deviated from the second parameter and has higher accuracy. This can achieve the correction of the parameter of the first scattering point of the perceived target.
[0208] In another optional implementation, the first device may first determine a first difference between a first parameter of a first scattering point of the perceived target and a second parameter of the centroid of the perceived target, and then determine a second ratio based on a first ratio of the first difference to the second parameter of the centroid of the perceived target. The sum of the first and second ratios is equal to 1. Further, if the second ratio is greater than or equal to a first threshold, the first device may determine the first parameter as a third parameter of the first scattering point of the perceived target.
[0209] For example, assuming the first parameter of the first scattering point of the perceived target includes a distance of 100m, the second parameter of the centroid of the perceived target includes a distance of 101m, and the confidence level of the second parameter included in the first threshold is 0.95, then the first device can first determine that the first difference between the first parameter 100m and the second parameter 101m is 1m, and then determine that the first ratio of the first difference 1m to the second parameter 101m is approximately 0.009, then the second ratio is 1 - 0.009 = 0.991. Since the second ratio 0.991 is greater than the first threshold 0.95, the first device can determine the first parameter 100m as the third parameter of the first scattering point of the perceived target.
[0210] It should be noted that if the second ratio is greater than or equal to the first threshold, it indicates that the reliability of the first parameter of the first scattering point of the perceived target is higher than the second parameter of the centroid of the perceived target output by the first model. This can be understood as the first parameter of the first scattering point obtained by the first device through signal processing and analysis of the second echo signal of the perceived target having a relatively high accuracy, as its deviation from the second parameter of the centroid of the perceived target is not too far. In this case, the first device can directly determine the first parameter as the third parameter of the first scattering point of the perceived target without needing to combine it with the second parameter of the centroid of the perceived target output by the first model to assist in determining the third parameter of the first scattering point of the perceived target. In other words, the first device can retain the first parameter of the first scattering point of the perceived target without needing to correct it, and can directly use it to determine the positioning result of the perceived target.
[0211] Based on the above, the value of the third parameter corresponding to the first scattering point of the perceived target can be understood as a value obtained by correcting the first parameter of the first scattering point of the perceived target, which has a large deviation from the second parameter of the centroid of the perceived target, using the second parameter of the centroid of the perceived target output by the first model. Compared with the first parameter of the first scattering point of the perceived target, the third parameter of this first scattering point has a smaller deviation from the second parameter of the centroid of the perceived target and has higher accuracy.
[0212] It should be understood that in actual implementation, the first device may also determine the third parameter of the first scattering point of the perceived target through other methods, and the embodiments of this application are not limited in this regard.
[0213] It should be noted that the preceding description refers to the process by which the first device determines the third parameter of the first scattering point of the perceived target based on the first parameter of the first scattering point (i.e., the aforementioned first scattering point) and the second parameter of the centroid of the perceived target. It should be understood that in actual implementation, the perceived target may have multiple scattering points. The process by which the first device determines the third parameter of each of these multiple scattering points is similar to the process described above for determining the third parameter of the first scattering point; please refer to the relevant content described above for details, which will not be repeated here.
[0214] S306, the first device determines the positioning result of the perceived target based on the third parameter.
[0215] In some feasible implementations, after determining the third parameter of the first scattering point of the perceived target, the first device can determine the positioning result of the perceived target based on the third parameter.
[0216] Optionally, after the first device obtains the third parameter of the first scattering point of the sensing target, it can cluster multiple scattering points of the sensing target (including the first scattering point), and then calculate the parameters of the geometric center point of these multiple scattering points, or calculate the average parameter of the multiple scattering points, thereby determining the centroid positioning result of the sensing target, i.e., the positioning result of the sensing target.
[0217] It should be understood that when the target has multiple scattering points, the first device can use the above method to obtain the third parameter of each scattering point, and then determine the positioning result of the target based on the third parameter of each scattering point. Here, the process of determining the positioning result of the target based on the third parameter of each scattering point is similar to the process described above where the first device determines the positioning result of the target based on the third parameter of the first scattering point of the target. For details, please refer to the above content, and it will not be repeated here.
[0218] In this embodiment, the first device uses the second parameter of the centroid of the perceived target determined by the first model, and the first parameter of the first scattering point of the perceived target determined by a traditional sensing processing method, to determine the third parameter of the first scattering point of the perceived target. Compared to existing solutions that rely solely on the first parameter of the first scattering point of the perceived target determined by a traditional sensing processing method, this solution utilizes the more accurate second parameter of the centroid of the perceived target output by the first model to correct the first parameter of the first scattering point of the perceived target that deviates from the centroid. This makes the third parameter of the first scattering point of the perceived target closer to the second parameter of the centroid of the perceived target with a smaller deviation, improving the estimation accuracy and confidence of the parameters of the scattering point of the perceived target, thereby enhancing the positioning accuracy.
[0219] Optionally, please refer to Figure 3. The communication method shown in Figure 3 may also include step S307. Optionally, step S307 may be performed before step S301.
[0220] S307, the first device sends the first dataset to the second device. Accordingly, the second device receives the first dataset.
[0221] In some feasible implementations, after receiving the first echo signal from the perceived target, the first device can directly use the first echo signal as the first dataset, or use the first signal obtained by performing a Fourier transform on the first echo signal as the first dataset. Furthermore, the first device can send the first dataset to the second device.
[0222] The first dataset can be used for training the first model, and / or, the first dataset can be used to determine the first threshold. Optionally, the first dataset may include a training set and a validation set, wherein the training set can be used for training the first model, and the validation set and the trained first model can be used to determine the first threshold.
[0223] Here, the first signal is similar to the second signal mentioned above. For details, please refer to the relevant content of the second signal described in step S301 above, which will not be repeated here.
[0224] It should be understood that the first echo signal can be the aforementioned third echo signal.
[0225] It should be noted that the first dataset can be included in the aforementioned echo signal dataset. In possible scenarios, the first dataset and the echo signal dataset can be the same. Here, the first dataset is similar to the aforementioned echo signal dataset, as detailed in step S301 above, and will not be repeated here.
[0226] Accordingly, the second device can receive the first dataset from the first device and obtain the contents contained in the first dataset.
[0227] Optionally, referring to Figure 3, the communication method shown in Figure 3 may further include step S308. Optionally, step S308 may be performed after step S301. For ease of explanation, the following description assumes that step S308 is performed after step S302 and before step S303.
[0228] S308, the second device sends a first threshold to the first device. Accordingly, the first device receives the first threshold.
[0229] In some feasible implementations, the second device can send the first threshold to the first device after determining the first threshold.
[0230] Optionally, after training the first model, the second device can determine a first threshold based on the first model and the validation set, and send the first threshold to the first device. The validation set may be included in the first dataset or in the echo signal dataset.
[0231] In possible implementations, the second device can send the first threshold and the aforementioned first information to the first device through the same message, or it can send them to the first device through different messages. That is, the second device can simultaneously indicate the first model and the first threshold to the first device, or it can indicate the first model and the first threshold to the first device separately. This application embodiment does not limit this.
[0232] Accordingly, the first device can receive the first threshold.
[0233] The communication method provided by the embodiments of this application has been described in detail above with reference to Figures 3 and 4. The communication device provided by the embodiments of this application will now be described in detail with reference to Figures 5 and 6. It should be understood that the description of the embodiments of the communication device corresponds to the description of the embodiments of the communication method; therefore, any parts not described in detail can be referred to the method embodiments above.
[0234] Please refer to Figure 5, which is a schematic diagram of the structure of a communication device provided in an embodiment of this application. As shown in Figure 5, the communication device 50 may include a processing unit 501 and a transceiver unit 502.
[0235] In some feasible implementations, the communication device 50 may correspond to the first device described above, or a component (such as a circuit, chip, or chip system) configured in the first device.
[0236] In a specific implementation, processing unit 501 is used to acquire first parameters of the first scattering point of the perceived target. The first parameters include at least one of the following: the echo incident angle of the first scattering point of the perceived target, the velocity of the first scattering point of the perceived target, the distance of the first scattering point of the perceived target, and the coordinates of the first scattering point of the perceived target. Processing unit 501 is also used to determine a third parameter of the first scattering point of the perceived target based on the first parameters and a second parameter of the centroid of the perceived target. The second parameter is determined based on a first model. The second parameter includes at least one of the echo incident angle of the centroid of the perceived target, the velocity of the centroid of the perceived target, the distance of the centroid of the perceived target, and the coordinates of the centroid of the perceived target. Processing unit 501 is also used to determine the positioning result of the perceived target based on the third parameter of the first scattering point of the perceived target.
[0237] In one possible implementation, the processing unit 501 is further configured to determine a third parameter based on the first parameter, the second parameter, and the first threshold. Here, the first threshold includes at least one of the first angle difference, the first velocity difference, the first distance difference, and the first coordinate difference, or the first threshold includes the confidence value of the second parameter.
[0238] In one possible implementation, the processing unit 501 is further configured to determine a third parameter based on the second parameter if the first difference between the first parameter and the second parameter is greater than a first threshold. Here, the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0239] In one possible implementation, the processing unit 501 is further configured to determine the first parameter as a third parameter if the first difference between the first parameter and the second parameter is less than or equal to a first threshold. Here, the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
[0240] In one possible implementation, processing unit 501 is further configured to determine a first difference between the first parameter and the second parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. Processing unit 501 is further configured to determine a second ratio based on a first ratio of the first difference to the second parameter. Here, the sum of the first ratio and the second ratio is equal to 1. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid. Processing unit 501 is further configured to determine a third parameter based on the second parameter if the second ratio is less than a first threshold.
[0241] In one possible implementation, processing unit 501 is further configured to determine a first difference between the first parameter and the second parameter. Here, the first difference includes at least one of the following: a second angular difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. Processing unit 501 is further configured to determine a second ratio based on a first ratio of the first difference to the second parameter. Here, the sum of the first ratio and the second ratio is equal to 1. The first ratio includes at least one of the following: the ratio of the second angular difference to the echo incident angle of the centroid; the ratio of the second velocity difference to the velocity of the centroid; the ratio of the second distance difference to the distance of the centroid; and the ratio of the second coordinate difference to the coordinates of the centroid. Processing unit 501 is further configured to determine the first parameter as a third parameter if the second ratio is greater than or equal to a first threshold.
[0242] In one possible implementation, the processing unit 501 is further configured to determine the second parameter as the third parameter, or to determine the third parameter based on the average of the first parameter and the second parameter. Here, the average of the first parameter and the second parameter includes at least one of the following: the average of the echo incident angle of the first scattering point and the echo incident angle of the centroid, the average of the velocity of the first scattering point and the velocity of the centroid, the average of the distance between the first scattering point and the distance between the centroid, and the average of the coordinates of the first scattering point and the coordinates of the centroid.
[0243] In one possible implementation, the transceiver unit 502 is used to receive first information. Here, the first information includes the network topology of the first model and the parameters of the neuron nodes.
[0244] In one possible implementation, the processing unit 501 is also used to obtain a first threshold.
[0245] In one possible implementation, the transceiver unit 502 is further configured to transmit a first dataset. Here, the first dataset includes a first echo signal of the sensed target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensed target. The first dataset is used for training a first model, and / or, the first dataset is used to determine a first threshold.
[0246] In one possible implementation, the first dataset includes a validation set, and the validation set and a first model are used to determine a first threshold.
[0247] In one possible implementation, the processing unit 501 is further configured to acquire a second echo signal of the perceived target, or the first device acquires a second signal obtained by performing a Fourier transform on the second echo signal of the perceived target. The processing unit 501 is also configured to determine a second parameter based on the first model and the second echo signal, or the first device determines the second parameter based on the first model and the second signal.
[0248] In some feasible implementations, the communication device 50 may correspond to the second device described above, or a component (such as a circuit, chip, or chip system) configured in the second device.
[0249] In specific implementation, processing unit 501 is used to determine a first model. The first model is used to determine a second parameter of the centroid of the perceived target. The first parameter of the first scattering point of the perceived target, along with the second parameter, is used to determine a third parameter of the first scattering point of the perceived target. The third parameter is used to determine the localization result of the perceived target. The first parameter includes at least one of the following: the echo incident angle of the first scattering point of the perceived target, the velocity of the first scattering point of the perceived target, the distance of the first scattering point of the perceived target, and the coordinates of the first scattering point. The second parameter includes at least one of the following: the echo incident angle of the centroid of the perceived target, the velocity of the centroid of the perceived target, the distance of the centroid of the perceived target, and the coordinates of the centroid of the perceived target. Transceiver unit 502 is used to transmit first information. The first information includes the network topology of the first model and the parameters of the neuron nodes.
[0250] In one possible implementation, the transceiver unit 502 is further configured to receive a first dataset. Here, the first dataset includes a first echo signal of the sensed target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensed target. The processing unit 501 is further configured to train a first model based on the first dataset.
[0251] In one possible implementation, processing unit 501 is further configured to determine a first threshold based on the validation set and the first model. Here, the first threshold, the first parameter, and the second parameter are used to determine the third parameter. The first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference, or the first threshold includes the confidence value of the second parameter.
[0252] In one possible implementation, the transceiver unit 502 is also used to transmit the first threshold.
[0253] Please refer to Figure 6, which is a schematic diagram of another communication device provided in an embodiment of this application. This communication device 60 can be used to implement the operations performed by the first device or the second device in the above embodiments, or, the communication device 60 can be the first device or the second device described above. The communication device 60 includes: a processor 601, a memory 602, and a bus system 603.
[0254] The memory 602 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM). The memory 602 is used to store related instructions and data. The memory 602 stores executable modules or data structures, or subsets thereof, or extended sets thereof:
[0255] Operation instructions: This includes various operation instructions used to perform various operations.
[0256] Operating system: includes various system programs used to implement various basic business functions and handle hardware-based tasks.
[0257] Figure 6 shows only one memory, but of course, multiple memories can be set as needed.
[0258] In one possible implementation, the communication device 60 may include only the processor 601 and the bus system 603, that is, it may exclude the memory 602.
[0259] The communication device 60 may further include a transceiver 604. The transceiver 604 may be a communication module or a transceiver circuit. In the embodiments of this application, the transceiver 604 is used to perform the message sending and receiving operations described in the above embodiments.
[0260] Processor 601 may be configured with at least one, specifically it may be a controller, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Processor 601 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of DSP and microprocessor, etc.
[0261] In practical applications, the various components of the communication device 60 are coupled together through a bus system 603. This bus system 603 includes not only a data bus but may also include a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 603 in Figure 6. Figure 6 is only schematically illustrated for ease of representation.
[0262] In specific implementation, the communication device 60 can execute the steps of the method performed by the first device or the second device in the above embodiments. Specifically, when the communication device 60 is used to implement the various steps performed by the first device or the second device in the communication method provided in the embodiments, the processor 601 can implement the function of the processing unit 501, and the transceiver 604 can implement the function of the transceiver unit 502.
[0263] It should be noted that in practical applications, the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above methods.
[0264] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be ROM, programmable read-only memory (PROM), EPROM, electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be RAM, which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.
[0265] This application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a computer, implements the method steps performed by the first device or the second device in the above embodiments.
[0266] This application also provides a computer program product that, when executed by a computer, implements the method steps performed by the first device or the second device in the above embodiments.
[0267] This application also provides a chip including at least one processor. The at least one processor is configured to execute computer execution instructions to cause a device on which the chip is mounted to perform the method steps performed by the first or second device in the above embodiments.
[0268] Optionally, the chip may also include interface circuitry. This interface circuitry is used to receive computer execution instructions and transmit them to the processor.
[0269] This application also provides a chip system including a processor for supporting the apparatus on which the chip system is installed to implement the method steps performed by the first or second device in the above embodiments, such as generating or processing data and / or information involved in the above methods. In one possible design, the chip system further includes a memory for storing program instructions and data necessary for the data transmission device. The chip system may be composed of chips or may include chips and other discrete devices.
[0270] Optionally, the chip system may also include interface circuitry. This interface circuitry can be used to receive computer-executed instructions and transmit them to the processor.
[0271] Please refer to Figure 7, which is a schematic diagram of another communication device provided in an embodiment of this application. The communication device 70 may include a processor 701 and an interface circuit 702. The interface circuit 702 can be used to receive signals from other communication devices besides the communication device 70 and transmit them to the processor 701, or to send signals from the processor 701 to other communication devices besides the communication device 70. The processor 701 can be used to execute computer programs or instructions through logic circuits to implement the communication methods described in the preceding embodiments.
[0272] In some possible designs, the communication device 70 may be the first device described above, or a device including the first device described above, or a device contained in the first device described above, such as a chip system. The communication device 70 may also be the second device described above, or a device including the second device described above, or a device contained in the second device described above.
[0273] This application also provides a communication system, which includes at least the first device and the second device described above. The first device and the second device work together to implement the communication method described in the preceding embodiments.
[0274] In the above method embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).
[0275] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.
[0276] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.
[0277] The above description is merely a preferred embodiment of the technical solution of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.
Claims
1. A communication method, characterized in that, Applied to a first device, the method includes: Acquire first parameters of the first scattering point of the perceived target, wherein the first parameters include at least one of the following: the echo incident angle of the first scattering point, the velocity of the first scattering point, the distance of the first scattering point, and the coordinates of the first scattering point; The third parameter of the first scattering point of the sensing target is determined based on the first parameter and the second parameter of the centroid of the sensing target. The second parameter is determined based on the first model and includes at least one of the following: the echo incident angle of the centroid of the sensing target, the velocity of the centroid of the sensing target, the distance of the centroid of the sensing target, and the coordinates of the centroid of the sensing target. The positioning result of the perceived target is determined based on the third parameter.
2. The method according to claim 1, characterized in that, The step of determining the third parameter of the first scattering point of the sensing target based on the first parameter and the second parameter of the centroid of the sensing target includes: The third parameter is determined based on the first parameter, the second parameter, and the first threshold, wherein the first threshold includes at least one of the first angle difference, the first velocity difference, the first distance difference, and the first coordinate difference, or the first threshold includes the confidence value of the second parameter.
3. The method of claim 2, wherein, The first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: If the first difference between the first parameter and the second parameter is greater than the first threshold, the third parameter is determined based on the second parameter, wherein the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
4. The method according to claim 2, characterized in that, The first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference. Determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: If the first difference between the first parameter and the second parameter is less than or equal to the first threshold, the first parameter is determined as the third parameter, wherein the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid.
5. The method according to claim 2, characterized in that, The first threshold includes the confidence value of the second parameter, and determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: Determine a first difference between the first parameter and the second parameter, wherein the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. A second ratio is determined based on a first ratio of the first difference to the second parameter, wherein the sum of the first ratio and the second ratio is equal to 1, and the first ratio includes at least one of the following: the ratio of the second angle difference to the echo incident angle of the centroid, the ratio of the second velocity difference to the velocity of the centroid, the ratio of the second distance difference to the distance of the centroid, and the ratio of the second coordinate difference to the coordinates of the centroid. If the second ratio is less than the first threshold, the third parameter is determined based on the second parameter.
6. The method according to claim 2, characterized in that, The first threshold includes the confidence value of the second parameter, and determining the third parameter based on the first parameter, the second parameter, and the first threshold includes: Determine a first difference between the first parameter and the second parameter, wherein the first difference includes at least one of the following: a second angle difference between the echo incident angle of the first scattering point and the echo incident angle of the centroid; a second velocity difference between the velocity of the first scattering point and the velocity of the centroid; a second distance difference between the distance of the first scattering point and the distance of the centroid; and a second coordinate difference between the coordinates of the first scattering point and the coordinates of the centroid. A second ratio is determined based on a first ratio of the first difference to the second parameter, wherein the sum of the first ratio and the second ratio is equal to 1, and the first ratio includes at least one of the following: the ratio of the second angle difference to the echo incident angle of the centroid, the ratio of the second velocity difference to the velocity of the centroid, the ratio of the second distance difference to the distance of the centroid, and the ratio of the second coordinate difference to the coordinates of the centroid. If the second ratio is greater than or equal to the first threshold, the first parameter is determined as the third parameter.
7. The method according to claim 3 or 5, characterized in that, Determining the third parameter based on the second parameter includes: The second parameter is determined as the third parameter, or the third parameter is determined based on the average of the first parameter and the second parameter, wherein the average of the first parameter and the second parameter includes at least one of the following: the average of the echo incident angle of the first scattering point and the echo incident angle of the centroid, the average of the velocity of the first scattering point and the velocity of the centroid, the average of the distance between the first scattering point and the distance between the centroid, and the average of the coordinates of the first scattering point and the coordinates of the centroid.
8. The method according to any one of claims 1-7, characterized in that, The method further includes: Receive first information, wherein the first information includes the network topology of the first model and the parameters of the neuron nodes.
9. The method according to any one of claims 2-8, characterized in that, The method further includes: Obtain the first threshold.
10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: Send a first dataset, wherein the first dataset includes a first echo signal of the perceived target or a first signal obtained by performing a Fourier transform on the first echo signal of the perceived target, the first dataset is used for training the first model, and / or the first dataset is used to determine the first threshold.
11. The method according to claim 10, characterized in that, The first dataset includes a validation set, and the validation set and the first model are used to determine the first threshold.
12. The method according to claim 1, characterized in that, The second parameter is determined based on the first model and includes: Acquire the second echo signal of the sensing target, or acquire the second signal obtained by performing a Fourier transform on the second echo signal of the sensing target; The second parameter is determined based on the first model and the second echo signal, or the second parameter is determined based on the first model and the second signal.
13. A communication method, characterized in that, Applied to a second device, the method includes: A first model is determined, wherein the first model is used to determine a second parameter of the centroid of the sensing target, a first parameter of the first scattering point of the sensing target and the second parameter are used to determine a third parameter of the first scattering point of the sensing target, the third parameter is used to determine the positioning result of the sensing target, the first parameter includes at least one of the echo incident angle of the first scattering point, the velocity of the first scattering point, the distance of the first scattering point and the coordinates of the first scattering point, and the second parameter includes at least one of the echo incident angle of the centroid of the sensing target, the velocity of the centroid of the sensing target, the distance of the centroid of the sensing target and the coordinates of the centroid of the sensing target; Send first information, wherein the first information includes the network topology of the first model and the parameters of the neuron nodes.
14. The method according to claim 13, characterized in that, The determination of the first model includes: Receive a first dataset, wherein the first dataset includes a first echo signal of the sensing target or a first signal obtained by performing a Fourier transform on the first echo signal of the sensing target; The first model is obtained by training the first dataset.
15. The method according to claim 14, characterized in that, The first dataset includes a validation set, and the method further includes: A first threshold is determined based on the validation set and the first model, wherein the first threshold, the first parameter, and the second parameter are used to determine the third parameter, and the first threshold includes at least one of a first angle difference, a first velocity difference, a first distance difference, and a first coordinate difference, or the first threshold includes the confidence value of the second parameter.
16. The method according to claim 15, characterized in that, The method further includes: Send the first threshold.
17. A communication device, characterized in that, The communication device includes a unit for implementing the communication method as described in any one of claims 1 to 12 or claims 13 to 16.
18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the communication method as described in any one of claims 1 to 12, or the communication method as described in any one of claims 13 to 16.
19. A chip system, characterized in that, Including the processor; The processor is configured to execute computer execution instructions to cause a device equipped with the chip system to perform the communication method as described in any one of claims 1 to 12, or the communication method as described in any one of claims 13 to 16.
20. The chip system according to claim 19, characterized in that, The chip system also includes an interface circuit, which is used to receive computer execution instructions and transmit them to the processor.
21. A computer program product, characterized in that, The computer program product is executed by a computer using the communication method according to any one of claims 1 to 12, or the communication method according to any one of claims 13 to 16.
22. A communication device, characterized in that, It includes at least one processor for executing a computer program stored in a memory to cause the communication device to perform the communication method as described in any one of claims 1 to 12, or the communication method as described in any one of claims 13 to 16.