Sensing method and apparatus

Abstract

A sensing method and apparatus, which can implement super-resolution and gridless acquisition of sensing information of a sensing target without requiring the use of a joint peak search technique and quantization of a parameter search space, thereby improving the sensing accuracy, resolution and computational efficiency of the sensing target. A first access network device is used as an execution body. The method comprises: receiving an echo signal; on the basis of the echo signal, obtaining an estimated quantity M of sensing targets; on the basis of the estimated quantity M, performing tensor decomposition on the echo signal to obtain sensing information, wherein the sensing information comprises M sensing parameter groups, and M is a positive integer; and sending the sensing information to a sensing network element, wherein the sensing information is used for determining a sensing result.

Description

Sensing methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202411956293.0, filed on December 25, 2024, entitled "Sensing Method and Apparatus", 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 sensing methods and devices. Background Technology

[0003] With the continuous evolution of communication technology, integrated sensing and communication (ISAC) has emerged. By organically combining communication and sensing functions, it breaks down the boundaries between communication and sensing, and achieves resource sharing and functional synergy.

[0004] In the ISAC system, without occupying additional spectrum resources or affecting normal communication links, access network devices use communication signals to sense and acquire sensing parameters such as speed, distance, and angle of targets in the environment, giving new capabilities to important information applications.

[0005] However, when sensing targets, the joint peak search technique using multidimensional beam spectrum requires quantizing (gridizing) the multi-domain parameter search space, which has problems such as accuracy and resolution performance being limited by the grid point spacing and high computational complexity. Summary of the Invention

[0006] This application provides a sensing method and apparatus that can achieve super-resolution, gridless acquisition of sensing information of a sensing target without the need for joint peak search technology and quantization parameter search space, thereby improving the sensing accuracy, resolution and computational efficiency of the sensing target.

[0007] Firstly, a sensing method is provided. This method can be executed by a first access network device, by a module (e.g., processor, chip, or chip system) applied to the first access network device, or by a logical node, logical module, or software capable of implementing all or part of the functions of the access network device. The method includes: receiving an echo signal; obtaining an estimated number M of sensing targets based on the echo signal; performing tensor decomposition on the echo signal based on the estimated number M to obtain sensing information, the sensing information including M sets of sensing parameters, where M is a positive integer; and sending the sensing information to a sensing network element, the sensing information being used to determine the sensing result.

[0008] In the above technical solution, the first access network device obtains the estimated number M of the sensing targets through the echo signal. Then, based on the estimated number M, it performs tensor decomposition on the echo signal to acquire the sensing information of the sensing targets, and then determines the sensing result through the sensing network elements. In other words, the first access network device can achieve super-resolution and gridless determination of the sensing results of the sensing targets without applying joint peak search technology and quantization parameter search space. This solves the problem that the accuracy and resolution performance of current sensing targets are limited by the grid point interval and the computational complexity is high, thus improving the sensing accuracy, resolution and computational efficiency of the sensing targets.

[0009] In conjunction with the first aspect above, in one possible implementation, the acquisition of the estimated number M of the sensing target includes: performing tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients; the R first weight coefficients correspond to R sub-signals of the echo signal; the first weight coefficients are used to reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, and R is a positive integer; sending the R first weight coefficients to the sensing network element or the third access network device, the R first weight coefficients being used to determine the estimated number M; and receiving first information from the sensing network element or the third access network device, the first information being used to indicate the estimated number M.

[0010] In the above technical solution, the first access network device obtains R first weight coefficients by tensor decomposition of the echo signal. Since the first weight coefficients reflect the importance of the corresponding sub-signals in the echo signal, sending the R weight coefficients to the sensing network element or the third access network device enables the sensing network element to determine the importance of the sub-signals reflected by the first weight coefficients in the echo signal, thereby determining the estimated quantity M. Furthermore, the first access network device obtains the estimated quantity M by receiving first information from the sensing network element or the third access network device.

[0011] In conjunction with the first aspect above, in one possible implementation, obtaining the estimated number M of the sensed targets based on the echo signal includes: performing tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients; determining a first estimated number of sensed targets based on the R first weight coefficients; where R is a positive integer; receiving R second weight coefficients from a second access network device; determining a second estimated number of sensed targets based on the R second weight coefficients; and determining the estimated number M of sensed targets based on the first and second estimated numbers.

[0012] In the above technical solution, the first access network device has the function of actively determining the estimated number M of sensing targets. Since the first weight coefficient can reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, the first access network device can know the importance of the sub-signal reflected by the first weight coefficient in the echo signal, and thus determine the first estimated number corresponding to the first access network device. Furthermore, the first access network device also determines the second estimated number corresponding to the second access network device based on R second weight coefficients of the second access network device; and then determines the estimated number M of sensing targets based on the first and second estimated numbers.

[0013] In conjunction with the first aspect above, in one possible implementation, the estimated number M of the perceived target is the maximum value between the first estimated number and the second estimated number; or, if the first estimated number and the second estimated number are the same, the estimated number M of the perceived target is either the first estimated number or the second estimated number.

[0014] The above technical solution illustrates a method for determining the estimated quantity M in two cases: when the first estimated quantity and the second estimated quantity are the same and when they are different.

[0015] In conjunction with the first aspect above, in one possible implementation, the first estimated number of perceived targets is the number of first weight coefficients that satisfy a preset threshold among R first weight coefficients.

[0016] In the above technical solution, R first weight coefficients are divided by a preset threshold, and the number of first weight coefficients that meet the preset threshold is used as the first estimated number.

[0017] In conjunction with the first aspect described above, in one possible implementation, the first weight coefficient that satisfies the preset threshold is the first weight coefficient among R first weight coefficients that is greater than or equal to the preset threshold; or, the first weight coefficient that satisfies the preset threshold is the first X first weight coefficients after the R first weight coefficients are sorted in descending order, and the ratio of two adjacent first weight coefficients among the first X first weight coefficients is greater than or equal to the preset threshold, where X is a positive integer less than or equal to R; or, the first weight coefficient that satisfies the preset threshold is the first N first weight coefficients after the R first weight coefficients are sorted in descending order; wherein the sum of the first N-1 first weight coefficients is less than the preset threshold, and the sum of the first N first weight coefficients is greater than or equal to the preset threshold; where N is a positive integer less than or equal to R.

[0018] The above technical solution specifically illustrates three methods for determining the first weight coefficient that meets the preset threshold. Through the above technical solution, R first weight coefficients can be divided to obtain the first weight coefficients that meet the preset threshold among the R first weight coefficients, which facilitates the subsequent determination of the first estimated number of perceived targets based on the number of first weight coefficients of the preset threshold.

[0019] In conjunction with the first aspect above, in one possible implementation, the sensing parameter set includes at least one of the following: a distance parameter, an angle parameter, or a velocity parameter of the sensing target.

[0020] In the above technical solution, the sensing parameter set may include distance parameters, angle parameters, or velocity parameters. These three parameters can be used to effectively obtain the motion trend of the sensed target and its current position.

[0021] Secondly, a sensing method is provided. This method can be executed by a sensing network element, by a module applied to the sensing network element (e.g., a processor, chip, or chip system), or by a logic node, logic module, or software capable of implementing all or part of the sensing network element's functions. The method includes: receiving R first weighting coefficients from a first access network device; the R first weighting coefficients correspond to R sub-signals of the echo signal; the first weighting coefficients reflect the importance of the corresponding sub-signals in the echo signal, where R is a positive integer; receiving R second weighting coefficients from a second access network device; the R second weighting coefficients correspond to R sub-signals of the echo signal; the second weighting coefficients reflect the importance of the corresponding sub-signals in the echo signal; determining a first estimated quantity of sensing targets based on the R first weighting coefficients; determining a second estimated quantity of sensing targets based on the R second weighting coefficients; determining an estimated quantity M of sensing targets based on the first and second estimated quantities, where M is a positive integer; and sending first information indicating the estimated quantity M.

[0022] In the above technical solution, since the first weight coefficient can reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, the sensing network element can know the importance of the sub-signal reflected by the first weight coefficient in the echo signal, and determine the first estimated quantity of the sensing target based on R first weight coefficients. Since the second weight coefficient can reflect the importance of the sub-signal corresponding to the second weight coefficient in the echo signal, the sensing network element can know the importance of the sub-signal corresponding to the second weight coefficient in the echo signal based on the second weight coefficient, and then determine the second estimated quantity of the sensing target based on R second weight coefficients. Furthermore, the sensing network element determines the estimated quantity M of the sensing target based on the first estimated quantity and the second estimated quantity. The sensing network element sends first information to indicate the estimated quantity M, so that the first access network device and other access network devices can obtain the estimated quantity M from the first information.

[0023] In conjunction with the second aspect above, in one possible implementation, the estimated number M of the perceived target is the maximum value between the first estimated number and the second estimated number; or, if the first estimated number and the second estimated number are the same, the estimated number M of the perceived target is either the first estimated number or the second estimated number.

[0024] In conjunction with the second aspect above, in one possible implementation, the first estimated number of perceived targets is the number of first weight coefficients that satisfy a preset threshold among R first weight coefficients.

[0025] In conjunction with the second aspect above, in one possible implementation, the first weight coefficient that satisfies the preset threshold is the first weight coefficient among R first weight coefficients that is greater than or equal to the preset threshold; or, the first weight coefficient that satisfies the preset threshold is the first X first weight coefficients after the R first weight coefficients are sorted in descending order, and the ratio of two adjacent first weight coefficients among the first X first weight coefficients is greater than or equal to the preset threshold, where X is a positive integer less than or equal to R; or, the first weight coefficient that satisfies the preset threshold is the first N first weight coefficients after the R first weight coefficients are sorted in descending order; wherein, the sum of the first N-1 first weight coefficients is less than the preset threshold, and the sum of the first N first weight coefficients is greater than or equal to the preset threshold; where N is a positive integer less than or equal to R.

[0026] In conjunction with the second aspect above, in one possible implementation, the method further includes: receiving first sensing information from a first access network device, the first sensing information including M first sensing parameter groups; receiving second sensing information from a second access network device, the second sensing information including M second sensing parameter groups; M being a positive integer; and performing fusion processing based on the first sensing information and the second sensing information to obtain sensing results for Y sensing targets, where Y is a positive integer less than or equal to M.

[0027] In conjunction with the second aspect above, in one possible implementation, the above-mentioned fusion processing based on the first and second perception information to obtain the perception results of Y perception targets includes: performing similarity matching processing on the first and second perception information to obtain Y perception parameter pairs; each perception parameter pair includes one first perception parameter pair from the first perception information and one second perception parameter pair from the second perception information, and the similarity between the first and second perception parameter pairs in the same perception parameter pair is greater than or equal to a similarity threshold; and performing fusion processing based on the y-th perception parameter pair to obtain the perception result of the y-th perception target, y = 1, ..., Y.

[0028] In the above technical solution, since each access network device obtains corresponding sensing information based on the echo signal, the sensing network element performs fusion processing on the first sensing information and the second sensing information, which can eliminate inaccurate sensing parameter groups in the sensing information, and obtain the sensing results of Y sensing targets while ensuring the accuracy of the sensing results.

[0029] In conjunction with the second aspect above, in one possible implementation, the sensing parameter set includes at least one of the following: a distance parameter, an angle parameter, or a velocity parameter of the sensing target.

[0030] The technical effects of any possible implementation of the second aspect can be referred to the technical effects of the corresponding design in the first aspect, and will not be repeated here.

[0031] Thirdly, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation of the methods, which 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 functions.

[0032] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively used to implement the receiving function and the transmitting function in any of the above aspects and any possible implementations thereof.

[0033] In some possible designs, the transceiver module can consist of transceiver circuits, transceivers, transceivers, or communication interfaces.

[0034] Fourthly, a communication device is provided, comprising: a processor and a memory; the memory is used to store computer instructions that, when executed by the processor, cause the communication device to perform the methods described in any aspect.

[0035] Fifthly, a communication device is provided, comprising: a processor and a communication interface; the communication interface being used to communicate with a module outside the communication device; the processor being used to execute computer programs or instructions to cause the communication device to perform the methods described in any of the aspects.

[0036] A sixth aspect provides a communication device comprising: at least one processor; said processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the methods described in any aspect. The memory may be coupled to the processor, or may be independent of the processor.

[0037] In a seventh aspect, a communication device (e.g., the communication device may be a chip or a chip system) is provided, the communication device including a processor for implementing the functions involved in any one of the first to sixth aspects.

[0038] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0039] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0040] It is understood that the communication device provided in the third to seventh aspects may be the first access network device in the first aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the first access network device that performs the methods / operations / steps / actions described in the first aspect, or a module or unit that can be used in conjunction with the first access network device, or a logical node, logical module, or software that can implement all or part of the functions of the first access network device; or, the communication device may be a sensing network element in the second aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the sensing network element that performs the methods / operations / steps / actions described in the second aspect, or a module or unit that can be used in conjunction with the sensing network element, or a logical node, logical module, or software that can implement all or part of the functions of the sensing network element.

[0041] It is understandable that when the communication device provided by any of the third to seventh aspects is a chip, the sending action / function of the communication device can be understood as outputting information, and the receiving action / function of the communication device can be understood as inputting information.

[0042] Eighthly, a computer-readable storage medium is provided that stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the method described in any one of the first to second aspects.

[0043] A ninth aspect provides a computer program product containing instructions that, when run on a communication device, enables the communication device to perform the method described in any one of the first to second aspects.

[0044] A tenth aspect provides a communication system comprising a first access network device and a sensing network element. The first access network device is configured to perform the methods described in the first aspect and any possible embodiments thereof, and the sensing network element is configured to perform the methods described in the second aspect and any possible embodiments thereof.

[0045] The technical effects of any of the design methods in aspects three through ten can be found in the technical effects of different implementation methods in aspects one or two, and will not be repeated here. Attached Figure Description

[0046] Figure 1 is a schematic diagram of an ISAC target perception method provided in this application;

[0047] Figure 2 is a schematic diagram of an ISAC target perception mode provided in this application;

[0048] Figure 3 is a schematic diagram of a method for sensing a target provided in a related technology;

[0049] Figure 4 is a schematic diagram of the architecture of a communication system provided in this application;

[0050] Figure 5 is a schematic diagram of an O-RAN node architecture provided in this application;

[0051] Figure 6 is a schematic diagram of the hardware architecture of an O-RAN node provided in this application;

[0052] Figure 7 is a schematic diagram of the architecture of another communication system provided in this application;

[0053] Figures 8-14 are flowcharts of the sensing method provided in this application;

[0054] Figures 15-18 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0055] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0056] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0057] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0058] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0059] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0060] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0061] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0062] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0063] To facilitate understanding of the technical solutions of the embodiments of this application, a brief introduction to the relevant technologies of this application is given below.

[0064] I. Sensing signals and echo signals.

[0065] In a sensing scenario, a transmitting device radiates electromagnetic waves to send sensing signals to the surrounding environment. A receiving device receives the sensing signals reflected from the surrounding environment and analyzes and compares them with the transmitted sensing signals to perceive relevant information about the surrounding environment, such as the presence of the target to be detected, the number of targets, and the location of each target. For example, the reflected sensing signal can also be called an echo signal or an echo of the sensing signal; these terms can be used interchangeably without limitation.

[0066] A sensing signal can be understood as a signal used to sense (or detect) a target. The target can also be understood as the sensing target or target object, such as a scatterer or reflector. The sensing signal can be a detection signal, a linear frequency modulated signal, a radar signal, a radar sensing signal, a radar detection signal, an environmental sensing signal, a pulse signal, or a signal in a wireless communication system. The sensing signal can also be a reference signal; for example, its initial amplitude and phase information can be pre-configured to the receiver through a configuration sequence. The sensing signal can also be a data signal; the receiver can calculate the initial amplitude and phase of each data signal using known modulation methods such as data verification. The sensing signal can also have other names, which are not specifically limited in this application.

[0067] II. Integrated sensing and communication (ISAC).

[0068] As fifth-generation mobile communication (5G) continues to evolve towards 5G-advanced (5G-A), communication systems face numerous challenges. On the one hand, spectrum resources are becoming increasingly scarce, requiring more efficient spectrum utilization methods. On the other hand, communication devices have limited ability to perceive their surroundings, hindering the full utilization of environmental information to optimize the communication process. Therefore, ISAC (Interactive Information Center) has emerged to address this issue, organically combining communication and sensing functions to break down the boundaries between them and achieve resource sharing and functional synergy.

[0069] As shown in Figure 1, in the ISAC system, without occupying additional spectrum resources and without affecting the communication link between the terminal device and the access network device, the access network device uses communication signals to perceive and acquire perception parameters such as speed, distance and angle of the perceived target in the environment (e.g., vehicles and drones) under various perception modes (e.g., self-transmission and self-reception and mutual transmission and reception modes), thus giving new capabilities to important information applications.

[0070] For example, in intelligent transportation environments, ISAC (Intelligent Transportation Automation) senses the position and speed of vehicles and pedestrians to provide early warnings of potential collisions, ensuring driving safety. Specifically, in self-transmitting and self-receiving mode, access network device 1 sends a sensing signal to the vehicle, which is then reflected by the vehicle and received by access network device 1; access network device 2 sends a sensing signal to the vehicle, which is also reflected by the vehicle and received by access network device 2. In mutual transmitting and receiving mode, access network device 1 sends a sensing signal to the vehicle, which is then reflected by the vehicle and received by access network device 2.

[0071] For example, in low-altitude security environments, ISAC (Intelligent Surveillance and Control System) monitors drones and ensures urban low-altitude safety by acquiring real-time information such as the distance and angle of drones. Specifically, in self-transmitting and self-receiving mode, access network device 1 sends a sensing signal to the drone, which is then received by access network device 1 after being reflected by the drone; access network device 2 sends a sensing signal to the drone, which is also received by access network device 2 after being reflected by the drone. In mutual transmitting and receiving mode, access network device 1 sends a sensing signal to the drone, which is then received by access network device 2 after being reflected by the drone; access network device 2 sends a sensing signal to the drone, which is then received by access network device 1 after being reflected by the drone. Exemplarily, in ISAC, the sensing modes mainly include access network device self-transmitting and self-receiving mode, access network device mutual transmitting and receiving mode, and terminal device transmitting and access network device receiving mode.

[0072] 1. Access network equipment self-transmission and self-reception mode.

[0073] As shown in Figure 2(a), access network device 1 sends a sensing signal, which is reflected by sensing target 1 and sensing target 2, and the reflected echo signal is received by access network device 1; access network device 2 sends a sensing signal, which is reflected by sensing target 1 and sensing target 2, and the reflected echo signal is received by access network device 2. The echo signal includes a sub-echo signal reflected by sensing target 1 and a sub-echo signal reflected by sensing target 2.

[0074] 2. Inter-device transmission and reception mode of access network devices.

[0075] As shown in Figure 2(b), access network device 1 sends a sensing signal, which is reflected by sensing target 1 and sensing target 2, and the reflected echo signal is received by access network device 2; access network device 2 sends a sensing signal, which is reflected by sensing target 1 and sensing target 2, and the reflected echo signal is received by access network device 1. The echo signal consists of a sub-echo signal reflected by sensing target 1 and a sub-echo signal reflected by sensing target 2.

[0076] 3. Terminal equipment transmits to access network equipment receives.

[0077] As shown in Figure 2(c), the terminal device sends a sensing signal, which is reflected by sensing target 1 and sensing target 2. The reflected echo signals are received by access network device 1 and access network device 2. The echo signals are sub-echo signals reflected by sensing target 1 and sensing target 2.

[0078] III. Accuracy.

[0079] Precision describes the error between the perceived result and the ideal, true result. Taking distance estimation as an example, if the estimated distance of the perceived target relative to the sensing device is 6 meters (m), while the actual distance is 5 meters, then the perception error is 1 meter, which is also the precision is 1 meter.

[0080] IV. Resolution.

[0081] Resolution is used to describe the smallest parameter unit that can distinguish two different targets. Taking distance estimation as an example, a distance resolution of 1m means that when the distance between two perceived targets is greater than or equal to 1m, the sensing device can distinguish between the two perceived targets, while when the distance between the two perceived targets is less than 1m, the sensing device cannot distinguish between the two perceived targets.

[0082] V. Tensor decomposition.

[0083] Generally, a first-order tensor is called a vector, a second-order tensor is called a matrix, and a third-order tensor and tensors of higher orders are called higher-order tensors.

[0084] Tensor decomposition is the process of representing a high-dimensional tensor as a combination of multiple low-rank tensors, which can be used to extract features from tensor data. Common tensor decomposition methods include canonical polyadic (CP) decomposition and Tucker decomposition.

[0085] Canonical polyadic (CP) decomposition is a typical tensor decomposition algorithm that can decompose high-dimensional tensor data into a combination of several rank-1 (rank-1) tensors. The number of rank-1 tensors after decomposition is the CP rank of the high-dimensional tensor data. For example, if the CP decomposition algorithm is used to decompose high-dimensional tensor data into 3 rank-1 tensors, then the number 3 is the CP rank of the high-dimensional tensor data.

[0086] VI. CP specific gravity coefficient.

[0087] After performing a rank-K CP decomposition on the high-dimensional tensor data, a combination of K rank-tensors can be obtained, along with the CP weight coefficient corresponding to each of the K rank-tensors. The CP weight coefficient reflects the importance of the rank-tensor relative to the original high-dimensional tensor data. The CP weight coefficient can also be referred to as weight, proportion, etc., and this application does not impose any restrictions on it.

[0088] VII. Incoherent fusion.

[0089] Incoherent fusion is a method that uses information from multiple sensors or multiple base stations / terminals to jointly determine target parameters. The core of this method lies in combining information from different sources to improve the accuracy and reliability of target parameter estimation. In incoherent fusion, a minimum mean square error (MMSE) estimator can be used to achieve effective fusion of various information sources.

[0090] The above provides a brief overview of the relevant technologies involved in this application.

[0091] Currently, when sensing targets, as shown in Figure 3, related technologies target the echo signal of the target. Based on the inverse discrete fourier transform (IDFT) in the frequency domain, the range characteristics of the target are reduced to the first beam spectrum in the range dimension. Based on the slow time domain discrete fourier transform (DFT) and point-wise division, the velocity characteristics of the target are reduced to the second beam spectrum in the velocity dimension. Based on the spatial domain 2D-DFT, the angular characteristics of the target are reduced to the third beam spectrum (i.e., the multi-domain filtered response beam spectrum). Then, constant false alarm rate (CFAR) detection and peak search are applied to find the corresponding positions of the sensing parameters on the multi-domain filtered response beam spectrum, thereby estimating the angular parameters of the target (such as azimuth angle θ and pitch angle). ), velocity parameter v and distance parameter r.

[0092] However, when the aforementioned technologies are used to sense targets, on the one hand, they require the combined use of CFAR detection and peak search techniques to determine the sensing parameters, resulting in high computational complexity; on the other hand, they require quantizing the parameter search space (i.e., quantizing and reducing each feature of the sensed target to the multi-domain filtered response beam spectrum) and determining the sensing parameters in the quantized multi-domain filtered response beam spectrum based on the grid point spacing, resulting in accuracy and resolution performance limited by the grid point spacing; furthermore, in the process of using peak search techniques to find sensing parameters in the multi-domain filtered response beam spectrum, since the multi-domain filtered response beam spectrum is composed of multiple light spots, and the light spots themselves have a certain width, that is, the light spot at the peak may correspond to covering an interval (e.g., 0.1-0.2) rather than a precise value, resulting in accuracy and resolution performance limited by the beam width.

[0093] Therefore, it can be seen that when the above-mentioned related technologies are used to sense the target, the joint peak search technology of multi-dimensional beam spectrum needs to quantize (gridize) the multi-domain parameter search space. This results in problems such as the accuracy and resolution performance being limited by the grid point spacing and beam width, and high computational complexity.

[0094] In view of this, this application proposes a sensing method in which a first access network device obtains an estimated number M of the sensing target through the echo signal, and then, based on the estimated number M, performs tensor decomposition on the echo signal to acquire the sensing information of the sensing target, and then determines the sensing result through sensing network elements. In other words, the first access network device can achieve super-resolution, gridless determination of the sensing result of the sensing target without applying joint peak search technology and quantization parameter search space. This solves the problem that the accuracy and resolution performance of current sensing methods are limited by the grid point spacing and have high computational complexity, thus improving the sensing accuracy, resolution, and computational efficiency of the sensing target.

[0095] The technical solutions of this application embodiment can be used in various communication systems, including third-generation partnership project (3GPP) communication systems, such as fourth-generation (4G) systems like long-term evolution (LTE), 5G systems like new radio (NR), hybrid LTE and 5G networks, non-terrestrial networks (NTN), or other future communication systems. The communication system can also be a non-3GPP communication system; there is no limitation on this.

[0096] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0097] Figure 4 is a schematic diagram illustrating the architecture of a possible, non-limiting communication system. As shown in Figure 4, the communication system 40 includes a radio access network (RAN) 400 and a core network (CN) 500.

[0098] The following is a detailed explanation of RAN 400.

[0099] In some embodiments, RAN 400 includes a plurality of access network devices (410a and 410b in FIG4, collectively referred to as 410) and at least one terminal (420a-420j in FIG4, collectively referred to as 420). The plurality of access network devices 410 includes a first access network device, a second access network device, a third access network device, ..., an Nth access network device, where N is a positive integer.

[0100] Optionally, RAN 400 may also include other access network devices, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 4). Terminal 420 is wirelessly connected to access network device 410. Access network device 410 is wirelessly or wired connected to core network 500.

[0101] In one possible implementation, RAN 400 can be a 3GPP-related cellular system, such as a 4G or 5G mobile communication system, or a future-oriented evolution system (such as a future communication network). RAN 400 can also be an open access network (open RAN, O-RAN, or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 400 can also be a communication system that integrates two or more of the above systems.

[0102] In some scenarios, the roles of access network device 410 and terminal 420 are relative. For example, in Figure 4, network element 420i can be a helicopter or drone, which can be configured as a mobile base station. For terminals 420j that access RAN 400 through network element 420i, network element 420i is a base station; but for base station 410a, network element 420i is a terminal. Access network device 410 and terminal 420 are sometimes referred to as communication devices. For example, in Figure 4, network elements 410a and 410b can be understood as communication devices with base station functions, and network elements 420a-420j can be understood as communication devices with terminal functions.

[0103] The terminal 420 and the access network device 410 will be described below.

[0104] 1. Terminal 420.

[0105] Terminal 420 is a user-side entity used to receive or transmit signals. It is used to send uplink signals to access network equipment 410, or receive downlink signals from access network equipment 410, or send signals to another terminal device, or receive signals from another terminal device, or receive echo signals of signals it has sent.

[0106] In one possible scenario, a terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, intelligent transportation, and smart cities.

[0107] Optionally, the terminal can be a mobile phone, tablet computer, virtual reality terminal device, augmented reality terminal device, wearable device, vehicle-mounted device, wireless terminal in industrial control, or a mobile object with communication capabilities such as a vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home device, or a wireless device (e.g., communication module, modem, or chip system) built into the above devices. The embodiments of this application do not limit the device form of the terminal.

[0108] II. Access Network Equipment 410.

[0109] Access network equipment 410, sometimes referred to as RAN entity or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple access network equipment 410 in the communication system 40 can be nodes of the same type or different types.

[0110] Scene 1:

[0111] In one possible scenario, access network equipment can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a 5G base station (next generation NodeB, gNB), a base station in a future mobile communication system, or an access node in a WiFi system. Access network equipment can be a macro base station (as shown in Figure 4, 410a), a micro base station or indoor station (as shown in Figure 4, 410b), a relay node or donor node, or a radio controller in a CRAN scenario.

[0112] Optionally, the access network device can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the access network device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The access network device in this application can also be a logical node, logical module, or software capable of implementing all or part of the access network device functions.

[0113] Scene 2:

[0114] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the functions of the access network equipment. For example, RAN nodes can be open RAN (O-RAN) nodes, specifically control units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc.

[0115] Specifically, regarding the architecture of the O-RAN node, as shown in Figure 5, the baseband unit (BBU) in the O-RAN node communicates with the sensing network elements via a backhaul link, and the RU in the O-RAN node communicates with at least one terminal 420 via an air interface. The BBU communicates with at least one RU via a fronthaul link. The BBU and RU may or may not be co-located. The BBU includes at least one CU and at least one DU, which can communicate via at least one midhaul link.

[0116] In some embodiments, 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 can be split into CU-CP and CU-UP. CU-CP is a logical node carrying the RRC layer and the 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) network elements, such as the access and mobility management (AMF) function in a 5G system. AMF network elements are responsible for mobility management in the mobile network, such as UE location updates, network registration, and handover. CU-UP is a logical node carrying the SDAP layer and the PDCP-U (user plane part of PDCP) layer, used to implement the CU's user plane functions. The CU-UP can interact with network elements in the core network used to implement user plane functions, such as the UPF (user plane function) in a 5G system, and is responsible for forwarding and receiving data in the UE. The above CU and DU configurations are merely examples; the functions of the CU and DU can be configured as needed. For example, the CU or DU can be configured to have more protocol layer functions, or it can be configured to have only some protocol layer processing functions. For instance, some RLC layer functions and protocol layer functions above the RLC layer can be set in the CU, while the remaining RLC layer functions and protocol layer functions below the RLC layer can be set in the DU.

[0117] In some embodiments, a DU is a logical node that carries the radio link control (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 may be fronthaul interfaces. In some examples, the Higher PHY layer includes PHY layer processing functions such as forward error correction (FEC) encoding and decoding, scrambling, modulation, and demodulation.

[0118] In some embodiments, the RU is a logical node that carries both lower physical layer (PHY) and radio frequency (RF) processing. In some examples, the RU may be a 3GPP transmission reception point (TRP), a remote radio head (RRH), or other similar entities. 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.

[0119] The CU and DU can be set up separately or included in the same network element, such as the baseband unit (BBU). The RU can be included in radio frequency equipment or radio frequency units, such as the remote radio unit (RRU), active antenna unit (AAU), or RRH.

[0120] The DU and RU can be co-located or not. The DU and RU exchange control plane and user plane information via a fronthaul link through a lower-layer split-control, user, and synchronization (LLS-CUS) interface. LLS-CUS may include an LLS-C interface providing CP and an LLS-U interface providing UP, respectively. In some examples, CP 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.

[0121] 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.

[0122] For example, the CU can be used to perform layer 2 (L2) and layer 3 (L3) functions. Furthermore, the CU can also have some core network functions. The DU can be used to perform layer 1 (L1) and some L2 functions, and the RU can be used to perform L1 computation and radio frequency (RF) digital functions.

[0123] Optionally, as shown in Figure 6, the CU can be connected to sensing network elements in the core network and one or more DUs. A backhaul interface exists between the CU and the sensing network elements in the core network to carry traffic between the CU and the sensing network elements in the core network. A midhaul interface exists between the CU and the DU to carry traffic between the CU and the DU. A DU can be connected to one or more RUs. A fronthaul interface exists between the DU and the RU to carry traffic between the DU and the RU.

[0124] In terms of hardware, CU and DU can include a chassis platform, motherboard, peripheral devices, and cooling equipment. The motherboard contains processing units, memory, internal input / output (I / O) interfaces, and external connection ports. Its hardware accelerator is designed with interfaces, and hardware functional components include: storage for software, hardware, and system debugging interfaces, and a single-board management controller.

[0125] CU / DU are typically implemented using multi-core processors and one or more hardware accelerators. Parts of the DU protocol stack can be implemented in software running on the multi-core processor, while computationally intensive L1 and L2 functions can be offloaded to a field-programmable gate array (FPGA) / graphics processing unit (GPU)-based hardware accelerator; or all L1 functions can be offloaded to an FPGA / GPU-based hardware accelerator, while other protocol stack content is implemented in software running on the processor; or the entire protocol stack can be implemented in software running on the processor. As shown in Figure 6, the hardware accelerator supports interconnection with x86 or non-x86 processors (e.g., ARM-based CPUs). Similarly, the accelerator has a multi-channel peripheral component interconnect express (PCIe) interface pointing to the central processing unit (CPU) and external connections via GbE.

[0126] An RU may include an O-RAN processing unit (OPU), a digital processing unit (DPU), and an RF processing unit.

[0127] The OPU is used to receive enhanced common public radio interface (eCPRI) frames from the O-RAN fronthaul and perform fronthaul interface, lowest level L1 (coding, scrambling, modulation, layer mapping, precoding), synchronization, beamforming, and resource unit mapping. As shown in Figure 6, the OPU can be implemented as a CPU, FPGA, or application-specific integrated circuit (ASIC).

[0128] The DPU is used to perform synchronization, uplink (UL) digital downconversion (DDC), downlink (DL) digital upconversion (DUC), channel failure ratio (CFR), and digital pre-distortion (DPD) processing. It improves power amplifier efficiency by reducing the peak-to-average power ratio (PAPR) / adjacent channel leakage ratio (ACLR) of the RF front-end. As shown in Figure 6, the DPU can be implemented as a CPU, FPGA, or ASIC.

[0129] The RF processing unit includes a transceiver module, up / down converters, power amplifiers (PA), low-noise amplifiers (LNA), and Tx / Rx filters. Analog-to-digital conversions (such as digital-to-analog converters (DACs), analog-to-digital converters (ADCs), RF sampling, and frequency conversion) can be performed within the transceiver module. Note that physical and logical partitions within the RF processing unit do not require specific boundaries.

[0130] It should be noted that CU (or CU-CP and CU-UP), DU, or RU may have different names in different systems, but those skilled in the art will understand their meaning. For example, in an O-RAN node, CU can also be called O-CU (Open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0131] In some embodiments, the CU interacts with the sensing network elements in the core network 500 via signaling. The signaling interaction process includes: 1. The CU uploads R first weight coefficients to the sensing network elements; 2. The CU receives an estimated number M of sensing targets from the sensing network elements; 3. The CU uploads sensing information to the sensing network elements.

[0132] In other embodiments, the DU communicates with at least one RU via a fronthaul link, and the RU communicates with another RU (or the same RU) via an air interface. The communication process includes: 1. The RU transmits a sensing signal, which is reflected by the sensing target and received by another RU (or the same RU); 2. The RU sends R first weight coefficients, which are received by another RU; 3. The RU sends an estimated number M of sensing targets, which are received by another RU.

[0133] Scene 3:

[0134] In another possible scenario, the access network device can also be a non-real time RAN intelligent controller (Non-RT RIC or NRT RIC) and / or a near-real time RAN intelligent controller (Near-RT RIC or nRT RIC).

[0135] Non-RT RIC is used to implement non-real-time intelligent management of the RAN, enabling artificial intelligence (AI) / machine learning (ML) for model training and updates, and guiding applications / functions within the Near-RT RIC based on policies. Near-RT RIC is used to implement near real-time intelligent management of the RAN, achieving near real-time control and optimization of O-RAN modules and resources through data collection and related operations on the E2 interface. The E2 interface can be understood as an open interface between two nodes (or endpoints).

[0136] All or part of the functions of the access network device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform), or through software modules, hardware modules, or a combination of software and hardware modules. The access network device in this application can also be a logical node, logical module, or software capable of implementing all or part of the functions of the access network device, or a device with some access network device functions, such as a chip system, which can be installed in the access network device.

[0137] The above provides a detailed explanation of RAN 400.

[0138] The following is a detailed explanation of the core network 500.

[0139] The core network equipment in the core network 500 and the access network equipment 410 in the RAN 400 can be different physical devices, or they can be the same physical device that integrates core network logical functions and radio access network logical functions.

[0140] Core network equipment can refer to the equipment in the core network 500 that provides service support to terminals. In this embodiment, the core network equipment in the core network 500 includes sensing function (SF) network elements. SF network elements are responsible for the processing and interaction of sensing services in the ISAC system, realizing the processing and transfer of sensing data from different access network devices, as well as the issuance and reception of sensing service-related instructions. Sensing functions include, for example, sensing control functions and / or sensing computing functions. Furthermore, SF network elements can also support sensing billing functions when terminals and / or access network devices perform sensing.

[0141] In one possible scenario, the functionality of the SF network element can be implemented by the network data analytics function (NWDAF) network element, or the SF network element and the NWDAF network element can be co-located. Alternatively, the SF network element can be deployed integrated with the core network or deployed independently.

[0142] In some embodiments, as shown in FIG7, the SF network element (sensing network element) is connected to each access network device 410 via a communication link, and the access network device 410 is connected to each terminal 420 via an air interface. Based on this connection relationship, 1. the SF network element can be used to receive R first weight coefficients from each RAN node (e.g., CU module), and determine the estimated number M of sensing targets based on the R first weight coefficients; 2. the SF network element can also be used to send first information to each RAN node (e.g., CU module), the first information being used to indicate the estimated number M; 3. the SF network element can also be used to receive sensing information from each RAN node (e.g., CU module), and perform fusion processing on the sensing information from each RAN node to obtain the sensing results of Y sensing targets.

[0143] The above provides a detailed explanation of the core network 500.

[0144] It should be noted that the communication system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0145] The following description, using the communication system shown in Figure 4 as an example, illustrates the sensing method provided in this application. It should be noted that the message names, parameter names, or information names between the access network device and the sensing network element in the following embodiments are merely examples; other names may exist in other embodiments, and the method provided in this application does not specifically limit these.

[0146] It is understood that in the embodiments of this application, the access network device and the sensing network element may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the various steps may be performed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to perform all the operations in the embodiments of this application.

[0147] It is understood that this application uses access network equipment and sensing network elements as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the access network equipment in this application can also be executed by a module applied to the access network equipment (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the functions of the access network equipment; similarly, the method executed by the sensing network element in this application can also be executed by a module applied to the sensing network element (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the functions of the sensing network element.

[0148] Furthermore, in this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "access network device sending information" can be understood as an access network device sending information to another device (such as a terminal), or it can be understood as logical module 1 (such as a processing module) in the access network device sending information to logical module 2 (such as a transceiver module) in the access network device.

[0149] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "sensing network element receiving information" can be understood as a sensing network element receiving information from another device (such as a RAN node), or it can be understood as logical module 1 (such as a processing module) in the sensing network element receiving information from logical module 2 (such as a transceiver module) in the sensing network element.

[0150] In this application, "sending information to... (e.g., a sensing network element)" or the related illustrations in the accompanying drawings can be understood as the destination of the information being a sensing network element. This can include sending information directly or indirectly to a terminal. "Receiving information from... (e.g., an access network device)" or "receiving information from... (e.g., an access network device)" or "receiving information sent by (e.g., an access network device)" or the related illustrations in the accompanying drawings can be understood as the source of the information being an access network device. This can include receiving information directly or indirectly from an access network device. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way, and will not be elaborated further here.

[0151] For example, this application is applied to an ISAC multi-access network device collaborative sensing scenario. In this scenario, the access network devices can process the echo signal corresponding to the sensing target in different sensing modes, thereby realizing the sensing target and uploading the sensing result to the sensing network element.

[0152] The sensing method provided in the embodiments of this application will be specifically described below with reference to Figures 8-14.

[0153] Figure 8 is a flowchart of a sensing method provided in an embodiment of this application. As shown in Figure 8, the sensing method may include the following steps S801-S804.

[0154] S801, The first access network device receives the echo signal.

[0155] Optionally, the echo signal can be composed of sub-signals reflected by each of the multiple sensing targets. For example, taking a number of sensing targets as 3, the echo signal can be composed of sub-signal 1 reflected by sensing target 1, sub-signal 2 reflected by sensing target 2, and sub-signal 3 reflected by sensing target 3. Here, the multiple sensing targets are multiple sensing targets within the same area.

[0156] In one possible implementation, the S801 implementation process includes: a first device sending a sensing signal, which is then reflected by the sensing target (i.e., an echo signal), and subsequently received by the first access network device.

[0157] Optionally, the first device can be any of the following: a terminal device, a first access network device, or an access network device other than the first access network device.

[0158] For example, a first access network device sends a sensing signal, which is reflected by the sensing target and received by the first access network device; or, another access network device (such as a second access network device) sends a sensing signal, which is reflected by the sensing target and received by the first access network device; or, a terminal device sends a sensing signal (also known as an uplink signal), which is reflected by the sensing target and received by the first access network device.

[0159] S802. The first access network device obtains an estimated number M of sensed targets based on the echo signal.

[0160] In one possible implementation, the S802 process includes: the first access network device can perform tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients, and send the R first weight coefficients to the sensing network element or the third access network device. The sensing network element or the third access network device can determine the estimated quantity of the sensing target based on the R first weight coefficients, and send first information to the first access network device, indicating the estimated quantity M of the sensing target. Correspondingly, the first access network device can receive the first information from the sensing network element or the third access network device, thereby obtaining the estimated quantity M.

[0161] Wherein, R first weight coefficients correspond to R sub-signals of the echo signal; the first weight coefficients are used to reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, and R is a positive integer. The third access network device can be a designated central access network device among multiple access network devices. This central access network device can be any one of the multiple access network devices in collaborative sensing, or it can be an access network device located in the middle geographical location among the multiple access network devices in collaborative sensing; this application does not impose any restrictions on this.

[0162] For example, the estimated number M of sensed targets can be understood as the number of sensed targets in the surrounding environment or a certain area estimated by the sensing network element or the third access network device. This estimated number M may be the same as or different from the actual number of sensed targets in the surrounding environment.

[0163] For example, the first access network device can represent the echo signal as high-dimensional tensor data, and then perform tensor decomposition on the high-dimensional tensor data based on a preset rank R to obtain R first weight coefficients and R rank tensor data. The R first weight coefficients correspond one-to-one with the R rank tensor data, and the rank tensor data can characterize the sub-signals in the echo signal.

[0164] Understandably, the first weighting coefficient can be interpreted as the weight of the rank-tensor data, specifically its importance within the high-dimensional tensor data. Since the high-dimensional tensor data is represented by echo signals, and the rank-tensor data can represent a sub-signal within the echo signal, the first weighting coefficient, through mapping, can reflect the importance of the sub-signal corresponding to the rank-tensor data within the echo signal. A higher importance indicates a higher probability that the sub-signal is a reflection from the target; conversely, a lower importance indicates a lower probability that the sub-signal is a reflection from the target.

[0165] For example, the preset rank R can be configured by the sensing network element or the third access network device, or it can be predefined by the protocol, or it can be determined by the first access network device itself, without restriction.

[0166] In the above implementation, the first access network device can determine a first estimated quantity of the sensed target through the sensing network element. As shown in Figure 9, the implementation process includes: the first access network device can send R first weighting coefficients to the sensing network element; correspondingly, the sensing network element receives R first weighting coefficients and determines the first estimated quantity of the sensed target based on the R first weighting coefficients. Furthermore, the sensing network element can send first information to the first access network device to indicate the estimated quantity M.

[0167] Specifically, the specific implementation process of the first access network device determining the first estimated number of sensing targets through sensing network elements is as described in Example 1 below, and will not be repeated here.

[0168] In the above implementation, the first access network device can also determine the first estimated quantity of the sensed target through the third access network device (i.e., the central access network device). As shown in Figure 10, the implementation process includes: the first access network device can also send R first weight coefficients to the third access network device; correspondingly, the third access network device receives R first weight coefficients and determines the first estimated quantity of the sensed target based on the R first weight coefficients. Furthermore, the third access network device can send first information to the first access network device to indicate the estimated quantity M.

[0169] Specifically, the process by which the first access network device determines the first estimated number of sensing targets through the third access network device is described in Example 2 below, and will not be repeated here.

[0170] In another possible implementation, the S802 implementation process includes: when the first access network device is the central access network device, the first access network device performs tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients; based on the R first weight coefficients, determines a first estimated number of sensing targets; R is a positive integer; receives R second weight coefficients from the second access network device, and determines a second estimated number of sensing targets based on the R second weight coefficients; and determines an estimated number M of sensing targets based on the first and second estimated numbers.

[0171] Specifically, when the first access network device acts as the central access network device, the specific implementation process for the first access network device to determine the first estimated number of sensing targets is as described in Example 3 below, and will not be repeated here.

[0172] S803. The first access network device performs tensor decomposition on the echo signal based on the estimated quantity M to obtain the first sensing information.

[0173] The first perception information includes M sets of first perception parameters, where M is a positive integer.

[0174] Optionally, the sensing parameter set includes at least one of the following: distance parameter, angle parameter, or velocity parameter of the sensing target.

[0175] In one possible implementation, the S803 implementation process includes: the first access network device represents the echo signal as high-dimensional tensor data, and adjusts the preset rank R to rank M according to the estimated quantity M; then, based on rank M, it performs tensor decomposition on the high-dimensional tensor data to obtain M first sensing parameter groups.

[0176] S804. The first access network device sends first sensing information to the sensing network element. Correspondingly, the sensing network element receives the first sensing information from the first access network device.

[0177] The first perception information is used to determine the perception result.

[0178] It is understandable that the first access network device sends the first sensing information to the sensing network element so that the sensing network element can determine the sensing result based on the first sensing information from the first access network device and the Nth sensing information from the other access network devices, where N is a positive integer.

[0179] Based on the above technical solution, the first access network device receives the echo signal and obtains an estimated number M of the sensing targets based on the echo signal. Then, the first access network device can perform tensor decomposition on the echo signal according to the estimated number M of the sensing targets to obtain sensing information. Subsequently, the first access network device sends sensing information to the sensing network element to determine the sensing result. Thus, in this technical solution, the first access network device, without needing to apply joint peak search technology or quantization parameter search space, can achieve super-resolution, gridless acquisition of sensing information of the sensing targets by obtaining the estimated number M of the sensing targets and performing tensor decomposition on the echo signal. This solves the problem that the accuracy and resolution performance of current target sensing is limited by the grid point spacing and has high computational complexity, improving the sensing accuracy, resolution, and computational efficiency of the sensing targets.

[0180] The following, in conjunction with a specific application scenario (multi-access network device collaborative sensing scenario), specifically describes the implementation process of the first access network device in S802 obtaining the estimated number M of the sensing target based on the echo signal through Embodiments 1, 2, and 3. Embodiment 1 specifically describes the implementation process of the first access network device determining the first estimated number of the sensing target through sensing network elements; Embodiment 2 specifically describes the implementation process of the first access network device determining the first estimated number of the sensing target through a third access network device; and Embodiment 3 specifically describes the implementation process of the first access network device determining the first estimated number of the sensing target when the first access network device acts as the central access network device.

[0181] Example 1:

[0182] As shown in Figure 9, taking the collaborative sensing of the first access network device and the second access network device as an example, the specific implementation process of the first access network device determining the first estimated quantity of sensing targets through sensing network elements is explained in detail through S900-S906.

[0183] S900: The first access network device sends a first sensing signal. The second access network device sends a second sensing signal.

[0184] For example, as shown in Figure 9, after the first access network device sends a first sensing signal, the first sensing signal is reflected by sensing target 1 and sensing target 2; and after the second access network device sends a second sensing signal, the second sensing signal is reflected by sensing target 1 and sensing target 2.

[0185] S901. The first access network device receives the first echo signal. The second access network device receives the second echo signal.

[0186] For example, the first echo signal can be an echo signal composed of sub-signals of the first sensing signal reflected by multiple sensing targets. For instance, as shown in Figure 9, the first echo signal can be an echo signal composed of sub-signals of the first sensing signal reflected by sensing target 1 and sub-signals reflected by sensing target 2.

[0187] The second echo signal can be an echo signal composed of sub-signals of the second sensing signal reflected by multiple sensing targets. For example, as shown in Figure 9, the second echo signal can be an echo signal composed of sub-signals of the second sensing signal reflected by sensing target 1 and sub-signals reflected by sensing target 2.

[0188] S902, the first access network device sends R first weighting coefficients to the sensing network element. Correspondingly, the sensing network element receives R first weighting coefficients from the first access network device.

[0189] Optionally, before the first access network device sends R first weight coefficients to the sensing network element, the first access network device determines R first weight coefficients based on the received echo signal.

[0190] The implementation of the R first weight coefficients can be referred to the relevant description in step S802 above, and will not be repeated here.

[0191] S903, the second access network device sends R second weighting coefficients to the sensing network element. Correspondingly, the sensing network element receives R second weighting coefficients from the second access network device.

[0192] Among them, the R second weight coefficients correspond to the R sub-signals of the echo signal; the second weight coefficients are used to reflect the importance of the sub-signals corresponding to the second weight coefficients in the echo signal.

[0193] Optionally, before the second access network device sends R second weighting coefficients to the sensing network element, the second access network device receives the echo signal and determines the R second weighting coefficients based on the received echo signal.

[0194] As one possible implementation, the R second weighting coefficients are obtained by the second access network device performing tensor decomposition on the echo signal based on a preset rank R.

[0195] Of course, the above is only an example illustrating the information interaction between the sensing network element and the first and second access network devices. This application should also include the information interaction process between the sensing network element and other access network devices. For example, other access network devices send their respective R weighting coefficients to the sensing network element, and correspondingly, the sensing network element receives the respective R weighting coefficients from the other access network devices. Specifically, other access network devices may include a third access network device, a fourth access network device, etc.

[0196] In other words, this application only illustrates the example of two access network devices performing collaborative sensing. Furthermore, the number of access network devices performing collaborative sensing can be greater than two, for example, three, four, or five. In this scenario, each access network device can implement the functions of either the first or second access network device described above.

[0197] S904. The sensing network element determines the first estimated number of sensing targets based on R first weight coefficients, and determines the second estimated number of sensing targets based on R second weight coefficients.

[0198] In some embodiments, the first estimated number of perceived targets is the number of first weight coefficients that satisfy a preset threshold among R first weight coefficients. The second estimated number of perceived targets is the number of second weight coefficients that satisfy a preset threshold among R second weight coefficients.

[0199] It should be noted that if the first weight coefficient corresponding to the sub-signal meets the preset threshold, it indicates that the sub-signal is a sub-signal reflecting the target; if the first weight coefficient corresponding to the sub-signal does not meet the preset threshold, it indicates that the sub-signal is a noise signal.

[0200] Optionally, for the first weighting coefficient that meets the preset threshold:

[0201] In one possible implementation, the first weight coefficient that satisfies the preset threshold is the first weight coefficient among R first weight coefficients that is greater than or equal to the preset threshold. That is, the sensing network element sorts the R first weight coefficients and takes the number of first weight coefficients among the sorted R first weight coefficients that are greater than or equal to the preset threshold as the first estimated number of sensing targets.

[0202] For example, with R = 5, and the R first weight coefficients being 10, 9, 8, 7, and 0.5, and a preset threshold of 5, the sensing network element determines the number of first weight coefficients (i.e., 10, 9, 8, and 7) among the R first weight coefficients 10, 9, 8, 7, and 0.5 that are greater than the preset threshold of 5 as the first estimated number of sensing targets.

[0203] In another possible implementation, the first weight coefficient that satisfies the preset threshold is the first X first weight coefficients after R first weight coefficients are sorted in descending order. Among the first X first weight coefficients, the ratio of any two adjacent first weight coefficients is greater than or equal to the preset threshold, and X is a positive integer less than or equal to R. That is, the sensing network element sorts the R first weight coefficients in descending order, determines the ratio of any two adjacent first weight coefficients for the sorted R first weight coefficients, and determines the number X of first weight coefficients whose ratio is greater than or equal to the preset threshold as the first estimated number of sensed targets.

[0204] For example, with R = 5, and R first weight coefficients being 10, 9, 8, 7, and 0.5, and a preset threshold of 0.5, the sensing network element determines that the ratio of 9 to 10 is 0.9, the ratio of 8 to 9 is 0.89, the ratio of 7 to 8 is 0.875, and the ratio of 0.5 to 7 is 0.07; then, it determines that the first weight coefficients with ratios greater than or equal to the preset threshold of 0.5 are 10, 9, 8, and 7; and then uses the number of the first weight coefficients 10, 9, 8, and 7 as the first estimated quantity of the sensing target.

[0205] In another possible implementation, the first weight coefficient that satisfies the preset threshold is the first N first weight coefficients after R first weight coefficients are sorted in descending order; wherein the sum of the first N-1 first weight coefficients is less than the preset threshold, and the sum of the first N first weight coefficients is greater than or equal to the preset threshold; N is a positive integer less than or equal to R. That is, the sensing network element sorts the R first weight coefficients in descending order, and accumulates the sorted R first weight coefficients from largest to smallest until the sum of the first N first weight coefficients is greater than or equal to the preset threshold, and the sum of the first N-1 first weight coefficients is less than the preset threshold. Then, the number N of the first weight coefficients is determined as the first estimated number of sensing targets.

[0206] For example, let's assume R is 5, and the R first weight coefficients can be 10, 9, 8, 7, and 0.5, with a preset threshold of 30. The sensing network element accumulates the values ​​10, 9, 8, 7, and 0.5 sequentially from largest to smallest, and determines that the sum of 10 and 9 is 19, the sum of 10, 9, and 8 is 27, and the sum of 10, 9, 8, and 7 is 34. At this point, it is determined that the sum of 10, 9, 8, and 7 is greater than the preset threshold of 30, and the sum of 10, 9, and 8 is less than the preset threshold of 30. Therefore, the sensing network element determines the number of the first weight coefficients 10, 9, 8, and 7 as 4 as the first estimated number of the sensed target.

[0207] Optionally, for the second weighting coefficient that meets the preset threshold:

[0208] In one possible implementation, the second weight coefficient that satisfies the preset threshold is the second weight coefficient among R second weight coefficients that is greater than or equal to the preset threshold.

[0209] In another possible implementation, the second weighting coefficient that satisfies the preset threshold is the first X second weighting coefficients after R second weighting coefficients are sorted in descending order. Among the first X second weighting coefficients, the ratio of two adjacent second weighting coefficients is greater than or equal to the preset threshold.

[0210] In another possible implementation, the second weight coefficient that satisfies the preset threshold is the first N second weight coefficients after the R second weight coefficients are sorted in descending order; wherein the sum of the first N-1 second weight coefficients is less than the preset threshold, and the sum of the first N second weight coefficients is greater than or equal to the preset threshold.

[0211] In some embodiments, this application also includes an information interaction process between the sensing network element and other access network devices. That is, when the sensing network element also receives R weight coefficients from other access network devices besides the first and second access network devices, the sensing network element can determine the estimated number of sensing targets corresponding to each of the other access network devices based on their respective R weight coefficients.

[0212] S905. The sensing network element determines the estimated quantity M of the sensing target based on the first estimated quantity and the second estimated quantity.

[0213] Where M is a positive integer.

[0214] In one possible implementation, if the first estimated quantity and the second estimated quantity are different, the estimated quantity M of the perceived target is determined to be the maximum value between the first estimated quantity and the second estimated quantity; or, if the first estimated quantity and the second estimated quantity are the same, the estimated quantity M of the perceived target is determined to be either the first estimated quantity or the second estimated quantity.

[0215] In one example, if the sensing network element determines the number of sensing targets to be 4 based on the first weighting coefficient uploaded by the first access network device, and determines the number of sensing targets to be 3 based on the second weighting coefficient uploaded by the second access network device, then the sensing network element determines the estimated number of sensing targets to be 4.

[0216] In another example, if the sensing network element determines that the number of sensing targets is 4 based on the first weighting coefficient uploaded by the first access network device, and determines that the number of sensing targets is 4 based on the second weighting coefficient uploaded by the second access network device, then the sensing network element determines that the estimated number of sensing targets is 4.

[0217] In some embodiments, where the sensing network element also determines the estimated number of sensing targets corresponding to each of the other access network devices, the sensing network element can determine the estimated number M of sensing targets based on the first estimated number of sensing targets, the second estimated number of sensing targets, and the estimated number of sensing targets corresponding to each of the other access network devices.

[0218] S906, the sensing network element sends the first information. Correspondingly, the first access network device receives the first information, and the second access network device receives the first information.

[0219] The first piece of information is used to indicate the estimated quantity M.

[0220] In one possible implementation, as shown in Figure 9, the sensing network element sends first information to the first access network device to indicate the estimated number M of the sensing targets. Correspondingly, the first access network device receives the first information and can obtain the estimated number M of the sensing targets based on the first information. The sensing network element also sends the first information to the second access network device to indicate the estimated number M of the sensing targets.

[0221] Based on the above technical solution, the first access network device sends R first weight coefficients to the sensing network element, and the second access network device also sends R second weight coefficients to the sensing network element. Since the first weight coefficients reflect the importance of the corresponding sub-signals in the echo signal, the sensing network element can determine the importance of the sub-signals reflected by the first weight coefficients in the echo signal and determine a first estimated quantity of the sensing target based on the R first weight coefficients. The sensing network element also determines a second estimated quantity of the sensing target based on the R second weight coefficients. Furthermore, the sensing network element determines an estimated quantity M of the sensing target based on the first and second estimated quantities. The sensing network element sends first information indicating the estimated quantity M, so that the first access network device and other access network devices can obtain the estimated quantity M from the first information.

[0222] Example 2:

[0223] As shown in Figure 10, taking the collaborative sensing of the first access network device, the second access network device, and the third access network device as an example, the specific implementation process of the first access network device determining the first estimated quantity of the sensing target through the third access network device is explained in detail through S1000-S1007.

[0224] S1000: The first access network device sends a first sensing signal. The second access network device sends a second sensing signal. The third access network device sends a third sensing signal.

[0225] Optionally, refer to the embodiment shown in S900, which will not be described again here.

[0226] S1001. The first access network device receives the first echo signal. The second access network device receives the second echo signal. The third access network device receives the third echo signal.

[0227] Optionally, referring to the embodiment shown in S901, which will not be repeated here, the third echo signal can be an echo signal composed of sub-signals of the third sensing signal reflected by at least one sensing target. For example, taking the number of at least two sensing targets as an example, the third echo signal can be an echo signal composed of sub-signals of the third sensing signal reflected by sensing target 1 and sub-signals reflected by sensing target 2.

[0228] S1002, the first access network device sends R first weighting coefficients to the third access network device. Correspondingly, the third access network device receives R first weighting coefficients from the first access network device.

[0229] Optionally, refer to the embodiment shown in S902, which will not be described again here.

[0230] S1003, the second access network device sends R second weighting coefficients to the third access network device. Correspondingly, the third access network device receives R second weighting coefficients from the second access network device.

[0231] Optionally, refer to the embodiment shown in S903, which will not be described again here.

[0232] Of course, the above example only illustrates the information interaction between the third access network device and the first and second access network devices. This application should also include the information interaction process between the third access network device and other access network devices. For example, other access network devices send their respective R weighting coefficients to the third access network device, and correspondingly, the sensing network element receives the respective R weighting coefficients from the other access network devices. Specifically, other access network devices may include a fourth access network device, a fifth access network device, etc.

[0233] In other words, this application only illustrates the example of three access network devices performing collaborative sensing. Furthermore, the number of access network devices performing collaborative sensing can be greater than three, for example, four or five. In this scenario, each access network device can implement the functions of the first, second, or third access network device described above.

[0234] S1004. The third access network device performs tensor decomposition on the echo signal based on a preset rank R, and obtains R third weight coefficients.

[0235] Specifically, the implementation process of the third access network device obtaining R third weighting coefficients is as shown in the embodiment shown in S802, and will not be repeated here.

[0236] S1005. The third access network device determines the first estimated number of sensing targets based on R first weight coefficients, the second estimated number of sensing targets based on R second weight coefficients, and the third estimated number of sensing targets based on R third weight coefficients.

[0237] S1006. The third access network device determines the estimated number M of the sensed targets based on the first estimated number, the second estimated number, and the third estimated number.

[0238] Optionally, if the first estimated quantity, the second estimated quantity, and the third estimated quantity are different, the estimated quantity M of the perceived target is determined to be the maximum value among the first estimated quantity, the second estimated quantity, and the third estimated quantity; or, if the first estimated quantity, the second estimated quantity, and the third estimated quantity are the same, the estimated quantity M of the perceived target is determined to be the first estimated quantity, the second estimated quantity, or the third estimated quantity.

[0239] S1007, the third access network device sends the first information. Correspondingly, the first access network device receives the first information, and the second access network device receives the first information.

[0240] It should be noted that the third access network device sends first information to each access network device so that each access network device can determine the estimated number M of the sensing targets based on the first information.

[0241] Based on the above technical solution, the third access network device can replace the sensing network element, receiving R first weight coefficients from the first access network device and R second weight coefficients from the second access network device, and determining R third weight coefficients itself. Furthermore, since the first weight coefficients reflect the importance of the corresponding sub-signals in the echo signal, the third access network device can determine the importance of the sub-signals reflected by the first weight coefficients in the echo signal, and determine the first estimated quantity corresponding to the first access network device, and the Nth estimated quantity corresponding to each of the other access network devices. Then, based on the Nth estimated quantity corresponding to each access network device, the estimated quantity M of the sensing target can be determined.

[0242] Example 3

[0243] As shown in Figure 11, taking the first access network device as the central access network device and the second access network device performing collaborative sensing as an example, the specific implementation process of the first access network device determining the first estimated number of sensing targets through S1100-S1106 will be explained in detail.

[0244] S1100, The first access network device sends a first sensing signal. The second access network device sends a second sensing signal.

[0245] Optionally, refer to the embodiment shown in S900, which will not be described again here.

[0246] S1101. The first access network device receives the first echo signal. The second access network device receives the second echo signal.

[0247] Optionally, refer to the embodiment shown in S901, which will not be described again here.

[0248] S1102. The first access network device performs tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients.

[0249] Specifically, the process of obtaining R first weighting coefficients for the first access network device is described in the embodiment shown in S802, and will not be repeated here.

[0250] S1103. The first access network device determines the first estimated number of sensing targets based on R first weight coefficients.

[0251] Specifically, the implementation process of the first access network device determining the first estimated number of sensing targets in S1103 above refers to the implementation process of the sensing network element determining the first estimated number of sensing targets based on R first weight coefficients in S903, and will not be repeated here.

[0252] S1104. The second access network device sends R second weighting coefficients to the first access network device. Correspondingly, the first access network device receives R second weighting coefficients from the second access network device.

[0253] Optionally, the first access network device may also receive weighting coefficients from other access network devices besides the first and second access network devices. For example, R third weighting coefficients from the third access network device, R fourth weighting coefficients from the fourth access network device, ..., and R Nth weighting coefficients from the Nth access network device, where N is a positive integer.

[0254] S1105. The first access network device determines the second estimated number of sensing targets based on R second weighting coefficients.

[0255] Specifically, the process by which the first access network device determines the second estimated number of sensing targets in S1105 above refers to the embodiment shown in S903, and will not be repeated here.

[0256] Optionally, if the first access network device also receives R Nth weight coefficients from the Nth access network device, the first access network device may also determine the Nth estimated number of the sensed target based on the R Nth weight coefficients.

[0257] S1106. The first access network device determines the estimated number M of the sensed targets based on the first estimated number and the second estimated number.

[0258] Optionally, the estimated number M of the perceived target is the maximum of the first estimated number and the second estimated number; or, if the first estimated number and the second estimated number are the same, the estimated number M of the perceived target is either the first estimated number or the second estimated number.

[0259] Optionally, after S1106, the first access network device may also send first information to the second access network device to indicate the estimated number M of the sensed targets.

[0260] Based on the above technical solution, the first access network device has the function of actively determining the estimated number M of sensing targets. Since the first weight coefficient can reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, the first access network device can know the importance of the sub-signal reflected by the first weight coefficient in the echo signal, and thus determine the first estimated number corresponding to the first access network device. Furthermore, the first access network device also determines the second estimated number corresponding to the second access network device based on R second weight coefficients of the second access network device; and then, based on the first and second estimated numbers, determines the estimated number M of sensing targets.

[0261] As a possible embodiment of this application, referring to FIG8 and FIG12, the process of determining the perception result of the perception target can be implemented by the following S1201-S1202.

[0262] S1201, the second access network device sends the second sensing information, and correspondingly, the sensing network element receives the second sensing information from the second access network device.

[0263] The second sensing information includes M sets of second sensing parameters; M is a positive integer.

[0264] Optionally, the sensing network element can also receive sensing information from other access network devices besides the first and second access network devices. For example, the third sensing information from the third access network device, the fourth sensing information from the fourth access network device, ..., and the Nth sensing information from the Nth access network device, where N is a positive integer.

[0265] S1202, The sensing network element performs fusion processing based on the first sensing information and the second sensing information to obtain the sensing results of Y sensing targets.

[0266] Where Y is a positive integer less than or equal to M.

[0267] In one possible implementation, the implementation process of S1202 includes: performing similarity matching processing on the first and second perception information to obtain Y pairs of perception parameters; performing fusion processing (e.g., incoherent fusion) on the yth pair of perception parameters to obtain the perception result of the yth perception target, y = 1, ..., Y.

[0268] Each perception parameter pair includes a first perception parameter pair in the first perception information and a second perception parameter pair in the second perception information. The similarity between the first perception parameter pair and the second perception parameter pair in the same perception parameter pair is greater than or equal to a similarity threshold.

[0269] It should be noted that if the similarity between one set of perceptual parameters and another set of perceptual parameters is greater than or equal to the similarity threshold, then they are considered to be perceptual parameter sets for the same perceptual target. Otherwise, if the similarity between one set of perceptual parameters and another set of perceptual parameters is less than the similarity threshold, then these multiple sets of perceptual parameters are determined to be perceptual parameter sets for different perceptual targets.

[0270] Furthermore, taking the first perception information as an example, if the similarity between a perception parameter group in the first perception information and all perception parameter groups in the second perception information is less than the similarity threshold, it indicates that a perception parameter group in the first perception information is erroneous information and is not the perception parameter group of the perception target.

[0271] In one example, the first sensing information includes first sensing parameter group 1, first sensing parameter group 2, and first sensing parameter group 3, and the second sensing information includes second sensing parameter group 1, second sensing parameter group 2, and second sensing parameter group 3. The sensing network element performs similarity matching processing on the first and second sensing information, determining that the similarity between first sensing parameter group 1 and second sensing parameter group 2 is greater than a similarity threshold, the similarity between first sensing parameter group 2 and second sensing parameter group 3 is greater than a similarity threshold, and the similarity between first sensing parameter group 3 and second sensing parameter group 1 is less than a similarity threshold, thus obtaining two pairs of sensing parameter groups. One pair of sensing parameter groups consists of first sensing parameter group 1 and second sensing parameter group 2 for sensing target 1, and the other pair consists of first sensing parameter group 2 and second sensing parameter group 3 for sensing target 2.

[0272] Then, the first perception parameter group 1 and the second perception parameter group 2 of the perceived target 1 are fused to obtain the perception result of the perceived target 1; the first perception parameter group 2 and the second perception parameter group 3 of the perceived target 2 are fused to obtain the perception result of the perceived target 2.

[0273] In another possible implementation, if the sensing network element also receives the Nth sensing information from the Nth access network device, the sensing network element can also perform fusion processing based on the first sensing information, the second sensing information, and the Nth sensing information to obtain the sensing results of Y sensing targets.

[0274] In one example, similarity matching is performed on the first, second, and Nth perceptual information to obtain Y pairs of perceptual parameter groups. Each pair of perceptual parameter groups includes a first perceptual parameter group from the first perceptual information, a second perceptual parameter group from the second perceptual information, and an Nth perceptual parameter group from the Nth perceptual information. The similarity between the first, second, and Nth perceptual parameter groups in the same pair is greater than or equal to a similarity threshold.

[0275] Based on the above technical solution, since each access network device obtains corresponding sensing information based on echo signals, the sensing network element performs fusion processing on the first and second sensing information, which can eliminate inaccurate sensing parameter groups in the sensing information, and obtain the sensing results of Y sensing targets while ensuring the accuracy of the sensing results.

[0276] As one possible embodiment of this application, taking the first access network device and the second access network device transmitting and receiving signals to each other to perform collaborative sensing of sensing targets in the same area, and determining the estimated number M of sensing targets through sensing network elements as an example, as shown in Figure 13, the sensing method can be implemented through the following S1301-S1312.

[0277] S1301. The first access network device performs tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients.

[0278] The implementation of S1301 can be referred to the relevant descriptions in steps S902 and S802 above, and will not be repeated here.

[0279] S1302, the second access network device performs tensor decomposition on the echo signal based on a preset rank R to obtain R second weight coefficients.

[0280] The implementation of S1302 can be referred to the relevant description in step S903 above, and will not be repeated here.

[0281] It should be noted that this application does not restrict the execution order of S1301 and S1302. For example, S1301 can be executed first and then S1302; S1302 can be executed first and then S1301; or S1301 and S1302 can be executed simultaneously.

[0282] S1303, The first access network device uploads R first weight coefficients to the sensing network element.

[0283] The implementation of S1303 can be referred to the relevant description in step S902 above, and will not be repeated here.

[0284] S1304. The second access network device uploads R second weight coefficients to the sensing network element.

[0285] The implementation of S1304 can be referred to the relevant description in step S903 above, and will not be repeated here.

[0286] It should be noted that this application does not restrict the execution order of S1303 and S1304. For example, S1303 can be executed first and then S1304; S1304 can be executed first and then S1304; or S1303 and S1304 can be executed simultaneously.

[0287] S1305. The sensing network element determines the first estimated quantity based on R first weight coefficients and the second estimated quantity based on R second weight coefficients.

[0288] The implementation of S1305 can be referred to the relevant description in step S904 above, and will not be repeated here.

[0289] S1306, The sensing network element determines the estimated quantity M of the sensing target based on the first estimated quantity and the second estimated quantity.

[0290] The implementation of S1306 can be referred to the relevant description in step S905 above, and will not be repeated here.

[0291] S1307, the sensing network element sends first information to the first access network device and the second access network device respectively to indicate the estimated quantity M.

[0292] The implementation of S1307 can be referred to the relevant description in step S906 above, and will not be repeated here.

[0293] S1308. The first access network device adjusts the preset rank R according to the estimated quantity M, and re-performs tensor decomposition on the echo signal to obtain the first sensing information.

[0294] The implementation of S1308 can be referred to the relevant description in step S803 above, and will not be repeated here.

[0295] S1309. The second access network device adjusts the preset rank R according to the estimated quantity M, and re-performs tensor decomposition on the echo signal to obtain the second sensing information.

[0296] The implementation of S1309 can be referred to the relevant description in step S803 above, and will not be repeated here.

[0297] It should be noted that this application does not restrict the execution order of S1308 and S1309. For example, S1308 can be executed first and then S1309 can be executed; S1309 can be executed first and then S1308 can be executed; or S1308 and S1309 can be executed simultaneously.

[0298] S1310, The first access network device uploads the first sensing information to the sensing network element.

[0299] The implementation of S1310 can be referred to the relevant description in step S804 above, and will not be repeated here.

[0300] S1311, the second access network device also uploads the second sensing information to the sensing network element.

[0301] The implementation of S1311 can be referred to the relevant description in step S1201 above, and will not be repeated here.

[0302] It should be noted that this application does not restrict the execution order of S1310 and S1311. For example, S1310 can be executed first and then S1311 can be executed; S1311 can be executed first and then S1310 can be executed; or S1310 and S1311 can be executed simultaneously.

[0303] S1312. The sensing network element combines the first sensing information and the second sensing information to obtain the sensing result.

[0304] The implementation of S1312 can be referred to the relevant description in step S1202 above, and will not be repeated here.

[0305] In the above technical solution, each access network device performs tensor decomposition on the echo signal to obtain its own weight coefficient. The weight coefficients of each access network device are then processed by the sensing network element to determine the estimated number M of the sensing target. Subsequently, each access network device can adjust its preset rank R based on the estimated number M and re-perform tensor decomposition on the echo signal to obtain sensing information. Finally, the sensing network element combines the sensing information obtained from each access network device to determine the sensing result.

[0306] As another possible embodiment of this application, taking the first access network device and the second access network device transmitting and receiving signals to each other to perform collaborative sensing of sensing targets in the same area, and without determining the estimated number M of sensing targets through sensing network elements, as shown in Figure 14, the sensing method includes the following S1401-S1411.

[0307] S1401, the second access network device performs tensor decomposition on the echo signal based on a preset rank R, and obtains R second weight coefficients.

[0308] The implementation of S1401 can be referred to the relevant description in step S903 above, and will not be repeated here.

[0309] S1402. The first access network device performs tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients.

[0310] The implementation of S1402 can be referred to the relevant descriptions in steps S1102 and S802 above, and will not be repeated here.

[0311] It should be noted that this application does not restrict the execution order of S1401 and S1402. For example, S1401 can be executed first and then S1402; S1402 can be executed first and then S1401; or S1401 and S1402 can be executed simultaneously.

[0312] S1403, The second access network device uploads R second weighting coefficients to the first access network device.

[0313] The implementation of S1403 can be referred to the relevant description in step S1104 above, and will not be repeated here.

[0314] S1404. The first access network device determines the first estimated quantity based on R first weighting coefficients and the second estimated quantity based on R second weighting coefficients.

[0315] The implementation of S1404 can be referred to the relevant descriptions in steps S1103 and S1105 above, and will not be repeated here.

[0316] S1405, The first access network device determines the estimated number M of the sensed targets based on the first estimated number and the second estimated number.

[0317] The implementation of S1405 can be referred to the relevant description in step S1106 above, and will not be repeated here.

[0318] S1406. The first access network device sends first information to the second access network device to indicate the estimated quantity M.

[0319] The implementation of S1406 can be referred to the relevant description in step S1106 above, and will not be repeated here.

[0320] S1407. The second access network device adjusts the preset rank R according to the estimated quantity M, and re-performs tensor decomposition on the echo signal to obtain the second sensing information.

[0321] The implementation of S1407 can be referred to the relevant description in step S803 above, and will not be repeated here.

[0322] S1408. The first access network device adjusts the preset rank R according to the estimated quantity M, and re-performs tensor decomposition on the echo signal to obtain the first sensing information.

[0323] The implementation of S1408 can be referred to the relevant description in step S803 above, and will not be repeated here.

[0324] It should be noted that this application does not restrict the execution order of S1407 and S1408. For example, S1407 can be executed first and then S1408; S1408 can be executed first and then S1407; or S1407 and S1408 can be executed simultaneously.

[0325] S1409, The second access network device uploads the second sensing information to the sensing network element.

[0326] The implementation of S1409 can be referred to the relevant description in step S1201 above, and will not be repeated here.

[0327] S1410, the first access network device also uploads the first sensing information to the sensing network element.

[0328] The implementation of S1410 can be referred to the relevant description in step S804 above, and will not be repeated here.

[0329] It should be noted that this application does not restrict the execution order of S1409 and S1410. For example, S1409 can be executed first and then S1410; S1410 can be executed first and then S1409; or S1409 and S1410 can be executed simultaneously.

[0330] S1411, the sensing network element combines the first sensing information and the second sensing information to obtain the sensing result.

[0331] The implementation of S1411 can be referred to the relevant description in step S1202 above, and will not be repeated here.

[0332] In the above technical solution, each access network device performs tensor decomposition on the echo signal to obtain its own weight coefficient. The central access network device (the first access network device) then processes these weight coefficients to determine the estimated number M of the sensing target. Furthermore, each access network device can adjust its preset rank R based on the estimated number M and re-perform tensor decomposition on the echo signal to obtain sensing information. Finally, the sensing network element combines the sensing information obtained from each access network device to determine the sensing result.

[0333] The method provided in this application has been described above. In addition, this application also provides a communication device for implementing the functions described in the above method embodiments.

[0334] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0335] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0336] Figure 15 shows a schematic diagram of a communication device 150. The communication device 150 includes a processing module 1501 and a transceiver module 1502. This communication device 150 can be used to implement the functions of the aforementioned first access network device or sensing network element.

[0337] In some embodiments, the communication device 150 may further include a storage module (not shown in FIG15) for storing program instructions and data.

[0338] In some embodiments, the transceiver module 1502, also referred to as a transceiver unit, is used to implement sending and / or receiving functions. The transceiver module 1502 may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0339] In some embodiments, the transceiver module 1502 may include a receiving module and a sending module, respectively configured to perform the receiving and sending steps performed by the first access network device or sensing network element in the above method embodiments, and / or other processes to support the technology described herein; the processing module 1501 may be configured to perform the processing steps performed by the first access network device or sensing network element in the above method embodiments, and / or other processes to support the technology described herein.

[0340] When the communication device 150 is used to implement the functions of the first access network device,

[0341] In one possible implementation, the transceiver module 1502 is configured to: receive an echo signal; the processing module 1501 is configured to obtain an estimated number M of the sensing targets based on the echo signal; the processing module 1501 is further configured to perform tensor decomposition on the echo signal based on the estimated number M to obtain first sensing information, the first sensing information including M first sensing parameter groups, where M is a positive integer; the transceiver module 1502 is further configured to send the first sensing information to the sensing network element, the first sensing information being used to determine the sensing result.

[0342] In one possible implementation, the processing module 1501 is specifically configured to: perform tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients; the R first weight coefficients correspond to R sub-signals of the echo signal; the first weight coefficients are used to reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, and R is a positive integer; send the R first weight coefficients to the sensing network element or the third access network device through the transceiver module 1502, the R first weight coefficients being used to determine the estimated quantity M; and receive first information from the sensing network element or the third access network device through the transceiver module 1502, the first information being used to indicate the estimated quantity M.

[0343] In one possible implementation, the processing module 1501 is specifically used for: performing tensor decomposition on the echo signal based on a preset rank R to obtain R first weight coefficients; determining a first estimated number of sensing targets based on the R first weight coefficients; where R is a positive integer; receiving R second weight coefficients from the second access network device through the transceiver module 1502; determining a second estimated number of sensing targets based on the R second weight coefficients; and determining an estimated number M of sensing targets based on the first and second estimated numbers.

[0344] Optionally, as shown in Figure 16, the communication device 150 may also include a CU module and an RU module, the transceiver module 1502 may be an antenna, and the processing module 1501 may be a DU module. In one possible implementation: the transceiver module 1502 (e.g., antenna) in the first access network device is communicatively connected to the transceiver module 1502 in the terminal device, and is used to receive communication signals from the transceiver module 1502 in the terminal device; the transceiver module 1502 (e.g., antenna) is also used to receive echo signals and transmit the echo signals to the DU module through the RU module; the DU module is used to perform tensor decomposition on the echo signals based on a preset rank R to obtain R first weight coefficients; the R first weight coefficients are uploaded to the transceiver module 1502 in the sensing network element through the CU module on the backhaul link, or the R first weight coefficients are sent to the RU module of another access network device through the RU module; the CU module is also used to receive first information (estimated number M of sensing targets), and the DU module is also used to perform a second tensor decomposition on the echo signals based on the first information to obtain sensing information; the CU module is also used to upload the sensing information to the transceiver module 1502 in the sensing network element through the backhaul link.

[0345] When the communication device 150 is used to implement the functions of a sensing network element:

[0346] In one possible implementation: the transceiver module 1502 is configured to receive R first weight coefficients from a first access network device; the R first weight coefficients correspond to R sub-signals of the echo signal; the first weight coefficients are used to reflect the importance of the sub-signals corresponding to the first weight coefficients in the echo signal, and R is a positive integer; the transceiver module 1502 is further configured to receive R second weight coefficients from a second access network device; the R second weight coefficients correspond to R sub-signals of the echo signal; the second weight coefficients are used to reflect the importance of the sub-signals corresponding to the second weight coefficients in the echo signal; the processing module 1501 is configured to determine a first estimated number of sensing targets based on the R first weight coefficients, and a second estimated number of sensing targets based on the R second weight coefficients; the processing module 1501 is further configured to determine an estimated number M of sensing targets based on the first estimated number and the second estimated number, where M is a positive integer; the transceiver module 1502 is further configured to send first information, which indicates the estimated number M.

[0347] In one possible implementation, the transceiver module 1502 is further configured to receive first sensing information from the first access network device, the first sensing information including M first sensing parameter groups; the transceiver module 1502 is further configured to receive second sensing information from the second access network device, the second sensing information including M second sensing parameter groups; M is a positive integer; the processing module 1501 is further configured to perform fusion processing based on the first sensing information and the second sensing information to obtain the sensing results of Y sensing targets, Y being a positive integer less than or equal to M.

[0348] In one possible implementation, the processing module 1501 is specifically used to perform similarity matching processing on the first perception information and the second perception information to obtain Y perception parameter pairs; each perception parameter pair includes a first perception parameter pair in the first perception information and a second perception parameter pair in the second perception information, and the similarity between the first perception parameter pair and the second perception parameter pair in the same perception parameter pair is greater than or equal to a similarity threshold; and the y-th perception parameter pair is fused to obtain the perception result of the y-th perception target, y = 1, ..., Y.

[0349] Optionally, the communication device is also used to implement the functions of a terminal. In one possible implementation, the transceiver module 1502 is used to transmit uplink signals. The uplink signals are reflected by the sensing target and then reach the first access network device.

[0350] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0351] In this application, the communication device 150 can be presented in an integrated manner by dividing it into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0352] In some embodiments, when the communication device 150 in FIG15 is a chip or chip system, the function / implementation process of the transceiver module 1502 can be implemented through the input / output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 1501 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0353] Since the communication device 150 provided in this embodiment can execute the above method, the technical effects it can achieve can be referred to the above method embodiment, and will not be repeated here.

[0354] As a possible product form, the access network device or sensing network element described in the embodiments of this application can be implemented using the following: one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0355] As another possible product form, the access network device or sensing network element described in this application embodiment can be implemented using a general bus architecture. For ease of explanation, refer to Figure 17, which is a schematic diagram of the communication device provided in this application embodiment. The communication device includes a processor 1701 and a transceiver 1702. This communication device can be an access network device, or a chip or chip system therein; alternatively, it can be a sensing network element, or a chip or module therein. Figure 17 only shows the main components of the communication device. In addition to the processor 1701 and transceiver 1702, the communication device may further include a memory 1703 and input / output devices (not shown in the figure).

[0356] Optionally, the processor 1701 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs, thereby implementing the methods provided in the above-described method embodiments. The memory 1703 is mainly used to store software programs and data. The transceiver 1702 may include radio frequency (RF) circuitry and an antenna. The RF circuitry is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0357] Optionally, the processor 1701, transceiver 1702, and memory 1703 can be connected via a communication bus.

[0358] When the communication device is powered on, the processor 1701 can read the software program in the memory 1703, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1701 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1701. The processor 1701 converts the baseband signal into data and processes the data.

[0359] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0360] In some embodiments, those skilled in the art will recognize that the above-described communication device 150 can take the form of the communication device shown in FIG17 in terms of hardware implementation.

[0361] As an example, the function / implementation of the processing module 1501 in Figure 15 can be achieved by the processor 1701 in the communication device shown in Figure 17 calling computer execution instructions stored in the memory 1703. The function / implementation of the transceiver module 1502 in Figure 15 can be achieved by the transceiver 1702 in the communication device shown in Figure 17.

[0362] As another possible product form, the access network device or sensing network element in this application may adopt the composition structure shown in Figure 18, or include the components shown in Figure 18. Figure 18 is a schematic diagram of the composition of another communication device provided in this application. The communication device may be an access network device or a chip or system-on-a-chip in the access network device; or it may be a sensing network element or a module, chip or system-on-a-chip in the sensing network element.

[0363] As shown in Figure 18, the communication device includes at least one processor 1801 and at least one communication interface (Figure 18 is merely an example illustrating the inclusion of a communication interface 1804 and a processor 1801). Optionally, the communication device may also include a communication bus 1802 and a memory 1803.

[0364] Processor 1801 can be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a PLD, or any combination thereof. Processor 1801 can also be other devices with processing functions, such as circuits, devices, or software modules, without limitation.

[0365] The communication bus 1802 is used to connect different components in the communication device, enabling communication between them. The communication bus 1802 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 18, but this does not indicate that there is only one bus or one type of bus.

[0366] Communication interface 1804 is used for communicating with other devices or communication networks. For example, communication interface 1804 can be a module, circuit, transceiver, or any device capable of communication. Optionally, communication interface 1804 can also be an input / output interface located within processor 1801, used to implement signal input and signal output for the processor.

[0367] The memory 1803 may be a device with storage function, used to store instructions and / or data. The instructions may be computer programs.

[0368] For example, the memory 1803 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and / or instructions; it may also be a random access memory (RAM) or other type of dynamic storage device capable of storing information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0369] It should be noted that the memory 1803 can exist independently of the processor 1801, or it can be integrated with the processor 1801. The memory 1803 can be located inside or outside the communication device, without limitation. The processor 1801 can be used to execute the instructions stored in the memory 1803 to implement the methods provided in the following embodiments of this application.

[0370] As an optional implementation, the communication device may also include an output device 1805 and an input device 1806. The output device 1805 communicates with the processor 1801 and can display information in various ways. For example, the output device 1805 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1806 communicates with the processor 1801 and can receive user input in various ways. For example, the input device 1806 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0371] In some embodiments, those skilled in the art will recognize that the communication device 150 shown in FIG15 can take the form of the communication device shown in FIG18 in terms of hardware implementation.

[0372] As an example, the function / implementation of the processing module 1501 in Figure 15 can be achieved by the processor 1801 in the communication device shown in Figure 18 calling computer execution instructions stored in the memory 1803. The function / implementation of the transceiver module 1502 in Figure 15 can be achieved by the communication interface 1804 in the communication device shown in Figure 18.

[0373] It should be noted that the structure shown in Figure 18 does not constitute a specific limitation on the access network device or sensing network element. For example, in other embodiments of this application, the access network device or sensing network element may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0374] In some embodiments, this application also provides a communication device, which includes a processor for implementing the methods in any of the above method embodiments.

[0375] As one possible implementation, the communication device also includes a memory. This memory stores necessary computer programs and data. The computer program may include instructions, which a processor can invoke to instruct the communication device to execute the methods described in any of the above method embodiments. Alternatively, the memory may not be present in the communication device.

[0376] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, used to receive computer execution instructions (which are stored in memory and may be read directly from memory or may be transmitted through other devices) and transmit them to the processor.

[0377] As another possible implementation, the communication device also includes a communication interface for communicating with modules outside the communication device.

[0378] It is understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete devices. This application does not specifically limit this.

[0379] This application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a computer, implements the functions of any of the above-described method embodiments.

[0380] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0381] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0382] It is understood that the systems, apparatuses, and methods described in this application can also be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0383] The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. The components shown as units may or may not be physical units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0384] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0385] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program 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 accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)). In this embodiment, the computer may include the aforementioned apparatus.

[0386] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0387] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of the claims and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A perception method, comprising: Applied to a first access network device, the method includes: Receive echo signal; Based on the echo signal, the estimated number M of the sensed targets is obtained; Based on the estimated quantity M, the echo signal is decomposed into tensors to obtain first sensing information, which includes M sets of first sensing parameters, where M is a positive integer. The first sensing information is sent to the sensing network element, and the first sensing information is used to determine the sensing result.

2. The method of claim 1, wherein, The step of obtaining an estimated number M of sensed targets based on the echo signal includes: Based on a preset rank R, the echo signal is decomposed into R first weight coefficients; the R first weight coefficients correspond to R sub-signals of the echo signal; the first weight coefficients are used to reflect the importance of the sub-signal corresponding to the first weight coefficient in the echo signal, and R is a positive integer; The R first weighting coefficients are sent to the sensing network element or the third access network device, and the R first weighting coefficients are used to determine the estimated quantity M; Receive first information from the sensing network element or the third access network device, the first information being used to indicate the estimated quantity M.

3. The method of claim 1, wherein, The step of obtaining an estimated number M of sensed targets based on the echo signal includes: Based on a preset rank R, the echo signal is decomposed into tensors to obtain R first weight coefficients; based on the R first weight coefficients, the first estimated number of sensing targets is determined; R is a positive integer. Receive R second weighting coefficients from the second access network device, and determine a second estimated number of sensing targets based on the R second weighting coefficients; The estimated number M of the perceived target is determined based on the first estimated number and the second estimated number.

4. The method according to claim 3, characterized in that, The estimated number M of the perceived target is the maximum value between the first estimated number and the second estimated number; Alternatively, if the first estimated number and the second estimated number are the same, the estimated number M of the perceived target is either the first estimated number or the second estimated number.

5. The method according to claim 3, characterized in that, The first estimated number of the perceived target is the number of first weight coefficients that satisfy a preset threshold among the R first weight coefficients.

6. The method according to claim 5, characterized in that, The first weighting coefficient that satisfies the preset threshold is one of the R first weighting coefficients that is greater than or equal to the preset threshold; or... The first weighting coefficient that satisfies the preset threshold is the first X first weighting coefficients after the R first weighting coefficients are sorted in descending order, wherein the ratio of any two adjacent first weighting coefficients in the first X first weighting coefficients is greater than or equal to the preset threshold, and X is a positive integer less than or equal to R; or, The first weight coefficient that satisfies the preset threshold is the first N first weight coefficients after the R first weight coefficients are sorted in descending order; wherein, the sum of the first N-1 first weight coefficients is less than the preset threshold, and the sum of the first N first weight coefficients is greater than or equal to the preset threshold; N is a positive integer less than or equal to R.

7. The method according to any one of claims 1-6, characterized in that, The sensing parameter set includes at least one of the following: distance parameter, angle parameter, or velocity parameter of the sensing target.

8. A perception method comprising: Applied to sensing network elements, the method includes: Receive R first weighting coefficients from a first access network device; the R first weighting coefficients correspond to R sub-signals of the echo signal; the first weighting coefficients are used to reflect the importance of the sub-signal corresponding to the first weighting coefficient in the echo signal, and R is a positive integer; Receive R second weighting coefficients from the second access network device; the R second weighting coefficients correspond to R sub-signals of the echo signal; the second weighting coefficients are used to reflect the importance of the sub-signals corresponding to the second weighting coefficients in the echo signal; A first estimated number of sensing targets is determined based on the R first weight coefficients, and a second estimated number of sensing targets is determined based on the R second weight coefficients; Based on the first estimated quantity and the second estimated quantity, determine the estimated quantity M of the perceived target, where M is a positive integer; Send a first message, which indicates the estimated quantity M.

9. The method according to claim 8, characterized in that, The estimated number M of the perceived target is the maximum value between the first estimated number and the second estimated number; Alternatively, if the first estimated number and the second estimated number are the same, the estimated number M of the perceived target is either the first estimated number or the second estimated number.

10. The method according to claim 8, characterized in that, The first estimated number of the perceived target is the number of first weight coefficients that satisfy a preset threshold among the R first weight coefficients.

11. The method according to claim 10, characterized in that, The first weighting coefficient that satisfies the preset threshold is one of the R first weighting coefficients that is greater than or equal to the preset threshold; or... The first weighting coefficient that satisfies the preset threshold is the first X first weighting coefficients after the R first weighting coefficients are sorted in descending order, wherein the ratio of any two adjacent first weighting coefficients in the first X first weighting coefficients is greater than or equal to the preset threshold, and X is a positive integer less than or equal to R; or, The first weight coefficient that satisfies the preset threshold is the first N first weight coefficients after the R first weight coefficients are sorted in descending order; wherein, the sum of the first N-1 first weight coefficients is less than the preset threshold, and the sum of the first N first weight coefficients is greater than or equal to the preset threshold; N is a positive integer less than or equal to R.

12. The method of claim 8, wherein, The method further includes: Receive first sensing information from the first access network device, the first sensing information including M first sensing parameter groups; Receive second sensing information from the second access network device, the second sensing information including M groups of second sensing parameters; M is a positive integer; Based on the fusion processing of the first perception information and the second perception information, the perception results of Y perception targets are obtained, where Y is a positive integer less than or equal to M.

13. The method of claim 12, wherein, The step of fusing the first and second perception information to obtain perception results for Y perception targets includes: The first perception information and the second perception information are subjected to similarity matching processing to obtain Y perception parameter pairings; each perception parameter pairing includes a first perception parameter pair in the first perception information and a second perception parameter pair in the second perception information, and the similarity between the first perception parameter pair and the second perception parameter pair in the same perception parameter pairing is greater than or equal to the similarity threshold. The fusion process is performed on the y-th perception parameter group to obtain the perception result of the y-th perception target, y = 1, ..., Y.

14. The method according to any one of claims 8-13, characterized in that, The sensing parameter set includes at least one of the following: distance parameter, angle parameter, or velocity parameter of the sensing target.

15. A communications device, characterized by include: A functional unit for performing the method as described in any one of claims 1-7 or 8-14; wherein the action performed by the functional unit is implemented by hardware or by hardware executing corresponding software.

16. A communications device, characterized by The communication device includes a processor; the processor is configured to run computer programs or instructions, or to use logic circuitry to cause the communication device to implement the method as described in any one of claims 1-7 or 8-14.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions or programs that, when executed on a computer, cause the communication device to perform the method as described in any one of claims 1-7 or 8-14.

18. A computer program product, characterised in that, The computer program product includes computer instructions that, when executed on a computer, cause the computer to perform the method as claimed in any one of claims 1-7 or 8-14.

Images