A method and system for calculating pedestrian flow trajectory based on millimeter wave base station

Abstract

The present invention relates to a method and system for calculating the trajectory of human flow based on a millimeter wave base station, and belongs to the field of communication technology. The method comprises: obtaining a target signal received by a millimeter wave base station; constructing a signal covariance matrix based on the target signal; inputting the signal covariance matrix into a pre-trained target convolutional neural network model, and outputting a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction; determining the horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle; calculating the trajectory of human flow corresponding to the mobile terminal based on the horizontal distance and the orientation angle; wherein the orientation angle is the direction angle of the receiving antenna corresponding to the mobile terminal with the millimeter wave base station as the center. This method has high measurement accuracy, is less affected by the environment, and does not capture personal images, and has wide applicability.

Description

Technical Field

[0001] The present invention belongs to the field of communication technology, and specifically provides a method and system for calculating pedestrian flow trajectories based on millimeter wave base stations. Background Art

[0002] Whether in public safety, urban planning, or commercial retail, detecting signs of crowd movement is of great significance.

[0003] In terms of public safety, monitoring crowd movement trajectories can help prevent and manage emergencies, such as terrorist attacks, fires and stampedes, and infectious disease prevention and control, and take timely response measures to ensure the safety of the crowd. In urban planning and management, crowd trajectory data can provide a scientific basis for traffic flow management, public facility layout, commercial area planning, etc., to improve urban operation efficiency and the quality of life of residents. In the commercial and retail sectors, analyzing crowd trajectories can help businesses understand consumer behavior and preferences, optimize store location and marketing strategies, and thus improve sales performance and customer satisfaction.

[0004] In the field of traditional crowd monitoring, common methods include optical video analysis and infrared sensors. Although these two technologies are widely favored due to their maturity and popularity, they still have limitations that cannot be ignored in practical applications. As one of the mainstream means of monitoring, the performance of optical video analysis technology is often affected by lighting conditions. At night or in low-light environments, its monitoring effect is greatly reduced, and it is difficult to ensure the accuracy of the data. In addition, once there are line-of-sight obstructions such as trees, buildings or other obstacles, the video analysis system cannot capture the complete picture, thereby reducing the reliability of monitoring. Although infrared sensors can overcome the limitations of lighting conditions to a certain extent, their performance is easily affected by ambient temperature fluctuations. For example, in an environment with rapid temperature changes, infrared sensors may have false alarms or missed alarms, thereby reducing the accuracy of monitoring.

[0005] In addition, both of the above technologies usually involve the capture of personal images, which may cause public concerns about privacy protection in some cases. As society pays more attention to personal privacy protection, how to balance the needs of pedestrian trajectory monitoring and privacy protection has become an urgent problem to be solved. Summary of the invention

[0006] In order to solve the above-mentioned problems in the prior art, the present invention provides a method and system for calculating pedestrian trajectory based on millimeter wave base stations.

[0007] In a first aspect, an embodiment of the present application provides a method for calculating a flow trajectory of a person based on a millimeter wave base station, which is applied to a millimeter wave base station, wherein the millimeter wave base station has a plurality of antennas arranged in an array, and the plurality of antennas are evenly distributed around the body of the millimeter wave base station, and the method includes:

[0008] Acquire a target signal received by a millimeter wave base station; wherein the target signal is a return signal of a mobile terminal within the communication range of the millimeter wave base station;

[0009] Based on the target signal, construct a signal covariance matrix;

[0010] Input the signal covariance matrix into a pre-trained target convolutional neural network model, and output a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction;

[0011] Determining a horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle;

[0012] Based on the horizontal distance and the direction angle, the pedestrian flow trajectory corresponding to the mobile terminal is calculated; wherein the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal, centered on the millimeter wave base station.

[0013] Optionally, the target convolutional neural network model is trained by the following steps, including:

[0014] Acquire a sample signal; wherein the sample signal is a return signal of a sample mobile terminal within the communication range of the millimeter wave base station;

[0015] Constructing a sample signal covariance matrix based on the sample signal;

[0016] Optimizing the weight vector based on the Lagrange multiplier to obtain an optimal weight vector; wherein the optimization strategy is to minimize the output power of the sample signal and keep the gain in the required signal direction unchanged; the optimal weight vector is associated with the angle between the sample signal and the corresponding receiving antenna in the vertical direction;

[0017] Based on the optimal weight vector, construct a power spectrum;

[0018] The sample signal covariance matrix is ​​used as the input of the initial convolutional neural network model, and the power spectrum is used as a label to train the initial convolutional neural network model to obtain the target convolutional neural network model.

[0019] Optionally, the target convolutional neural network model includes two convolutional layers with ReLU functions, a BN layer and a fully connected layer.

[0020] Optionally, determining the horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle includes:

[0021] Based on the target signal, determining an arrival time of the target signal;

[0022] Determining a straight-line distance between the millimeter wave base station and the mobile terminal based on the arrival time of the target signal;

[0023] The horizontal distance is determined based on the target angle and the straight-line distance.

[0024] Optionally, the orientation angle is determined by the following steps, including:

[0025] The multiple antennas are numbered in sequence, and a starting point antenna is determined; wherein the starting point antenna is numbered 0, and the starting point antenna is any antenna among the multiple antennas;

[0026] Determining an access antenna for the target signal;

[0027] The orientation angle is determined based on the difference between the serial number of the access antenna and the serial number of the starting point antenna, and the total number of the multiple antennas.

[0028] Optionally, the method further comprises:

[0029] Acquire multiple location nodes of the mobile terminal within a preset time period; each of the location nodes includes a horizontal distance between the mobile terminal and the millimeter wave base station at a current time node, and a direction angle;

[0030] Clustering multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters;

[0031] Construct a circle with a set radius with the geometric center point of each cluster as the center;

[0032] The trajectory of people flow is calculated using the circle as an individual.

[0033] Optionally, the set radius is determined by the following steps, including:

[0034] Get the distance from the geometric center point to each position node in the cluster;

[0035] The maximum distance between the geometric center point in the cluster and the remaining position nodes is determined as the set radius.

[0036] Optionally, clustering the multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters includes:

[0037] An adaptive ellipse distance density method is used to cluster multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters.

[0038] Optionally, the method further comprises:

[0039] Taking the millimeter wave base station as a reference point, the pedestrian flow trajectory is connected to a third-party map to visualize the pedestrian flow trajectory.

[0040] In a second aspect, the present application provides a pedestrian flow trajectory measurement system based on a millimeter wave base station, which is applied to a millimeter wave base station, wherein the millimeter wave base station has a plurality of antennas arranged in an array, and the plurality of antennas are evenly distributed around the body of the millimeter wave base station, and the system includes:

[0041] An acquisition module, used to acquire a target signal received by a millimeter wave base station; wherein the target signal is a return signal of a mobile terminal within the communication range of the millimeter wave base station;

[0042] A construction module, used for constructing a signal covariance matrix based on the target signal;

[0043] A prediction module, used to input the signal covariance matrix into a pre-trained target convolutional neural network model, and output a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction;

[0044] A determination module, configured to determine a horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle;

[0045] A measurement module is used to measure the pedestrian flow trajectory corresponding to the mobile terminal based on the horizontal distance and the direction angle; wherein the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal, centered on the millimeter wave base station.

[0046] The beneficial effects of the present invention include:

[0047] First, the method for calculating the flow trajectory of people provided by this application utilizes millimeter wave base station resources. Compared with the existing optical video analysis and infrared sensors, this method is less affected by the environment, that is, the accuracy and reliability of the flow trajectory calculation are better. At the same time, personal images will not be captured, which can protect personal privacy and security;

[0048] Second, in the embodiment of the present application, when calculating the trajectory of human flow, a signal covariance matrix is ​​first constructed based on the target signal, and then the pre-trained target convolutional neural network model is used to obtain the angle between the target signal and the received antenna in the vertical direction, and then the angle can be used to effectively calculate the horizontal distance between the millimeter wave base station and the mobile terminal, and then the orientation angle of the mobile terminal is determined with the millimeter wave base station as the center. The method of calculating the trajectory of human flow through horizontal distance and orientation angle is simple and efficient, and has a high measurement accuracy.

[0049] In summary, the crowd flow trajectory measurement method based on millimeter wave base stations provided in this application provides a new crowd flow trajectory measurement method, which has high measurement accuracy, is less affected by the environment, and will not capture personal images, and has wide applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of the steps of a method for calculating pedestrian trajectory based on a millimeter wave base station provided in an embodiment of the present invention.

[0051] Figure 2 A flowchart of the steps of another method for calculating pedestrian trajectory based on millimeter wave base stations provided in an embodiment of the present invention.

[0052] Figure 3 A module block diagram of a pedestrian trajectory estimation system based on millimeter wave base stations provided in an embodiment of the present invention.

[0053] Figure 4 A module block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0055] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0056] At present, in the field of traditional crowd monitoring, common methods include optical video analysis and infrared sensors. As one of the mainstream means of monitoring, the performance of optical video analysis technology is often affected by lighting conditions. At night or in low-light environments, its monitoring effect is greatly reduced, and it is difficult to ensure the accuracy of the data. In addition, once there are sight obstructions such as trees, buildings or other obstacles, the video analysis system cannot capture the complete picture, thereby reducing the reliability of monitoring. Although infrared sensors can overcome the limitations of lighting conditions to a certain extent, their performance is easily affected by ambient temperature fluctuations. For example, in an environment with rapid temperature changes, infrared sensors may have false alarms or missed alarms, thereby reducing the accuracy of monitoring. In addition, the above two technologies usually involve the capture of personal images, which may cause public concerns about privacy protection in some cases. With the society's emphasis on personal privacy protection, how to balance the needs of crowd trajectory monitoring and privacy protection has become an urgent problem to be solved.

[0057] In view of the above problems, the present application proposes the following embodiments to solve the above technical problems.

[0058] See also Figure 1 An embodiment of the present application provides a method for calculating pedestrian flow trajectories based on a millimeter wave base station, which is applied to a millimeter wave base station. The millimeter wave base station has multiple antennas arranged in an array, and the multiple antennas are evenly distributed around the body of the millimeter wave base station. The method includes: steps 101 to 105.

[0059] Step 101: Acquire a target signal received by a millimeter wave base station.

[0060] The target signal is a return signal from a mobile terminal within the communication range of the millimeter wave base station.

[0061] The following is an explanation of the communication system of the method for calculating the flow trajectory of people based on the millimeter wave base station. The communication system includes a server and a client. The server refers to the millimeter wave base station used for communication, and the client refers to the mobile terminal used for user communication. It should be noted that after receiving the signal from the server, the user terminal will return the signal to the server.

[0062] Step 102: construct a signal covariance matrix based on the target signal.

[0063] Here, before constructing the signal covariance matrix based on the target signal, the target signal may be denoised first. A conventional noise processing method may be used here.

[0064] Step 103: Input the signal covariance matrix into the pre-trained target convolutional neural network model and output the target angle.

[0065] The target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction.

[0066] That is, in an embodiment of the present application, a target convolutional neural network model is pre-trained, and the network model can output the angle (target angle) between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction through the input signal covariance matrix corresponding to the target signal.

[0067] It should be noted that the millimeter wave base station has multiple antennas arranged in an array, and the multiple antennas are evenly distributed around the body of the millimeter wave base station. For example, they can be distributed around the body of the millimeter wave base station like a circle, that is, multiple antennas form a circle to receive signals at different angles. For example, antenna a receives the target signal. When antenna a receives the target signal, the target angle represents the angle between the target signal and antenna a in the vertical direction.

[0068] Step 104: Determine the horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle.

[0069] Since the height of the millimeter wave base station antenna is generally around 35-55 meters, in order to obtain accurate pedestrian flow trajectories, the horizontal distance between the millimeter wave base station and the mobile terminal is determined in combination with the target angle output by the network model.

[0070] Step 105: Based on the horizontal distance and the orientation angle, the pedestrian flow trajectory corresponding to the mobile terminal is calculated.

[0071] Among them, the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal, centered on the millimeter wave base station.

[0072] Finally, the pedestrian flow trajectory corresponding to the mobile terminal is calculated through the horizontal distance between the mobile terminal and the millimeter wave base station, as well as the orientation angle of the mobile terminal.

[0073] In summary, the method for calculating the flow of people based on the millimeter wave base station provided in the embodiment of the present application has the following beneficial effects, including:

[0074] First, the method for calculating the trajectory of human traffic provided by the embodiment of the present application utilizes millimeter wave base station resources. Compared with the optical video analysis and infrared sensors in the prior art, this method is less affected by the environment, that is, the accuracy and reliability of the human traffic trajectory calculation are better. At the same time, personal images will not be captured, which can protect personal privacy and security;

[0075] Second, in the embodiment of the present application, when calculating the trajectory of human flow, a signal covariance matrix is ​​first constructed based on the target signal, and then the pre-trained target convolutional neural network model is used to obtain the angle between the target signal and the received antenna in the vertical direction, and then the angle can be used to effectively calculate the horizontal distance between the millimeter wave base station and the mobile terminal, and then the orientation angle of the mobile terminal is determined with the millimeter wave base station as the center. The method of calculating the trajectory of human flow through horizontal distance and orientation angle is simple and efficient, and has a high measurement accuracy.

[0076] In summary, the crowd flow trajectory calculation method based on millimeter wave base stations provided in the embodiments of the present application provides a new crowd flow trajectory calculation method, which has high measurement accuracy, is less affected by the environment, and will not capture personal images, and has wide applicability.

[0077] For the above steps, the formula parameters involved are as follows:

[0078] First, the expression of the target signal received by the millimeter wave base station is: ;in, represents the target signal received by the millimeter wave base station, represents the signal of the kth antenna at time t, represents Gaussian additive white noise, and for Corresponding steering vector.

[0079] in, ; represents the angle between the target signal and the vertical direction when it reaches the kth antenna of the millimeter wave base station (a parameter to be determined), d represents the straight-line distance from the mobile terminal to the millimeter wave base station (which can be calculated using time), λ represents the wavelength of the target signal; j represents an imaginary unit.

[0080] The signal covariance matrix is ​​calculated as follows:

[0081] ;

[0082] in represents the calculation of mathematical expectation, represents the calculation of conjugate transpose, and M represents the total number of antennas.

[0083] Optionally, see Figure 2 , the target convolutional neural network model is trained through the following steps, including: step 201 to step 205.

[0084] Step 201: Acquire a sample signal.

[0085] The sample signal is a return signal of a sample mobile terminal within the communication range of the millimeter wave base station. The description of the sample signal can refer to the description of the target signal in the above embodiment, and will not be repeated here.

[0086] Step 202: construct a sample signal covariance matrix based on the sample signal.

[0087] Similarly, the construction of the sample signal covariance matrix may also refer to the description of the signal covariance matrix in the aforementioned embodiment, which will not be elaborated here.

[0088] Step 203: Optimize the weight vector based on the Lagrange multiplier to obtain the optimal weight vector.

[0089] The optimization strategy is to minimize the output power of the sample signal and keep the gain in the required signal direction unchanged; the optimal weight vector is associated with the angle between the sample signal and the corresponding receiving antenna in the vertical direction.

[0090] The calculation formula of the weight vector is:

[0091] ;

[0092] in, is the inverse of the signal covariance matrix; for The corresponding steering vector. H represents the calculation of the conjugate transpose.

[0093] It should be noted that, through the above optimization strategy, the steering vector corresponding to the angle between the sample signal and the corresponding receiving antenna in the vertical direction can be calculated.

[0094] Step 204: construct a power spectrum based on the optimal weight vector.

[0095] The calculation formula of power spectrum is:

[0096] ;

[0097] in, is the transpose of w.

[0098] Step 205: Using the sample signal covariance matrix as the input of the initial convolutional neural network model and the power spectrum as the label, the initial convolutional neural network model is trained to obtain the target convolutional neural network model.

[0099] That is, let the model learn to output the power spectrum based on the sample signal covariance matrix, and the power spectrum can be obtained , which is the target angle.

[0100] In summary, the embodiment of the present application obtains the optimal weight vector by optimizing the weight vector based on the Lagrange multiplier, and then constructs the power spectrum using the optimal weight vector. The initial convolutional neural network model is then trained in combination with the sample signal covariance moment and the power spectrum, so that it can learn to calculate the target angle, so as to facilitate the subsequent accurate measurement of the pedestrian flow trajectory.

[0101] Optionally, the target convolutional neural network model includes two convolutional layers with ReLU functions, one BN layer and one fully connected layer.

[0102] Optionally, the above steps determine the horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle, including: determining the arrival time of the target signal based on the target signal; determining the straight-line distance between the millimeter wave base station and the mobile terminal based on the arrival time of the target signal; determining the horizontal distance based on the target angle and the straight-line distance.

[0103] Specifically, the calculation formula for the horizontal distance is:

[0104] ;

[0105] Among them, l represents the horizontal distance, d represents the straight-line distance, The above process can be used to accurately calculate the horizontal distance between the millimeter wave base station and the mobile terminal.

[0106] Optionally, the direction angle is determined by the following steps, including: numbering multiple antennas in sequence and determining a starting point antenna; wherein the starting point antenna is numbered 0, and the starting point antenna is any one of the multiple antennas; determining an access antenna for the target signal; and determining the direction angle based on the difference between the number of the access antenna and the starting point antenna, and the total number of the multiple antennas.

[0107] Multiple antennas are distributed around the body of the millimeter wave base station like a circle, that is, multiple antennas form a circle to receive signals at different angles. Here, any antenna is used as the starting antenna and is numbered 0. The angles of other antennas are is equivalent to . Wherein, K represents the Kth antenna, and M represents the total number of antennas.

[0108] Finally, a location node of the mobile terminal can be obtained as .

[0109] Optionally, the method provided in the embodiment of the present application also includes: obtaining multiple location nodes of the mobile terminal within a preset time period; each location node includes the horizontal distance between the mobile terminal and the millimeter wave base station at the current time node, and the direction angle; clustering the multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters; constructing a circle with a set radius with the geometric center point of each cluster as the center; and measuring the trajectory of people flow with the circle as an individual.

[0110] The above preset time period can be set according to actual needs, such as 10 minutes, 5 minutes, 1 minute, etc.

[0111] Considering that when a user holds a mobile terminal, the user may not move, but the mobile terminal may move up, down, left, or right, which may cause errors in the calculation of the flow of people. Therefore, in the embodiment of the present application, the location nodes are clustered, and the circles corresponding to the clusters are used to represent the moving individuals to calculate the flow of people, thereby eliminating the error caused by the user holding the communication tool (i.e., the mobile terminal) and not moving, but the tool moving.

[0112] Specifically, the position of the mobile terminal at each moment is regarded as a particle. The movement of the mobile terminal represents the movement of the person. The particles of a fixed time period are taken as , corresponding to n position nodes, Perform clustering and obtain A clusters. Then, calculate the geometric center of each cluster:

[0113] ;

[0114] in Represents clusters Then, the geometric center of each cluster is A circle with a set radius is constructed as the center, and then the trajectory of the crowd is calculated using the circle as an individual.

[0115] Optionally, the set radius is determined by the following steps, including: obtaining the distance from the geometric center point to each position node in the cluster; and determining the maximum distance between the geometric center point in the cluster and the remaining position nodes as the set radius r.

[0116] Right now, .

[0117] By determining the maximum distance between the geometric center point in the cluster and the other position nodes as the set radius, it can be ensured that all points in the cluster fall within the range of the circle.

[0118] Optionally, clustering multiple location nodes of the mobile terminal within a preset time period to obtain multiple clusters includes: clustering multiple location nodes of the mobile terminal within the preset time period using an adaptive ellipse distance density method to obtain multiple clusters.

[0119] It should be noted that the adaptive ellipse distance density method is an algorithm for cluster analysis, which replaces the traditional Euclidean distance with the adaptive ellipse distance to better describe the structure of the data. In the embodiment of the present application, the adaptive ellipse distance density method is used for clustering to obtain very accurate clusters for the location nodes.

[0120] Optionally, the method provided in the embodiment of the present application also includes: using the millimeter wave base station as a reference point, connecting the pedestrian flow trajectory to a third-party map, and visually displaying the pedestrian flow trajectory.

[0121] It should be noted that since the location of the millimeter wave base station is known and accurate, by using the millimeter wave base station as a reference point and connecting the crowd flow trajectory to the third-party map data, the actual measurement and visualization of the crowd flow trajectory can be completed.

[0122] In summary, the present invention proposes a method for calculating the trajectory of human flow based on millimeter wave base stations. The straight-line distance between the communication tools used by people and the base station is calculated through the existing millimeter wave base stations, and the angle of the signal arrival in the vertical direction is calculated (fitted) through the convolutional neural network to construct coordinates with the millimeter wave base station as the origin. Secondly, the influence of the movement of non-human communication tools on the trajectory measurement is eliminated by clustering and obtaining the geometric center to improve the measurement accuracy. Compared with the existing methods, the present invention does not require additional equipment, can use existing base stations, and has better accuracy.

[0123] See also Figure 3 Based on the same inventive concept, the present application provides a human flow trajectory estimation system 30 based on a millimeter wave base station, which is applied to a millimeter wave base station. The millimeter wave base station has a plurality of antennas arranged in an array, and the plurality of antennas are evenly distributed around the body of the millimeter wave base station. The system includes:

[0124] An acquisition module 301 is used to acquire a target signal received by a millimeter wave base station; wherein the target signal is a return signal of a mobile terminal within the communication range of the millimeter wave base station;

[0125] A construction module 302 is used to construct a signal covariance matrix based on the target signal;

[0126] The prediction module 303 is used to input the signal covariance matrix into a pre-trained target convolutional neural network model and output a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction;

[0127] A determination module 304 is used to determine a horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle;

[0128] The calculation module 305 is used to calculate the pedestrian flow trajectory corresponding to the mobile terminal based on the horizontal distance and the direction angle; wherein the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal with the millimeter wave base station as the center.

[0129] See also Figure 4 Based on the same inventive concept, the present application embodiment provides a module frame of an electronic device 400 that applies the above method. The electronic device 400 includes: at least one processor 401 ( Figure 4 Only one is shown in the figure), a memory 402, a computer program 403 stored in the memory 402 and executable on at least one processor 401, and when the processor 401 executes the computer program 403, the steps of the method in any of the foregoing embodiments are implemented.

[0130] The electronic device 400 can be any hardware device in a millimeter wave base station that has data processing capabilities.

[0131] Those skilled in the art will understand that Figure 4 The electronic device 400 is merely an example and does not constitute a limitation on the electronic device 400 , and may include more or less components than those shown in the figure, or may combine certain components, or may include different components.

[0132] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0133] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 400. Further, the memory 402 may also include both an internal storage unit of the electronic device 400 and an external storage device.

[0134] It should be noted that the above-mentioned systems, devices, etc. are based on the same concept as the method embodiments of the present application. The modules designed for the systems, the steps performed by the devices, and the technical effects brought about can all be found in the method embodiment section and will not be repeated here.

[0135] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0136] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0137] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0138] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0139] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for calculating the trajectory of human traffic based on millimeter wave base stations. It is characterized in that Applied to a millimeter wave base station, the millimeter wave base station has a plurality of antennas arranged in an array, and the plurality of antennas are evenly distributed around a body of the millimeter wave base station, the method comprising: Acquire a target signal received by a millimeter wave base station; wherein the target signal is a return signal of a mobile terminal within the communication range of the millimeter wave base station; Based on the target signal, construct a signal covariance matrix; Input the signal covariance matrix into a pre-trained target convolutional neural network model, and output a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction; Determining a horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle; Based on the horizontal distance and the direction angle, the pedestrian flow trajectory corresponding to the mobile terminal is calculated; wherein the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal, centered on the millimeter wave base station.

2. According to the method for calculating the flow of people based on the millimeter wave base station in claim 1, It is characterized in that The target convolutional neural network model is trained by the following steps, including: Acquire a sample signal; wherein the sample signal is a return signal of a sample mobile terminal within the communication range of the millimeter wave base station; Constructing a sample signal covariance matrix based on the sample signal; Optimizing the weight vector based on the Lagrange multiplier to obtain the optimal weight vector; wherein the optimization strategy is to minimize the output power of the sample signal and keep the gain in the required signal direction unchanged; the optimal weight vector is associated with the angle in the vertical direction between the sample signal and the receiving antenna corresponding to the millimeter wave base station; Based on the optimal weight vector, construct a power spectrum; The sample signal covariance matrix is ​​used as the input of the initial convolutional neural network model, and the power spectrum is used as a label to train the initial convolutional neural network model to obtain the target convolutional neural network model.

3. The method for calculating the flow of people based on a millimeter wave base station according to claim 2, It is characterized in that The target convolutional neural network model includes two convolutional layers with ReLU functions, one BN layer and one fully connected layer.

4. The method for calculating the flow of people based on a millimeter wave base station according to claim 1, It is characterized in that The determining, based on the target signal and the target angle, a horizontal distance between the millimeter wave base station and the mobile terminal includes: Based on the target signal, determining an arrival time of the target signal; Determining a straight-line distance between the millimeter wave base station and the mobile terminal based on the arrival time of the target signal; The horizontal distance is determined based on the target angle and the straight-line distance.

5. The method for calculating the flow of people based on a millimeter wave base station according to claim 1, It is characterized in that The orientation angle is determined by the following steps, including: The multiple antennas are numbered in sequence, and a starting point antenna is determined; wherein the starting point antenna is numbered 0, and the starting point antenna is any antenna among the multiple antennas; Determining an access antenna for the target signal; The orientation angle is determined based on a difference between the number of the access antenna and the number of the starting point antenna, and a total number of the plurality of antennas.

6. The method for calculating the flow of people based on a millimeter wave base station according to claim 1, It is characterized in that The method further comprises: Acquire multiple location nodes of the mobile terminal within a preset time period; each of the location nodes includes a horizontal distance between the mobile terminal and the millimeter wave base station at a current time node, and a direction angle; Clustering multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters; Construct a circle with a set radius with the geometric center point of each cluster as the center; The trajectory of people flow is calculated using the circle as an individual.

7. The method for calculating the flow of people based on a millimeter wave base station according to claim 6, It is characterized in that The set radius is determined by the following steps, including: Get the distance from the geometric center point to each position node in the cluster; The maximum distance between the geometric center point in the cluster and the remaining position nodes is determined as the set radius.

8. The method for calculating the flow of people based on a millimeter wave base station according to claim 6, It is characterized in that The clustering of the multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters includes: An adaptive ellipse distance density method is used to cluster multiple location nodes of the mobile terminal within the preset time period to obtain multiple clusters.

9. The method for calculating the flow of people based on a millimeter wave base station according to claim 1, It is characterized in that The method further comprises: Taking the millimeter wave base station as a reference point, the pedestrian flow trajectory is connected to a third-party map to visualize the pedestrian flow trajectory.

10. A pedestrian trajectory estimation system based on millimeter wave base stations, It is characterized in that Applied to a millimeter wave base station, the millimeter wave base station has a plurality of antennas arranged in an array, and the plurality of antennas are evenly distributed around the body of the millimeter wave base station, and the system includes: An acquisition module, used to acquire a target signal received by a millimeter wave base station; wherein the target signal is a return signal of a mobile terminal within the communication range of the millimeter wave base station; A construction module, used for constructing a signal covariance matrix based on the target signal; A prediction module, used to input the signal covariance matrix into a pre-trained target convolutional neural network model, and output a target angle; wherein the target angle represents the angle between the target signal and the receiving antenna of the millimeter wave base station in the vertical direction; A determination module, configured to determine a horizontal distance between the millimeter wave base station and the mobile terminal based on the target signal and the target angle; A measurement module is used to measure the pedestrian flow trajectory corresponding to the mobile terminal based on the horizontal distance and the direction angle; wherein the direction angle is the direction angle of the receiving antenna corresponding to the mobile terminal, centered on the millimeter wave base station.

Images