A signal processing method, device and storage medium

Abstract

The application discloses a signal processing method and device and a storage medium. The method comprises the following steps: collecting signal data corresponding to the same position at a preset sampling point; determining probability information that the signal data is derived from different types of signal sources based on the signal data by using a preset data classification model; and determining the type of the signal source from which the signal data is derived based on the probability information that the signal data is derived from different types of signal sources for the preset sampling point. Through the technical scheme, the accuracy and efficiency of signal source type determination are improved.

Description

Technical Field

[0001] This application relates to the field of data processing, and more particularly to a signal processing method, apparatus, and storage medium. Background Technology

[0002] During transmission, wireless signals can propagate in a straight line if there are no obstructions (line-of-sight propagation). In real-world environments, due to obstacles, wireless signals cannot propagate in a straight line from the transmitter to the receiver (non-line-of-sight propagation). In this case, the propagation methods are mainly reflection, diffraction, or scattering.

[0003] Currently, due to the obstruction of buildings, the signal cannot propagate in a straight line from the transmitter to the receiver. This causes interference signals reflected from buildings to be mistaken for signals emitted by a certain signal source, resulting in errors in identifying the type of signal source and poor accuracy. Furthermore, the method of eliminating interference sources generally requires manual investigation to narrow down the scope, which is inefficient. Summary of the Invention

[0004] To address the aforementioned technical problems, embodiments of the present invention aim to provide a signal processing method, apparatus, and storage medium that directly utilizes a preset data classification model to determine the type of signal source from which the acquired signal data originates, thereby improving the accuracy and efficiency of signal source type determination.

[0005] The technical solution of this invention is implemented as follows:

[0006] This invention provides a signal processing method, the method comprising:

[0007] At preset sampling points, collect signal data corresponding to the same location;

[0008] Using a preset data classification model, the probability information of the signal data originating from different types of signal sources is determined based on the signal data;

[0009] For the preset sampling point, based on the probability information that the signal data comes from different types of signal sources, the type of signal source from which the signal data originates is determined.

[0010] In the above method, the probability information that the signal data originates from different types of signal sources includes: a first probability that the signal data originates from a normal signal source, and a second probability that the signal data originates from an abnormal signal source. Determining the type of signal source from which the signal data originates based on the probability information of the signal data originating from different types of signal sources includes:

[0011] Obtain a preset probability parameter, and multiply the preset probability parameter by the second probability to determine the reference probability;

[0012] If the first probability is greater than the reference probability, the signal source from which the signal data originates is determined to be the normal signal source;

[0013] If the first probability is less than the reference probability, the signal source from which the signal data originates is determined to be the abnormal signal source.

[0014] In the above method, after determining the product of the preset probability parameter and the second probability as the reference probability, the method further includes:

[0015] If the first probability is equal to the reference probability, the signal data is determined to be noise data, and the determination of the type of signal source from which the signal data originates is terminated.

[0016] In the above method, after determining the type of signal source from which the signal data originates based on the probability information of the signal data originating from different types of signal sources, the method further includes:

[0017] If the signal source from which the signal data originates is a normal signal source or an interference signal source, the signal source from which the signal data originates is determined as the target signal source.

[0018] Based on the horizontal and vertical angles of arrival in the signal data, the spatial orientation of the target signal source relative to the preset sampling point is determined;

[0019] Using a preset propagation loss model, the straight-line distance between the preset sampling point and the target signal source is determined based on the signal strength in the signal data;

[0020] The spatial location information of the target signal source is determined based on the arrival pitch angle, the arrival horizontal angle, and the straight-line distance.

[0021] In the above method, determining the spatial location information of the target signal source based on the elevation angle, the horizontal angle, and the straight-line distance includes:

[0022] Based on the pitch angle and the straight-line distance, determine the altitude information of the target signal source and the horizontal distance between the target signal source and the preset sampling point;

[0023] Based on the horizontal distance and the horizontal angle of arrival, the planar position information of the target signal source is determined;

[0024] The height information and the planar position information are determined as the spatial position information.

[0025] In the above method, the spatial location information includes planar location information and height information. After determining the spatial location information of the target signal source based on the arrival pitch angle, the arrival horizontal angle, and the straight-line distance, the method further includes:

[0026] Using the planar location information, the planar geographical location of the target signal source in a preset three-dimensional spatial map is determined;

[0027] When the planar geographical location is within a preset building in the preset three-dimensional spatial map, the floor information of the target signal source within the preset building is determined using the height information.

[0028] In the above method, before determining the probability information of the signal data originating from different types of signal sources based on the signal data using a preset data classification model, the method further includes:

[0029] Acquire sample data and use the data to be trained classification model to determine the probability information of the sample data originating from different types of signal sources based on the sample data;

[0030] The loss information between the probability information of the sample data originating from different types of signal sources and the target probability information preset for the sample data is calculated to obtain the target loss information;

[0031] Based on the target loss information, the model parameters of the data classification model to be trained are adjusted to obtain the preset data classification model.

[0032] This invention provides a signal processing apparatus, comprising:

[0033] The acquisition module is used to acquire signal data at preset sampling points corresponding to the same location;

[0034] The determination module is used to determine the probability information of the signal data originating from different types of signal sources based on the signal data using a preset data classification model.

[0035] The determination module is used to determine the type of signal source from which the signal data originates, based on the probability information of the signal data originating from different types of signal sources, for the preset sampling points.

[0036] In the above device, the determination module is specifically used to obtain a preset probability parameter and determine the product of the preset probability parameter and the second probability as a reference probability; when the first probability is greater than the reference probability, the signal source from which the signal data originates is determined to be the normal signal source; when the first probability is less than the reference probability, the signal source from which the signal data originates is determined to be the abnormal signal source.

[0037] In the above-described device, the determination module is specifically used to determine that the signal data is noise data when the first probability is equal to the reference probability, and to terminate the determination of the type of signal source from which the signal data originates.

[0038] The aforementioned device further includes a positioning module, used to determine the signal source of the signal data as a target signal source when the signal source is a normal signal source or an interference signal source; determine the spatial direction of the target signal source relative to the preset sampling point based on the horizontal and vertical angles of arrival in the signal data; determine the straight-line distance between the preset sampling point and the target signal source based on the signal strength in the signal data using a preset propagation loss model; and determine the spatial location information of the target signal source based on the vertical angle of arrival, the horizontal angle of arrival, and the straight-line distance.

[0039] In the above device, the positioning module is specifically used to determine the height information of the target signal source and the horizontal distance between the target signal source and the preset sampling point based on the elevation angle and the straight-line distance; determine the planar position information of the target signal source based on the horizontal distance and the horizontal angle; and determine the height information and the planar position information as the spatial position information.

[0040] In the above-described device, the positioning module is further configured to use the planar location information to determine the corresponding planar geographical location of the target signal source in a preset three-dimensional spatial map; and, if the planar geographical location is located within a preset building in the preset three-dimensional spatial map, to use the height information to determine the floor information of the target signal source within the preset building.

[0041] The aforementioned device further includes a training module for acquiring sample data and, using a data classification model to be trained, determining the probability information of the sample data originating from different types of signal sources based on the sample data; calculating the loss information between the probability information of the sample data originating from different types of signal sources and the preset target probability information for the sample data to obtain target loss information; and adjusting the model parameters of the data classification model to be trained based on the target loss information to obtain the preset data classification model.

[0042] This invention provides a signal processing device, comprising: a processor, a memory, and a communication bus;

[0043] The communication bus is used to realize the communication connection between the processor and the memory;

[0044] The processor is used to execute the signal processing program stored in the memory to implement the above-described signal processing method.

[0045] The present invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the above-described signal processing method.

[0046] This invention provides a signal processing method, apparatus, and storage medium. The method includes: acquiring signal data corresponding to the same location at preset sampling points; using a preset data classification model, determining the probability information of the signal data originating from different types of signal sources based on the signal data; and, for the preset sampling points, determining the type of signal source from which the signal data originates based on the probability information of different types of signal sources. The technical solution provided by this invention directly utilizes a preset data classification model to determine the type of signal source from which the acquired signal data originates, improving the accuracy and efficiency of signal source type determination. Attached Figure Description

[0047] Figure 1 This is a schematic flowchart of a signal processing method provided in an embodiment of the present invention;

[0048] Figure 2a This is a schematic diagram illustrating the location of an exemplary preset sampling point provided in an embodiment of the present invention.

[0049] Figure 2b A schematic diagram of an exemplary preset area provided for an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of an exemplary preset data classification model provided in an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of the structure of a signal processing device provided in an embodiment of the present invention. Figure 1 ;

[0052] Figure 5 The second schematic diagram shows the structure of a signal processing device provided in an embodiment of the present invention. Detailed Implementation

[0053] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings of the embodiments of the present invention. It is to be understood that the specific embodiments described herein are merely for explaining the relevant application and are not intended to limit the application. Furthermore, it should be noted that, for ease of description, only the parts relevant to the relevant application are shown in the accompanying drawings.

[0054] This invention provides a signal processing method, applied to a signal processing device. Figure 1 This is a schematic flowchart illustrating a signal processing method provided in an embodiment of the present invention. Figure 1 As shown, the main steps include:

[0055] S101. Collect signal data at the preset sampling points corresponding to the same location.

[0056] In an embodiment of the present invention, the signal processing device collects signal data corresponding to the same location at a preset sampling point.

[0057] It should be noted that, in the embodiments of the present invention, the signal processing device includes a frequency sweep signal processing device and a phased array directional antenna. The phased array directional antenna supports the acquisition of signal data in the horizontal and vertical directions within a preset range. The preset range can be ±60 degrees or other angle ranges. The specific preset range can be set according to actual needs and application scenarios. The present invention does not limit this.

[0058] It should be noted that, in the embodiments of the present invention, the preset sampling point is the location where the signal processing device acquires the signal data.

[0059] Figure 2a This is a schematic diagram illustrating the location of an exemplary preset sampling point provided in an embodiment of the present invention. Figure 2a As shown, the largest area is the region to be sampled. Preset sampling points can be any point within this region, whether solid or dashed. The preset sampling area, centered on a solid or dashed point, represents the signal range that the phased array directional antenna in the signal processing device can receive. Figure 2b As shown, the preset area can be the area encompassed by preset lengths in the east, north, west, and south directions, centered on a preset sampling point. The preset length is mainly set according to actual needs and application scenarios. For example, if receiving 4G signal propagation, the preset length can be 500 meters. Or, if receiving 5G signal propagation, since higher frequency signals have a relatively shorter propagation distance, the preset length may be 400 meters. The specific preset length is not limited in this invention.

[0060] It should be noted that, in the embodiments of the present invention, the signal processing device can receive signal data of multiple signals at a preset sampling point. These multiple signals originate from different locations in the preset area. The signal data obtained by the signal processing device corresponding to the same location can be any one of the different locations in the preset area.

[0061] S102. Using a preset data classification model, determine the probability information of the signal data originating from different types of signal sources based on the signal data.

[0062] In an embodiment of the present invention, the signal processing device uses a preset data classification model to determine the probability information of the signal data originating from different types of signal sources based on the signal data.

[0063] It should be noted that, in the embodiments of the present invention, after the signal processing device collects signal data corresponding to the same location at a preset sampling point, it uses a preset data classification model to obtain probability information of the signal data originating from different types of signal sources, thereby being able to determine the type of signal source from which the signal data originates based on the corresponding probability information.

[0064] Specifically, in embodiments of the present invention, before the signal processing device uses a preset data classification model to determine the probability information of signal data originating from different types of signal sources based on the signal data, it may also perform the following steps: acquiring sample data, and using a data classification model to be trained to determine the probability information of sample data originating from different types of signal sources based on the sample data; calculating the loss information between the probability information of sample data originating from different types of signal sources and the preset target probability information for the sample data to obtain target loss information; and adjusting the model parameters of the data classification model to be trained based on the target loss information to obtain the preset data classification model.

[0065] It should be noted that, in the embodiments of the present invention, the sample data acquired by the signal processing device can be directly collected signal data or simulated signal data.

[0066] It should be noted that, in the embodiments of the present invention, if the sample data obtained by the signal processing device is the actual collected signal data, the actual collected signal data is the signal data of the base station transmitted at different locations near the base station collected by the signal processing device by moving the phased array directional antenna under interference-free conditions. The sample data are all signal data transmitted by normal base stations.

[0067] It should be noted that, in the embodiments of the present invention, if the sample data acquired by the signal processing device is analog signal data, the analog signal data may be signal data received at different locations by the signal processing device through information such as the latitude, longitude, altitude, and cell transmission power of the base station, or it may be signal data received at different locations by setting up interference sources at random points. The signal strength included in the sample data can be calculated by a preset propagation loss model.

[0068] It should be noted that, in the embodiments of the present invention, the preset propagation loss model is mainly divided into two forms based on different application scenarios: one is line-of-sight propagation loss, and the other is non-line-of-sight propagation loss. Line-of-sight propagation loss corresponds to the case of direct signal transmission, that is, the method of calculating signal strength under no interference conditions. Non-line-of-sight propagation loss corresponds to the case of signal refraction, reflection, or scattering during propagation, that is, the method of calculating signal strength under interference conditions.

[0069] It should be noted that, in the embodiments of the present invention, when the preset propagation loss model is in the form of line-of-sight propagation loss, it can be expressed by formula (1), as shown in the following formula:

[0070] PL LOS =28.0+40lg(d) 3D )+20lgf c -9lg((d BP ) 2 +(h BS -h UT ) 2 (1)

[0071] Among them, PL LOS Let d be the signal strength in the form of line-of-sight propagation loss. 3D d is the straight-line distance between the base station antenna and the preset sampling point. BP The breakpoint distance is set for the model. This breakpoint distance is a preset value, and the signal processing device can set it according to actual needs and application scenarios. The specific breakpoint distance is not limited in this invention. c h is the operating frequency of the base station. BS This refers to the effective height of the base station antenna, which is also a preset value, such as 25, h. UT The height range of the preset sampling points can be any value between 1.5 meters and 22.5 meters, with a shadow attenuation of 4 dB.

[0072] It should be noted that, in the embodiments of the present invention, when the preset propagation loss model is a non-line-of-sight propagation loss form, it can be expressed by formula (2), as shown in the following formula:

[0073] PL NLOS =13.54+39.08lg(d) 3D )+20lgf c -0.6(h UT -1.65) (2)

[0074] Among them, PL NLOS The signal strength in the form of non-line-of-sight propagation loss is d. 3Df is the straight-line distance between the base station antenna and the preset sampling point. c h is the operating frequency of the base station. UT The height range of the preset sampling points can be any value between 1.5 meters and 22.5 meters, with a shadow attenuation of 6 dB.

[0075] It should be noted that in the embodiments of the present invention, the preset propagation loss model is in the form of non-line-of-sight propagation loss, which generally takes the second refraction, scattering and diffraction as the standard. The signal intensity of more than one refraction, diffraction and scattering is significantly weakened and can be ignored.

[0076] It should be noted that, in the embodiments of the present invention, the signal processing device inputs the base station parameters corresponding to the preset area, the three-dimensional geographic information, and the sample data into the data classification model to be trained, and determines the type information corresponding to the sample data. The base station parameters include the base station location, height, and cell transmission power. The three-dimensional geographic information includes the latitude and longitude coordinates, height, coverage area, and land area of ​​buildings. The sample data includes the latitude and longitude of the sampling point, signal strength, signal frequency, horizontal angle of arrival, and pitch angle of arrival.

[0077] It should be noted that, in the embodiments of the present invention, the classification model of the data to be trained can be a convolutional neural network model based on gradient descent.

[0078] Figure 3 This is a schematic diagram illustrating the structure of an exemplary preset data classification model provided in an embodiment of the present invention. Figure 3 As shown, the signal processing device converts the base station parameters, three-dimensional geographic information, and sample data in the preset area into a 120*120 matrix. After feature extraction through three convolutional units and three fully connected layers, the probability information of the sample data originating from different types of signal sources is obtained. This probability information represents the probability that the sample data is signal data from a normal signal source or signal data from an abnormal signal source. The convolutional unit includes a convolutional layer, an activation layer, and a pooling layer. The activation layer uses the ReLU activation function.

[0079] It should be noted that, in the embodiments of the present invention, after obtaining the probability information of the sample data originating from different types of signal sources, the signal processing device calculates the loss information between the probability information of the sample data originating from different types of signal sources and the target probability information preset for the sample data, and obtains the target loss information. Then, based on the target loss information, the model parameters of the training data classification model are adjusted to obtain the preset data classification model, so as to determine whether the signal data originates from different types of signal sources.

[0080] It should be noted that, in the embodiments of the present invention, the sample data used by the signal processing device to train the data classification model includes both directly collected signal data and simulated signal data, thereby improving the accuracy and precision of the preset data classification model.

[0081] S103. For the preset sampling points, based on the probability information of the signal data originating from different types of signal sources, determine the type of signal source from which the signal data originates.

[0082] In an embodiment of the present invention, the signal processing device determines the type of signal source from which the signal data originates based on probability information of the signal data originating from different types of signal sources for a preset sampling point.

[0083] It should be noted that, in the embodiments of the present invention, after the signal processing device obtains the probability information of the signal data originating from different types of signal sources using a preset data classification model, it determines the type of signal source from which the signal data originates based on the probability information.

[0084] Specifically, in embodiments of the present invention, the probability information of signal data originating from different types of signal sources includes: a first probability that the signal data originates from a normal signal source, and a second probability that the signal data originates from an abnormal signal source. The signal processing device determines the type of signal source from which the signal data originates based on the probability information of the signal data originating from different types of signal sources, including: acquiring a preset probability parameter and multiplying the preset probability parameter by the second probability to determine a reference probability; if the first probability is greater than the reference probability, determining that the signal source from which the signal data originates is a normal signal source; if the first probability is less than the reference probability, determining that the signal source from which the signal data originates is an abnormal signal source.

[0085] It should be noted that, in the embodiments of the present invention, the preset probability parameter can be 1.5, 2, or other values. The specific preset probability parameter can be set according to actual needs and application scenarios, and the present invention does not limit it.

[0086] It should be noted that, in the embodiments of the present invention, the signal processing device multiplies the preset probability parameter by the second probability to obtain the reference probability, and then determines the type of signal source from which the signal data originates based on the comparison result between the reference probability and the first probability. For example, when the preset probability parameter is 2, the first probability is y1, and the second probability is y2, if y1 > 2 * y2, then the signal source from which the signal data originates is a normal signal source; if y1 < 2 * y2, then the signal source from which the signal data originates is an abnormal signal source.

[0087] It should be noted that, in the embodiments of the present invention, the signal processing device directly uses a preset data classification model to determine the type of signal source from which the acquired signal data originates, without having to consider the problem of multipath interference.

[0088] Specifically, in an embodiment of the present invention, after the signal processing device determines the product of the preset probability parameter and the second probability as the reference probability, it may also perform the following steps: when the first probability is equal to the reference probability, determine that the signal data is noise data and terminate the determination of the type of signal source from which the signal data originates.

[0089] It should be noted that, in the embodiments of the present invention, if the first probability is equal to the reference probability, the signal data is determined to be noise data, and the determination of the type of signal source from which the signal data originates is terminated. For example, if the preset probability parameter is 2, the first probability is y1, and the second probability is y2, and if y1 = 2*y2, then the signal data is noise data, and there is no need to determine the type of signal source from which the signal data originates.

[0090] Specifically, in embodiments of the present invention, after determining the type of signal source from which the signal data originates based on probability information indicating that the signal data originates from different types of signal sources, the signal processing device may further perform the following steps: if the type of signal source from which the signal data originates is a normal signal source or an interfering signal source, the signal source from which the signal data originates is identified as the target signal source; the spatial direction of the target signal source relative to a preset sampling point is determined based on the horizontal and vertical angles of arrival in the signal data; the straight-line distance between the preset sampling point and the target signal source is determined based on the signal strength in the signal data using a preset propagation loss model; and the spatial location information of the target signal source is determined based on the vertical angle of arrival, the horizontal angle of arrival, and the straight-line distance.

[0091] It should be noted that, in the embodiments of the present invention, after the signal processing device acquires the type of the signal source from which the signal data originates, it uses the signal data to determine the spatial location information of the corresponding signal source. The signal processing device first determines the signal source from which the signal data originates as the target signal source. Based on the horizontal and vertical angles of arrival in the signal data, it determines the spatial direction of the target signal source relative to the preset sampling point. Then, based on the type of the signal source, it determines the form of using the preset propagation loss model. Subsequently, using the corresponding preset propagation loss model, it determines the straight-line distance between the preset sampling point and the target signal source. Finally, based on the vertical angle of arrival, the horizontal angle of arrival, and the straight-line distance, it determines the spatial location information of the target signal source.

[0092] Specifically, in embodiments of the present invention, the signal processing device determines the spatial location information of the target signal source based on the elevation angle, the horizontal angle, and the straight-line distance, including: determining the height information of the target signal source and the horizontal distance between the target signal source and the preset sampling point based on the elevation angle and the straight-line distance; determining the planar location information of the target signal source based on the horizontal distance and the horizontal angle; and determining the height information and the planar location information as spatial location information.

[0093] It should be noted that, in the embodiments of the present invention, the signal processing device determines the height information of the target signal source and the horizontal distance between the target signal source and the preset sampling point based on the elevation angle and the straight-line distance. In order to obtain the height information more accurately after determining the height information of the target signal source, the calculated height information can be added to the distance of the preset sampling point from the horizontal plane. Then, based on the horizontal distance and the horizontal angle of arrival, the planar position information of the target signal source is determined, and the spatial position information of the target signal source is obtained.

[0094] Specifically, in the embodiments of the present invention, the spatial location information includes planar location information and height information. After the signal processing device determines the spatial location information of the target signal source based on the elevation angle, horizontal angle, and straight-line distance, it can also perform the following steps: using the planar location information, determine the planar geographical location of the target signal source in a preset three-dimensional spatial map; if the planar geographical location is located within a preset building in the preset three-dimensional spatial map, use the height information to determine the floor information of the target signal source within the preset building.

[0095] It should be noted that, in the embodiments of the present invention, after the signal processing device obtains the spatial location information of the target signal source, it first uses the planar location information of the spatial location information to determine whether there is a preset building at the planar location information corresponding to the preset three-dimensional spatial map. If there is a preset building at the planar location information, it uses the height information in the spatial location information to determine the specific floor of the target signal source within the preset building. Since the specific floor information can be directly located, the efficiency and accuracy of on-site investigation are improved.

[0096] This invention provides a signal processing method, comprising: acquiring signal data corresponding to the same location at preset sampling points; using a preset data classification model, determining the probability information of the signal data originating from different types of signal sources based on the signal data; and, for the preset sampling points, determining the type of signal source from which the signal data originates based on the probability information of different types of signal sources. The signal processing method provided by this invention directly utilizes a preset data classification model to determine the type of signal source from which the acquired signal data originates, thereby improving the accuracy and efficiency of signal source type determination.

[0097] This invention provides a signal processing device. Figure 4 A schematic diagram of the structure of a signal processing device provided in an embodiment of the present invention. Figure 1 .like Figure 4 As shown, it includes:

[0098] The acquisition module 401 is used to acquire signal data corresponding to the same location at preset sampling points;

[0099] The determination module 402 is used to determine the probability information of the signal data originating from different types of signal sources based on the signal data using a preset data classification model.

[0100] The determination module 403 is used to determine the type of signal source from which the signal data originates based on the probability information of the signal data originating from different types of signal sources for the preset sampling point.

[0101] Optionally, the determination module 403 is specifically used to obtain a preset probability parameter and determine the product of the preset probability parameter and the second probability as a reference probability; when the first probability is greater than the reference probability, determine that the signal source from which the signal data originates is the normal signal source; when the first probability is less than the reference probability, determine that the signal source from which the signal data originates is the abnormal signal source.

[0102] Optionally, the determination module 403 is specifically used to determine that the signal data is noise data when the first probability is equal to the reference probability, and to terminate the determination of the type of signal source from which the signal data originates.

[0103] Optionally, the signal processing device further includes a positioning module (not shown in the figure), used to determine the signal source of the signal data as a target signal source when the signal source of the signal data is a normal signal source or an interference signal source; determine the spatial direction of the target signal source relative to the preset sampling point based on the horizontal and vertical angles of arrival in the signal data; determine the straight-line distance between the preset sampling point and the target signal source based on the signal strength in the signal data using a preset propagation loss model; and determine the spatial location information of the target signal source based on the vertical angle of arrival, the horizontal angle of arrival, and the straight-line distance.

[0104] Optionally, the positioning module (not shown in the figure) is specifically used to determine the height information of the target signal source and the horizontal distance between the target signal source and the preset sampling point based on the elevation angle and the straight-line distance; determine the planar position information of the target signal source based on the horizontal distance and the horizontal angle; and determine the height information and the planar position information as the spatial position information.

[0105] Optionally, the positioning module (not shown in the figure) is further configured to use the planar location information to determine the planar geographical location of the target signal source in a preset three-dimensional spatial map; and, if the planar geographical location is located within a preset building in the preset three-dimensional spatial map, to use the height information to determine the floor information of the target signal source within the preset building.

[0106] Optionally, the signal processing device further includes a training module (not shown in the figure), used to acquire sample data, and using a data classification model to be trained, determine the probability information of the sample data originating from different types of signal sources based on the sample data; calculate the loss information between the probability information of the sample data originating from different types of signal sources and the target probability information preset for the sample data to obtain target loss information; and adjust the model parameters of the data classification model to be trained based on the target loss information to obtain the preset data classification model.

[0107] This invention provides a signal processing device. Figure 5 This is a schematic diagram of a signal processing device provided in an embodiment of the present invention. Figure 5 As shown, the device includes: a processor 501, a memory 502, and a communication bus 503;

[0108] The communication bus 503 is used to realize the communication connection between the processor 501 and the memory 502;

[0109] The processor 501 is used to execute the signal processing program stored in the memory 502 to implement the above-mentioned signal processing method.

[0110] This invention provides a signal processing device that collects signal data corresponding to the same location at preset sampling points; uses a preset data classification model to determine the probability information of the signal data originating from different types of signal sources; and, for each preset sampling point, determines the type of signal source from which the signal data originates based on the probability information of different types of signal sources. The signal processing device provided by this invention directly utilizes a preset data classification model to determine the type of signal source from which the collected signal data originates, thereby improving the accuracy and efficiency of signal source type determination.

[0111] This invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the above-described method. The computer-readable storage medium can be volatile memory, such as random-access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or it can be a device comprising one or any combination of the above-described memories, such as a mobile phone, computer, tablet device, personal digital assistant, etc.

[0112] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0113] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0114] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0116] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this utility application should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A signal processing method, characterized in that, The method includes: At preset sampling points, collect signal data corresponding to the same location; Using a preset data classification model, the probability information of the signal data originating from different types of signal sources is determined based on the signal data; For the preset sampling points, based on the probability information that the signal data comes from different types of signal sources, the type of signal source from which the signal data originates is determined; If the signal source from which the signal data originates is a normal signal source or an interference signal source, the signal source from which the signal data originates is determined as the target signal source. Based on the horizontal and vertical angles of arrival in the signal data, the spatial orientation of the target signal source relative to the preset sampling point is determined; Using a preset propagation loss model, the straight-line distance between the preset sampling point and the target signal source is determined based on the signal strength in the signal data; The spatial location information of the target signal source is determined based on the arrival pitch angle, the arrival horizontal angle, and the straight-line distance.

2. The method according to claim 1, characterized in that, The probability information that the signal data originates from different types of signal sources includes: a first probability that the signal data originates from a normal signal source, and a second probability that the signal data originates from an abnormal signal source. Determining the type of signal source from which the signal data originates based on the probability information of the signal data originating from different types of signal sources includes: Obtain a preset probability parameter, and multiply the preset probability parameter by the second probability to determine the reference probability; If the first probability is greater than the reference probability, the signal source from which the signal data originates is determined to be the normal signal source; If the first probability is less than the reference probability, the signal source from which the signal data originates is determined to be the abnormal signal source.

3. The method according to claim 2, characterized in that, After determining the reference probability by multiplying the preset probability parameter by the second probability, the method further includes: If the first probability is equal to the reference probability, the signal data is determined to be noise data, and the determination of the type of signal source from which the signal data originates is terminated.

4. The method according to claim 1, characterized in that, Determining the spatial location information of the target signal source based on the elevation angle, the horizontal angle, and the straight-line distance includes: Based on the pitch angle and the straight-line distance, determine the altitude information of the target signal source and the horizontal distance between the target signal source and the preset sampling point; Based on the horizontal distance and the horizontal angle of arrival, the planar position information of the target signal source is determined; The height information and the planar position information are determined as the spatial position information.

5. The method according to claim 1, characterized in that, The spatial location information includes planar location information and height information. After determining the spatial location information of the target signal source based on the arrival pitch angle, the arrival horizontal angle, and the straight-line distance, the method further includes: Using the planar location information, the planar geographical location of the target signal source in a preset three-dimensional spatial map is determined; When the planar geographical location is within a preset building in the preset three-dimensional spatial map, the floor information of the target signal source within the preset building is determined using the height information.

6. The method according to claim 1, characterized in that, Before determining the probability information of the signal data originating from different types of signal sources based on the signal data using a preset data classification model, the method further includes: Acquire sample data and use the data to be trained classification model to determine the probability information of the sample data originating from different types of signal sources based on the sample data; The loss information between the probability information of the sample data originating from different types of signal sources and the target probability information preset for the sample data is calculated to obtain the target loss information; Based on the target loss information, the model parameters of the data classification model to be trained are adjusted to obtain the preset data classification model.

7. A signal processing apparatus, characterized in that, include: The acquisition module is used to acquire signal data at preset sampling points corresponding to the same location; The determination module is used to determine the probability information of the signal data originating from different types of signal sources based on the signal data using a preset data classification model; The determination module is used to determine the type of signal source from which the signal data originates, based on the probability information of the signal data originating from different types of signal sources, for the preset sampling points; The positioning module is used to determine the signal source of the signal data as the target signal source when the type of the signal source from which the signal data originates is a normal signal source or an interference signal source. Based on the horizontal and vertical angles of arrival in the signal data, the spatial orientation of the target signal source relative to the preset sampling point is determined; using a preset propagation loss model, the straight-line distance between the preset sampling point and the target signal source is determined based on the signal strength in the signal data; The spatial location information of the target signal source is determined based on the arrival pitch angle, the arrival horizontal angle, and the straight-line distance.

8. A signal processing apparatus, characterized in that, include: Processor, memory, and communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is configured to execute the signal processing program stored in the memory to implement the signal processing method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the signal processing method according to any one of claims 1-6.

Images