Radar parameter optimization method, device, terminal and storage medium

Abstract

The embodiments of the present invention disclose a radar parameter optimization method, device, terminal and storage medium. The solution can receive a radar optimization instruction, obtain the scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instruction, obtain the depth data currently detected by the radar, and determine the spatial coordinates of the abnormal signal in the current scene based on the depth data, associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal, and adjust the algorithm parameters in the radar based on the physical source and environmental information. The solution provided by the embodiment of the present application can fuse the environmental information of the radar with the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the parameters of the radar to improve the accuracy of radar detection.

Description

Technical Field

[0001] The present invention relates to the field of radar technology, and in particular to a radar parameter optimization method, device, terminal and storage medium. Background Art

[0002] Millimeter-wave radar technology, with its high-precision ability to detect target distance, speed, angle, and micro-motion characteristics, is widely used in smart homes and building automation, for applications such as human presence detection, fall monitoring, and sleep tracking. Its non-invasive sensing capabilities and all-weather operation provide reliable technical support for intelligent services.

[0003] During actual use, the applicant discovered that in actual deployments, the performance degradation of millimeter-wave radar sensors in complex interference environments has become increasingly prominent. This is especially true in bathrooms and kitchens, where environmental interference signals often couple with human body signature signals, leading to frequent false positives and false negatives. For example, continuous dripping water may be misinterpreted as slight human movement, causing the device to trigger falsely; strong reflection interference may mask actual human signals, causing service responses to fail. Such issues significantly affect the accuracy of radar detection. Summary of the Invention

[0004] Embodiments of the present invention provide a radar parameter optimization method, device, terminal, and storage medium. These methods can fuse information about the radar's environment with depth data within the radar to determine the interference source emitting abnormal signals, and then adaptively adjust the radar's parameters to improve radar detection accuracy.

[0005] An embodiment of the present invention provides a radar parameter optimization method, comprising:

[0006] receiving a radar optimization instruction, and acquiring a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction;

[0007] Acquire depth data currently detected by the radar, and determine the spatial coordinates of abnormal signals in the current scene based on the depth data;

[0008] Associating the spatial coordinates with the scene image to determine a physical source corresponding to the abnormal signal;

[0009] Algorithm parameters in the radar are adjusted based on the physical source and the environmental information.

[0010] In one embodiment, obtaining the depth data currently detected by the radar includes:

[0011] Obtaining raw data sampled by an analog-to-digital converter in the radar;

[0012] Performing Fourier transform processing on the raw data to obtain atlas data;

[0013] Point cloud data corresponding to multiple detection points are calculated based on the original data using a preset algorithm.

[0014] In one embodiment, determining the spatial coordinates of an abnormal signal in the current scene based on the depth data includes:

[0015] Identify abnormal signals that persist or appear periodically in vacant scenes and meet preset conditions based on the atlas data and point cloud data;

[0016] The azimuth angle, pitch angle, and distance information corresponding to the abnormal signal are extracted to calculate the spatial coordinates of the abnormal signal.

[0017] In one embodiment, the preset condition includes that a stable peak at a preset position reaches a preset value, or a micro-Doppler frequency reaches a preset frequency, or a signal strength is greater than a background noise threshold.

[0018] In one embodiment, associating the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal includes:

[0019] constructing a three-dimensional scene according to the scene image, wherein the three-dimensional scene takes the position of the radar as an origin;

[0020] The spatial coordinates are mapped to the three-dimensional scene to determine the physical source corresponding to the abnormal signal.

[0021] In one embodiment, mapping the spatial coordinates to the three-dimensional scene to determine the physical source corresponding to the abnormal signal includes:

[0022] Mapping the spatial coordinates to the three-dimensional scene to determine a target area corresponding to the abnormal signal;

[0023] Identify characteristic information of the abnormal signal and compare it with a pre-stored interference source characteristic database;

[0024] The physical source in the target area is determined according to the comparison result.

[0025] In one embodiment, adjusting algorithm parameters in the radar includes:

[0026] Lowering the signal detection sensitivity threshold of the radar at the location corresponding to the physical source; and / or,

[0027] reducing the signal weight of the location corresponding to the physical source in the radar; and / or,

[0028] Adjust the filter parameters in the radar to filter out the frequency corresponding to the abnormal signal.

[0029] An embodiment of the present invention further provides a radar parameter optimization device, comprising:

[0030] an acquisition unit, configured to receive a radar optimization instruction and acquire a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction;

[0031] a determining unit, configured to obtain depth data currently detected by the radar, and determine the spatial coordinates of an abnormal signal in a current scene based on the depth data;

[0032] an associating unit, configured to associate the spatial coordinates with the scene image to determine a physical source corresponding to the abnormal signal;

[0033] An adjustment unit is configured to adjust algorithm parameters in the radar based on the physical source and the environmental information.

[0034] An embodiment of the present invention further provides a terminal, comprising: a memory and a processor, wherein an application processing program is stored on the memory, and when the application processing program is executed by the processor, the steps of the radar parameter optimization method provided in any one of the embodiments of the present invention are implemented.

[0035] An embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute any radar parameter optimization method provided by an embodiment of the present invention.

[0036] The radar parameter optimization method provided in an embodiment of the present invention can receive a radar optimization instruction, obtain a scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instruction, obtain the depth data currently detected by the radar, and determine the spatial coordinates of the abnormal signal in the current scene based on the depth data, associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal, and adjust the algorithm parameters in the radar based on the physical source and environmental information. The solution provided in the embodiment of the present application can fuse the environmental information of the radar with the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the radar parameters to improve the accuracy of radar detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 This is a schematic diagram of a first flow chart of a radar parameter optimization method provided by an embodiment of the present invention;

[0039] Figure 2 This is a schematic structural diagram of a remote diagnostic system for a radar provided by an embodiment of the present invention;

[0040] Figure 3 1 is a second flow chart of the radar parameter optimization method provided by an embodiment of the present invention;

[0041] Figure 4 1 is a schematic structural diagram of a radar parameter optimization device provided by an embodiment of the present invention;

[0042] Figure 5 It is a schematic structural diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0044] It should be noted that, in this document, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0045] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and they can be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0046] It should be noted that in this article, step codes such as 101 and 102 are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the order. Those skilled in the art may execute 102 first and then 101, etc. during specific implementation, but these should all be within the scope of protection of this application.

[0047] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] An embodiment of the present invention provides a radar parameter optimization method. The executor of the radar parameter optimization method can be the radar parameter optimization device provided by the embodiment of the present invention, or an intelligent terminal and server integrating the radar parameter optimization device, wherein the radar parameter optimization device can be implemented in hardware or software.

[0049] For details, please refer to Figure 1 , Figure 1 1 is a schematic diagram of a first flow chart of a radar parameter optimization method provided by an embodiment of the present invention. The specific flow of the radar parameter optimization method may be as follows:

[0050] 101. Receive a radar optimization instruction, and obtain a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction.

[0051] In one embodiment, the execution subject of the radar parameter optimization method may be a remote diagnosis server, and the remote diagnosis system of the radar may be as follows: Figure 2As shown, the radar optimization command can be generated by a user terminal and sent to the analysis module of the remote diagnosis server via a remote interactive interface. Alternatively, the remote diagnosis server can automatically generate the command based on the radar's detection results, which is not further limited in this embodiment. The radar optimization command refers to a control signal that triggers adaptive adjustment of radar parameters. For example, when a millimeter-wave radar generates a false alarm (e.g., water droplets misidentified as human activity) or a false alarm (e.g., strong reflections masking the true signal) in a complex environment such as a bathroom or kitchen, the user can click the "Optimize" button on the mobile app to generate the radar optimization command and send it to the remote diagnosis server to initiate the parameter optimization process.

[0052] Specifically, when the remote diagnostic server receives radar optimization instructions, it can collect multimodal information. For example, a user can use the user interface deployed on their terminal device to enter a text description of the user experience issues encountered with the target millimeter-wave radar sensor and upload or authorize the capture of one or more scene images that reflect the actual physical environment in which the target radar is deployed. The terminal device here can be a smartphone app, for example. The user also grants the backend system access to the target radar's internal data for a specified subsequent time period.

[0053] In one embodiment, the terminal device can send a diagnostic request containing a problem description, a photo of the environment, a unique identifier of the target radar, and user authorization information to a pre-defined remote diagnostic server. Based on the diagnostic requirements, the remote diagnostic server can also selectively request and obtain information related to the target radar's deployment environment, or environmental information, such as current ambient temperature and humidity readings provided by the target radar or other associated devices.

[0054] In the logic for triggering remote diagnosis in this embodiment, the triggering event can be a user-initiated trigger, a radar internal error flag trigger, a performance anomaly, a remote server command trigger, or a combination of the above conditions. Among them, performance anomalies include a surge in false alarm rate, a sudden decrease in detection range, etc.

[0055] 102. Obtain depth data currently detected by the radar, and determine the spatial coordinates of abnormal signals in the current scene based on the depth data.

[0056] In one embodiment, upon receiving a valid radar optimization instruction, the remote diagnostic server may establish a connection based on the target radar's unique identifier and send a data collection instruction to the target radar within an idle environment time window specified by the user or determined by the system based on the radar's status. It should be noted that the idle environment time window may be a specific time period during which no human activity is confirmed within the target radar's detection range.

[0057] Next, the target radar can, according to the instructions, collect and upload the deep internal data generated by its operation within the time window to the remote diagnosis server. Deep internal data refers to the underlying data generated during the radar's internal signal processing process, which is used to characterize the spatial and signal characteristics of the detection scene. It includes at least one or more of the following: raw analog-to-digital converter (ADC) sampling data, such as the binary data stream after the radar receives the echo signal through analog-to-digital conversion; fast Fourier transform (FFT) to convert the time domain signal into frequency domain feature data, such as range-Doppler spectrum and range-angle spectrum; detection point list / point cloud data output by the preliminary detection algorithm (such as CFAR), such as the set of detection points extracted from the raw data, each point contains parameters such as distance, azimuth, pitch angle, and signal strength; key algorithm parameter configuration values ​​currently used by the target radar, such as detection threshold, filter settings, static clutter map, etc.; and the device's own operating status information.

[0058] In one embodiment, before determining the spatial coordinates of abnormal signals, the radar depth internal data is analyzed within a preset idle environment time window to identify signal components that persist or periodically appear at specific distances, angles, or Doppler bins, and whose signal strength exceeds a preset background noise threshold. These signal components, known as abnormal signals, are then determined based on this depth data.

[0059] 103. Associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal.

[0060] In one embodiment, an analysis module on the remote diagnostic server can process and fuse the collected multimodal data. The analysis module can be implemented by an artificial intelligence model or an engineer-assisted analysis tool. Specifically, the deep internal data from the target radar, particularly FFT data and / or point cloud data, is analyzed to identify signal components with abnormal characteristics that persist or appear periodically in an empty environment. The precise spatial coordinates corresponding to these abnormal signals, including distance, azimuth, and elevation angle, are then extracted.

[0061] These abstract spatial coordinates extracted from the radar data are then combined with user-uploaded photos of the surrounding environment for visual-spatial correlation analysis. This analysis understands the physical layout and composition of objects in the photo and maps the spatial coordinates represented by the radar coordinate system to corresponding physical objects or areas in the surrounding image.

[0062] In one embodiment, the method for identifying specific interference sources during correlation analysis includes analyzing and recording the spectral characteristics of multipath reflections from common sources such as faucet / toilet drips, exhaust fan vibrations, heater airflow, and tile mirrors into an expert database. The characteristics of the identified abnormal signal components, such as Doppler signatures, are then compared with a pre-stored database of known interference source characteristics to assist in identifying the type of physical source. Furthermore, when identifying the physical source, reference is made to a user-provided diagnostic request containing a textual description of the problem. Ultimately, the physical interference source causing the radar false alarm or performance degradation is precisely located.

[0063] 104. Adjust the algorithm parameters in the radar based on physical source and environmental information.

[0064] In one embodiment, based on the located interference source and its signal characteristics, the remote diagnostic server can send instructions to the target radar through a specific remote interaction interface that allows internal parameter interaction with the target radar to modify key parameters of one or more signal processing algorithms running within the target radar.

[0065] In one embodiment, the process of adjusting the algorithm parameters in the radar is interactive, that is, the analysis module is allowed to further fine-tune the parameters according to the real-time internal data changes fed back by the adjusted target radar.

[0066] In one embodiment, after parameter adjustment is complete, to verify the optimization results, the remote diagnostic server can also control the target radar to collect internal data for a preset period of time under specific conditions (for example, remaining idle or simulating a user presence / absence scenario) or simply observe its output reporting status. The analysis module examines the updated data or status to confirm that previously identified abnormal signal characteristics have been effectively suppressed and that the radar's behavior (e.g., whether it falsely reports "person") is consistent with expectations. Upon confirming that personalized environmental adaptation has successfully resolved the user's issue, the remote diagnostic server sends a notification to the user via the user terminal device, informing them that the diagnostic and optimization process has been completed.

[0067] As described above, the radar parameter optimization method proposed in the embodiment of the present invention can receive a radar optimization instruction, obtain the scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instruction, obtain the depth data currently detected by the radar, and determine the spatial coordinates of the abnormal signal in the current scene based on the depth data, associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal, and adjust the algorithm parameters in the radar based on the physical source and environmental information. The solution provided in the embodiment of the present application can fuse the environmental information of the radar with the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the parameters of the radar to improve the accuracy of radar detection.

[0068] The method described in the above embodiment will be further described below.

[0069] See also Figure 3 , Figure 3 FIG. 2 is a second flow chart of a radar parameter optimization method provided by an embodiment of the present invention. The method includes:

[0070] 201. Receive a radar optimization instruction, and obtain a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction.

[0071] For example, users can proactively submit optimization requests through a mobile app. Alternatively, commands may be triggered by abnormal radar performance (such as a sudden increase in false alarms) or by scheduled inspections by a remote server. For example, if a bathroom radar frequently falsely reports "personnel," the user can click the "Correction" button in the app, and the system will generate radar optimization instructions. The system then receives photos of the radar deployment environment, such as the bathroom tile walls, toilet, and faucet layout. When taking photos, the system may prompt the user to capture them from different angles to ensure coverage of key areas within the radar's detection range. In addition to the images, auxiliary data such as ambient temperature and humidity (provided by the radar or associated equipment) and the presence of running water (which can be briefly picked up via a microphone) is also collected. For example, in a kitchen scenario, this environmental information can help determine interference such as range hood vibration. Finally, the terminal device can encrypt and transmit a data packet containing the instructions, images, environmental data, and the radar's unique identifier to the remote diagnostic server, laying the foundation for subsequent analysis.

[0072] 202. Obtain raw data sampled by an analog-to-digital converter in the radar.

[0073] In one embodiment, after receiving the command, the server sends a data collection command to the radar during a quiet time window (e.g., 3:00 AM). This ensures that there is no human activity during this time window to prevent interference with the actual target signal. The analog-to-digital converter (ADC) acquires the binary data stream of the radar's echo signal after analog-to-digital conversion. For example, in a bathroom scenario, the echo of falling water drops and the reflection signal from metal pipes are converted into raw digital signals. The radar then packages the raw data and uploads it to the server. The data can also be annotated with metadata such as the acquisition time and environmental conditions during storage to facilitate subsequent tracing and analysis.

[0074] 203. Perform Fourier transform processing on the original data to obtain atlas data, and calculate point cloud data corresponding to multiple detection points using a preset algorithm based on the original data.

[0075] In one embodiment, the above-mentioned spectrum data may include a range-Doppler spectrum and a distance-angle spectrum. The process of generating the range-Doppler spectrum may include: performing an FFT transform on the raw data to convert the time domain signal into a frequency domain feature. For example, the micro-Doppler signature of continuous dripping water will appear as a peak at a specific frequency in the spectrum, while the reflection of a stationary object will appear as a strong signal at a fixed distance. The process of generating the distance-angle spectrum may include: performing FFT processing on the phase difference of the signals received by multiple antennas to obtain the angle information of the target. For example, the signal reflected by a bathroom mirror will correspond to a position at a specific distance and angle in the spectrum.

[0076] Next, the raw data can be processed using a pre-set algorithm (such as constant false alarm detection (CFAR)) to extract information such as the distance, speed, and angle of the detection points, generating point cloud data. For example, the continuous reflection points generated by water flow will show dynamic changes in the point cloud.

[0077] 204. Based on the atlas data and point cloud data, identify abnormal signals that persist or appear periodically in vacant scenes and meet preset conditions.

[0078] In one embodiment, the preset conditions include a stable peak at a preset location reaching a preset value, a micro-Doppler frequency reaching a preset frequency, or a signal strength exceeding a background noise threshold. Specifically, the identification process based on a stable peak at a preset location may include dividing the radar detection range into three-dimensional grid cells based on range, azimuth, and elevation angle, and presetting key monitoring areas. Then, within the map data, the temporal changes in signal strength are analyzed cell by cell. If a cell exhibits a stable peak for N consecutive sampling periods (e.g., N=10, corresponding to 10 seconds) and the peak strength exceeds the background noise threshold for that cell, it is marked as an abnormal signal. The identification process based on micro-Doppler frequency may include performing frequency domain analysis on the range-Doppler spectrum to extract the frequency components of the signal. The micro-Doppler effect can reflect the micro-motion characteristics of the target. The extracted frequencies are then compared with a preset interference source signature library. If a frequency component persists in an unoccupied scenario and its strength exceeds a threshold, it is determined to be an abnormal signal. The identification process based on signal strength exceeding a threshold may include traversing all detection points in the point cloud data, calculating the signal strength (e.g., RSSI) at each point, and comparing it with a global background noise threshold. If the signal strength at a certain point is consistently above the threshold and there is no corresponding human target in an unoccupied scene, it is considered an anomaly. Furthermore, the spatial coordinates and time series of the point cloud data can be combined to eliminate occasional transient signals (such as interference from a door opening). If the signal repeatedly appears at the same spatial location and its strength exceeds the threshold, it is confirmed as a valid anomaly.

[0079] 205. Extract the azimuth, elevation, and distance information corresponding to the abnormal signal to calculate the spatial coordinates of the abnormal signal.

[0080] In one embodiment, the azimuth and elevation angles can be calculated using the phase differences between multiple received signals, while the distance information can be calculated using the time delay of the echo signals. The angle and distance information can then be integrated into three-dimensional spatial coordinates (distance, azimuth, and elevation), accurately marking the location of the abnormal signal in the radar coordinate system. For example, the coordinates of an abnormal signal are (2m, 30°, 15°), corresponding to the faucet area.

[0081] 206. Construct a three-dimensional scene based on the scene image, wherein the three-dimensional scene uses the position of the radar as the origin.

[0082] In one embodiment, computer vision technology can be used to match feature points in multiple scene images uploaded by users, combining them with camera parameters to reconstruct a 3D model. For example, objects such as a bathroom tile wall, toilet, and mirror can be converted into a 3D mesh model. The radar's actual installation location is used as the coordinate origin (0,0,0) of the 3D scene, ensuring alignment between the radar coordinate system and the scene model. For example, if the radar is installed in the center of the bathroom ceiling, the origin would be set to that location. Environmental information such as temperature, humidity, and object material (e.g., metal, tile) can also be assigned to corresponding objects in the 3D scene to enhance the model's realism.

[0083] 207. Map the spatial coordinates into a three-dimensional scene to determine the physical source corresponding to the abnormal signal.

[0084] In one embodiment, the above-mentioned step of mapping the spatial coordinates into a three-dimensional scene to determine the physical source corresponding to the abnormal signal may include: mapping the spatial coordinates into a three-dimensional scene to determine the target area corresponding to the abnormal signal, identifying the characteristic information of the abnormal signal, and comparing it with a pre-stored interference source characteristic database, and determining the physical source in the target area based on the comparison results.

[0085] Specifically, the spatial coordinates of the abnormal signal collected by the millimeter-wave radar (including three-dimensional parameters such as distance, azimuth, and elevation) are first converted. A three-dimensional coordinate system is constructed based on the radar device's installation position and orientation, combined with the physical scene captured in the environmental photograph. Image recognition technology is used to extract the outlines, structural features, and relative position of objects in the photograph, and the abnormal signal coordinates in the radar coordinate system are mapped to the corresponding three-dimensional scene in the photograph. For example, if the radar detects a continuous signal at an azimuth of 30 degrees and a distance of 2 meters, combined with the presence of a flush toilet or metal shelf at that location in the environmental photograph, the abstract coordinates can be localized to a specific object or area, forming a "radar signal source-three-dimensional scene location" association. The abnormal signal is then subjected to multi-dimensional feature analysis to extract key parameters such as its Doppler spectrum characteristics (such as periodic micro-motion frequency), signal intensity fluctuation pattern, and spatial distribution range. A pre-set interference source feature database is also used. This database, accumulated through laboratory simulations and field data, contains radar signal fingerprints of typical interference sources (such as water flow, mechanical vibration, and metal reflections). For example, water drop interference usually manifests as a periodic micro-Doppler feature of 0.5-2Hz, while metal surface reflections present a strong signal feature of high-frequency flickering. Through pattern matching algorithms or machine learning classification models, the current abnormal signal features are compared with the feature templates in the database for similarity calculation, and the most matching candidate set of interference types is screened out. Finally, the comprehensive spatial positioning results and feature matching results are cross-validated. For example, if an abnormal signal is mapped to the faucet position in a three-dimensional scene, and the degree of matching between its features and the water drop interference in the database exceeds the threshold, the signal is determined to be caused by water droplet flow; if the signal source is located at the vent and the features match the airflow disturbance pattern, it is determined to be air flow interference.

[0086] This embodiment also performs contextual verification based on user-submitted problem descriptions (e.g., "The bathroom light doesn't turn off when no one is around"), prioritizing interference hypotheses that are strongly relevant to the scenario. The final output includes a diagnostic conclusion, including the specific physical object (e.g., a flush toilet), the interference type (water flow interference), and a confidence rating, providing a precise target for subsequent parameter optimization.

[0087] 208. Adjust the algorithm parameters in the radar based on physical source and environmental information.

[0088] In one embodiment, the step of adjusting the algorithm parameters in the radar may include: lowering the signal detection sensitivity threshold of the position corresponding to the physical source in the radar; and / or lowering the signal weight of the position corresponding to the physical source in the radar; and / or adjusting the filter parameters in the radar to filter out the frequency corresponding to the abnormal signal.

[0089] Specifically, the detection threshold can be increased based on the spatial coordinates of the interference source (such as the distance-angle unit corresponding to a faucet). For example, the detection threshold at 2m and 30° can be increased by 5dB to reduce false positives due to water droplets. Alternatively, the radar's internal algorithm can reduce the weight of signals originating from fixed interference sources. For example, the weight of mirror-reflected signals can be reduced by 40% to prevent strong reflections from masking human signals. Bandpass filter parameters can also be adjusted based on the frequency characteristics of the interference signal (such as the micro-Doppler frequency of water droplets, which is 0.5Hz) to filter out signals in this frequency range. After adjusting the parameters, the server can instruct the radar to provide real-time data feedback. If the abnormal signal is not effectively suppressed, the algorithm parameters can be further fine-tuned.

[0090] As described above, the radar parameter optimization method proposed in the embodiment of the present invention can receive a radar optimization instruction, obtain a scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instruction, obtain raw data sampled by an analog-to-digital converter in the radar, perform Fourier transform processing on the raw data to obtain atlas data, calculate point cloud data corresponding to multiple detection points according to the raw data through a preset algorithm, identify abnormal signals that persist or appear periodically in an empty scene and meet preset conditions based on the atlas data and point cloud data, extract the azimuth, pitch angle and distance information corresponding to the abnormal signal to calculate the spatial coordinates of the abnormal signal, construct a three-dimensional scene based on the scene image, wherein the three-dimensional scene uses the radar position as the origin, maps the spatial coordinates into the three-dimensional scene, determines the physical source corresponding to the abnormal signal, and adjusts the algorithm parameters in the radar based on the physical source and environmental information. The solution provided in the embodiment of the present application can integrate the environmental information of the radar and the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the radar parameters to improve the accuracy of radar detection.

[0091] In order to implement the above method, an embodiment of the present invention further provides a radar parameter optimization device, which can be integrated into a terminal device such as a mobile phone, a tablet computer, or the like.

[0092] For example, Figure 4 FIG. 1 is a schematic diagram of a first structure of a radar parameter optimization device according to an embodiment of the present invention. The radar parameter optimization device may include:

[0093] An acquisition unit 301 is configured to receive a radar optimization instruction and acquire a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction;

[0094] a determination unit 302 configured to obtain depth data currently detected by the radar and determine the spatial coordinates of an abnormal signal in a current scene based on the depth data;

[0095] an associating unit 303, configured to associate the spatial coordinates with the scene image to determine a physical source corresponding to the abnormal signal;

[0096] The adjustment unit 304 is configured to adjust algorithm parameters in the radar based on the physical source and the environmental information.

[0097] The radar parameter optimization device proposed in the embodiment of the present invention can receive radar optimization instructions, obtain the scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instructions, obtain the depth data currently detected by the radar, and determine the spatial coordinates of the abnormal signal in the current scene based on the depth data, associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal, and adjust the algorithm parameters in the radar based on the physical source and environmental information. The solution provided in the embodiment of the present application can fuse the environmental information of the radar with the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the radar parameters to improve the accuracy of radar detection.

[0098] The embodiment of the present invention further provides a terminal, such as Figure 5 As shown, the terminal may include components such as a radio frequency (RF) circuit 601, a memory 602 including one or more computer-readable storage media, an input unit 603, a display unit 604, a sensor 605, an audio circuit 606, a wireless fidelity (WiFi) module 607, a processor 608 including one or more processing cores, and a power supply 609. Those skilled in the art will appreciate that Figure 5 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0099] The RF circuit 601 can be used to receive and transmit signals during information transmission or calls. Specifically, it receives downlink information from the base station and transmits it to one or more processors 608 for processing. It also transmits uplink data to the base station. Typically, the RF circuit 601 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, and the like. Furthermore, the RF circuit 601 can communicate with the network and other devices via wireless communication. Wireless communication can utilize any communication standard or protocol, including but not limited to Global System of Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Messaging Service (SMS).

[0100] Memory 602 can be used to store software programs and modules. Processor 608 executes various functional applications and information processing by running the software programs and modules stored in memory 602. Memory 602 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback). The data storage area may store data generated based on terminal usage (such as audio data and a phone book). Memory 602 may also include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state memory device. Accordingly, memory 602 may also include a memory controller to provide access to memory 602 by processor 608 and input unit 603.

[0101] The input unit 603 can be used to receive digital or character input and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control. Specifically, in one embodiment, the input unit 603 may include a touch-sensitive surface and other input devices. A touch-sensitive surface, also known as a touch display or touchpad, can detect user touch operations on or near it (for example, operations performed on or near the touch-sensitive surface using a finger, stylus, or any other suitable object or accessory) and drive corresponding connected devices according to a pre-set program. Optionally, the touch-sensitive surface may include a touch detection device and a touch controller. The touch detection device detects the user's touch position and detects signals generated by the touch operation, transmitting the signals to the touch controller. The touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then transmits it to the processor 608. The touch controller can also receive and execute commands from the processor 608. Furthermore, touch-sensitive surfaces can be implemented using various types of technologies, including resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface, the input unit 603 may also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0102] The display unit 604 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the terminal, which can be composed of graphics, text, icons, videos, and any combination thereof. The display unit 604 may include a display panel. Optionally, the display panel may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Furthermore, the touch-sensitive surface may cover the display panel. When the touch-sensitive surface detects a touch operation on or near it, it is transmitted to the processor 608 to determine the type of touch event. The processor 608 then provides corresponding visual output on the display panel according to the type of touch event. Although in Figure 5 In the embodiment, the touch-sensitive surface and the display panel are used as two independent components to realize input and output functions, but in some embodiments, the touch-sensitive surface and the display panel can be integrated to realize input and output functions.

[0103] The terminal may also include at least one sensor 605, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel according to the brightness of the ambient light, and the proximity sensor can turn off the display panel and / or backlight when the terminal is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes) and the magnitude and direction of gravity when stationary. It can be used for applications that recognize the phone's posture (such as switching between landscape and portrait modes, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the terminal, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they are not further described here.

[0104] Audio circuit 606, a speaker, and a microphone provide an audio interface between the user and the terminal. Audio circuit 606 converts received audio data into electrical signals and transmits them to the speaker, which then converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuit 606 and converted into audio data. The audio data is then processed by output processor 608 and transmitted via RF circuit 601 to, for example, another terminal. Alternatively, the audio data is output to memory 602 for further processing. Audio circuit 606 may also include an earphone jack to allow communication between an external headset and the terminal.

[0105] WiFi is a short-range wireless transmission technology. The terminal can help users send and receive emails, browse web pages and access streaming media through the WiFi module 607. It provides users with wireless broadband Internet access. Figure 5 A WiFi module 607 is shown, but it is understandable that it is not an essential component of the terminal and can be omitted as needed without changing the essence of the invention.

[0106] Processor 608 is the terminal's control center, connecting all components of the phone using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 602 and accessing data stored in memory 602, it executes various terminal functions and processes data, thereby providing overall monitoring of the phone. Optionally, processor 608 may include one or more processing cores; preferably, processor 608 may integrate an application processor and a modem processor, with the application processor primarily handling the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 608.

[0107] The terminal also includes a power supply 609 (e.g., a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 608 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 609 can also include any of one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other components.

[0108] Although not shown, the terminal may also include a camera, a Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 608 in the terminal will load the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 608 will run the applications stored in the memory 602 to implement various functions:

[0109] receiving a radar optimization instruction, and acquiring a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction;

[0110] Acquire depth data currently detected by the radar, and determine the spatial coordinates of abnormal signals in the current scene based on the depth data;

[0111] Associating the spatial coordinates with the scene image to determine a physical source corresponding to the abnormal signal;

[0112] Algorithm parameters in the radar are adjusted based on the physical source and the environmental information.

[0113] In the above embodiments, the description of each embodiment has its own focus. For the parts that are not described in detail in a certain embodiment, please refer to the detailed description of the radar parameter optimization method above, which will not be repeated here.

[0114] As can be seen from the above, the terminal of the embodiment of the present invention can receive a radar optimization instruction, obtain the scene image and environmental information of the scene in which the radar is currently located according to the radar optimization instruction, obtain the depth data currently detected by the radar, and determine the spatial coordinates of the abnormal signal in the current scene based on the depth data, associate the spatial coordinates with the scene image to determine the physical source corresponding to the abnormal signal, and adjust the algorithm parameters in the radar based on the physical source and environmental information. The solution provided by the embodiment of the present application can fuse the environmental information of the radar with the depth data inside the radar to determine the interference source that emits the abnormal signal, and then adaptively adjust the parameters of the radar to improve the accuracy of radar detection.

[0115] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0116] To this end, an embodiment of the present invention provides a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any radar parameter optimization method provided in an embodiment of the present invention. For example, the instructions can execute the following steps:

[0117] receiving a radar optimization instruction, and acquiring a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction;

[0118] Acquire depth data currently detected by the radar, and determine the spatial coordinates of abnormal signals in the current scene based on the depth data;

[0119] Associating the spatial coordinates with the scene image to determine a physical source corresponding to the abnormal signal;

[0120] Algorithm parameters in the radar are adjusted based on the physical source and the environmental information.

[0121] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0122] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0123] Since the instructions stored in the storage medium can execute the steps in the parameter optimization method of any radar provided in the embodiments of the present invention, the beneficial effects that can be achieved by the parameter optimization method of any radar provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0124] The above describes in detail the radar parameter optimization method, device, terminal, and storage medium provided in the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core concept of the present invention. At the same time, for those skilled in the art, based on the concept of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A radar parameter optimization method, characterized in that: include: receiving a radar optimization instruction, and acquiring a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction; Acquire depth data currently detected by the radar, and determine the spatial coordinates of abnormal signals in the current scene based on the depth data; constructing a three-dimensional scene according to the scene image, wherein the three-dimensional scene takes the position of the radar as an origin; Mapping the spatial coordinates to the three-dimensional scene to determine a target area corresponding to the abnormal signal; Identify characteristic information of the abnormal signal and compare it with a pre-stored interference source characteristic database; determining a physical source in the target area based on the comparison result; Based on the physical source and the environmental information, the algorithm parameters in the radar are adjusted, wherein the algorithm parameters in the radar include lowering the signal detection sensitivity threshold of the position corresponding to the physical source in the radar; and / or lowering the signal weight of the position corresponding to the physical source in the radar; and / or adjusting the filter parameters in the radar to filter out the frequency corresponding to the abnormal signal.

2. The radar parameter optimization method according to claim 1, wherein: Obtain the depth data currently detected by the radar, including: Obtaining raw data sampled by an analog-to-digital converter in the radar; Performing Fourier transform processing on the raw data to obtain atlas data; Point cloud data corresponding to multiple detection points are calculated based on the original data using a preset algorithm.

3. The radar parameter optimization method according to claim 2, wherein: Determining the spatial coordinates of an abnormal signal in the current scene based on the depth data includes: Identify abnormal signals that persist or appear periodically in vacant scenes and meet preset conditions based on the atlas data and point cloud data; The azimuth angle, pitch angle, and distance information corresponding to the abnormal signal are extracted to calculate the spatial coordinates of the abnormal signal.

4. The radar parameter optimization method according to claim 3, wherein: The preset conditions include that a stable peak at a preset position reaches a preset value, or a micro-Doppler frequency reaches a preset frequency, or a signal strength is greater than a background noise threshold.

5. A radar parameter optimization device, characterized in that: include: an acquisition unit, configured to receive a radar optimization instruction and acquire a scene image and environmental information of a scene currently located by the radar according to the radar optimization instruction; a determining unit, configured to obtain depth data currently detected by the radar, and determine the spatial coordinates of an abnormal signal in a current scene based on the depth data; an association unit configured to construct a three-dimensional scene based on the scene image, wherein the three-dimensional scene uses the position of the radar as an origin; map the spatial coordinates into the three-dimensional scene to determine a target area corresponding to the abnormal signal; identify characteristic information of the abnormal signal and compare it with a pre-stored interference source characteristic database; and determine a physical source in the target area based on the comparison result; An adjustment unit is configured to adjust algorithm parameters in the radar based on the physical source and the environmental information, wherein adjusting the algorithm parameters in the radar includes lowering a signal detection sensitivity threshold at a position corresponding to the physical source in the radar; and / or lowering a signal weight at a position corresponding to the physical source in the radar; and / or adjusting filter parameters in the radar to filter out a frequency corresponding to the abnormal signal.

6. A terminal, characterized in that: The terminal includes: a memory and a processor, wherein the memory stores an application processing program, and when the application processing program is executed by the processor, the steps of the radar parameter optimization method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that: The storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute the radar parameter optimization method according to any one of claims 1 to 4.

Images