Target area control method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to a target area control method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring detection information of each target object in a target space; identifying current track information of each target object according to the detection information; based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object, predicting a target area where each target object will appear in the next step; and if the target area meets a triggering condition in a preset automation scheme, controlling target equipment to execute the preset automation scheme. According to the invention, the problem of untimely control caused by radar signal lag is overcome; and when the target area meets the triggering condition in the preset automation scheme, the target equipment is controlled to execute the preset automation scheme, so that the equipment in the target area is controlled more timely, conveniently and intelligently.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a control method, device, electronic device, and storage medium for a target area. Background Art

[0002] With the development of Internet of Things technology, intelligent control is widely applied in various scenarios. For example, a radar control system can be deployed in various scenarios and spaces to achieve intelligent control of devices in various scenarios and spaces.

[0003] However, due to the uncertainty of radar detection, the detection result is prone to lag, making the detection result inaccurate, and further resulting in inaccurate and non-intelligent control of the device. Summary of the Invention

[0004] Based on the above technical problems, the present invention aims to provide a control method, device, electronic device, and storage medium for a target area to solve at least one of the above technical problems.

[0005] The first aspect of this application provides a control method for a target area, the method comprising:

[0006] Obtaining detection information of each target object in a target space;

[0007] Identifying the current trajectory information of each target object according to the detection information;

[0008] Predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object;

[0009] If the target area meets the trigger condition in a preset automation scheme, controlling a target device to execute the preset automation scheme.

[0010] The second aspect of this application provides a control device for a target area, the device comprising:

[0011] An obtaining module, configured to obtain detection information of each target object in a target space;

[0012] An identifying module, configured to identify the current trajectory information of each target object according to the detection information;

[0013] A predicting module, configured to predict the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and the current trajectory information of each target object;

[0014] A control module, configured to control a target device to execute the preset automation solution when the target area meets the trigger condition in the preset automation solution.

[0015] In some embodiments of the present application, when the recognition module realizes identifying the current trajectory information of each target object according to the detection information, the following steps are specifically executed:

[0016] Extract consecutive frame point cloud data from the detection information;

[0017] Perform noise reduction processing on the point cloud data, and group the noise-reduced point cloud data according to each target object; wherein, each group of point cloud data represents the point cloud data of one target object;

[0018] For each group of point cloud data, track each target object to obtain the current trajectory information of each target object.

[0019] In some embodiments of the present application, when the prediction module realizes predicting the target area where each target object will appear in the next step based on the historical trajectory information and / or the current trajectory information corresponding to each target object, the following steps are specifically executed:

[0020] Determine the moving speed and moving direction of each target object according to the historical trajectory information and the current trajectory information corresponding to each target object;

[0021] Predict the target area where each target object will appear in the next step based on the moving speed and moving direction of each target object.

[0022] In some embodiments of the present application, when the prediction module realizes predicting the target area where each target object will appear in the next step based on the historical trajectory information and / or the current trajectory information corresponding to each target object, the following steps are specifically executed:

[0023] Associate the current trajectory information corresponding to each target object with the historical trajectory information corresponding to each target object;

[0024] After each target object is correctly associated with the corresponding historical trajectory information, estimate the motion mode of each target object;

[0025] Predict the target area where each target object will appear in the next step based on the motion mode of each target object.

[0026] In some embodiments of the present application, predicting the target area where each target object will appear in the next step includes:

[0027] Predict the appearance probabilities of each of the target objects corresponding to each detection area in the target space based on the motion patterns of the target objects;

[0028] Based on the appearance probabilities of the detection areas, determine the target area where the target object will appear in the next step from the detection areas.

[0029] In some embodiments of the present application, the control device for the target area further includes a response module, and the response module is configured to display a regional configuration page for the target space in response to a trigger operation on the regional configuration entry before obtaining the detection information of each target object in the target space;

[0030] Obtain the custom area selected on the regional configuration page, and configure the custom area as the detection area in the target space;

[0031] In response to the entry area selected on the regional configuration page, determine the entry area within the detection area.

[0032] In some embodiments of the present application, the target space includes multiple sub-spaces; the control device for the target area of the method further performs the following steps:

[0033] In response to the configuration operation for the entry area of each sub-space on the regional configuration page, configure the corresponding entry area for each sub-space;

[0034] When it is predicted that the target area where the target object will appear in the next step is the entry area of the sub-space in the target space, if the entry area meets the trigger condition in the corresponding automation scheme, control the target device in the automation scheme to perform the corresponding target action.

[0035] A third aspect of the present application provides an electronic device, including a memory and a processor. When a computer program stored in the memory is executed by the processor, the processor is caused to execute the methods described in the embodiments of the present application.

[0036] A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the methods described in the embodiments of the present application are implemented.

[0037] A fifth aspect of the present application provides a computer program product, where the computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; a processor of the computer device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, the steps in the control method for the target area in the embodiments of the present application are implemented.

[0038] The technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0039] The present application obtains the detection information of each target object in the target space, identifies the current trajectory information of each target object according to the detection information, and predicts the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object. If the target area meets the trigger condition in the preset automation solution, the target device is controlled to execute the preset automation solution. In this way, by accurately obtaining in advance the target area where each target object will appear in the next step, the problem of untimely control caused by the lag of radar signals is overcome. When the target area meets the trigger condition in the preset automation solution, controlling the target device to execute the preset automation solution makes the control of the device in the target area more timely, convenient and intelligent. In short, through accurate target tracking and triggering of automation solutions, the present application can improve the performance and user experience of various applications.

[0040] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0042] Figure 1 is a schematic diagram of the implementation environment involved in the control method of the target area of the present application;

[0043] Figure 2 is a schematic diagram of the steps of a control method for a target area in an exemplary embodiment of the present application;

[0044] Figure 3 is a schematic diagram of the steps of two methods for predicting the target area where each target object will appear in the next step in an exemplary embodiment of the present application;

[0045] Figure 4 is a schematic diagram of the radar detection area configuration in an exemplary embodiment of the present application;

[0046] Figure 5 is a schematic diagram of the structure of a control device for a target area in an exemplary embodiment of the present application;

[0047] Figure 6 is a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of the present application. Detailed implementation manners

[0048] The following further describes the present application in detail with reference to the accompanying drawings and embodiments. It can be understood that the embodiments described herein are only used to explain the related invention, rather than limiting the invention. Additionally, it should be noted that for the convenience of description, only the parts related to the relevant invention are shown in the drawings.

[0049] As a component in the control system, radars are commonly arranged in various scenarios and spaces. The accuracy of radar signals facilitates the precision of various scenarios and spaces. However, the uncertainty of radar detection requires the control system to obtain effective detection information through multiple frames of data, resulting in a lag in the detection information of the detection area in the space. That is, even if the user configures an automated control scheme for the detection area, the detection area cannot be controlled in a timely manner. Moreover, since the target cannot be accurately detected in the target space, the devices in the target space cannot be controlled to perform corresponding operations in a timely manner. Generally speaking, the control of devices in the space in the prior art is not convenient, not timely, and not intelligent.

[0050] Therefore, in some embodiments of the present application, a control method for a target area is provided. To better understand the control method, device, electronic device, and storage medium for the target area provided by the embodiments of the present application, the implementation environment applicable to the embodiments of the present application will be described first. The following embodiments of the present application can be applied to the system as shown Figure 1 as follows, Figure 1 An intelligent control system is provided, which includes an intelligent device 110, a network device 120 (specifically, it can be a gateway, a router, etc.) communicatively connected to the intelligent device 110, a cloud server 130, and a user terminal 140. Among them, the intelligent device 110 can be an intelligent curtain, an intelligent door lock, an intelligent lamp, etc., which are not limited herein.

[0051] The intelligent device 110 establishes a network connection with the user terminal 140 or the cloud server 130 through the network device 120. In one implementation manner, the network device 120 and the user terminal 140 can establish a network connection through a local area network or a wide area network path. Through this network connection, the intelligent device connected to the network device can be controlled by the user through the terminal to perform corresponding actions.

[0052] Among them, the user terminal can be a smart phone, a laptop computer, a personal computer, a tablet computer, an intelligent control panel, or other electronic devices that can implement a network connection, which are not limited herein. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0053] Specifically, detection information of each target object in the target space is obtained through radar, and then this detection information is uploaded to the cloud server through a network device. The cloud server identifies the current trajectory information of each target object based on the detection information, and predicts the target area where each target object will appear in the next step, such as a bedroom. If the target area, such as a bedroom, meets the trigger condition in the preset automation plan, the cloud server issues an instruction to send it to an intelligent device, such as the intelligent door lock in the bedroom, through the network device to execute the preset automation plan, such as controlling the intelligent door lock to open the bedroom door. Among them, the specific preset automation plan can be set by the user terminal. This makes the control of devices in the target area more timely, convenient, and intelligent.

[0054] In one embodiment, as Figure 2 shown, a control method for a target area is shown. Taking this method applied to an electronic device as an example for illustration, the electronic device may specifically be Figure 1 the intelligent device 110, network device 120, cloud server 130, user terminal 140, etc. in

[0055] S1. Obtain detection information of each target object in the target space.

[0056] The target space refers to the range of operation and control of the intelligent device, such as a specific room or the entire house. In this application, it mainly refers to the entire house, that is, the entire house that may include a living room, bedroom, kitchen, study, bathroom, etc. A target object refers to an object or entity that needs to be detected and identified in the target space, such as a person or a pet.

[0057] It can be understood that the detection information refers to data about the target object obtained through sensors, cameras, or other sensing devices. In this application, the detection information is mainly obtained through radar. Among them, the radar is used to detect and sense whether there is a target object within its detection range, and the radar can be installed at any position in the target space according to requirements and reasonably arranged.

[0058] Specifically, the detection information of each target object in the target space can be obtained through a radar device.

[0059] In one embodiment, the detection information of each target object can be obtained by using a lidar. Considering that ordinary radars use radio waves, usually microwaves or millimeter waves, to detect targets. It sends radio wave pulses and then measures the time it takes for these pulses to be reflected back by the target to calculate the distance, but its resolution is relatively low. In contrast, lidars use visible light or infrared laser beams to measure the distance to the target with high precision. It sends short pulses of laser beams and calculates the distance by measuring the time it takes for the beam to travel from the lidar to the target and back. Lidars usually have a very high spatial resolution and can provide very detailed environmental perception data.

[0060] Many types of detection information can be obtained through a lidar, such as distance information, angle information, height information, speed information, emission intensity information, 3D point cloud data, and so on. Among them, the distance information is the distance between the target object and the lidar. The distance information provides the accuracy of the target position and calculates the distance by measuring the time it takes for the laser beam to travel from the lidar to the target and back. The angle information represents the angle of the target object, that is, the position of the target object relative to the horizontal and vertical directions of the lidar. The angle information helps to determine the direction and position of the target. The height information refers to the height information in the vertical direction, which is very useful for detecting multi-level target objects. The speed information represents the speed of the target object, and the speed information is conducive to real-time monitoring of the motion state of the target object.

[0061] In addition to obtaining distance information, angle information, height information, and speed information, emission intensity information and point cloud data (referring to 3D point cloud data) can also be obtained. The emission intensity information refers to the intensity of the laser beam reflected by the target object. The point cloud data is generated by combining distance, angle, and height information. This is a set of discrete points, and each point represents a point in space, thus providing the three-dimensional shape and position information of the target object. Here, due to the adoption of the lidar, the problem of delayed detection is overcome to a certain extent, and the point cloud data generated by the lidar prepares for the subsequent operations of this application.

[0062] S2. Identify the current trajectory information of each of the target objects according to the detection information.

[0063] The current trajectory information refers to the motion trajectory data of the target object at the current moment, such as data on the motion state of the target object including its position, speed, acceleration, moving direction, and so on.

[0064] After the electronic device obtains the detection information, it analyzes and processes the detection information. For example, specifically, it can perform a series of processes such as target recognition and target trajectory tracking on the detection information, so as to identify the current trajectory information of each target object from these detection information, which helps with the subsequent analysis of the motion patterns of each target object.

[0065] S3. Based on the historical trajectory information corresponding to each of the target objects and / or the current trajectory information of each of the target objects, predict the target areas where each of the target objects will appear in the next step.

[0066] Among them, the historical trajectory information refers to the motion trajectory data of the target object in the past period of time, such as the past week, month, etc. The motion trajectory data may include motion state data such as the positions, speeds, accelerations, moving directions, etc. that the target object has passed through in the past period of time.

[0067] Specifically, the electronic device can predict the target areas where each target object will appear in the next step only based on the historical trajectory information corresponding to each target object; the electronic device can also predict the target areas where each target object will appear in the next step according to the current trajectory information corresponding to each target object. For example, if there is no historical trajectory information of each target object currently, the prediction can be made only based on the current trajectory information of each target object. Further, the electronic device can combine the historical trajectory information and the current trajectory information corresponding to each target object to predict the target areas where each target object will appear in the next step to improve the accuracy of the prediction.

[0068] By obtaining the historical trajectory information and the current trajectory information of each target object, the electronic device helps to analyze the motion patterns, frequently visited locations, activity paths, etc. of the target objects, and thus helps to predict the target areas where each target object will appear in the next step.

[0069] S4. If the target area meets the trigger condition in the preset automation plan, control the target device to execute the preset automation plan.

[0070] It can be understood that the automation plan can be a preset device control plan that automatically performs control under certain conditions. Among them, the automation plan includes a predetermined trigger condition and corresponding target actions. The automation plan here can be set by the user customarily.

[0071] After the electronic device predicts the target areas where each target object will appear in the next step, if there is a corresponding automation plan set for the target area, and when the target object appears in the target area, it meets the trigger condition in the preset automation plan, then control the target device to execute the target action in the automation plan.

[0072] For example, it can be set to turn on the intelligent lighting system in the entrance area for lighting when someone enters the entrance area; or start the temperature control system in the entrance area to ensure that the people entering are in a comfortable temperature environment. For another example, it can be set to control the sound system to automatically play personalized welcome music or greetings when someone enters the area where the sofa is located, etc. In this way, through precise target tracking and automated scenario triggering, the performance of various applications and the user experience can be improved.

[0073] In a possible implementation manner, the current trajectory information of each target object is identified according to the detection information, including steps S201 - S203.

[0074] S201. Extract consecutive frame point cloud data from the detection information.

[0075] The point cloud data extracted from the detection information reflects the spatial distribution of the detected target objects. Therefore, the detection information contains the target objects in each space, such as the target objects in spaces like the living room, bedroom, kitchen, study, bathroom, etc.

[0076] For each time frame, point cloud data is extracted to obtain consecutive frame point cloud data, which can ensure the continuity in time. That is, from one time frame to the next, the changes in the movement of the target objects can be obtained. This helps to capture the movement trajectories of the target objects, thus helping to understand the behaviors of the target objects and analyze the subsequent movement trends of the target objects, and further helping to predict the target areas where each target object will appear in the next step.

[0077] S202. Perform noise reduction processing on the point cloud data and group the noise-reduced point cloud data according to each target object; wherein, each group of point cloud data represents the point cloud data of a target object.

[0078] Specifically, when the electronic device performs noise reduction processing on the point cloud data, statistical filtering methods, Gaussian filtering methods, SOR (Statistical Outlier Removal) filtering methods, bilateral filtering methods, voxel filtering methods, normal vector filtering methods, etc. can be used. Statistical filtering methods include mean filtering and median filtering. These methods calculate the statistical information of the neighboring points around the point cloud, such as the average value or median value, to replace the coordinate value of each point, thereby reducing noise. The Gaussian filtering method uses a Gaussian kernel function to smooth the point cloud. The SOR filtering method is a statistics-based filtering method that compares the points in the point cloud with the surrounding points and excludes outliers. The bilateral filtering method is a non-linear filtering method that not only considers the spatial distance but also the similarity between the points in the point cloud. The voxel filtering method divides the point cloud data into voxels (cubes or small pieces within the cube), and then performs filtering based on the number of points within each voxel, which is useful for reducing the point cloud density and removing sparse noise points. The normal vector filtering method utilizes the normal vector information of the points in the point cloud to remove the points that are inconsistent with the normal vectors of the surrounding points, which is effective for removing spike noise and surface discontinuities.

[0079] In one embodiment, the point cloud data is divided into different groups, and each group represents a possible target object, that is, each set of point cloud data represents the point cloud data of a target object. Specifically, it can be achieved through a clustering algorithm (such as K-means clustering) or other grouping methods. Through noise reduction processing, unnecessary or irrelevant information in the point cloud data can be removed, thereby improving the accuracy of subsequent target recognition and tracking.

[0080] S203. For each set of point cloud data, track each target object to obtain the current trajectory information of each target object.

[0081] For each group, the formed point cloud data represents an independent target object. The point cloud data contains the spatial position information of the target object. For example, if the target object is a person and it is assumed to be divided into 5 groups, then each set of point cloud data corresponds to the current trajectory information of a person, and there are 5 people as target objects in total. Track the point cloud data of each target object and update the trajectory information of the target object in consecutive frames to reflect its motion state. Summarize the trajectory information of each target object to form their motion paths in the current time frame, which can provide real-time understanding of the target objects and lay a foundation for subsequent behavior analysis.

[0082] In a specific implementation manner, refer to Figure 3 , based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object, predict the target areas where each target object will appear in the next step, including steps S31 and S32.

[0083] S31. Determine the moving speed and moving direction of each target object based on the historical trajectory information and the current trajectory information corresponding to each target object.

[0084] Specifically, assume that a set of historical trajectory data of target objects is obtained. The trajectory of each target object consists of a series of coordinate points, where each coordinate point includes a timestamp, an x coordinate, and a y coordinate. This data should include the coordinate information for each time step, and data for multiple time steps is required to calculate the speed. Select a suitable time interval (Δt) to calculate the speed, which can be the time interval between two adjacent time steps in the historical trajectory. For each time step t, calculate the displacement of the target object within the time interval Δt. The speed is obtained by dividing the displacement by the time interval Δt, and the moving direction represents the deflection angle of the target object's motion direction relative to the x-axis, which can also be obtained through the arctangent function.

[0085] S32. Predict the target areas where each target object will appear in the next step based on the moving speed and moving direction of each target object.

[0086] The target area refers to the area where it is predicted that each target object will appear at the next time point from the current moment. In one embodiment, the current state of the target object includes the position (x, y coordinates), moving speed, and moving direction. Using the current position, speed, and direction information, calculate the position of the target object at the next time step by means of time stepping. This can be achieved through simple physical motion equations. For example: Next position = Current position + (Speed × Time step). If the target object is moving to the right, then at the next time step, its x coordinate will increase, thereby predicting the target areas where each target object will appear in the next step.

[0087] As Figure 3 shown, when predicting the target areas where each target object will appear in the next step based on the historical trajectory information and / or the current trajectory information corresponding to each target object, in addition to performing S31 - S32, steps S310 - S330 can also be selected.

[0088] S310. Associate the current trajectory information corresponding to each target object with the historical trajectory information corresponding to each target object.

[0089] When specifically associating, for each target object (for example, each of 5 people), use a target association algorithm to associate the current trajectory information with the historical trajectory information. This can be part of a multi-target tracking algorithm, such as the Kalman filter or data association algorithm.

[0090] In one embodiment, a preset association algorithm such as the Dynamic Time Warping (DTW) algorithm is used to calculate the similarity between the current trajectory information and the historical trajectory information corresponding to each target object. Trajectories with high similarity may belong to the same target object and exhibit similar motion patterns.

[0091] Specifically, the historical trajectory information and the current trajectory information can be represented as time series, where each point corresponds to a coordinate in space. Then, a distance matrix is constructed, which contains the distances between all pairs of points between the historical trajectory information and the current trajectory information. Next, the method of dynamic programming is used to calculate the optimal alignment path between the historical trajectory information and the current trajectory information. Finally, the sum of the distances between the corresponding points on the optimal alignment path is calculated as the similarity measure between the historical trajectory information and the current trajectory information. A smaller total distance indicates that the two trajectories are more similar in shape and trend. Moreover, based on the result of the similarity measure, a threshold can be set to determine whether two trajectories are similar enough. The association between the current trajectory information and the historical trajectory information corresponding to each target object helps to better estimate the motion patterns of each target object.

[0092] S320. After each target object is correctly associated with the corresponding historical trajectory information, estimate the motion patterns of each target object.

[0093] Once the current trajectory information and the historical trajectory information are successfully associated, this data can be used to estimate the motion pattern of each person. For example, by fitting a mathematical model, such as a linear model or a non-linear model, to estimate the next future behavior of each person. Based on the motion pattern of each person, motion prediction can be performed, such as linear motion or curvilinear motion, or using a random forest or a deep learning model. By simulating the motion of each person in the next step, the possible areas where each person may appear can be predicted.

[0094] S330. Based on the motion patterns of each target object, predict the target areas where each target object will appear in the next step.

[0095] After the electronic device estimates the motion patterns of each target object, it predicts the target areas where each target object will appear in the next step according to the motion patterns of each target object. By combining the motion patterns of each target object, the areas that the behavior of the target object may point to in the next step can be predicted, so that the target areas where each target object will appear in the next step can be predicted more accurately.

[0096] In a specific implementation manner, predicting the target areas where each of the target objects will appear in the next step based on the motion patterns of each of the target objects includes: predicting the appearance probabilities of each of the target objects corresponding to each detection area in the target space based on the motion patterns of each of the target objects; and determining the target areas where the target objects will appear in the next step from each of the detection areas based on the appearance probabilities of each of the detection areas.

[0097] In one embodiment, a preset conditional probability algorithm can be used to predict the appearance probabilities of each of the target objects corresponding to each detection area in the target space according to the motion patterns of each of the target objects. For example, the preset conditional probability algorithm model satisfies the Bayes formula, and the specific model expression can be as follows:

[0098]

[0099] where P refers to probability, B refers to the historical trajectory information corresponding to the target object and the current trajectory information of the target object, A i , A j represent different detection areas, i and j refer to subscripts, and their value ranges are the same, P(A i ) represents the reference probability. If i is equal to 0, then P(A0) refers to the first reference probability. If i is equal to 1, then P(A1) refers to the second reference probability. The reference probability is the appearance probability of each detection area.

[0100] Further, based on the appearance probabilities of each of the detection areas, determine the target areas where the target objects will appear in the next step from each of the detection areas.

[0101] Referring again to Figure 4 , assume that a person is sitting on a sofa and then walks northward. Based on the appearance probabilities of the bathroom entrance area and the kitchen entrance area, determine the target areas where the target object will appear in the next step from the bathroom entrance area and the kitchen entrance area. Assume that the appearance probability of the bathroom entrance area is 0.51, while the appearance probability of the kitchen entrance area is 0.67. Then it can be determined that the kitchen entrance area is the target area, that is, the automation scheme configured by the user in the kitchen entrance area can be executed in a timely manner, such as automatically opening the kitchen door and lights. Moreover, the posterior probability of Bayesian estimation allows the user to set the threshold by himself, and allows the user to set the sensitivity of radar prediction by himself. By accurately obtaining in advance the target areas where each of the target objects will appear in the next step, the problem of untimely control caused by radar signal lag is overcome, and when the target area meets the trigger condition in the preset automation scheme, the target device is controlled to execute the preset automation scheme, making the control of the devices in the target area more timely, convenient and intelligent.

[0102] As a transformable implementation, before obtaining the detection information of each target object in the target space, it further includes steps S3301 - S3303.

[0103] S3301. In response to a trigger operation for the area configuration entry, display an area configuration page for the target space.

[0104] In one embodiment, the user performs certain actions, such as clicking a specific button, entering a specific command, or using a specific gesture, to indicate the desire to configure the entry of a certain area. In response, an area configuration page dedicated to configuring the target space will be displayed. This page may include a graphical interface where users can make various settings. On the area configuration page, users can select the target space they wish to configure. The target space here includes multiple sub - spaces, and users can select and configure the entry area among them.

[0105] S3302. Obtain the custom area selected on the area configuration page, and configure the custom area as the detection area in the target space.

[0106] In one embodiment, the user uses tools or interface elements on the area configuration page to select a specific area they want to be the detection area. This can be a selection process completed by drawing, dragging, or other visual means. The system captures or records the detailed information of the custom area selected by the user, such as coordinates, shape, or other necessary data, and applies the captured custom area information to the target space, marking the area as the detection area in the target space for easy detection of the selected custom area.

[0107] S3303. In response to the entry area selected on the area configuration page, determine the entry area within the detection area.

[0108] Specifically, referring again to Figure 4 , the user marks the detection area of the lidar through the UI interface. The space corresponding to the detection area includes multiple sub - spaces, such as Figure 4 shown, the sub - spaces such as the sofa, the entrance area of the bathroom, the entrance area of the kitchen, etc., and mark information such as somewhere being the sofa, the entrance area of the bathroom, the entrance area of the kitchen, etc. In this way, the user associates the user - defined detection area with each sub - space in the target space through the marking operation, that is, determines and marks the entry area of each sub - space within the detection area. So that when a target object just enters a certain entry area later, detection data can be obtained, and subsequent timely and intelligent control can be realized.

[0109] In some embodiments, the method further includes: in response to a configuration operation for the entrance area of each subspace in the area configuration page, configuring a corresponding entrance area for each subspace; when it is predicted that the target area where the target object will appear next is the entrance area of a subspace under the target space, if the entrance area meets the trigger condition in the corresponding automation scheme, controlling the target device in the automation scheme to perform the corresponding target action.

[0110] When it is predicted that the target object is about to enter the entrance area of a certain subspace, the system checks whether the entrance area meets the trigger condition defined in the corresponding automation scheme. If the entrance area meets the trigger condition in the corresponding automation scheme, the target device in the automation scheme is controlled to perform the corresponding target action. For example: once it is detected and recognized that there is someone in the entrance area of the bathroom, the bathroom door will be automatically opened; once it is detected and recognized that someone passes through the aisle, the aisle light will be turned on. This makes the automation scenarios triggered by the radar faster, more timely, and provides a good user experience.

[0111] This application also provides an application scenario that applies the above-mentioned control method for the target area. Specifically, this application scenario is a smart home, which includes multiple spaces, and different spaces are further divided into subspaces. For example, in the living room, there are entrance areas for the bedroom, kitchen, bathroom, etc. The application of the control method for the target area in this application scenario is as follows:

[0112] Suppose it is predicted that a target object, such as a person, is moving in the living room. Taking this person as a target object, when the target area where the target object will appear next is the entrance area of the bedroom, the bedroom door can be automatically opened.

[0113] Specifically, first, obtain the detection information of the target object in the target space, extract the continuous frame point cloud data from the detection information, perform noise reduction processing on the point cloud data, group the noise-reduced point cloud data of the target object, track the group of data, and obtain the current trajectory information of the target object. Then, associate the current trajectory information corresponding to the target object with its corresponding historical trajectory information. After correct association, estimate the motion pattern of the target object, and predict the target area where the target object will appear next based on the motion pattern of the target object.

[0114] Finally, in response to the configuration operation for the entrance area of each subspace in the target space in the area configuration page, configure a corresponding entrance area for each subspace. When it is predicted that the target area where the target object will appear next is the entrance area of a subspace under the target space, if the entrance area meets the trigger condition in the corresponding automation scheme, control the target device in the automation scheme to perform the corresponding target action.

[0115] For example, according to the historical trajectory information of the target object, the probability that the target object has stayed on the sofa and then goes to the kitchen entrance area is 20%, and the probability of going to the bathroom entrance area is 80%. Now, combining the current trajectory information of the target object, such as the target object is currently sitting on the sofa, and predicting the target area where the target object will appear next according to its movement pattern, then the automation solution can be triggered when the target object enters the kitchen entrance area, and the target device in the kitchen can be controlled to perform the corresponding target action, such as controlling the kitchen light to turn on. It can be seen that in the application scenario of smart home, the control method of the target area makes the control of the devices in the target area more timely, more convenient and more intelligent.

[0116] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application.

[0117] In some embodiments of the present application, a control device for a target area is also provided, which executes the control method of the target area described in each embodiment, such as Figure 5 As shown, the device includes:

[0118] An acquisition module 501, configured to acquire detection information of each target object in the target space;

[0119] An identification module 502, configured to identify the current trajectory information of each target object according to the detection information;

[0120] A prediction module 503, configured to predict the target area where each target object will appear next based on the historical trajectory information corresponding to each target object and the current trajectory information of each target object;

[0121] A control module 504, configured to control the target device to execute the preset automation solution when the target area meets the trigger condition in the preset automation solution.

[0122] In a specific implementation manner, when the identification module realizes identifying the current trajectory information of each target object according to the detection information, it specifically performs the following steps: extracting continuous frame point cloud data from the detection information; performing noise reduction processing on the point cloud data, and grouping the noise-reduced point cloud data according to each target object; where each group of point cloud data represents the point cloud data of a target object; for each group of point cloud data, tracking each target object to obtain the current trajectory information of each target object.

[0123] In a specific implementation manner, when the prediction module predicts the target areas where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object, the following steps are specifically executed: Determine the moving speed and moving direction of each target object according to the historical trajectory information and the current trajectory information corresponding to each target object; Predict the target areas where each target object will appear in the next step based on the moving speed and moving direction of each target object.

[0124] In a specific implementation manner, when the prediction module predicts the target areas where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object, the following steps are specifically executed: Associate the current trajectory information corresponding to each target object with the historical trajectory information corresponding to each target object; After each target object is correctly associated with the corresponding historical trajectory information, estimate the motion pattern of each target object; Predict the target areas where each target object will appear in the next step based on the motion pattern of each target object.

[0125] In a specific implementation manner, predicting the target areas where each target object will appear in the next step includes: Predicting the appearance probabilities of each target object corresponding to each detection area in the target space based on the motion pattern of each target object; Determining the target areas where the target objects will appear in the next step from each detection area based on the appearance probabilities of each detection area.

[0126] In a specific implementation manner, the control device of the target area further includes a response module. The response module is configured to, before obtaining the detection information of each target object in the target space, in response to a trigger operation for the area configuration entry, display a region configuration page for the target space; Obtain the custom region selected on the region configuration page, and configure the custom region as the detection area in the target space; In response to the entry area selected on the region configuration page, determine the entry area within the detection area.

[0127] In another specific implementation manner, the target space includes multiple sub-spaces; The control device of the method target area further executes the following steps: In response to the configuration operation for the entry area of each sub-space on the region configuration page, configure the corresponding entry area for each sub-space; When it is predicted that the target area where the target object will appear in the next step is the entry area of the sub-space in the target space, if the entry area meets the trigger condition in the corresponding automation scheme, control the target device in the automation scheme to execute the corresponding target action.

[0128] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application.

[0129] Please refer to the followingFigure 6 , which is a schematic diagram of an electronic device provided by some embodiments of the present application. As Figure 6 shown, the electronic device 2 includes: a processor 200, a memory 201, a bus 202, and a communication interface 203. The processor 200, the communication interface 203, and the memory 201 are connected through the bus 202. A computer program that can run on the processor 200 is stored in the memory 201. When the processor 200 runs the computer program, it executes a control method for a target area in any one of the embodiments of the present application. The method includes: obtaining detection information of each target object in the target space; identifying the current trajectory information of each target object according to the detection information; predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object; and if the target area meets the trigger condition in the preset automation scheme, controlling the target device to execute the preset automation scheme.

[0130] Among them, the memory 201 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 203 (which can be wired or wireless), a communication connection is established between this system network element and at least one other network element, and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0131] The bus 202 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 201 is used to store a program. After receiving an execution instruction, the processor 200 executes the program. The control method for the target area disclosed in any one of the embodiments of the present application described above can be applied to the processor 200 or implemented by the processor 200.

[0132] The processor 200 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 200 or the instructions in the form of software. The above-mentioned processor 200 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and combines its hardware to complete the steps of the control method for the target area. The steps include: obtaining the detection information of each target object in the target space; identifying the current trajectory information of each target object according to the detection information; predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object; if the target area meets the trigger condition in the preset automation scheme, then controlling the target device to execute the preset automation scheme.

[0133] The embodiment of the present application also provides a computer-readable storage medium corresponding to the control method for the target area provided in the foregoing embodiment. A computer program is stored thereon, and when the computer program is run by a processor, it will execute the control method for the target area provided in any of the foregoing embodiments. Moreover, examples of the computer-readable storage medium may include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here one by one.

[0134] In addition, the embodiment of the present application also provides a computer program product, including a computer program, which implements the control method for the target area in any of the foregoing embodiments when executed by a processor.

[0135] Those skilled in the art can understand that the various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation device according to the embodiments of the present application.

[0136] As mentioned above, only the preferred specific embodiments of the present application are described, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the technical field of the present application within the technical scope disclosed by the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method for a target area, characterized in that, The method includes: Obtaining detection information of each target object in the target space; Identifying the current trajectory information of each target object according to the detection information; Predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object; If the target area meets the trigger condition in the preset automation scheme, controlling the target device to execute the preset automation scheme.

2. The control method for a target area according to claim 1, characterized in that, The identifying the current trajectory information of each target object according to the detection information includes: Extracting continuous frame point cloud data from the detection information; Performing noise reduction processing on the point cloud data, and grouping the noise-reduced point cloud data according to each target object; wherein, each group of point cloud data represents the point cloud data of one target object; For each group of point cloud data, tracking each target object to obtain the current trajectory information of each target object.

3. The control method for a target area according to claim 1, characterized in that, The predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object includes: Determining the moving speed and moving direction of each target object according to the historical trajectory information and the current trajectory information corresponding to each target object; Predicting the target area where each target object will appear in the next step based on the moving speed and moving direction of each target object.

4. The control method for a target area according to claim 1, characterized in that, The predicting the target area where each target object will appear in the next step based on the historical trajectory information corresponding to each target object and / or the current trajectory information of each target object includes: Associating the current trajectory information corresponding to each target object with the historical trajectory information corresponding to each target object; After each target object is correctly associated with the corresponding historical trajectory information, estimating the motion mode of each target object; Predicting the target area where each target object will appear in the next step based on the motion mode of each target object.

5. The control method for a target area according to claim 4, characterized in that, The predicting the target area where each target object will appear in the next step based on the motion mode of each target object includes: Predicting the appearance probability of each target object corresponding to each detection area in the target space based on the motion mode of each target object; Determining the target area where the target object will appear in the next step from each detection area based on the appearance probability of each detection area.

6. The control method for a target area according to claim 1, characterized in that, Before obtaining the detection information of each target object in the target space, it further includes: Responding to a trigger operation for the area configuration entry, and displaying an area configuration page for the target space; Obtaining the custom area selected on the area configuration page, and configuring the custom area as the detection area in the target space; Responding to the entry area selected on the area configuration page, and determining the entry area within the detection area.

7. The control method for a target area according to claim 6, characterized in that, The target space includes multiple sub-spaces; the method further includes: Responding to the configuration operation for the entry area of each sub-space on the area configuration page, and configuring the corresponding entry area for each sub-space; When it is predicted that the target area where the target object will appear next is the entrance area of the subspace in the target space, if the entrance area meets the trigger condition in the corresponding automation scheme, the target device in the automation scheme is controlled to perform the corresponding target action.

8. A control device for a target area, characterized in that, The device includes: An acquisition module, configured to acquire detection information of each target object in the target space; An identification module, configured to identify the current trajectory information of each target object according to the detection information; A prediction module, configured to predict the target area where each target object will appear next based on the historical trajectory information corresponding to each target object and the current trajectory information of each target object; A control module, configured to control the target device to execute the preset automation scheme when the target area meets the trigger condition in the preset automation scheme.

9. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and when the computer program is executed by a processor, the processor is caused to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1-7 is implemented.

Images