Room layout prediction methods, devices, air conditioning equipment and storage media
By acquiring the trajectory data of moving objects collected by radar, setting a default height and updating the height, the problem of low room layout prediction accuracy caused by moving objects not being on a fixed horizontal plane is solved, and higher accuracy room layout prediction is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GD MIDEA AIR CONDITIONING EQUIP CO LTD
- Filing Date
- 2024-11-25
- Publication Date
- 2026-05-26
AI Technical Summary
Existing technologies for indoor layout recognition suffer from low accuracy in predicting room layouts because moving objects do not move on a fixed horizontal plane.
By acquiring trajectory data of moving objects collected by radar, setting a default height, and making predictions based on the trajectory data, the height of the moving objects is updated, and the room layout is iteratively adjusted until high accuracy is achieved.
It improves the accuracy of room layout prediction and ensures the accuracy of layout prediction.
Smart Images
Figure CN122085265A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of room layout prediction technology, and in particular to room layout prediction methods, devices, air conditioning equipment and storage media. Background Technology
[0002] A single-transmitter, dual-receiver radar can identify the distance of a moving object relative to the radar and its angle along a fixed horizontal axis. When used for indoor layout identification, this angle is generally horizontal. The system assumes the moving object and the radar are installed on the same horizontal plane, or a fixed height difference is set to calculate the moving object's coordinates within the building's floor plan. Based on a time-series series of moving object coordinates, the building layout can be inferred.
[0003] In actual prediction, moving objects do not always move on a fixed horizontal plane. The moving object will have corresponding height differences at different positions, which will cause a large error when calculating the plane coordinates, thus affecting the accuracy of the room layout prediction. Summary of the Invention
[0004] The main objective of this application is to provide a method, apparatus, air conditioning equipment, and storage medium for predicting room layout, aiming to solve the technical problem of low accuracy in room layout prediction.
[0005] To achieve the above objectives, this application proposes a room layout prediction method, which includes:
[0006] Acquire the trajectory data of the moving object collected by the radar, and set the height of the moving object in the trajectory data to the default height;
[0007] The trajectory data of the moving object is predicted to obtain the room layout, which includes the layout classification of each location in the room;
[0008] Based on the layout classification, determine the target height of the moving object in each moving object trajectory data, and update the moving object trajectory data.
[0009] Based on the updated trajectory data of the moving object, an updated room layout is obtained through prediction.
[0010] In one embodiment, the step of predicting the trajectory data of the moving object to obtain the room layout includes:
[0011] The distance and angle of the moving object relative to the radar are obtained based on the trajectory data of the moving object.
[0012] The room layout is predicted based on the distance, the angle, and the default height.
[0013] In one embodiment, the step of predicting the room layout based on the distance, the angle, and the default height includes:
[0014] Obtain radar altitude;
[0015] The planar coordinates of the moving object within the room are calculated based on the radar height, the distance, the angle, and the default height.
[0016] The room layout is obtained by using a preset inference strategy based on the plane coordinates.
[0017] In one embodiment, the step of predicting the room layout based on the planar coordinates using a preset inference strategy includes:
[0018] The temporal two-dimensional trajectory of a moving object within a preset time period is determined by a preset inference strategy and the plane coordinates.
[0019] Convert the room into a grid map with radar as the origin;
[0020] The grid diagram is classified according to the time-series two-dimensional trajectory to obtain the layout classification of each location in the room.
[0021] In one embodiment, after the step of predicting the updated room layout based on the updated trajectory data of the moving object, the method further includes:
[0022] Calculate the similarity between the updated room layout and the room layout before the update;
[0023] When the calculated similarity is greater than the preset similarity threshold, the updated room layout will be used as the target room layout.
[0024] When the calculated similarity is less than or equal to a preset similarity threshold, return to the step of predicting the trajectory data of the moving object to obtain the room layout.
[0025] In one embodiment, the step of calculating the similarity between the updated room layout and the original room layout includes:
[0026] Get the first layout category of each position in the room in the updated room layout and the second layout category of each position in the room in the original room layout;
[0027] Calculate the similarity between the first layout category and the second layout category.
[0028] In one embodiment, the step of calculating the similarity between the first layout classification and the second layout classification in the rooms includes:
[0029] Based on the first layout classification and the second layout classification, determine objects of equal category;
[0030] Obtain the number of grid cells for objects of the same category;
[0031] The similarity between the first layout classification and the second layout classification is obtained based on the ratio between the number of grid cells and the total number of grid cells.
[0032] Furthermore, to achieve the above objectives, this application also proposes a room layout prediction device, the room layout prediction device comprising:
[0033] The acquisition module is used to acquire the trajectory data of a moving object collected by the radar, and set the height of the moving object in the trajectory data to a default height;
[0034] The prediction module is used to predict the trajectory data of the moving object to obtain the room layout, which includes the layout classification of each location in the room.
[0035] The determination module is used to determine the target height of the moving object in each moving object trajectory data according to the layout classification, and update the moving object trajectory data;
[0036] The prediction module is also used to make predictions based on the updated trajectory data of the moving object to obtain an updated room layout.
[0037] In addition, to achieve the above objectives, this application also proposes an air conditioning device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the room layout prediction method as described above.
[0038] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the room layout prediction method described above.
[0039] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the room layout prediction method described above.
[0040] This application proposes one or more technical solutions that acquire moving object trajectory data collected by radar and set the height of the moving object in the trajectory data as a default height; predict the room layout based on the moving object trajectory data, the room layout including layout classification for each location in the room; determine the target height of the moving object in each trajectory data based on the layout classification, and update the moving object trajectory data; and predict the updated room layout based on the updated moving object trajectory data. By first predicting the room layout using the default height and continuously updating the default height, the activity height of the moving object is obtained that is closer to the actual value, thereby obtaining a more accurate house layout and improving the accuracy of house layout prediction. Attached Figure Description
[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 This is a flowchart illustrating an embodiment of the room layout prediction method of this application.
[0044] Figure 2 This diagram illustrates the difference between the default height prediction method and the room layout prediction method in this embodiment of the application.
[0045] Figure 3 This is a flowchart illustrating Embodiment 2 of the room layout prediction method of this application;
[0046] Figure 4 This is a schematic diagram of the predicted room layout in one embodiment of the room layout prediction method of this application;
[0047] Figure 5 This is a flowchart illustrating Embodiment 3 of the room layout prediction method of this application;
[0048] Figure 6 This is a simplified flowchart of an embodiment of the room layout prediction method of this application;
[0049] Figure 7 This is a schematic diagram of the module structure of the room layout prediction device according to an embodiment of this application;
[0050] Figure 8This is a schematic diagram of the device structure of the hardware operating environment involved in the room layout prediction method in the embodiments of this application.
[0051] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0052] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0053] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0054] The main solution of this application embodiment is as follows: acquire the trajectory data of a moving object collected by radar, and set the height of the moving object in the trajectory data as a default height; predict the trajectory data of the moving object to obtain a room layout, wherein the room layout includes a layout classification for each location in the room; determine the target height of the moving object in each trajectory data according to the layout classification, and update the trajectory data of the moving object; predict the updated room layout based on the updated trajectory data of the moving object.
[0055] Current technology assumes that the moving object and the radar are installed on the same horizontal plane, or sets a fixed height difference, to calculate the coordinates of the moving object within the building's floor plan. Based on a series of moving coordinates over time, the building's layout can be inferred. However, the moving object does not always move on a fixed horizontal plane; therefore, there is a vertical angle between the moving object and the radar. For example, when the radar is installed high in the room, the center of movement when a person walks is generally at their head, roughly corresponding to their height. But when a person lies in bed, the center of movement is approximately at the bed's height. This height difference leads to significant errors in calculating the planar coordinates, thus affecting the accuracy of the room layout prediction.
[0056] This application provides a solution for using a radar trajectory height adaptive algorithm in indoor layout prediction, thereby improving the accuracy of house layout prediction.
[0057] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or air conditioning device capable of performing the above functions. The following description uses an air conditioning device as an example to illustrate this embodiment and the subsequent embodiments.
[0058] Based on this, embodiments of this application provide a room layout prediction method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the room layout prediction method of this application.
[0059] In this embodiment, the room layout prediction method includes steps S10 to S40:
[0060] Step S10: Obtain the trajectory data of the moving object collected by the radar, and set the height of the moving object in the trajectory data to the default height.
[0061] It should be noted that when predicting room layout, radar can be deployed in advance within the room to be predicted. The radar can be placed on a wall of the house, such as any one of the four walls. After the radar is deployed, its coordinates can be recorded as (0, 0, Z). radar ).
[0062] The moving object trajectory data includes information such as the position, angle, and height of the moving object relative to the radar within the room. It also includes the time point t when the radar detected the moving object's position.
[0063] In practice, radar can be used to collect trajectory data of moving objects relative to the radar.
[0064] It should be noted that when predicting the room layout, since the height of the moving object is unknown, the height of the moving object can be set to a default height, such as 160cm or 165cm. This embodiment does not impose any restrictions on this.
[0065] Step S20: Predict the trajectory data of the moving object to obtain the room layout, which includes the layout classification of each location in the room.
[0066] It is understandable that after collecting the trajectory data of moving objects, the room layout can be inferred based on certain prediction rules or models. The room layout includes the layout classification of each location in the room, such as (x0, y0, bed), that is, the bed is located at (x0, y0) in the room.
[0067] It should be noted that the room layout is an initial room layout predicted based on the default height, and may not be accurate. Therefore, the default height can be updated based on the obtained initial room layout.
[0068] Step S30: Based on the layout classification, determine the target height of the moving object in each moving object trajectory data, and update the moving object trajectory data.
[0069] In practice, after determining the initial layout classification, the activity height of the trajectory point in different categories under the current room layout can be calculated. For example, if the coordinates of the trajectory point belong to the bed, the activity height is about 50cm. If it is next to the desk, the activity height is about 120cm. When walking, the activity height is about the height of a human body. Thus, the height information of all trajectory points can be reassigned to obtain the target height z1. The target height is then updated to the trajectory data of the moving object, thus completing the update of the trajectory data of the moving object.
[0070] Step S40: Based on the updated trajectory data of the moving object, make a prediction to obtain the updated room layout.
[0071] In practice, the room layout can be predicted again based on the updated trajectory data of the moving objects, thus obtaining the updated room layout.
[0072] The updated room layout can be the final room layout or a room layout that is still not accurate enough. The updated room layout can be determined according to certain judgment rules to determine whether it needs to be updated again, so as to continuously iterate the prediction of the room layout until the most accurate room layout is obtained.
[0073] like Figure 2 As shown, Figure 2 This diagram illustrates the difference between the default height prediction method and the room layout prediction method in this embodiment. Using a known actual room layout, including the front and top views (blue area represents radar position), Step 1: Using a default height, e.g., 1.6m, the x and y coordinates of the moving object's trajectory point are at the red star position. Step 2: When the layout recognition in this embodiment identifies the trajectory point as being on a bed, the bed height is set to 0.6m, resulting in the moving object's trajectory point at the yellow star position. It's clear that there's a certain deviation between using the default height and the prediction method. When predicting the room layout, Step 1: Calculating the trajectory point and predicting the room layout using the default height results in a room length longer than the actual room length, and the bed position deviates from the actual position. Step 2: At the point predicted as a bed in Step 1, the moving object's trajectory point is updated using the bed height, and the layout is re-predicted. The resulting room layout is closer to the actual layout. Different heights of the active point will lead to differences in the calculated x and y coordinates of the active point (e.g., ...). Figure 2 Using different activity point coordinates (yellow and red stars in the diagram), different house layouts can be predicted. The most accurate prediction of room layout is only when the actual height of the activity point is accurately predicted.
[0074] This embodiment provides a room layout prediction method. It acquires moving object trajectory data collected by radar and sets the height of the moving object in the trajectory data as a default height. The method then predicts the room layout based on the moving object trajectory data, whereby the room layout includes layout classifications for each location within the room. Based on these layout classifications, the method determines the target height of the moving object in each trajectory data point and updates the trajectory data. Finally, based on the updated trajectory data, it predicts the room layout to obtain an updated room layout. By first predicting the room layout using the default height and continuously updating the default height, the method obtains an activity height for the moving object that is closer to the actual value, thereby achieving a more accurate room layout and improving the prediction accuracy.
[0075] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S20 includes steps S201 to S202:
[0076] Step S201: Obtain the distance and angle of the moving object relative to the radar based on the moving object trajectory data.
[0077] It should be noted that after acquiring the trajectory of the moving object, the distance d and angle alpha of the moving object relative to the radar can be obtained.
[0078] Step S202: Predict the room layout based on the distance, the angle, and the default height.
[0079] In practice, the height of the moving object is set to a default height, and the trajectory point is denoted as (t, d, alpha, z0), where t is the time point at which the radar detects the position of the moving object, and z0 is the default height. The room layout is predicted using a certain prediction rule or a pre-trained model based on the distance d, angle alpha, and default height, thus obtaining the room layout at the default height.
[0080] In one feasible implementation, step S201 may include steps A21 to A23:
[0081] Step A21: Obtain radar altitude.
[0082] It should be noted that the radar altitude is z. radar The radar height can be set directly when installing the radar, such as 180cm or 200cm from the room floor. This embodiment does not impose any restrictions on this.
[0083] Step A22: Calculate the planar coordinates of the moving object in the room based on the radar height, the distance, the angle, and the default height.
[0084] In practical implementation, the polar coordinates of the trajectory points can be converted into the xy coordinates of the building plane relative to the radar using the conversion formula. Specifically, the planar coordinates of the moving object relative to the radar within the room can be calculated based on the radar height, distance, angle, and default height. The calculation process is shown in Equation 1 below:
[0085]
[0086] According to radar altitude z radar The distance d, the default height z0, and the angle α are used to calculate the planar coordinates (t, x, y, z).
[0087] Step A23: Based on the plane coordinates, a preset inference strategy is used to predict the room layout.
[0088] Understandably, the pre-defined inference strategy can be a certain inference rule or inference model. The inference rule can be set to statistically analyze the user's movement information within a corresponding time period to predict the category of the user's planar coordinate location. The inference model can be trained by pre-labeling the locations and categories within the room.
[0089] In one feasible implementation, step A23 may include: determining the temporal two-dimensional trajectory of a moving object within a preset time period using a preset inference strategy and the planar coordinates; converting the room into a grid map with the radar as the coordinate origin; and classifying the grid map according to the temporal two-dimensional trajectory to obtain the layout classification of each location in the room.
[0090] It should be understood that when the preset inference strategy is an inference rule, the temporal two-dimensional trajectory of a moving object within a certain time period can be statistically analyzed based on the inference rule and planar coordinates. For example, the temporal two-dimensional trajectory of a moving object during the night (0:00-6:00) can be analyzed, as well as the temporal two-dimensional trajectory of a moving object during the day (9:00-10:00). The room is then converted into a grid map with the radar as the coordinate origin. The grid map is then classified based on the statistically analyzed temporal two-dimensional trajectory, for example, (x0, y0, bed), (x1, y1, corridor). Since the statistical time is nighttime, it can be inferred that the user's temporal two-dimensional trajectory is likely the bed, and therefore the coordinates of the bed can be determined based on the user's coordinates at this location. Figure 4 As shown, Figure 4 The system generates a diagram of the predicted room layout, for example, a gray bed, an orange table, and a blue chair. This allows the objects in the room to be classified according to a grid, resulting in the category of each grid and its corresponding coordinates.
[0091] This embodiment obtains the distance and angle of the moving object relative to the radar based on the moving object trajectory data; and predicts the room layout based on the distance, angle, and default height. By quickly predicting the object categories within the room using moving object trajectory data, the room layout is obtained, improving prediction efficiency.
[0092] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5 After step S40, the room layout prediction method further includes steps S41 to S43:
[0093] Step S41: Calculate the similarity between the updated room layout and the original room layout.
[0094] It should be noted that after updating the room layout, it is possible to determine whether the updated room layout is accurate. Therefore, the similarity between the updated room layout and the room layout before the update can be calculated. Specifically, a similarity algorithm can be used or the similarity can be calculated based on the data in the room layout before and after the update. This embodiment does not impose any restrictions on this.
[0095] In one feasible implementation, step S41 may include steps B11 to B12:
[0096] Step B11: Obtain the first layout category for each location in the updated room layout and the second layout category for each location in the original room layout.
[0097] It should be noted that the room layout includes layout categories for each location. Therefore, the first layout category for each location in the room can be obtained based on the updated room layout, which may include layout categories for beds, tables, chairs, etc., and the second layout category for each location in the room can be obtained based on the room layout before the update, which may also include layout categories for beds, tables, chairs, etc.
[0098] Step B12: Calculate the similarity between the first layout category and the second layout category.
[0099] In practice, after obtaining the first layout classification and the second layout classification, the similarity between the layout classifications can be calculated, thereby representing the similarity of the room layouts.
[0100] In one feasible implementation, the step of calculating the similarity between the first layout classification and the second layout classification may include: determining objects of equal category based on the first layout classification and the second layout classification; obtaining the number of grids of the objects of equal category; and obtaining the similarity between the first layout classification and the second layout classification based on the ratio between the number of grids and the total number of grids.
[0101] It should be noted that, in order to improve the accuracy of similarity calculation, similarity calculation can be performed on objects of equal category in the predicted layout classification. Therefore, objects of equal category in the room layout can be determined based on the first layout classification and the second layout classification. For example, objects of equal category are all beds, or all are tables, etc.
[0102] Since the above content converts the room into a grid map with the radar as the coordinate origin, it is possible to count the number of grid cells occupied by objects of the same category.
[0103] The total grid can be the union of rooms predicted twice, area(A∩B).
[0104] Specifically, the similarity between the first layout category and the second layout category can be calculated based on the ratio between the number of grid cells and the total number of grid cells, thereby obtaining the similarity between the room layout before and after the update, as shown in Formula 2 below:
[0105]
[0106] In Equation 2 above, q represents the similarity, sum(A=B) represents the number of grid cells in the grid diagram occupied by objects of the same category, and area(A∩B) represents the total number of grid cells. The similarity between the first layout category and the second layout category is calculated using Equation 2 above.
[0107] Step S42: When the calculated similarity is greater than the preset similarity threshold, the updated room layout is used as the target room layout.
[0108] In practice, a preset similarity threshold can be set to assess whether room layout prediction needs to continue. The preset similarity threshold can be 0.9, 0.95, etc., and this embodiment does not limit it.
[0109] If the calculated similarity is greater than the preset similarity threshold, it proves that the updated room layout is close to the real room layout. Therefore, the updated room layout is taken as the target room layout, which is the accurate room layout predicted in this embodiment, and the prediction ends.
[0110] Step S43: When the calculated similarity is less than or equal to the preset similarity threshold, return to the step of predicting the trajectory data of the moving object to obtain the room layout.
[0111] Understandably, if the calculated similarity is less than or equal to the preset similarity threshold, it means that the updated room layout is not close to the actual room layout and prediction needs to continue. Therefore, the process returns to the step of predicting the trajectory data of the moving object to obtain the room layout. The height in the updated room layout is used as the calculated height, and the height of the moving object is updated again. Through continuous iteration, compared with using the default height, an activity height that is closer to the actual value is obtained, thus obtaining a more accurate house layout.
[0112] Understandably, once the final room layout is obtained, air conditioning equipment can be used to regulate the airflow based on that layout. For example, if the air conditioning equipment is a fresh air system, it can be operated according to the final room layout. Air conditioning equipment can also include air purifiers, air conditioners, etc., allowing for faster control of airflow direction and temperature within the room based on the final room layout.
[0113] In one feasible implementation, for example, the air conditioning device is an air conditioner. After obtaining the final room layout, the location information of each point in the room can be determined according to the final room layout, so as to control the airflow direction or temperature of the air conditioner when it is running.
[0114] This embodiment calculates the similarity between the updated room layout and the original room layout. When the calculated similarity is greater than a preset similarity threshold, the updated room layout is used as the target room layout. When the calculated similarity is less than or equal to the preset similarity threshold, the process returns to the step of predicting the trajectory data of the moving object to obtain the room layout. When the layout change is small, the final room layout is obtained directly. When the room layout change is large, the trajectory of the moving object is re-predicted to ensure that the obtained room layout is more accurate. This can reduce errors caused by layout prediction and improve the reliability of the prediction results.
[0115] For example, to help understand the implementation process of the room layout prediction method obtained by combining this embodiment with the above embodiment one, please refer to... Figure 6 , Figure 6 A simplified flowchart of a room layout prediction method is provided, specifically: acquiring radar trajectory data; calculating the room layout based on the default height; assigning new height data to the trajectory points according to the layout; regenerating the layout; comparing the similarity with the previous layout; whether the similarity is greater than a threshold, if yes, outputting the current layout as the final layout, otherwise returning to the step of assigning new height data to the trajectory points according to the layout to continue layout prediction until the final layout is output.
[0116] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the room layout prediction method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.
[0117] This application also provides a room layout prediction device, please refer to... Figure 7 The room layout prediction device includes:
[0118] The acquisition module 10 is used to acquire the trajectory data of the moving object collected by the radar, and set the height of the moving object in the trajectory data to the default height.
[0119] The prediction module 20 is used to predict the trajectory data of the moving object to obtain the room layout, which includes the layout classification of each location in the room.
[0120] The determination module 30 is used to determine the target height of the moving object in each moving object trajectory data according to the layout classification, and to update the moving object trajectory data.
[0121] The prediction module 20 is also used to make predictions based on the updated trajectory data of the moving object to obtain an updated room layout.
[0122] The room layout prediction device provided in this application, employing the room layout prediction method described in the above embodiments, can solve the technical problem of low room layout prediction accuracy. Compared with the prior art, the beneficial effects of the room layout prediction device provided in this application are the same as those of the room layout prediction method described in the above embodiments, and other technical features in the room layout prediction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0123] In one embodiment, the prediction module 20 is further configured to obtain the distance and angle of the moving object relative to the radar based on the moving object trajectory data; and to make a prediction based on the distance, the angle, and the default height to obtain the room layout.
[0124] In one embodiment, the prediction module 20 is further configured to obtain the radar height; calculate the planar coordinates of the moving object in the room based on the radar height, the distance, the angle, and the default height; and make a prediction based on the planar coordinates using a preset inference strategy to obtain the room layout.
[0125] In one embodiment, the prediction module 20 is further configured to determine the temporal two-dimensional trajectory of a moving object within a preset time period using a preset inference strategy and the planar coordinates; convert the room into a grid map with the radar as the coordinate origin; and classify the grid map according to the temporal two-dimensional trajectory to obtain the layout classification of each location in the room.
[0126] In one embodiment, the device further includes a calculation module, which is used to calculate the similarity between the updated room layout and the original room layout; when the calculated similarity is greater than a preset similarity threshold, the updated room layout is used as the target room layout; when the calculated similarity is less than or equal to the preset similarity threshold, the step of predicting the trajectory data of the moving object to obtain the room layout is returned.
[0127] In one embodiment, the calculation module is further configured to obtain a first layout classification for each location of the room in the updated room layout and a second layout classification for each location of the room in the unupdated room layout; and calculate the similarity between the first layout classification and the second layout classification.
[0128] In one embodiment, the calculation module is further configured to determine objects of equal category based on the first layout classification and the second layout classification; obtain the number of grids of the objects of equal category; and obtain the similarity between the first layout classification and the second layout classification based on the ratio between the number of grids and the total number of grids.
[0129] This application provides an air conditioning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the room layout prediction method in Embodiment 1 above.
[0130] The following is for reference. Figure 8 The diagram illustrates a structural schematic of an air conditioning device suitable for implementing embodiments of this application. The air conditioning device in the embodiments of this application may include, but is not limited to, terminals such as air conditioners, air purifiers, and fresh air systems. Figure 8 The air conditioning device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application.
[0131] like Figure 8As shown, the air conditioning device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the air conditioning device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the air conditioning unit to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an air conditioning unit with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.
[0132] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0133] The air conditioning device provided in this application, employing the room layout prediction method described in the above embodiments, can solve the technical problem of low room layout prediction accuracy. Compared with the prior art, the beneficial effects of the air conditioning device provided in this application are the same as those of the room layout prediction method described in the above embodiments, and other technical features of the air conditioning device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0134] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0135] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0136] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to perform the room layout prediction method described in the above embodiments.
[0137] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0138] The aforementioned computer-readable storage medium may be included in the air conditioning equipment; or it may exist independently and not be assembled into the air conditioning equipment.
[0139] The aforementioned computer-readable storage medium carries one or more programs that, when executed by an air conditioning device, cause the air conditioning device to: acquire trajectory data of a moving object collected by radar and set the height of the moving object in the trajectory data to a default height; predict the trajectory data of the moving object to obtain a room layout, the room layout including a layout classification for each location in the room; determine the target height of the moving object in each trajectory data according to the layout classification and update the trajectory data of the moving object; and predict the updated room layout based on the updated trajectory data of the moving object.
[0140] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0141] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0142] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0143] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described room layout prediction method, which can solve the technical problem of low room layout prediction accuracy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the room layout prediction method provided in the above embodiments, and will not be repeated here.
[0144] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the room layout prediction method described above.
[0145] The computer program product provided in this application can solve the technical problem of low accuracy in room layout prediction. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the room layout prediction method provided in the above embodiments, and will not be repeated here.
[0146] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A method for predicting room layout, characterized in that, The room layout prediction method includes: Acquire the trajectory data of the moving object collected by the radar, and set the height of the moving object in the trajectory data to the default height; The trajectory data of the moving object is predicted to obtain the room layout, which includes the layout classification of each location in the room; Based on the layout classification, determine the target height of the moving object in each moving object trajectory data, and update the moving object trajectory data. Based on the updated trajectory data of the moving object, an updated room layout is obtained through prediction.
2. The method as described in claim 1, characterized in that, The step of predicting the room layout from the trajectory data of the moving object includes: The distance and angle of the moving object relative to the radar are obtained based on the trajectory data of the moving object. The room layout is predicted based on the distance, the angle, and the default height.
3. The method as described in claim 2, characterized in that, The step of predicting the room layout based on the distance, the angle, and the default height includes: Obtain radar altitude; The planar coordinates of the moving object within the room are calculated based on the radar height, the distance, the angle, and the default height. The room layout is obtained by using a preset inference strategy based on the plane coordinates.
4. The method as described in claim 3, characterized in that, The step of predicting the room layout based on the planar coordinates using a preset inference strategy includes: The temporal two-dimensional trajectory of a moving object within a preset time period is determined by a preset inference strategy and the plane coordinates. Convert the room into a grid map with radar as the origin; The grid diagram is classified according to the time-series two-dimensional trajectory to obtain the layout classification of each location in the room.
5. The method as described in claim 1, characterized in that, After the step of predicting the updated room layout based on the updated trajectory data of the moving object, the method further includes: Calculate the similarity between the updated room layout and the original room layout; When the calculated similarity is greater than the preset similarity threshold, the updated room layout will be used as the target room layout. When the calculated similarity is less than or equal to a preset similarity threshold, return to the step of predicting the trajectory data of the moving object to obtain the room layout.
6. The method as described in claim 5, characterized in that, The step of calculating the similarity between the updated room layout and the original room layout includes: Get the first layout category of each position in the room in the updated room layout and the second layout category of each position in the room in the original room layout; Calculate the similarity between the first layout category and the second layout category.
7. The method as described in claim 6, characterized in that, The step of calculating the similarity between the first layout category and the second layout category in the rooms includes: Based on the first layout classification and the second layout classification, determine objects of equal category; Obtain the number of grid cells for objects of the same category; The similarity between the first layout classification and the second layout classification is obtained based on the ratio between the number of grid cells and the total number of grid cells.
8. A room layout prediction device, characterized in that, The device includes: The acquisition module is used to acquire the trajectory data of a moving object collected by the radar, and set the height of the moving object in the trajectory data to a default height; The prediction module is used to predict the trajectory data of the moving object to obtain the room layout, which includes the layout classification of each location in the room. The determination module is used to determine the target height of the moving object in each moving object trajectory data according to the layout classification, and update the moving object trajectory data; The prediction module is also used to make predictions based on the updated trajectory data of the moving object to obtain an updated room layout.
9. An air conditioning device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the room layout prediction method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the room layout prediction method as described in any one of claims 1 to 7.