Air conditioner, control method of air conditioner, and computer device

Abstract

The application relates to an air conditioner, a control method of the air conditioner and a computer device, the air conditioner comprising: an indoor unit for adjusting indoor air; a radar module for collecting human body detection data and object detection data of a target space according to a preset time interval; and a controller configured to: for each time interval, performing spatio-temporal clustering on the human body detection data and the object detection data to obtain a first clustering center and a second clustering center corresponding to each time interval; in the case that a time sum of the time intervals reaches a preset time sum threshold, performing clustering on the first clustering center and the second clustering center corresponding to each time interval to generate a spatio-temporal weight matrix of the target space; obtaining a current position of the human body and time information corresponding to the current position through the radar module; and adjusting an operation mode of the air conditioner according to the current position, the time information and the spatio-temporal weight matrix, so that the intelligent level of the air conditioner is improved.

Description

Technical Field

[0001] This application relates to the field of air conditioner technology, and in particular to an air conditioner, an air conditioner control method, and a computer device. Background Technology

[0002] Intelligent control of air conditioners, achieved through various sensor devices, has become a mainstream trend in air conditioning intelligence. Radar sensors, with their lower cost, relatively stable performance, and good privacy, have become a solution to replace cameras and infrared sensors. Radar sensors can detect the distance, angle, and speed of people, reporting this information to the air conditioner to enable human-sensing functions, such as detecting when the airflow is blowing on or away from people.

[0003] However, in related technologies, when radar sensors are used on air conditioners to achieve smart home scenarios, the level of intelligence is not high. Summary of the Invention

[0004] Therefore, it is necessary to provide an air conditioner, an air conditioner control method, and a computer device that can improve the intelligence level of air conditioners, in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides an air conditioner, comprising:

[0006] Indoor unit, used to regulate the air in the target space;

[0007] The radar module, located inside the indoor unit, is used to collect human detection data and object detection data in the target space at preset time intervals. The human detection data includes human position information and the corresponding time information; the object detection data includes target object position information and the corresponding time information.

[0008] The controller, connected to the radar module, is configured as follows:

[0009] For each time interval, spatiotemporal clustering is performed on the human detection data and object detection data to obtain the first cluster center and the second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area.

[0010] When the sum of time intervals reaches a preset time sum threshold, the first cluster center and the second cluster center corresponding to each time interval are clustered to generate the spatiotemporal weight matrix of the target space.

[0011] The radar module acquires the current location of the human body and the corresponding time information; based on the current location, time information, and spatiotemporal weight matrix, the operating mode of the air conditioner is adjusted.

[0012] The above technical solution has the following advantages or effects: By collecting human detection data and object detection data in the target space at preset time intervals through the radar module, and performing spatiotemporal clustering on the human detection data and object detection data at each time interval through the controller, the first cluster center and the second cluster center corresponding to each time interval are obtained. The first cluster center and the second cluster center within the preset time sum threshold are clustered to generate a spatiotemporal weight matrix. By combining the spatiotemporal weight matrix, the current position of the human body and the time information corresponding to the current position, the operating mode of the air conditioner is adjusted. This allows the air conditioner to achieve long-term learning and personalized adaptation of user behavior habits, thereby improving the intelligence level of the air conditioner.

[0013] In one embodiment, the controller is configured to:

[0014] If the current location is in the human activity area represented by the spatiotemporal weight matrix, the time information corresponding to the current location is in the time period associated with the human activity area, and the human stay time in the target space reaches the preset stay time threshold, the target operation mode corresponding to the human activity area where the current location is located is determined according to the preset mapping relationship between the human activity area and the air conditioner operation mode.

[0015] Adjust the air conditioner from its current operating mode to the target operating mode.

[0016] The above technical solution has the following advantages or effects: by collecting the current location of the human body and the time information corresponding to the current location in real time, the human activity area is determined based on the current location and time information, and then the target operation mode of the air conditioner is determined. This allows the air conditioner to operate in different modes at different times, achieving personalized adaptation for users and improving the intelligence level of the air conditioner.

[0017] In one embodiment, before the step of determining the target operating mode corresponding to the current location's human activity area based on a preset mapping relationship between human activity areas and air conditioner operating modes, the controller is configured to:

[0018] When the time period associated with the human activity area is the mealtime period, the human activity area is determined to be the dining table area, and the air conditioner's operating mode is determined to be the first operating mode. The first operating mode includes: when the current operating mode is cooling mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically upward to lower the air conditioner's temperature, and controlling the air conditioner's fan speed to medium speed; when the current operating mode is heating mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically downward to raise the air conditioner's temperature.

[0019] When the time period associated with the human activity area is the sleep period, the human activity area is determined to be the bed area, and the air conditioner operation mode is determined to be the second operation mode; the second operation mode includes: adjusting the air guide plate horizontally toward the bed area, adjusting the vertical angle of the air guide plate to the minimum angle, and adjusting the fan speed to the lowest fan speed.

[0020] If the time period associated with the human activity area is not the mealtime or sleeptime, the human activity area is determined to be the desk area or sofa area, and the air conditioner operation mode is determined to be the third operation mode; the third operation mode includes: adjusting the air guide plate horizontally and vertically to the non-direct airflow area to reduce the air conditioner's fan speed.

[0021] The above technical solution has the following advantages or effects: by establishing a preset mapping relationship between human activity areas and air conditioner operation modes, the air conditioner can operate in different modes for different human activity areas, thereby improving the intelligence level of the air conditioner.

[0022] In one embodiment, the controller is configured to:

[0023] If the current location leaves the target space, reduce the air conditioner's fan speed and increase its temperature.

[0024] The above technical solution has the following advantages or effects: after the human body leaves the target space, by reducing the air conditioner's fan speed and increasing the air conditioner's temperature, energy saving of the air conditioner can be achieved.

[0025] In one embodiment, the controller is configured to:

[0026] The radar detection area of ​​the radar module is divided into multiple partitions; based on these partitions, an initial spatiotemporal weight matrix is ​​determined.

[0027] Clustering is performed on the first cluster center and the second cluster center corresponding to each time interval to generate the first clustering result and the second clustering result;

[0028] Based on the first and second clustering results, the initial spatiotemporal weight matrix is ​​updated to generate the spatiotemporal weight matrix.

[0029] The above technical solution has the following advantages or effects: by dividing the radar detection area into multiple partitions and using the first clustering result and the second clustering result to update the initial weight value of each partition, the spatiotemporal weight matrix can be obtained automatically and quickly.

[0030] In one embodiment, the radar module is configured to:

[0031] When a human body is present within the radar detection area of ​​the radar module, human body detection data is acquired;

[0032] Acquire object detection data when there is no human body within the radar detection area of ​​the radar module.

[0033] The above technical solution has the following advantages or effects: by collecting human body detection data and object detection data in a time-sharing manner, signal interference caused by collecting human body and target object data at the same time is avoided, which can improve data processing efficiency and target recognition accuracy.

[0034] In one embodiment, prior to the step of acquiring human detection data when a human body is present within the radar detection area of ​​the radar module, the radar module is configured to:

[0035] Acquire the echo energy of the radar module;

[0036] If the echo energy is greater than the preset echo energy threshold, it is determined that there is a moving target in the radar detection area;

[0037] If the moving target is determined to be a human body, and the duration of the moving target's presence in the radar detection area is greater than a first preset duration, then the presence of a human body in the radar detection area is determined.

[0038] The above technical solution has the following advantages or effects: by using a breathing detection algorithm and a timer to determine the presence of a human body twice, the accuracy and reliability of human body detection can be improved, and false judgments can be reduced.

[0039] In one embodiment, prior to the step of acquiring object detection data when no human body is present within the radar detection area, the radar module is configured to:

[0040] If it is determined that the moving target is not a human body, and the duration of the moving target's presence in the radar detection area is longer than the second preset duration, then it is determined that there is no human body in the radar detection area.

[0041] The above technical solution has the following advantages or effects: in the absence of a human body, combining it with a timer can improve the accuracy and reliability of detecting the absence of a human body.

[0042] Secondly, this application also provides a method for controlling an air conditioner, the method comprising:

[0043] The radar module collects human detection data and object detection data in the target space at preset time intervals.

[0044] For each time interval, spatiotemporal clustering is performed on the human detection data and object detection data to obtain the first cluster center and the second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area.

[0045] When the sum of time intervals reaches a preset time sum threshold, the first cluster center and the second cluster center corresponding to each time interval are clustered respectively to generate the spatiotemporal weight matrix of the target space.

[0046] The radar module acquires the current location of the human body and the corresponding time information; based on the current location, time information, and spatiotemporal weight matrix, the operating mode of the air conditioner is adjusted.

[0047] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of the second aspect.

[0048] The aforementioned air conditioner, its control method, and computer equipment collect human detection data and object detection data in the target space at preset time intervals via a radar module. The controller performs spatiotemporal clustering on the human detection data and object detection data for each time interval to obtain the first cluster center and the second cluster center corresponding to each time interval. The controller then clusters the first cluster center and the second cluster center within a preset time sum threshold to generate a spatiotemporal weight matrix. By combining the spatiotemporal weight matrix, the current position of the human body, and the time information corresponding to the current position, the air conditioner's operating mode is adjusted. This allows the air conditioner to learn and personalize its operation based on user behavior over a long period, thereby improving the air conditioner's intelligence level. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a structural block diagram of an air conditioner in one embodiment;

[0051] Figure 2 This is a schematic diagram illustrating the process of a radar module acquiring human body detection data and object detection data in one embodiment.

[0052] Figure 3 This is a schematic diagram of the radar module's human body recognition process in one embodiment;

[0053] Figure 4 This is a flowchart illustrating the process of obtaining the human activity area and the object interference area in one embodiment;

[0054] Figure 5 This is a schematic diagram of the process by which the controller generates the spatiotemporal weight matrix in one embodiment;

[0055] Figure 6 This is a schematic diagram of the partitioning of the radar detection area in one embodiment;

[0056] Figure 7 This is a schematic diagram of the initial spatiotemporal weight matrix in one embodiment;

[0057] Figure 8 This is a schematic diagram of the first and second clustering results in one embodiment;

[0058] Figure 9 This is a schematic diagram of the spatiotemporal weight matrix in one embodiment;

[0059] Figure 10 This is a schematic diagram of the process for generating a spatiotemporal weight matrix in one embodiment;

[0060] Figure 11 This is a schematic diagram illustrating the process of the controller adjusting the air conditioner's operating mode in one embodiment;

[0061] Figure 12 This is a flowchart illustrating the process of establishing a preset mapping relationship between human activity areas and air conditioner operating modes in one embodiment.

[0062] Figure 13 This is a flowchart illustrating a control method for an air conditioner in one embodiment;

[0063] Figure 14This is a structural block diagram of the control device of an air conditioner in one embodiment;

[0064] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] An air conditioner, short for room air conditioner, is a compact local air conditioning system assembled from air handling equipment, fans, refrigeration units, and automatic control instruments. The air handling equipment filters the air, regulates temperature, controls humidity, and improves air cleanliness. It includes filters, evaporators, condensers, humidification modules, and dehumidification modules. Fans drive air circulation, ensuring efficient indoor and outdoor air and heat exchange. Fans come in various types, including centrifugal fans, axial fans, and cross-flow fans. The refrigeration unit implements a vapor compression refrigeration cycle (compression → condensation → throttling → evaporation). It includes a compressor, refrigerant, and expansion valve. Automatic control instruments automatically regulate temperature, humidity, and fan speed, and provide fault protection. These instruments include temperature sensors, humidity sensors, pressure sensors, microcontrollers (MCUs) or programmable logic controllers (PLCs), electric dampers, electronic expansion valves, and compressor inverter modules.

[0067] Air conditioners can be divided into packaged air conditioners and split air conditioners. In a packaged air conditioner, all components are integrated into one casing (such as window air conditioners and portable air conditioners). In a split air conditioner, the indoor unit and the outdoor unit are separate and connected by pipes. The indoor unit is used for air handling and ventilation, while the outdoor unit is used for refrigeration cycle.

[0068] The radar module is a radar sensor. Specifically, it can be a millimeter-wave radar. Millimeter-wave radar operates in the millimeter-wave band (wavelength 1-10mm, frequency 30-300GHz) and can calculate the target's speed, azimuth, and distance to the radar.

[0069] In one exemplary embodiment, such as Figure 1 As shown, an air conditioner is provided, the air conditioner comprising:

[0070] Indoor unit 110 is used to regulate the air in the target space;

[0071] Radar module 120 is installed inside the indoor unit and is used to collect human detection data and object detection data in the target space at preset time intervals. The human detection data includes human position information and time information corresponding to the human position information. The object detection data includes target object position information and time information corresponding to the target object position information.

[0072] Controller 130, connected to the radar module, is configured as follows:

[0073] For each time interval, spatiotemporal clustering is performed on the human detection data and object detection data to obtain the first cluster center and the second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area.

[0074] When the sum of time intervals reaches a preset time sum threshold, the first cluster center and the second cluster center corresponding to each time interval are clustered to generate the spatiotemporal weight matrix of the target space.

[0075] The radar module acquires the current location of the human body and the corresponding time information; based on the current location, time information, and spatiotemporal weight matrix, the operating mode of the air conditioner is adjusted.

[0076] The target space includes, but is not limited to, living space, office space, teaching space, and meeting space. Specifically, the target space can be a room.

[0077] The preset time interval can be set according to actual needs. For example, the preset time interval is 24 hours.

[0078] The target object is an object capable of slight movement. Specifically, the target object includes, but is not limited to, curtains and potted plants. The position of the target object may change. For example, the curtains may flutter or the potted plants may sway due to the wind.

[0079] Spatiotemporal clustering is a data analysis method that combines spatial and temporal dimensions, aiming to group objects with similar spatial locations and temporal patterns (such as events, trajectories, sensor data, etc.) into the same cluster.

[0080] The preset total time threshold can be set according to actual needs. For example, the preset total time threshold is 30 days.

[0081] Among them, the spatiotemporal weight matrix is ​​used to characterize the spatiotemporal distribution of human activity areas and object disturbance areas in the target space.

[0082] In this embodiment of the application, a radar module is used to detect targets in the target space. The electromagnetic waves emitted by the radar module are reflected by the moving target and received by the antenna of the radar module. The echo energy contains the target's motion state information.

[0083] The targets include human bodies and target objects. The radar module collects human body location information and corresponding time information at preset time intervals (e.g., 24 hours), recording them in the variable `Human_presence`. The radar module collects target object location information and corresponding time information at preset time intervals, recording them in the variable `Human_absence`.

[0084] The data recorded in the variables `Human_presence` and `Human_absence` is processed. Specifically, this includes time extraction, second conversion, and cyclic encoding. Time extraction is used to extract the time portion (hour, minute, second) from the timestamp with date. Second conversion is used to convert the time portion into the total number of seconds in a day. Cyclic encoding is used to map the total number of seconds into a two-dimensional feature with periodicity.

[0085]

[0086]

[0087] The target information acquired in each frame can be written as: x and y represent the target's position information, including the distance and angle of the target. and This indicates the time information when the target appeared.

[0088] Since the target information contains information in both time and space dimensions, a spatiotemporal clustering algorithm can be used to perform spatiotemporal clustering on the human detection data and object detection data within each time interval, obtaining the first cluster center and the second cluster center corresponding to each time interval. The spatiotemporal clustering algorithm can be a Gaussian Mixture Model (GMM).

[0089] Specifically, the human detection data within each time interval is fitted to several Gaussian distributions. Each Gaussian distribution has a central point (the first cluster center), which itself contains average spatial and temporal information, resulting in multiple human activity areas and the time intervals associated with each human activity area. This can be represented in Cartesian coordinates as follows: [The text abruptly ends here, so the translation stops as well.] The time period associated with the human activity area is time period 1: to .

[0090] The object detection data within each time interval is fitted to several Gaussian distributions, each with a central point (second cluster center). This central point itself contains average spatial and temporal information, resulting in multiple object interference regions and the time intervals associated with each interference region. This can be represented in Cartesian coordinates as follows: the object interference region is... The time period associated with the object interference area is time period 2: to .

[0091] As time goes on, the first and second cluster centers within a preset total time threshold (e.g., 30 days) are clustered to identify areas of frequent human activity and object interference that are close in location and time. This information is represented by a spatiotemporal weight matrix.

[0092] After generating the spatiotemporal weight matrix, the radar module monitors in real time whether a human body exists in the target space. If a human body is present, its current position and the corresponding time information are obtained. It is then determined whether the human body's current position is within the human activity area represented by the spatiotemporal weight matrix, and whether the time information corresponding to the current position is within the time period associated with the human activity area. If so, the air conditioner's current operating mode is adjusted to the preset target operating mode.

[0093] The aforementioned air conditioner uses a radar module to collect human detection data and object detection data in the target space at preset time intervals. The controller performs spatiotemporal clustering on the human detection data and object detection data for each time interval to obtain the first cluster center and the second cluster center corresponding to each time interval. It then clusters the first cluster center and the second cluster center within a preset time sum threshold to generate a spatiotemporal weight matrix. Combining the spatiotemporal weight matrix, the current position of the human body, and the time information corresponding to the current position, the air conditioner adjusts its operating mode. This allows the air conditioner to learn and personalize its operation based on user behavior over a long period of time, thus improving the air conditioner's intelligence level.

[0094] In one embodiment, such as Figure 2 As shown, the radar module is configured as follows:

[0095] Step S210: If a human body is present in the radar detection area of ​​the radar module, acquire human body detection data.

[0096] Step S220: Acquire object detection data when there is no human body within the radar detection area of ​​the radar module.

[0097] The radar detection area is the spatial range within which the radar module can effectively detect, identify, and track targets. The coverage area of ​​the radar module in three-dimensional space is typically conical or fan-shaped. Specifically, the radar detection area can be a fan-shaped region centered on the radar module, with the maximum detection range as its radius and the horizontal detection angle as its central angle.

[0098] In this embodiment, when the radar module detects a human body in the target space, it can periodically (e.g., every 30 seconds) collect the position and time of the human body and record them in the variable Human_presence. When the radar module detects that no human body is present in the target space, it can periodically (e.g., every 20 seconds) collect the position and time of the target object and record them in the variable Human_absence.

[0099] This application embodiment avoids signal interference caused by simultaneously collecting human body detection data and object detection data by collecting human body and target object data in a time-division manner, which can improve data processing efficiency and target recognition accuracy.

[0100] In one embodiment, such as Figure 3 As shown, when a human body is present within the radar detection area of ​​the radar module, before acquiring human body detection data, the radar module is configured as follows:

[0101] Step S310: Obtain the echo energy of the radar module;

[0102] Step S320: If the echo energy is greater than the preset echo energy threshold, it is determined that there is a moving target in the radar detection area;

[0103] Step S330: If the moving target is determined to be a human body and the duration of the moving target's presence in the radar detection area is greater than a first preset duration, then the presence of a human body in the radar detection area is determined.

[0104] The preset echo energy threshold and the first preset duration can be set according to actual needs.

[0105] In this embodiment, when the echo energy of the radar module exceeds a preset echo energy threshold, it is determined that a target is moving within the detection area. The built-in breathing detection algorithm of the radar module is activated to detect whether the target is a human body. Specifically, the breathing detection algorithm identifies whether a human body exists in the target space. If so, a timer determines whether the duration for which a target with vital signs is continuously detected exceeds a first preset duration T1. If so, it is determined that a human body exists in the target space.

[0106] The embodiments of this application use a breathing detection algorithm and a timer to determine the presence of a human body twice, which can improve the accuracy and reliability of human body detection and reduce false positives.

[0107] In one embodiment, prior to the step of acquiring object detection data when no human body is present within the radar detection area, the radar module is further configured to:

[0108] If it is determined that the moving target is not a human body, and the duration of the moving target's presence in the radar detection area is longer than the second preset duration, then it is determined that there is no human body in the radar detection area.

[0109] In this embodiment of the application, a breathing detection algorithm is used to identify whether there is a human body in the target space. If there is no human body, a timer is used to determine whether the duration of continuous detection of the absence of a human body exceeds a second preset duration T2. ​​If so, it is determined that there is no human body in the target space.

[0110] In the embodiment of this application, by combining the judgment with a timer when the human body is not present, the accuracy and reliability of detecting the absence of the human body can be improved.

[0111] To facilitate understanding of the above embodiments, as follows Figure 4 As shown, the specific process for acquiring human activity areas and object interference areas every 24 hours is illustrated.

[0112] In one embodiment, such as Figure 5 As shown, the controller is also configured as follows:

[0113] Step S510: Divide the radar detection area of ​​the radar module into multiple partitions; determine the initial spatiotemporal weight matrix based on the multiple partitions.

[0114] In this embodiment, taking a radar module with a horizontal detection angle of -60° to 60°, a maximum detection range of 5 meters, and a fan-shaped radar detection area as an example, the radar detection area of ​​the radar module is divided into multiple zones. Specifically, as shown... Figure 6 As shown, 20 zones are formed according to the distances of 1 meter, 2 meters, 3 meters, 4 meters, and 5 meters, and between -60°, -30°, 0°, 30°, and 60°. Each zone is further divided into a left sub-zone and a right sub-zone. Taking zone 1 as an example, it is a region centered on the location of the radar module, consisting of rays from -60° and -30° and an arc with a radius of 1 meter. Zone 1 is further divided into a left sub-zone and a right sub-zone by a ray from -45°.

[0115] After obtaining multiple partitions, an initial spatiotemporal weight matrix can be obtained. For example... Figure 7 As shown, the horizontal axis of the recorded data is the angle, and the vertical axis is the distance. The initial weight value of each partition is (0, 0), which means that the initial weight value of the left sub-partition is 0, the initial weight value of the right sub-partition is 0, and the initial time information of each partition is None.

[0116] Step S520: Cluster the first cluster center and the second cluster center corresponding to each time interval respectively to generate the first clustering result and the second clustering result.

[0117] In this embodiment, a Gaussian Mixture Model (GMM) or K-means clustering algorithm can be used to cluster the first cluster center and the second cluster center corresponding to each time interval, respectively, to obtain the first clustering result and the second clustering result. The first clustering result includes the location of the human body and the time interval, which can characterize the frequent activity area of ​​the human body in the target space. The second clustering result includes the location of the target object and the time interval, which can represent the location area of ​​the target object in the target space.

[0118] Specifically, such as Figure 8 As shown, the positions of the bed and desk represent the human activity area, while the location of the curtains represents the object interference area. Clustering during 30 days of inhabited periods reveals that the human activity area is primarily located in partition 14 (0, 1) from 14:30 to 16:00; and in partitions 15 (0, 1) and 19 (0, 1) from 12:00 to 13:30 and from 22:30 to 7:00 the next day. Clustering during 30 days of unoccupied periods reveals that the object interference area is primarily located in partitions 9 (-1, -1) and 13 (0, -1) from 8:30 to 10:30.

[0119] Step S530: Update the initial spatiotemporal weight matrix based on the first clustering result and the second clustering result to generate the spatiotemporal weight matrix.

[0120] In this embodiment of the application, after obtaining the first clustering result and the second clustering result, the weight of the partition where the human body is located can be increased and the weight of the partition where the target object is located can be decreased to obtain the spatiotemporal weight matrix.

[0121] Specifically, such as Figure 9 As shown, the human activity area and the object interference area are distinguished by weight values ​​of +1 and -1.

[0122] Figure 9 The spatiotemporal weight matrix is ​​the result of accumulating one month's worth of human and object detection data. The human activity area and object interference area within the target space are clearly described by the spatiotemporal weight matrix. When a person is detected in the activity area corresponding to the time period, the air conditioning control mode can be adjusted accordingly based on the actual situation. Even if the layout of the target space changes, this spatiotemporal weight matrix will continuously update over time, adapting to environmental changes and dynamically learning scene patterns to provide users with more intelligent services.

[0123] This application embodiment divides the radar detection area into multiple partitions and uses the first clustering result and the second clustering result to update the initial weight value of each partition, thereby automatically and quickly obtaining the spatiotemporal weight matrix.

[0124] To facilitate understanding of the above embodiments, as follows Figure 10 The diagram illustrates the specific process for generating the spatiotemporal weight matrix.

[0125] In one embodiment, such as Figure 11 As shown, the controller is also configured as follows:

[0126] Step S1110: If the current location is in the human activity area represented by the spatiotemporal weight matrix, the time information corresponding to the current location is in the time period associated with the human activity area, and the human stay time in the target space reaches the preset stay time threshold, the target operation mode corresponding to the human activity area where the current location is located is determined according to the preset mapping relationship between the human activity area and the air conditioner operation mode.

[0127] Step S1120: Adjust the air conditioner from the current operating mode to the target operating mode.

[0128] The preset dwell time threshold can be set according to actual needs. For example, 10 minutes.

[0129] In the preset mapping relationship between human activity areas and air conditioner operating modes, each human activity area corresponds to a unique air conditioner operating mode.

[0130] In this embodiment of the application, after obtaining the spatiotemporal weight matrix, the main activity areas of a person at different times in the target space can be inferred. The location of the bed is determined by the human activity area corresponding to nighttime, the location of the dining table is determined by the human activity area corresponding to breakfast, lunch and dinner, and the location of the sofa / desk is determined by the human activity area corresponding to other times.

[0131] After detecting a human body entering the target space, it is determined whether the human body is located in the human activity area represented by the spatiotemporal weight matrix. If so, the duration of the human body's stay in the human activity area is obtained. If the duration of the stay reaches the preset stay time threshold, the associated human activity area is determined based on the human body's current time. From the preset mapping relationship between human activity areas and air conditioner operating modes, the target operating mode of the air conditioner is obtained, and the air conditioner is switched from the current operating mode to the target operating mode.

[0132] This application embodiment collects the current location of the human body and the corresponding time information in real time. Based on the current location and time information, it determines the human body's activity area and then determines the target operating mode of the air conditioner. This allows the air conditioner to operate in different modes at different times, achieving personalized adaptation for users and improving the intelligence level of the air conditioner.

[0133] In one embodiment, such as Figure 12 As shown, before determining the target operating mode corresponding to the current location's human activity area based on the preset mapping relationship between human activity areas and air conditioner operating modes, the controller is also configured as follows:

[0134] Step S1210: If the time period associated with the human activity area is a mealtime, determine that the human activity area is the dining table area and determine that the air conditioner's operating mode is the first operating mode; the first operating mode includes: when the current operating mode is cooling mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically upward to lower the air conditioner's temperature and controlling the air conditioner's fan speed to medium speed; when the current operating mode is heating mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically downward to raise the air conditioner's temperature.

[0135] In this embodiment, the first operating mode is related to the current operating mode. When the current operating mode is cooling mode, the air conditioner operates in the first operating mode, adjusting the horizontal direction of the air guide vane towards the dining area to directly blow air onto the people. Adjusting the vertical direction of the air guide vane upward causes the cold air to rise and then sink, forming a circulation, which can improve cooling efficiency. When the current operating mode is heating mode, hot air has a lower density and naturally rises. By adjusting the vertical direction of the air guide vane downward, the hot air can be blown directly onto the ground, accelerating the heating of the bottom and reducing the waste of heat accumulating on the ceiling.

[0136] Step S1220: If the time period associated with the human activity area is the sleep period, determine the human activity area as the bed area and determine the air conditioner operation mode as the second operation mode; the second operation mode includes: adjusting the air guide plate horizontally toward the bed area, adjusting the angle of the air guide plate vertically to the minimum angle, and adjusting the wind speed to the lowest wind speed.

[0137] In this embodiment, the second operating mode is the air conditioner's sleep mode. Specifically, by adjusting the air guide vane horizontally towards the bed area, airflow can be concentrated near the bed to create localized temperature regulation, preventing the overall space from becoming too cold or too hot. By adjusting the vertical angle of the air guide vane to its minimum, vertical airflow diffusion can be reduced, allowing the air to flow gently horizontally and avoiding direct airflow to the head or feet. By adjusting the fan speed to the lowest setting, airflow intensity can be reduced, minimizing noise and perceived impact while maintaining air circulation.

[0138] Step S1230: If the time period associated with the human activity area is not the meal period or the sleep period, determine that the human activity area is the desk area or the sofa area, and determine that the air conditioner operation mode is the third operation mode; the third operation mode includes: adjusting the horizontal and vertical directions of the air guide plate to the non-human direct blowing area, and reducing the air conditioner's fan speed.

[0139] In this embodiment, the third operating mode is the anti-direct-blow mode in the air conditioner. By adjusting the direction, angle, or wind speed of the air conditioner's air outlet, the airflow is delivered in a gentler and more dispersed manner, avoiding direct impact on the human body. Specifically, by changing the tilt angle of the air guide plate, the airflow is directed to the ceiling, walls, or surroundings, utilizing the natural sinking or diffusion of air to achieve cooling or heating, and reducing wind speed.

[0140] This application embodiment establishes a preset mapping relationship between human activity areas and air conditioner operating modes, enabling the air conditioner to operate in different modes for different human activity areas, thereby improving the intelligence level of the air conditioner.

[0141] In one embodiment, the controller is further configured to:

[0142] If the current location leaves the target space, reduce the air conditioner's fan speed and increase its temperature.

[0143] In this embodiment, after the radar module detects that a human body has left the target space, the controller can control the air conditioner to save energy. Specifically, this is achieved by reducing the air conditioner's fan speed and increasing the air conditioner's temperature.

[0144] In an optional embodiment, the air conditioner can be turned off after the human body has been away from the target space for a period of time.

[0145] In this embodiment of the application, after the human body leaves the target space, the air conditioner can be energy-saving by reducing the air conditioner's fan speed and increasing its temperature.

[0146] like Figure 13 As shown, this application also provides a method for controlling an air conditioner, the method comprising:

[0147] Step S1310: Collect human detection data and object detection data in the target space through the radar module at preset time intervals;

[0148] Step S1320: For each time interval, perform spatiotemporal clustering on the human detection data and the object detection data to obtain the first cluster center and the second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area.

[0149] Step S1330: When the total time of each time interval reaches the preset total time threshold, cluster the first cluster center and the second cluster center corresponding to each time interval respectively to generate the spatiotemporal weight matrix of the target space.

[0150] Step S1340: Obtain the current position of the human body and the time information corresponding to the current position through the radar module; adjust the operating mode of the air conditioner according to the current position, time information and spatiotemporal weight matrix.

[0151] It should be noted that the specific limitations of the above steps can be found in the specific limitations of an air conditioner mentioned above, and will not be repeated here.

[0152] In one embodiment, if the current location is located in the human activity area represented by the spatiotemporal weight matrix, the time information corresponding to the current location is located in the time period associated with the human activity area, and the human stay time in the target space reaches a preset stay time threshold, the target operation mode corresponding to the human activity area where the current location is located is determined according to the preset mapping relationship between the human activity area and the air conditioner operation mode.

[0153] Adjust the air conditioner from its current operating mode to the target operating mode.

[0154] In one embodiment, before the step of determining the target operating mode corresponding to the current location's human activity area based on a preset mapping relationship between human activity areas and air conditioner operating modes, the controller is configured to:

[0155] When the time period associated with the human activity area is the mealtime period, the human activity area is determined to be the dining table area, and the air conditioner's operating mode is determined to be the first operating mode. The first operating mode includes: when the current operating mode is cooling mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically upward to lower the air conditioner's temperature, and controlling the air conditioner's fan speed to medium speed; when the current operating mode is heating mode, adjusting the air guide plate horizontally towards the dining table area and adjusting the air guide plate vertically downward to raise the air conditioner's temperature.

[0156] When the time period associated with the human activity area is the sleep period, the human activity area is determined to be the bed area, and the air conditioner operation mode is determined to be the second operation mode; the second operation mode includes: adjusting the air guide plate horizontally toward the bed area, adjusting the vertical angle of the air guide plate to the minimum angle, and adjusting the fan speed to the lowest fan speed.

[0157] If the time period associated with the human activity area is not the mealtime or sleeptime, the human activity area is determined to be the desk area or sofa area, and the air conditioner operation mode is determined to be the third operation mode; the third operation mode includes: adjusting the air guide plate horizontally and vertically to the non-direct airflow area to reduce the air conditioner's fan speed.

[0158] In one embodiment, the radar detection area of ​​the radar module is divided into multiple partitions; an initial spatiotemporal weight matrix is ​​determined based on the multiple partitions.

[0159] Clustering is performed on the first cluster center and the second cluster center corresponding to each time interval to generate the first clustering result and the second clustering result;

[0160] Based on the first and second clustering results, the initial spatiotemporal weight matrix is ​​updated to generate the spatiotemporal weight matrix.

[0161] The technical solution of this embodiment uses a radar module to collect human detection data and object detection data in the target space at preset time intervals. The controller performs spatiotemporal clustering on the human detection data and object detection data at each time interval to obtain the first cluster center and the second cluster center corresponding to each time interval. The first cluster center and the second cluster center within a preset time sum threshold are clustered to generate a spatiotemporal weight matrix. Combining the spatiotemporal weight matrix, the current position of the human body and the time information corresponding to the current position, the operating mode of the air conditioner is adjusted. This allows the air conditioner to learn and personalize its operation based on the user's behavior habits over a long period of time, thereby improving the intelligence level of the air conditioner.

[0162] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0163] Based on the same inventive concept, this application also provides a control device for an air conditioner that implements the control method for the air conditioner described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more air conditioner control device embodiments provided below can be found in the limitations of the air conditioner control method described above, and will not be repeated here.

[0164] In one exemplary embodiment, such as Figure 14 As shown, a control device for an air conditioner is provided, comprising:

[0165] The data acquisition module 1410 is used to acquire human detection data and object detection data in the target space through the radar module at preset time intervals;

[0166] The cluster center acquisition module 1420 is used to perform spatiotemporal clustering on the human detection data and the object detection data for each time interval to obtain a first cluster center and a second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area.

[0167] The spatiotemporal weight matrix generation module 1430 is used to cluster the first cluster center and the second cluster center corresponding to each time interval respectively, when the sum of the time intervals reaches a preset time sum threshold, to generate the spatiotemporal weight matrix of the target space.

[0168] The operating mode adjustment module 1440 is used to acquire the current position of the human body and the time information corresponding to the current position through the radar module; and adjust the operating mode of the air conditioner according to the current position, the time information and the spatiotemporal weight matrix.

[0169] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 15 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for controlling an air conditioner. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0170] Those skilled in the art will understand that Figure 15 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the aforementioned air conditioner control method. The steps of the air conditioner control method described here can be steps from the air conditioner control methods of the various embodiments described above.

[0171] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the air conditioner control method described above. The steps of the air conditioner control method described here can be the steps in the air conditioner control method of the various embodiments described above.

[0172] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the air conditioner control method described above. The steps of the air conditioner control method described here can be the steps in the air conditioner control method of the various embodiments described above.

[0173] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0174] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0175] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0176] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An air conditioner, characterized in that, include: Indoor unit, used to regulate the air in the target space; A radar module, which is installed inside the indoor unit, is used to collect human detection data and object detection data of the target space at preset time intervals; The human body detection data includes human body location information and time information corresponding to the human body location information; The object detection data includes target object location information and time information corresponding to the target object location information; A controller, connected to the radar module, is configured to: For each time interval, spatiotemporal clustering is performed on the human body detection data and the object detection data to obtain the first cluster center and the second cluster center corresponding to each time interval; The first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area. When the sum of the time intervals reaches a preset time sum threshold, the first cluster center and the second cluster center corresponding to each time interval are clustered to generate the spatiotemporal weight matrix of the target space. The radar module acquires the current position of the human body and the time information corresponding to the current position. The operating mode of the air conditioner is adjusted based on the current location, the time information, and the spatiotemporal weight matrix. Specifically, when the current location is within the human activity area represented by the spatiotemporal weight matrix, the time information corresponding to the current location is within the time period associated with the human activity area, and the human's stay time in the target space reaches a preset stay time threshold, the target operating mode corresponding to the human activity area where the current location is located is determined according to the preset mapping relationship between the human activity area and the air conditioner's operating mode, and the air conditioner is adjusted from the current operating mode to the target operating mode.

2. The air conditioner according to claim 1, characterized in that, Before the step of determining the target operating mode corresponding to the current location's human activity area based on a preset mapping relationship between human activity areas and air conditioner operating modes, the controller is further configured to: If the time period associated with the human activity area is a mealtime, the human activity area is determined to be a dining area, and the air conditioner operation mode is determined to be the first operation mode. The first operating mode includes: when the current operating mode is cooling mode, adjusting the air guide plate horizontally toward the dining table area and adjusting the air guide plate vertically upward to lower the temperature of the air conditioner and controlling the air conditioner's fan speed to medium speed; when the current operating mode is heating mode, adjusting the air guide plate horizontally toward the dining table area and adjusting the air guide plate vertically downward to raise the temperature of the air conditioner. If the time period associated with the human activity area is a sleep period, the human activity area is determined to be the bed area, and the air conditioner operation mode is determined to be the second operation mode; the second operation mode includes: adjusting the air guide plate horizontally toward the bed area, adjusting the angle of the air guide plate vertically to the minimum angle, and adjusting the wind speed to the lowest wind speed. If the time period associated with the human activity area is not a mealtime or sleeptime, the human activity area is determined to be a desk area or a sofa area, and the air conditioner's operating mode is determined to be the third operating mode; the third operating mode includes: adjusting the air guide plate horizontally and vertically to the non-direct airflow area to reduce the air conditioner's fan speed.

3. The air conditioner according to claim 1, characterized in that, The controller is also configured to: When the current position leaves the target space, the air conditioner's fan speed is reduced and the air conditioner's temperature is increased.

4. The air conditioner according to claim 1, characterized in that, The controller is also configured to: The radar detection area of ​​the radar module is divided into multiple partitions; an initial spatiotemporal weight matrix is ​​determined based on the multiple partitions. Clustering is performed on the first cluster center and the second cluster center corresponding to each time interval to generate the first clustering result and the second clustering result; Based on the first clustering result and the second clustering result, the initial spatiotemporal weight matrix is ​​updated to generate the spatiotemporal weight matrix.

5. The air conditioner according to claim 1, characterized in that, The radar module is configured as follows: When a human body is present within the radar detection area of ​​the radar module, human body detection data is acquired; When there is no human body within the radar detection area of ​​the radar module, object detection data is acquired.

6. The air conditioner according to claim 5, characterized in that, Before the step of acquiring human detection data when a human body is present within the radar detection area of ​​the radar module, the radar module is configured as follows: Acquire the echo energy of the radar module; If the echo energy is greater than a preset echo energy threshold, it is determined that there is a moving target in the radar detection area; If the moving target is determined to be a human body, and the duration of the moving target's presence in the radar detection area is greater than a first preset duration, then the presence of a human body in the radar detection area is determined.

7. The air conditioner according to claim 6, characterized in that, Before the step of acquiring object detection data when no human body is present in the radar detection area, the radar module is further configured as follows: If it is determined that the moving target is not a human body, and the duration of the moving target's presence in the radar detection area is greater than a second preset duration, then it is determined that there is no human body in the radar detection area.

8. A control method for an air conditioner, characterized in that, The method includes: The radar module collects human detection data and object detection data in the target space at preset time intervals. For each time interval, spatiotemporal clustering is performed on the human body detection data and the object detection data to obtain a first cluster center and a second cluster center corresponding to each time interval; the first cluster center is used to characterize the human activity area in the target space and the time period associated with the human activity area; the second cluster center is used to characterize the object interference area in the target space and the time period associated with the object interference area. When the sum of the time intervals reaches a preset time sum threshold, the first cluster center and the second cluster center corresponding to each time interval are clustered respectively to generate the spatiotemporal weight matrix of the target space. The radar module acquires the current position of the human body and the corresponding time information; based on the current position, the time information, and the spatiotemporal weight matrix, the operating mode of the air conditioner is adjusted. Specifically, when the current location is within the human activity area represented by the spatiotemporal weight matrix, the time information corresponding to the current location is within the time period associated with the human activity area, and the human's stay time in the target space reaches a preset stay time threshold, the target operating mode corresponding to the human activity area where the current location is located is determined according to the preset mapping relationship between the human activity area and the air conditioner's operating mode, and the air conditioner is adjusted from the current operating mode to the target operating mode.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 8.

Images