A control method and device of an air conditioner, a storage medium and an air conditioner

Abstract

This invention provides a control method, device, storage medium, and air conditioner for an air conditioner. The method includes: acquiring first human activity data of a target user in the room while the air conditioner is running; determining whether the target user is in a rest area of ​​the room based on the acquired first human activity data; if the target user is determined to be in the rest area, determining whether the target user is in a sleep state based on the acquired first human activity data; if the target user is determined to be in a sleep state, controlling the air conditioner to operate according to a preset sleep mode. The solution provided by this invention can automatically identify the user's sleep state and automatically adjust the air conditioner mode according to the state, providing a more comfortable bedroom environment.

Description

Technical Field

[0001] This invention relates to the field of control, and more particularly to a control method, apparatus, storage medium, and air conditioner for an air conditioner. Background Technology

[0002] With the development of smart homes, people hope to utilize advanced sensing technologies and machine learning algorithms to better understand and learn from user behavior, providing a comfortable living environment intelligently based on that behavior. Traditional bedroom air conditioning control methods cannot intelligently adjust according to the user's actual needs and activity levels, lacking personalized control for sleep states. Therefore, a new technology is needed to achieve intelligent bedroom air conditioning control based on user activity states, automatically detecting the user's sleep state and adjusting the air conditioning mode accordingly. Summary of the Invention

[0003] The main objective of this invention is to overcome the deficiencies of the aforementioned related technologies and provide a method, apparatus, storage medium, and air conditioner for air conditioning, so as to solve the problem that bedroom air conditioners in the related technologies cannot intelligently adjust according to the user's activity status and lack personalized control for sleep status.

[0004] The present invention provides a method for controlling an air conditioner, comprising: acquiring first human activity data of a target user in the room when the air conditioner is running; determining whether the target user is in a rest area of ​​the room based on the acquired first human activity data; if the target user is determined to be in the rest area, determining whether the target user is in a sleep state based on the acquired first human activity data; and if the target user is determined to be in a sleep state, controlling the air conditioner to operate according to a preset sleep mode.

[0005] Optionally, the first human activity data of the target user in the room can be obtained, including: collecting human activity data of the target user in the room through a millimeter-wave radar sensor.

[0006] Optionally, the first human activity data includes: human posture, movement, respiratory rate and / or heart rate; determining whether the target user is in a sleep state based on the acquired first human activity data includes: determining whether the target user's activity mode in the rest area is a preset activity mode based on the human posture and / or movement in the acquired first human activity data; if the activity mode is determined to be a preset activity mode, then determining whether the target user is in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

[0007] Optionally, it further includes: determining the rest area of ​​the room, including: acquiring second human activity data of the target user in the room within a preset time period; and identifying the location of the rest area of ​​the room based on the acquired second human activity data.

[0008] Optionally, the second human activity data includes: the coordinates of the trajectory points of the target user's activities within a preset time period; identifying the location of the rest area of ​​the room based on the acquired second human activity data includes: calculating the average of the trajectory point coordinates of the target user's activities within the preset time period, and using the calculated average coordinates as the current centroid of the rest area; determining the center position, width, and length of the rest area based on the current centroid and the distance between the trajectory point coordinates of the target user's activities and the current centroid; and / or, the second human activity data includes: the coordinates of the trajectory points of the target user's activities within a preset time period; identifying the location of the rest area of ​​the room based on the acquired second human activity data includes: identifying the initial dwelling area of ​​the target user after entering the room and / or the area where the target user spends the longest time in the room based on the trajectory point coordinates of the target user's activities within the preset time period; determining the rest area of ​​the room based on the identified initial dwelling area of ​​the target user after entering the room and / or the area where the target user spends the longest time in the room.

[0009] In another aspect, the present invention provides a control device for an air conditioner, comprising: an acquisition unit, configured to acquire first human activity data of a target user in a room when the air conditioner is running; a first determination unit, configured to determine whether the target user is in a rest area of ​​the room based on the first human activity data of the target user acquired by the acquisition unit; a second determination unit, configured to determine whether the target user is in a sleep state based on the first human activity data acquired by the acquisition unit if the first determination unit determines that the target user is in the rest area; and a control unit, configured to control the air conditioner to operate according to a preset sleep mode if the second determination unit determines that the target user is in a sleep state.

[0010] Optionally, the acquisition unit acquires the first human activity data of the target user in the room, including: collecting the human activity data of the target user in the room through a millimeter-wave radar sensor.

[0011] Optionally, the first human activity data includes: human posture, movement, respiratory rate and / or heart rate; the first determining unit determines whether the target user is in a sleep state based on the first human activity data acquired by the acquiring unit, including: determining whether the target user's activity mode in the rest area is a preset activity mode based on the human posture and / or movement in the acquired first human activity data; if the activity mode is determined to be a preset activity mode, then determining whether the target user is in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

[0012] Optionally, it further includes: a third determining unit, used to determine the rest area of ​​the room, including: acquiring second human activity data of the target user in the room within a preset time period; and identifying the location of the rest area of ​​the room based on the acquired second human activity data.

[0013] Optionally, the second human activity data includes: the coordinates of the trajectory points of the target user's activities within a preset time period; the third determining unit identifies the location of the rest area of ​​the room based on the acquired second human activity data, including: calculating the average of the trajectory point coordinates of the target user's activities within the preset time period, and using the calculated average coordinates as the current centroid of the rest area; determining the center position, width, and length of the rest area based on the current centroid and the distance between the trajectory point coordinates of the target user's activities and the current centroid; and / or, the second human activity data includes: the coordinates of the trajectory points of the target user's activities within a preset time period; the third determining unit identifies the location of the rest area of ​​the room based on the acquired second human activity data, including: identifying the initial dwelling area of ​​the target user after entering the room and / or the area where the target user spends the longest time in the room based on the trajectory point coordinates of the target user's activities within the preset time period; determining the rest area of ​​the room based on the identified initial dwelling area of ​​the target user after entering the room and / or the area where the target user spends the longest time in the room.

[0014] In another aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0015] In another aspect, the present invention provides an air conditioner, including a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0016] In another aspect, the present invention provides an air conditioner including any of the control devices described above.

[0017] According to the technical solution of the present invention, the user's sleep state can be automatically identified, and the air conditioner can be automatically adjusted to a preset sleep mode based on the state, providing a more comfortable bedroom environment. Human activity data is collected by a millimeter-wave sensor, and when the target user is determined to be in a resting area and asleep based on the human activity data, the air conditioner is controlled to enter sleep mode. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0019] Figure 1 This is a schematic diagram of an embodiment of the air conditioner control method provided by the present invention;

[0020] Figure 2 A flowchart illustrating the steps of a specific embodiment of the present invention for determining the rest area of ​​a room is shown;

[0021] Figure 3a The trajectory of a person moving around the edge of the bed is shown;

[0022] Figure 3b The center position of the bed is shown;

[0023] Figure 4 This is a schematic diagram of a specific embodiment of the air conditioner control method provided by the present invention;

[0024] Figure 5 This is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] This invention provides a method for controlling an air conditioner. The method can be implemented in an air conditioner controller or in a server, such as a cloud server.

[0028] Figure 1 This is a schematic diagram of an embodiment of the air conditioner control method provided by the present invention.

[0029] like Figure 1 As shown, according to an embodiment of the present invention, the air conditioner control method includes at least steps S110, S120, S130 and S140.

[0030] Step S110: When the air conditioner is running, acquire the first human activity data of the target user in the room.

[0031] In one specific implementation, millimeter-wave radar sensors can be used to collect initial human activity data of a target user within a room. The room is preferably a bedroom. For example, a millimeter-wave radar sensor can be configured in a bedroom air conditioning unit to collect human activity data within the bedroom. The millimeter-wave sensor transmits millimeter-wave signals and receives echo signals; by analyzing the echo data, high-precision information on object position and motion can be obtained. Optionally, the collected human activity data can be preprocessed, including noise reduction, data normalization, and / or time period setting (time information of the human activity data, facilitating the filtering out of invalid data, such as data collected when a user enters the room in the morning, as users typically only enter briefly during this time period and are considered invalid data), to reduce noise and interference in the data and to standardize the data to an appropriate scale.

[0032] The first human activity data may include, for example, human posture, movement, respiratory rate, and / or heart rate. Millimeter-wave sensors can detect minute human movements (heart rate, breathing, etc.) and changes in position. For example, when the method is implemented in a server, the air conditioner controller can upload the first human activity data collected by the millimeter-wave sensor to a cloud server via a communication module, and the cloud server can retrieve the first human activity data collected by the millimeter-wave sensor uploaded by the air conditioner controller.

[0033] Step S120: Determine whether the target user is in the rest area of ​​the room based on the first human activity data of the target user.

[0034] The first set of human activity data may also include the location of the target user, which can be used to determine whether the target user is in the rest area of ​​the room. The rest area is the area within the room where the user rests. For example, it could be the area where the bed is located in a bedroom. The rest area of ​​the room can be determined by analyzing the human activity data within the room.

[0035] Figure 2 A flowchart illustrating the steps of a specific embodiment of the present invention for determining the rest area of ​​a room is shown. Figure 2 As shown, in one specific embodiment, determining the rest area of ​​the room includes steps S1 and S2.

[0036] Step S1: Obtain the second human activity data of the target user in the room within a preset time period.

[0037] In one specific implementation, a millimeter-wave radar sensor can collect second human activity data of a target user within a room over a preset time period. The preset time period can be, for example, a sleep period, such as 22:00 to 6:00 the next day. A millimeter-wave radar sensor is configured in the bedroom air conditioning unit to collect human activity data within the bedroom. The second human activity data can, for example, include the coordinates of the trajectory points of the target user's activities within the preset time period. For example, using the location of the millimeter-wave sensor as the origin, the millimeter-wave sensor can directly collect the target user's position information (including angle, x-axis, and y-axis information), and the collected position information of the target user is calibrated as a dataset (xi, yi).

[0038] Millimeter-wave sensors can detect minute human movements (heart rate, breathing, etc.) and location. For example, when the method is implemented in a server, the air conditioner controller can upload the second human activity data collected by the millimeter-wave sensor to a cloud server via a communication module, and the cloud server can then retrieve the second human activity data collected by the millimeter-wave sensor uploaded by the air conditioner controller.

[0039] Step S2: Based on the acquired second human activity data, identify the location of the rest area in the room.

[0040] Specifically, the mean coordinates of the trajectory points of the target user's activities within the preset time period are calculated, and the calculated mean coordinates are used as the current centroid of the rest area. Based on the current centroid and the distance between the trajectory point coordinates of the target user's activities and the current centroid, the center position, width, and length of the rest area are determined.

[0041] Specifically, the mean coordinates of the trajectory points of the target user's activities within the preset time period are calculated to obtain the current centroid (coordinates) of the rest area. Then, the distances between the trajectory point coordinates of the target user's activities and the current centroid are calculated, and the number of trajectory points equidistant from the current centroid is determined. This number is then compared to a preset number. If the number of trajectory points is greater than or equal to the preset number, the current centroid is determined as the center position of the rest area, and the width and length of the rest area are determined based on this center position. If the number of trajectory points is less than the preset number, ... The process involves extracting the coordinates of trajectory points equidistant from the current centroid; calculating the average of these coordinates and using the average coordinates as the current centroid of the rest area; iterating through and calculating the distances between the target user's activity trajectory points and the current centroid, and comparing the number of trajectory points equidistant from the current centroid with a preset number; ... until the number of trajectory points equidistant from the current centroid is greater than or equal to the preset number, then determining the current centroid as the center position of the rest area and determining the width and length of the rest area based on the center position. In other words, this process repeats the steps of iterating through and calculating the distances between the target user's activity trajectory points and the current centroid, and comparing the number of trajectory points equidistant from the current centroid with a preset number, until the number of trajectory points equidistant from the current centroid is greater than or equal to the preset number, then determining the current centroid as the center position of the rest area and determining the width and length of the rest area based on the center position. The center position is the current centroid when the number of trajectory points equidistant from the current centroid is greater than or equal to a preset number; the width of the rest area is the distance between the trajectory points equidistant from the current centroid and the current centroid. The length of the rest area is a preset value; for example, if the rest area is a bed, the length of the bed is generally a fixed value.

[0042] Taking the identification of the area where the bed is located as an example: the activity status of a person at the edge of the bed, such as... Figure 3a As shown, Figure 3aThe image shows the trajectory of a person moving around the edge of the bed.

[0043] (1) A millimeter-wave sensor collects data on the target user's activities at the edge of the bed and performs coordinate transformation to obtain a calibration dataset (xi,yi) of the trajectory points of the target user's activities, i=1,2,3,4……

[0044] (2) Calculate the mean coordinates of the dataset The mean is used as the initial centroid (p,q), which is the current centroid of the resting region.

[0045] (3) Traverse and calculate the distance between each coordinate data (xi, yi) and the current centroid.

[0046] (4) Calculate the number of items that are equal to d, and denote them as m.

[0047] (5) Compare m with a preset value (e.g., F = 100). If m < F, extract the coordinate dataset (xj, yj) of the trajectory points with the same calculated d. The preset value F is a constant set during algorithm design. Its purpose is to collect and process a certain amount of sample data to identify the bed's position. Here, F is preset to 100 to achieve and calculate a certain amount of data to identify the bed's position. (The distances from the left and right sides of the bed to the centroid are equal; setting F to 100 is sufficient to identify the bed's position.)

[0048] (6) Calculate the mean coordinates of the extracted coordinate dataset (xj, yj). Use the mean coordinates as the current centroid.

[0049] (7) Repeat steps (3), (4), and (5) until m ≥ F. At this point, find the centroid, which is the center position of the bed and the width of the bed. The width is the d value of the number of equal distances satisfying F. Figure 3b As shown, Figure 3b The center position of the bed is shown.

[0050] (8) Based on the lowest value of different d values ​​and empirical modal analysis, the expected length of the bed is obtained, thereby identifying the bed.

[0051] For example, based on experience and estimation, the length of a typical bed is around 2 meters. If the value of d is 1.2m, meaning the width of the bed is 1.2m, then it can be classified as a children's bed. Based on experience and assessment, the bed length is estimated to be 1.8 to 2 meters. Therefore, the bed area can be defined as 2 x 1.2m. 2 If the d-value is 1.8m, it can be determined to be a double bed. Based on experience and analysis, the bed length is determined to be 2-2.2m. Therefore, the bed area can be defined as 2.2m x 1.8m. 2 .

[0052] The specific implementation method described above for determining the resting area in a room can learn and adjust itself based on continuously collected data to adapt to possible changes in the bedroom layout. Through feedback and correction, the algorithm can continuously optimize the bed position recognition results, improving the system's performance and adaptability.

[0053] In another specific implementation, based on the coordinates of the trajectory points of the target user's activities within the preset time period, the initial dwelling area of ​​the target user after entering the room and / or the area where the target user stays for the longest time in the room are identified; based on the identified initial dwelling area of ​​the target user after entering the room and / or the area where the target user stays for the longest time in the room, the resting area of ​​the room is determined.

[0054] The bed in the bedroom is usually the first place people touch upon upon entering and where they spend a significant amount of time. By analyzing daily human activity data, we can identify the areas where target users initially spend the most time in the bedroom and mark them as the location of the bed.

[0055] For example, a cloud server uses machine learning algorithms to determine the bed's location based on the initial and longest-staying position a person makes upon entering the bedroom. For instance, a Convolutional Neural Network (CNN) or a Long Short-Term Memory (LSTM) neural network can be used to identify the initial area the target user initially stays in the room and / or the area where the target user spends the longest time in the room. Furthermore, classification algorithms such as Support Vector Machines (SVM), decision trees, and random forests can be used to identify the resting area (e.g., the bed's location) in the room to enhance the algorithm's accuracy and reliability.

[0056] Step S130: If it is determined that the target user is in the rest area, then determine whether the target user is in a sleeping state based on the acquired first human activity data.

[0057] Specifically, the first human activity data includes: human posture, movement, respiratory rate, and / or heart rate. Based on the human posture and / or movement in the acquired first human activity data, it can be determined whether the target user's activity pattern in the rest area is a preset activity pattern; if the activity pattern is determined to be a preset activity pattern, then it can be determined whether the target user is in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

[0058] The activity mode may specifically include at least one of micro-movement, sitting, and lying down. The preset activity mode may include, for example, lying down and / or micro-movement. Whether the target user is lying down and / or micro-moving can be identified based on the human posture and / or movements in the acquired first human activity data. When the user has no obvious activity or micro-movement for a certain period of time, the system can intelligently identify whether the user is asleep by analyzing the user's respiratory rate and / or heart rate.

[0059] Millimeter-wave radar can measure minute movements of objects, including breathing, micro-movements, and heartbeats. It captures these minute movements by monitoring changes in the phase and frequency of microwave signals reflected from the human body. When a person moves slightly, the phase and frequency of the reflected signal also change slightly, which millimeter-wave radar can detect and interpret as micro-movements. Millimeter-wave radar can also detect changes in human posture, such as sitting or lying down. This is achieved by monitoring changes in the reflected signal over time. When a person changes from standing to sitting or lying down, the reflected signal changes significantly, which millimeter-wave radar can detect and interpret as sitting, lying down, or other similar actions.

[0060] Millimeter-wave radar detects human breathing activity by utilizing the electromagnetic wave characteristics of the millimeter-wave frequency band to sense minute movements of the body, including those of the chest and abdomen, and to detect respiratory rate. For example, the respiratory rate during sleep typically undergoes a series of changes before and during the sleep process. The respiratory rate is usually relatively stable before falling asleep, and gradually decreases as the body enters a sleep state. The trend of respiratory rate changes from before to during sleep is as follows: Before falling asleep: Before entering sleep, the respiratory rate is generally at a relatively stable level, similar to that of the waking state, typically around 16-20 breaths per minute; During the sleep process: As the body enters a sleep state, the respiratory rate gradually decreases. In the early stages of sleep, the respiratory rate may be 12-16 breaths per minute. As the body enters deeper sleep, the respiratory rate continues to decrease, typically between 8-12 breaths per minute.

[0061] Step S140: If it is determined that the target user is in a sleep state, then control the air conditioner to operate according to the preset sleep mode.

[0062] For example, when the method is implemented in a cloud server, when the cloud server identifies that the user is in a rest area and has entered a sleep state based on the data collected by the millimeter-wave sensor, the cloud server sends a control command to the air conditioning device to automatically adjust the air conditioning to a preset sleep mode and provide a comfortable sleep environment.

[0063] To clearly illustrate the technical solution of the present invention, the execution flow of the air conditioner control method provided by the present invention will be described below with reference to a specific embodiment.

[0064] Figure 4 This is a schematic diagram of a specific embodiment of the air conditioner control method provided by the present invention. Figure 4 As shown,

[0065] The air conditioner's millimeter-wave sensor collects human activity data in the bedroom and uploads it to a cloud server. The cloud server uses machine learning algorithms to process the data, analyzing the location and activity patterns of the human body. The cloud server's machine learning algorithm identifies activity patterns in the bed area. When it determines that the user has entered a sleep state, the cloud server instructs the air conditioner to adjust its operating parameters. Upon receiving the instruction from the cloud server, the air conditioner automatically adjusts to the preset sleep mode.

[0066] The present invention also provides a control device for an air conditioner. The device can be implemented in an air conditioner controller or in a server, such as a cloud server.

[0067] Figure 5 This is a schematic diagram of an embodiment of the air conditioner control device provided by the present invention. Figure 5 As shown, the control device 100 includes an acquisition unit 110, a first determination unit 120, a second determination unit 130, and a control unit 140.

[0068] The acquisition unit 110 is used to acquire the first human activity data of the target user in the room when the air conditioner is running.

[0069] In one specific embodiment, the acquisition unit 110 can collect first human activity data of a target user within a room using a millimeter-wave radar sensor. The room is preferably a bedroom. For example, a millimeter-wave radar sensor can be configured in a bedroom air conditioning unit to collect human activity data within the bedroom. The millimeter-wave sensor transmits millimeter-wave signals and receives echo signals; by analyzing the echo data, it can obtain high-precision information on object position and motion. Optionally, the collected human activity data can be preprocessed, including noise reduction, data normalization, and / or time period setting (time information of the human activity data, which facilitates filtering out invalid data, such as data collected when a user enters the room in the morning, as users typically only enter briefly during this time period and are considered invalid data), to reduce noise and interference in the data and to standardize the data to an appropriate scale.

[0070] The first human activity data may include, for example, human posture, movement, respiratory rate, and / or heart rate. Millimeter-wave sensors are capable of sensing minute human movements (heart rate, breathing, etc.) and positional changes. For example, when the method is implemented in a server, the air conditioner controller can upload the first human activity data collected by the millimeter-wave sensor to a cloud server via a communication module. The cloud server (acquisition unit 110) then acquires the first human activity data collected by the millimeter-wave sensor uploaded by the air conditioner controller.

[0071] The first determining unit 120 is used to determine whether the target user is in the rest area of ​​the room based on the first human activity data of the target user obtained by the obtaining unit 110.

[0072] The first human activity data may further include the location of the target user. The first determining unit 120 can determine whether the target user is in the rest area of ​​the room based on the location of the target user. The rest area is the area within the room where the user rests. For example, it could be the area where the bed is located in a bedroom. The rest area of ​​the room can be determined by analyzing the human activity data within the room.

[0073] The device 100 further includes a third determining unit (not shown) for determining the rest area of ​​the room.

[0074] The third determining unit determines the rest area of ​​the room, which may specifically include: acquiring second human activity data of the target user in the room within a preset time period; and identifying the location of the rest area of ​​the room based on the acquired second human activity data.

[0075] In one specific implementation, a millimeter-wave radar sensor can collect second human activity data of a target user within a room over a preset time period. The preset time period can be, for example, a sleep period, such as 22:00 to 6:00 the next day. A millimeter-wave radar sensor is configured in the bedroom air conditioning unit to collect human activity data within the bedroom. The second human activity data can, for example, include the coordinates of the trajectory points of the target user's activities within the preset time period. For example, using the location of the millimeter-wave sensor as the origin, the millimeter-wave sensor can directly collect the target user's position information (including angle, x-axis, and y-axis information), and the collected position information of the target user is calibrated as a dataset (xi, yi).

[0076] Millimeter-wave sensors can detect minute human movements (heart rate, breathing, etc.) and location. For example, when the method is implemented in a server, the air conditioner controller can upload the second human activity data collected by the millimeter-wave sensor to a cloud server via a communication module, and the cloud server can then retrieve the second human activity data collected by the millimeter-wave sensor uploaded by the air conditioner controller.

[0077] The third determining unit, based on the acquired second human activity data, identifies the location of the rest area in the room. Specifically, this may include: calculating the average coordinates of the trajectory points of the target user's activities within the preset time period, and using the calculated average coordinates as the current centroid of the rest area. Based on the current centroid and the distance between the trajectory points of the target user's activities and the current centroid, the center position, width, and length of the rest area are determined.

[0078] Specifically, the mean coordinates of the trajectory points of the target user's activities within the preset time period are calculated to obtain the current centroid of the rest area. Then, the distances between the trajectory point coordinates of the target user's activities and the current centroid are calculated iteratively, and the number of trajectory points equidistant from the current centroid is determined. This number is then compared to a preset number. If the number of trajectory points is greater than or equal to the preset number, the current centroid is determined as the center position of the rest area, and the width and length of the rest area are determined based on this center position. If the number of trajectory points is less than the preset number... The process involves: extracting the coordinates of trajectory points equidistant from the current centroid; calculating the average of these coordinates and using the average as the current centroid of the rest area; iterating through and calculating the distances between the target user's activity trajectory points and the current centroid, and comparing the number of trajectory points equidistant from the current centroid with a preset number; and continuing until the number of trajectory points equidistant from the current centroid is greater than or equal to the preset number, then determining the current centroid as the center of the rest area and determining the width and length of the rest area based on the center position. This process is repeated until the number of trajectory points equidistant from the current centroid is greater than or equal to the preset number, at which point the current centroid is determined as the center of the rest area and the width and length of the rest area are determined based on the center position. The center position is the current centroid when the number of trajectory points equidistant from the current centroid is greater than or equal to a preset number; the width of the rest area is the distance between the trajectory points equidistant from the current centroid and the current centroid. The length of the rest area is a preset value; for example, if the rest area is a bed, the length of the bed is generally a fixed value.

[0079] Taking the identification of the area where the bed is located as an example: the activity status of a person at the edge of the bed, such as... Figure 3a As shown, Figure 3a The image shows the trajectory of a person moving around the edge of the bed.

[0080] (1) A millimeter-wave sensor collects data on the target user's activities at the edge of the bed and performs coordinate transformation to obtain a calibration dataset (xi,yi) of the trajectory points of the target user's activities, i=1,2,3,4……

[0081] (2) Calculate the mean of the dataset The mean is used as the initial centroid (p,q), which is the current centroid of the resting region.

[0082] (3) Traverse and calculate the distance between each coordinate data (xi, yi) and the current centroid.

[0083] (4) Calculate the number of items that are equal to d, and denote them as m.

[0084] (5) Compare m with a preset value (e.g., F = 100). If m < F, extract the coordinate dataset (xj, yj) of the trajectory points with the same calculated d. The preset value F is a constant set during algorithm design. Its purpose is to collect and process a certain amount of sample data to identify the bed's position. Here, F is preset to 100 to achieve and calculate a certain amount of data to identify the bed's position. (The distances from the left and right sides of the bed to the centroid are equal; setting F to 100 is sufficient to identify the bed's position.)

[0085] (6) Calculate the mean coordinates of the extracted coordinate dataset (xj, yj). Use the mean coordinates as the current centroid.

[0086] (7) Repeat steps (3), (4), and (5) until m ≥ F. At this point, find the centroid, which is the center position of the bed and the width of the bed. The width is the d value of the number of equal distances satisfying F. Figure 3b As shown, Figure 3b The center position of the bed is shown. The indicated location.

[0087] (8) Based on the lowest value of different d values ​​and empirical modal analysis, the expected length of the bed is obtained, thereby identifying the bed.

[0088] For example, based on experience and estimation, the length of a typical bed is around 2 meters. If the value of 'd' is 1.2m, meaning the width of the bed is 1.2m, it can be identified as a children's bed. Based on experience and assessment, the bed length is estimated to be 1.8 to 2m. Therefore, the bed area can be defined as 2 * 1.2m². If the value of 'd' is 1.8m, it can be identified as a double bed. Based on experience and assessment, the bed length is estimated to be 2 to 2.2m. Therefore, the bed area can be defined as 2.2 * 1.8m².

[0089] The specific implementation method described above for determining the resting area in a room can learn and adjust itself based on continuously collected data to adapt to possible changes in the bedroom layout. Through feedback and correction, the algorithm can continuously optimize the bed position recognition results, improving the system's performance and adaptability.

[0090] In another specific embodiment, the third determining unit identifies the initial dwelling area of ​​the target user after entering the room and / or the area where the target user stays for the longest time in the room based on the coordinates of the trajectory points of the target user's activities within the preset time period; and determines the resting area of ​​the room based on the identified initial dwelling area of ​​the target user after entering the room and / or the area where the target user stays for the longest time in the room.

[0091] The bed in the bedroom is usually the first place people touch upon upon entering and where they spend a significant amount of time. By analyzing daily human activity data, we can identify the areas where target users initially spend the most time in the bedroom and mark them as the location of the bed.

[0092] For example, a cloud server uses machine learning algorithms to determine the bed's location based on the initial and longest-staying position a person makes upon entering the bedroom. For instance, a Convolutional Neural Network (CNN) or a Long Short-Term Memory (LSTM) neural network can be used to identify the initial area the target user initially stays in the room and / or the area where the target user spends the longest time in the room. Furthermore, classification algorithms such as Support Vector Machines (SVM), decision trees, and random forests can be used to identify the resting area (e.g., the bed's location) in the room to enhance the algorithm's accuracy and reliability.

[0093] The second determining unit 130 is used to determine whether the target user is in a sleeping state based on the first human activity data acquired by the acquiring unit 110 if the first determining unit 120 determines that the target user is in the rest area.

[0094] Specifically, the first human activity data includes: human posture, movement, respiratory rate, and / or heart rate. The second determining unit 130 can determine whether the target user's activity mode in the rest area is a preset activity mode based on the human posture and / or movement in the acquired first human activity data; if the activity mode is determined to be a preset activity mode, then it determines whether the target user is in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

[0095] The activity mode may specifically include at least one of micro-movement, sitting, and lying down. The preset activity mode may include, for example, lying down and / or micro-movement. The second determining unit 130 can identify whether the target user is lying down and / or micro-moving based on the human posture and / or movement in the acquired first human activity data. When the user has no obvious activity or micro-movement for a certain period of time, the unit can intelligently identify whether the user is in a sleep state by analyzing the user's respiratory rate and / or heart rate.

[0096] Millimeter-wave radar can measure minute movements of objects, including breathing, micro-movements, and heartbeats. It captures these minute movements by monitoring changes in the phase and frequency of microwave signals reflected from the human body. When a person moves slightly, the phase and frequency of the reflected signal also change slightly, which millimeter-wave radar can detect and interpret as micro-movements. Millimeter-wave radar can also detect changes in human posture, such as sitting or lying down. This is achieved by monitoring changes in the reflected signal over time. When a person changes from standing to sitting or lying down, the reflected signal changes significantly, which millimeter-wave radar can detect and interpret as sitting, lying down, or other similar actions.

[0097] Millimeter-wave radar detects human breathing activity by utilizing the electromagnetic wave characteristics of the millimeter-wave frequency band to sense minute movements of the body, including those of the chest and abdomen, and to detect respiratory rate. The respiratory rate typically undergoes a series of changes before and during sleep. The respiratory rate is usually relatively stable before falling asleep, gradually decreasing as the body enters a sleep state. The trend of respiratory rate changes from before to during sleep is as follows: Before falling asleep: Before entering sleep, the respiratory rate is generally at a relatively stable level, similar to the waking state, typically around 16-20 breaths per minute; During sleep: As the body enters a sleep state, the respiratory rate gradually decreases. In the early stages of sleep, the respiratory rate may be 12-16 breaths per minute. As the body enters deeper sleep, the respiratory rate continues to decrease, typically between 8-12 breaths per minute.

[0098] The control unit 140 is configured to control the air conditioner to operate according to a preset sleep mode if the second determining unit 130 determines that the target user is in a sleep state.

[0099] For example, when the method is implemented in a cloud server, when the cloud server identifies that the user is in a rest area and has entered a sleep state based on the data collected by the millimeter-wave sensor, the cloud server sends a control command to the air conditioning device to automatically adjust the air conditioning to a preset sleep mode and provide a comfortable sleep environment.

[0100] The present invention also provides a storage medium corresponding to the control method of the air conditioner, wherein a computer program is stored thereon, and when the program is executed by a processor, the steps of any of the aforementioned methods are implemented.

[0101] The present invention also provides an air conditioner corresponding to the control method of the air conditioner, comprising a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of any of the aforementioned methods.

[0102] The present invention also provides an air conditioner corresponding to the control device of the air conditioner, including the control device of any of the aforementioned air conditioners.

[0103] Accordingly, the solution provided by this invention can automatically identify a user's sleep state and automatically adjust the air conditioner to a preset sleep mode based on the state, providing a more comfortable bedroom environment. Human activity data is collected using millimeter-wave sensors. When the system determines that the target user is in a resting area and has entered a sleep state based on the human activity data, it controls the air conditioner to enter sleep mode. The data is processed by a machine learning algorithm on a cloud server to identify the location of the resting area and the user's activity state. When the system detects that the user has entered a sleep state, it sends a control command to the air conditioning device via the cloud server, automatically adjusting the air conditioning mode to provide a comfortable sleep environment.

[0104] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0106] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0107] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0108] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A control method of an air conditioner, characterized by, include: When the air conditioner is running, the first human activity data of the target user in the room is acquired; Based on the acquired first human activity data of the target user, determine whether the target user is in the rest area of ​​the room; If it is determined that the target user is in the rest area, then it is determined whether the target user is in a sleeping state based on the acquired first human activity data; If it is determined that the target user is asleep, the air conditioner is controlled to operate according to the preset sleep mode; Determine the rest area in the room, including: Acquire second human activity data of the target user in the room within a preset time period; the second human activity data includes: coordinates of trajectory points of the target user's activities within the preset time period; Based on the acquired second human activity data, the location of the rest area in the room is identified, including: The mean coordinates of the trajectory points of the target user's activities within the preset time period are calculated, and the calculated mean coordinates are used as the current centroid of the rest area. Based on the current centroid and the distance between the coordinates of the trajectory points of the target user's activity and the current centroid, the center position, width, and length of the rest area are determined.

2. The method according to claim 1, characterized in that, Obtain the initial human activity data of the target user in the room, including: The system uses millimeter-wave radar sensors to collect data on the human activity of the target user within the room.

3. The method according to claim 1, characterized in that, The first human activity data includes: human posture, movement, respiratory rate and / or heart rate; determining whether the target user is in a sleep state based on the acquired first human activity data includes: Based on the human posture and / or movement in the first human activity data obtained, determine whether the target user's activity mode in the rest area is a preset activity mode; If the activity mode is determined to be a preset activity mode, then the target user is determined to be in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

4. A control device of an air conditioner, characterized by comprising: include: The acquisition unit is used to acquire the first human activity data of the target user in the room when the air conditioner is running; The first determining unit is used to determine whether the target user is in the rest area of ​​the room based on the first human activity data of the target user obtained by the obtaining unit. The second determining unit is configured to determine whether the target user is in a sleeping state based on the first human activity data obtained by the acquiring unit if the first determining unit determines that the target user is in the rest area. The control unit is configured to control the air conditioner to operate according to a preset sleep mode if the second determining unit determines that the target user is in a sleep state; The third determining unit is used to determine the rest area of ​​the room, including: Acquire second human activity data of the target user in the room within a preset time period; the second human activity data includes: coordinates of trajectory points of the target user's activities within the preset time period; Based on the acquired second human activity data, the location of the rest area in the room is identified, including: calculating the average coordinates of the trajectory points of the target user's activities within the preset time period, and using the calculated average coordinates as the current centroid of the rest area; and determining the center position, width, and length of the rest area based on the current centroid and the distance between the trajectory points of the target user's activities and the current centroid.

5. The apparatus according to claim 4, characterized in that, The acquisition unit acquires the first human activity data of the target user in the room, including: The system uses millimeter-wave radar sensors to collect data on the human activity of the target user within the room.

6. The apparatus according to claim 4, characterized in that, The first human activity data includes: human posture, movement, respiratory rate and / or heart rate; the first determining unit determines whether the target user is in a sleep state based on the first human activity data acquired by the acquiring unit, including: Based on the human posture and / or movement in the first human activity data obtained, determine whether the target user's activity mode in the rest area is a preset activity mode; If the activity mode is determined to be a preset activity mode, then the target user is determined to be in a sleep state based on the respiratory rate and / or heart rate in the first human activity data.

7. A storage medium, characterized by It stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-3.

8. An air conditioner, characterized in that, It includes a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of the method of any one of claims 1-3, or includes a control device as described in any one of claims 4-6.

Images