Air conditioner air supply control method, air conditioner and storage medium

Abstract

The invention provides an air conditioner air supply control method, an air conditioner and a storage medium, and the method comprises the following steps: when entering an air avoiding mode, obtaining thermal field data of a current indoor space; using a preset human body thermal field classification model to identify whether a human body target exists or not according to the thermal field data, and if yes, obtaining the human body thermal field area of the human body target and the distance between the human body target and the air conditioner; performing wind avoiding grade division according to the human body thermal field area and distance; and performing air-avoiding air supply control on the air conditioner according to the air-avoiding grade. By means of the air conditioner air supply control method, the air supply precision in the air avoiding mode can be improved, and the user experience degree is improved.

Description

Technical Field

[0001] This invention relates to the field of air conditioner technology, specifically to an air conditioning air supply control method, an air conditioner using the air supply control method, and a computer-readable storage medium using the air supply control method. Background Technology

[0002] Most existing air conditioners use a single infrared sensor to track the position of a person and deliver air at a fixed angle. This method has the following problems: it cannot distinguish between a person and a high-temperature object (such as an electric heater or furniture exposed to direct sunlight), resulting in a high false trigger rate; it relies only on the single parameter of "person position" without incorporating distance, heat field distribution, and time dimensions, resulting in a large proportion of direct airflow and a low user comfort score; and the control logic is fixed and cannot adapt to different room layouts and personalized user needs.

[0003] One existing type of air conditioner is equipped with a thermal imaging device that can acquire thermal images of an infrared detection area. These thermal images are generated based on the temperatures of various objects within the infrared detection area. The temperatures of each object can be read from the thermal images, and based on the characteristics of human body temperature, the location of a person can be accurately identified within the thermal images. According to the person's location and the air conditioner's selected operating mode, the controller adjusts the air conditioner's airflow direction, allowing the user to enjoy direct airflow or avoid direct airflow without moving. This makes the air conditioner more intelligent and better meets user needs.

[0004] However, the proposed solution does not include an air supply control strategy that adapts to the size of the human body and the distance between the human body and the air conditioner, resulting in low accuracy of the air supply control strategy.

[0005] Therefore, more optimized air supply control methods need to be considered. Summary of the Invention

[0006] The primary objective of this invention is to provide an air conditioning air supply control method that can improve the air supply accuracy in wind-avoidance mode and enhance the user experience.

[0007] The second objective of this invention is to provide an air conditioner that can improve the air delivery accuracy in wind avoidance mode and enhance the user experience.

[0008] A third objective of this invention is to provide a computer-readable storage medium that can improve the air delivery accuracy in wind-avoidance mode and enhance the user experience.

[0009] To achieve the aforementioned first objective, the air conditioning air supply control method provided by the present invention includes: when entering the wind avoidance mode, acquiring the thermal field data of the current indoor space; using a preset human thermal field classification model to identify whether there is a human target based on the thermal field data; if so, acquiring the human thermal field area of ​​the human target and the distance between the human target and the air conditioner; classifying the wind avoidance level based on the human thermal field area and distance; and controlling the air conditioner to supply air in a wind avoidance manner based on the wind avoidance level.

[0010] As can be seen from the above scheme, in the air conditioning air supply control method of the present invention, when entering the wind avoidance mode, based on thermal field data and a preset human thermal field classification model, it can more accurately distinguish between the human body and high-temperature objects (such as heaters and ovens), reducing misjudgments. By classifying the human body thermal field area and distance, the wind avoidance strategy can be adjusted in real time according to changes in human body position and shape, improving the air supply accuracy in the wind avoidance mode, avoiding discomfort caused by the air conditioner blowing directly on the human body, while ensuring the overall cooling or heating efficiency of the room and improving the user experience.

[0011] In a further scheme, the step of identifying the presence of a human target based on thermal field data using a preset human thermal field classification model includes: using the preset human thermal field classification model to make predictions based on thermal field data to obtain a human thermal field mask and a confidence score corresponding to the human thermal field mask; when the confidence score is greater than a preset threshold, the presence of a human target is confirmed.

[0012] Therefore, by using a pre-set human thermal field classification model to predict based on thermal field data and obtain human thermal field masks, the complete human thermal distribution contour can be identified. Combined with confidence scores for authentication and verification, the false judgment rate of human identification is greatly reduced.

[0013] In a further scheme, the step of obtaining the human thermal field area of ​​the human target includes: determining the human thermal field area based on the human thermal field mask.

[0014] Therefore, it can be seen that using human body thermal field masks to calculate the human body thermal field area can facilitate the determination of human body size and improve detection accuracy.

[0015] In a further scheme, the steps for classifying wind-avoidance levels based on the human body's thermal field area and distance include: when the human body's thermal field area is greater than a first preset area and the distance is less than a first preset distance, the wind-avoidance level is Level 1; when the human body's thermal field area is less than or equal to the first preset area and greater than a second preset area, and the distance is greater than or equal to the first preset distance and less than or equal to the second preset distance, the wind-avoidance level is Level 2; when the human body's thermal field area is less than or equal to the second preset area, or the distance is greater than the second preset distance, the wind-avoidance level is Level 3.

[0016] Therefore, combining the two parameters of human body thermal field area and distance from the air conditioner provides a more comprehensive assessment than using a single parameter. When the human body thermal field area is greater than a first preset area and the distance is less than a first preset distance, it is considered a close-range adult or a large human body area. In this scenario, the person is directly exposed to the air conditioner's airflow and faces the highest risk of being directly exposed to strong winds, requiring the strictest wind avoidance measures. When the human body thermal field area is less than or equal to the first preset area but greater than the second preset area, and the distance is greater than or equal to the first preset distance but less than or equal to the second preset distance, it is considered a medium-distance adult, a close-range child, or a small human body area. In this scenario, although the person is not in the closest airflow area, they may still be affected by strong airflow, posing a moderate risk, requiring moderate wind avoidance measures. When the human body thermal field area is less than or equal to the second preset area, or the distance is greater than the second preset distance, it is considered a distant human body or a small heat source. In this scenario, the person is far from the core airflow area of ​​the air conditioner, facing less direct exposure and posing the lowest risk, allowing for a more lenient wind avoidance mode.

[0017] In a further proposed solution, the first preset distance and the second preset distance are determined based on the air conditioner's horsepower.

[0018] Therefore, setting distance thresholds based on horsepower can avoid either excessive or insufficient wind protection for people. If a small-horsepower air conditioner uses a distance threshold set for a large-horsepower unit, it may mistakenly classify areas without strong winds as high-risk, leading to over-adjustment and affecting cooling or heating efficiency. Conversely, if a large-horsepower air conditioner uses a distance threshold set for a small-horsepower unit, it may miss areas with strong winds at medium distances, resulting in untimely wind protection for people. Furthermore, it can adapt to the airflow needs of different spaces. Large-horsepower air conditioners are typically used in large spaces with a wider range of human activity, requiring a larger distance threshold to cover potentially affected areas. Small-horsepower air conditioners used in small spaces may have excessively large distance thresholds, causing most areas to be classified as requiring wind protection for people, thus negatively impacting the user experience.

[0019] In a further scheme, the steps for controlling the air conditioner's air supply to avoid human presence based on the human presence level include: when the human presence level is Level 1, performing at least one of the following: prohibiting the left and right sweeping angles from covering the area of ​​the human target; reducing the airflow speed to a first preset speed; limiting the up and down sweeping angles to the range of a first preset sweeping angle, with the first preset sweeping angle located above the top of the human target; and / or when the human presence level is Level 2, performing at least one of the following: deflecting the left and right sweeping angles to the left or right of the area of ​​the human target by a preset angle; reducing the airflow speed to a second preset speed, with the second preset speed being greater than the first preset speed; and / or when the human presence level is Level 3, maintaining the current air supply mode.

[0020] Therefore, Level 1 requires the strictest wind-avoidance measures to prioritize human comfort. Level 2 allows for moderate wind-avoidance measures to balance comfort and heat exchange efficiency. Level 3 maintains the current mode, minimizing unnecessary adjustments. In low-to-medium risk scenarios, temperature control efficiency is considered while reducing energy consumption caused by frequent adjustments, such as energy loss from repeatedly starting and stopping fans and switching angles.

[0021] In a further proposed solution, after the step of controlling the air conditioner's air supply to avoid human presence based on the wind avoidance level, the solution also includes: detecting the hand gestures of at least one human target using a camera; and executing the corresponding air supply mode based on the hand gestures.

[0022] It is evident that the wind avoidance level classification is based on the thermal field area and distance. While it can handle most scenarios, it cannot identify the user's personalized preferences. Gesture interaction provides users with the convenience of real-time control, and gesture interaction can quickly respond to instantaneous changes.

[0023] In a further proposed solution, the steps for executing the corresponding air supply mode based on the gesture include: determining whether a temporary wind avoidance command is triggered based on the gesture; if so, executing a preset temporary wind avoidance operation within a preset duration.

[0024] Therefore, when the trigger signal of the temporary wind shelter command is obtained, the preset temporary wind shelter operation is executed within the preset time. This can not only meet the needs of the temporary wind shelter, but also avoid room temperature imbalance caused by long-term deviation from the basic mode.

[0025] In a further scheme, the preset temporary wind avoidance operation includes at least one of the following: prohibiting wind from blowing into the preset area of ​​the human target who issued the temporary wind avoidance command; reducing the wind speed to a third preset wind speed.

[0026] Therefore, by pre-setting temporary wind avoidance operation, it is possible to avoid blowing wind towards the target area of ​​the human body or reduce the wind speed, thereby improving the user experience.

[0027] To achieve the second objective of the present invention, the present invention provides an air conditioner including a processor and a memory, the memory storing a computer program, which, when executed by the processor, implements the steps of the above-described air conditioning air supply control method.

[0028] To achieve the third objective of the present invention, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a controller, implements the steps of the above-described air conditioning air supply control method. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of an air conditioner that applies the air supply control method of the present invention.

[0030] Figure 2 This is a flowchart of an embodiment of the air conditioning air supply control method of the present invention.

[0031] Figure 3 This is a flowchart illustrating the step of identifying the presence of a human target based on thermal field data using a preset human thermal field classification model in an embodiment of the air conditioning air supply control method of the present invention.

[0032] Figure 4 This is a flowchart following the step of controlling the air conditioner's air supply according to the wind avoidance level in an embodiment of the air conditioner air supply control method of the present invention.

[0033] Figure 5 This is a flowchart of the steps for executing the corresponding air supply mode based on a gesture in an embodiment of the air conditioning air supply control method of the present invention.

[0034] The present invention will be further described below with reference to the accompanying drawings and embodiments. Detailed Implementation

[0035] The air conditioning air supply control method of the present invention is an application program used in air conditioners to control the air supply of air conditioners.

[0036] Preferred, such as Figure 1 As shown, the air conditioner includes a main control circuit 1, a thermopile sensor 2, a time-of-flight (ToF) ranging module 3, and a camera 4. The thermopile sensor 2, the time-of-flight ranging module 3, and the camera 4 are all electrically connected to the main control circuit 1. The thermopile sensor 2 is used to acquire thermal field data of the current indoor space, including temperature data at various locations within the space. Preferably, the thermopile sensor 2 is an 8×8 matrix thermopile sensor. The time-of-flight ranging module 3 is used to acquire the horizontal distance between objects and the air conditioner. The camera 4 is used to acquire human images for recognizing human gestures.

[0037] Example of air conditioning air supply control method: like Figure 2As shown in this embodiment, when the air conditioning air supply control method is working, it first executes step S1, and when entering the wind avoidance mode, it acquires the thermal field data of the current indoor space. The wind avoidance mode can be entered by the user through a remote control or control panel. When entering the wind avoidance mode, in order to better perform the wind avoidance operation, it is necessary to acquire the thermal field data of the current indoor space to confirm whether there is a human target. The thermal field data of the current indoor space can be acquired by thermopile sensor 2, which collects the thermal field data of the current indoor space at a frequency of 5fps. When the air conditioner starts up, the thermopile sensor 2 will first scan the front indoor space and record the temperature of each position in the front indoor space. This temperature data is the initial thermal field baseline temperature. Its function is to eliminate the influence of ambient temperature when identifying human targets. For example, if the ambient temperature suddenly rises, the system can accurately determine which temperature changes are caused by human activity rather than changes in the environment itself by comparing the current temperature with the initial thermal field baseline temperature. For example, when the air conditioner is turned on in summer, the initial thermal field baseline temperature will record the temperature of the air-conditioned environment. When someone enters, the system can accurately identify the thermal signal of the human body.

[0038] After acquiring the thermal field data of the current indoor space, step S2 is executed to identify the presence of human targets based on the thermal field data using a preset human thermal field classification model. This preset human thermal field classification model is generated using a convolutional neural network. Based on the thermal field data and the preset human thermal field classification model, the model can more accurately distinguish between human bodies and high-temperature objects, thereby reducing false positives.

[0039] In this embodiment, see Figure 3When identifying the presence of a human target using a preset human thermal field classification model based on thermal field data, step S11 is first executed. The preset human thermal field classification model is used to predict based on the thermal field data, obtaining a human thermal field mask and a corresponding confidence score. Using the preset human thermal field classification model to predict based on thermal field data and obtain a human thermal field mask can identify the complete thermal distribution contour of the human body. Combined with the confidence score for authentication verification, this significantly reduces the false positive rate of human identification. Inputting the obtained thermal field data into the preset human thermal field classification model outputs a human thermal field mask. The human thermal field mask is a region extracted from thermal imaging data. In the thermal imaging image, the human body region is automatically identified based on the temperature distribution (similar to using different colors to outline each human target). Meanwhile, the preset human thermal field classification model also generates a confidence score corresponding to the human thermal field mask. The confidence score is a probability score of the human body derived from multiple features. For example, the preset human thermal field classification model analyzes the input features through a convolutional neural network (CNN) to analyze whether the temperature distribution conforms to human characteristics (such as high temperature at the center and low temperature at the edge), whether the shape is similar to a human figure (such as an upright cylinder), and whether there are signs of movement (such as moving or waving). The confidence score is determined based on the input features.

[0040] After obtaining the confidence score, step S12 is executed to determine whether the confidence score is greater than a preset threshold. The preset threshold can be pre-set based on the experimental data; for example, the preset threshold is 80 points.

[0041] When the confidence score is greater than a preset threshold, step S13 is executed to confirm the existence of a human target. A confidence score greater than the preset threshold indicates that almost all features match those of a human target; therefore, it can be confirmed that the human thermal mask corresponds to a human target. When the confidence score is less than or equal to the preset threshold, step S14 is executed to confirm the absence of a human target. A confidence score less than or equal to the preset threshold suggests that the thermal mask may be caused by a high-temperature object, and therefore no human target exists.

[0042] After confirming the presence of a human target, step S3 is executed to obtain the thermal field area of ​​the human target and the distance between the human target and the air conditioner. To more precisely control the air conditioner's wind-avoidance operation, it is necessary to obtain the thermal field area of ​​the human target and the distance between the human target and the air conditioner for further control.

[0043] In this embodiment, the step of obtaining the thermal field area of ​​a human target includes: determining the thermal field area of ​​the human body based on a thermal field mask. The thermal field mask is a binary matrix (such as an 8×8 pixel matrix) output by a preset thermal field classification model to mark the thermal field region of the human body. Using the pixels of the thermal field mask, the thermal field area of ​​the human body can be calculated, which facilitates the determination of the human body's size and improves detection accuracy.

[0044] The distance between the human target and the air conditioner can be obtained through the time-of-flight ranging module 3. After identifying the human target, the distance between the human target and the air conditioner can be determined using the time-of-flight ranging module 3.

[0045] After obtaining the thermal field area of ​​the human target and the distance between the human target and the air conditioner, step S4 is executed to classify the wind avoidance level based on the thermal field area and distance of the human target.

[0046] In this embodiment, the step of classifying the wind avoidance level based on the human body thermal field area and distance includes: when the human body thermal field area is greater than a first preset area and the distance is less than a preset first preset distance, the wind avoidance level is level one; when the human body thermal field area is less than or equal to the first preset area and greater than a second preset area, and the distance is greater than or equal to the preset first preset distance and less than or equal to the preset second preset distance, the wind avoidance level is level two; when the human body thermal field area is less than or equal to the second preset area, or the distance is greater than the second preset distance, the wind avoidance level is level three.

[0047] The system combines two parameters—human body thermal field area and distance from the air conditioner—for a more comprehensive assessment than a single parameter. When the human body thermal field area is greater than a first preset area and the distance is less than a first preset distance, it is considered a close-range adult or a large human body area. In this scenario, the person is directly exposed to the air conditioner's airflow and faces the highest risk of being directly exposed to strong winds, requiring the strictest wind avoidance measures. When the human body thermal field area is less than or equal to the first preset area but greater than the second preset area, and the distance is greater than or equal to the first preset distance but less than or equal to the second preset distance, it is considered a medium-distance adult, a close-range child, or a small human body area. In this scenario, although the person is not in the closest airflow area, they may still be affected by strong airflow, posing a moderate risk, requiring moderate wind avoidance measures. When the human body thermal field area is less than or equal to the second preset area, or the distance is greater than the second preset distance, it is considered a distant human body or a small heat source. In this scenario, the person is far from the core airflow area of ​​the air conditioner, facing less direct exposure and posing the lowest risk, allowing for a more lenient wind avoidance mode.

[0048] In this embodiment, the first preset distance and the second preset distance are determined based on the air conditioner's horsepower. Setting distance thresholds according to horsepower avoids either excessive or insufficient wind protection for people. If a small-horsepower air conditioner uses a distance threshold set for a large-horsepower unit, it may mistakenly classify areas without strong winds as high-risk, leading to over-adjustment and affecting cooling or heating efficiency. If a large-horsepower air conditioner uses a distance threshold set for a small-horsepower unit, it may miss medium-distance areas with strong winds, resulting in untimely wind protection for people. Simultaneously, it can adapt to the air supply needs of different spaces. Large-horsepower air conditioners are typically used in large spaces with a wider range of human activity, requiring a larger distance threshold to cover potentially affected areas. Small-horsepower air conditioners are used in small spaces; an excessively large distance threshold would cause most areas to be classified as requiring wind protection for people, negatively impacting the user experience.

[0049] After obtaining the wind avoidance level, proceed to step S5 to control the air conditioner's air supply according to the wind avoidance level. Each wind avoidance level has a corresponding wind avoidance air supply strategy. Therefore, the corresponding wind avoidance air supply strategy can be determined based on the wind avoidance level to control the air conditioner to blow air.

[0050] In this embodiment, the steps for controlling the air conditioner's airflow according to the human-avoidance level include: when the human-avoidance level is level one, performing at least one of the following: prohibiting the left and right sweeping angles from covering the area of ​​the human target; reducing the airflow speed to a first preset speed; limiting the up and down sweeping angles to a range of the first preset sweeping angles, with the first preset sweeping angle located above the top of the human target; and / or when the human-avoidance level is level two, performing at least one of the following: deflecting the left and right sweeping angles to the left or right of the human target area by a preset angle; reducing the airflow speed to a second preset speed, where the second preset speed is greater than the first preset speed; and / or when the human-avoidance level is level three, maintaining the current airflow mode. The first preset speed, second preset speed, and preset angle can be preset based on experimental data. Level one employs the most stringent human-avoidance measures, prioritizing human comfort. Level two allows for moderate human-avoidance measures, balancing comfort and heat exchange efficiency. Level three maintains the current mode, reducing unnecessary adjustments. In low- to medium-risk scenarios, temperature control efficiency is taken into account, and the energy consumption increase caused by frequent adjustments, such as the energy loss from repeatedly starting and stopping fans and switching angles, is reduced.

[0051] In this embodiment, see Figure 4After controlling the air conditioner's airflow according to the wind avoidance level, step S6 is executed, which uses camera 4 to detect the hand gestures of at least one human target. Since the wind avoidance level is based on thermal field area and distance, while it can handle most scenarios, it cannot recognize the user's personalized preferences. Gesture interaction provides users with the convenience of real-time control, and gesture interaction can quickly respond to immediate changes. Therefore, camera 4 detects the hand gestures of at least one human target for corresponding control. Images are acquired by camera 4, and combined with computer vision algorithms (such as gesture recognition models) to extract the hand feature points of at least one human target, determining the gesture type and intent. Examples include waving gestures (left / right or up / down waving lasting more than 0.5 seconds); palm orientation (e.g., palm facing the air conditioner indicates "too strong wind," back of hand facing the air conditioner indicates "too weak wind"); gesture trajectory (e.g., drawing a circle indicates "increase the airflow range," vertical finger indicates "lock angle"); and so on.

[0052] After acquiring the human target's hand gesture, step S7 is executed, and the corresponding airflow mode is performed according to the gesture. Each preset gesture is bound to a specific airflow adjustment command, forming a mapping relationship between the gesture and the airflow action. For example, a hand wave lasting more than 0.5 seconds triggers a temporary wind avoidance operation; a horizontal hand swing expands or shrinks the left and right sweeping range; a vertical hand swing adjusts the up and down sweeping angle; and a fist gesture immediately pauses the sweeping and locks the current angle.

[0053] In this embodiment, see Figure 5 When the corresponding air supply mode is executed based on the gesture, step S21 is executed to determine whether a temporary wind avoidance command is triggered based on the gesture. The gesture corresponding to the temporary wind avoidance command can be preset by the program developers, for example, a wave of the hand lasting more than 0.5 seconds.

[0054] If the hand gesture confirms that the temporary wind-avoidance command has not been triggered, then proceed to step S21 for continuous monitoring. If the hand gesture confirms that the temporary wind-avoidance command has been triggered, proceed to step S22 to execute a preset temporary wind-avoidance operation within a preset duration. The preset duration is pre-set based on experimental data. Executing the preset temporary wind-avoidance operation within the preset duration upon receiving the trigger signal for the temporary wind-avoidance command satisfies the needs of temporary wind-avoidance while avoiding room temperature imbalance caused by prolonged deviation from the basic mode.

[0055] In this embodiment, the preset temporary wind avoidance operation includes at least one of the following: prohibiting airflow towards a preset area of ​​the human target who issued the temporary wind avoidance command; reducing the airflow speed to a third preset wind speed. The third preset wind speed can be preset based on experimental data. By presetting the temporary wind avoidance operation, airflow towards the human target area can be avoided, or the airflow speed can be reduced, thereby improving the user experience.

[0056] In this embodiment, after controlling the air conditioner's airflow according to the user avoidance level, user behavior data is collected and the model is trained. The user behavior database is updated every 30 minutes, recording things like human movement trajectories, preferred areas (e.g., users in a study spend 70% of their time in the left zone), and the distribution of air conditioning usage time (an average of 120 minutes / day on weekdays). A Long Short-Term Memory (LSTM) network model is used to predict the probability distribution of human location at the same time the following day based on historical data, and the corresponding airflow parameters are pre-loaded to improve the convenience of air conditioning control.

[0057] Furthermore, when using a preset human thermal field classification model to identify the presence of human targets based on thermal field data, if the room is detected to be empty for one hour, a low-power monitoring mode is entered, the sensor module frame rate drops to 1fps, and the airflow speed is maintained at 1m / s for continuous air circulation. If the room remains empty for three hours, a reminder message asking "Do you want to turn off the air conditioner?" is automatically sent to the user's mobile phone. If the user does not respond, the system will shut down after four hours.

[0058] As described above, in the air conditioning air supply control method of the present invention, when entering the wind avoidance mode, based on thermal field data and a preset human thermal field classification model, it can more accurately distinguish between the human body and high-temperature objects (such as heaters and ovens), reducing misjudgments. By classifying the human body thermal field area and distance, the wind avoidance strategy can be adjusted in real time according to changes in human body position and shape, improving the air supply accuracy in the wind avoidance mode, avoiding discomfort caused by the air conditioner blowing directly on the human body, while ensuring the overall cooling or heating efficiency of the room and improving the user experience.

[0059] Air conditioner example: The air conditioner in this embodiment includes a controller, which executes the steps in the above-described air conditioning air supply control method embodiment when executing a computer program.

[0060] For example, a computer program can be divided into one or more modules, one or more of which are stored in memory and executed by a controller to complete the present invention. One or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in an air conditioner.

[0061] An air conditioner may include, but is not limited to, a controller and a memory. Those skilled in the art will understand that an air conditioner may include more or fewer components, or a combination of certain components, or different components; for example, an air conditioner may also include input / output devices, network access devices, buses, etc.

[0062] For example, the controller can be a Central Processing Unit (CPU), or other general-purpose controllers, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose controller can be a microcontroller or any conventional controller. The controller is the control center of the air conditioner, connecting all parts of the air conditioner through various interfaces and lines.

[0063] The memory can be used to store computer programs and / or modules. The controller implements various functions of the air conditioner by running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory. For example, the memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound receiving function, sound-to-text function, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, text data, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0064] Examples of computer-readable storage media: If the modules integrated into the air conditioner in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above air conditioning air supply control method embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a controller, it can implement the steps of the above air conditioning air supply control method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The storage medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0065] It should be noted that the above are only preferred embodiments of the present invention, but the design concept of the invention is not limited thereto. Any non-substantial modifications made to the present invention using this concept also fall within the protection scope of the present invention.

Claims

1. An air conditioning air supply control method, characterized in that, include: When entering the wind-avoidance mode, acquire the thermal field data of the current indoor space; Using a preset human thermal field classification model, identify whether there is a human target based on the thermal field data. If so, obtain the human thermal field area of ​​the human target and the distance between the human target and the air conditioner. The level of wind avoidance is classified according to the area of ​​the human body's thermal field and the distance. The air conditioner is controlled to provide airflow based on the wind avoidance level.

2. The air conditioning air supply control method according to claim 1, characterized in that: The steps for identifying the presence of a human target based on the thermal field data using a pre-defined human thermal field classification model include: The preset human thermal field classification model is used to make predictions based on the thermal field data to obtain a human thermal field mask and a confidence score corresponding to the human thermal field mask. When the confidence score is greater than a preset threshold, the presence of a human target is confirmed.

3. The air conditioning air supply control method according to claim 2, characterized in that: The steps for obtaining the thermal field area of ​​the human target include: The area of ​​the human body thermal field is determined based on the human body thermal field mask.

4. The air conditioning air supply control method according to any one of claims 1 to 3, characterized in that: The steps for classifying wind-avoidance levels based on the human body thermal field area and the distance include: When the area of ​​the human body thermal field is greater than the first preset area and the distance is less than the first preset distance, the wind avoidance level is the first level; When the area of ​​the human body thermal field is less than or equal to the first preset area and greater than the second preset area, and the distance is greater than or equal to the first preset distance and less than or equal to the second preset distance, the wind avoidance level is the second level. When the area of ​​the human body thermal field is less than or equal to the second preset area, or when the distance is greater than the second preset distance, the wind avoidance level is the third level.

5. The air conditioning air supply control method according to claim 4, characterized in that: The first preset distance and the second preset distance are determined according to the air conditioner's horsepower.

6. The air conditioning air supply control method according to claim 5, characterized in that: The steps for controlling the air conditioner's air supply to avoid human interference based on the aforementioned wind avoidance level include: When the wind avoidance level is the first level, at least one of the following shall be performed: prohibiting the left and right sweeping angles from covering the area of ​​the human target; reducing the blowing speed to a first preset wind speed; limiting the up and down sweeping angles to a first preset sweeping angle range, wherein the first preset sweeping angle is located in the area above the top of the human target; and / or When the wind avoidance level is the second level, at least one of the following is performed: the left and right sweeping angles are deflected by a preset angle to the left or right of the target area; the blowing speed is reduced to a second preset speed, where the second preset speed is greater than the first preset speed; and / or When the wind protection level is the third level, maintain the current air supply mode.

7. The air conditioning air supply control method according to any one of claims 1 to 3, characterized in that: After the step of controlling the air conditioner's air supply according to the wind avoidance level, the method further includes: The camera detects the hand gesture of at least one of the human targets; The corresponding air supply mode is executed according to the gesture.

8. The air conditioning air supply control method according to claim 7, characterized in that: The steps for executing the corresponding air supply mode based on the gesture include: The system determines whether a temporary wind avoidance command is triggered based on the gesture. If so, the system executes a preset temporary wind avoidance operation within a preset time period.

9. The air conditioning air supply control method according to claim 8, characterized in that: The preset temporary wind shelter operation includes at least one of the following: It is prohibited to blow wind into the predetermined area of ​​the human target who issued the temporary wind avoidance command; The airflow speed is reduced to the third preset speed.

10. An air conditioner, comprising a processor and a memory, characterized in that: The memory stores a computer program, which, when executed by the processor, implements the steps of the air conditioning air supply control method as described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the controller, it implements the steps of the air conditioning air supply control method as described in any one of claims 1 to 9.

Images