Control method and system of air conditioner control system and storage medium

Abstract

The embodiment of the invention provides a control method and system of an air conditioner control system and a storage medium, and belongs to the field of air conditioner control. The method comprises the following steps: receiving first detection data of a passive infrared sensor, second detection data of a visual sensor and third detection data of a multi-path detection sensor; determining the temperature confidence of the target object according to the first detection data; determining the attitude confidence of the target object according to the second detection data; according to the third detection data, the air supply path interference confidence coefficient of the target object is determined; performing confidence coefficient weighting processing according to the temperature confidence coefficient, the attitude confidence coefficient and the air supply path interference confidence coefficient to obtain a target object confidence coefficient; when the confidence coefficient of the target object is smaller than or equal to a preset first confidence coefficient threshold value, the visual sensor and the multi-path detection sensor are controlled to enter a dormant state; otherwise, the air conditioner power parameters and / or the air supply path are / is adjusted. According to the embodiment of the invention, energy consumption and use experience can be considered.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of air conditioner control, and in particular to an air conditioner control system control method, system and storage medium. BACKGROUND

[0002] With the popularization of smart home, air conditioner control systems are designed and installed for air conditioners to achieve targeted air supply and temperature control. However, the existing air conditioner control systems have the problem of high energy consumption, and the recognition accuracy is affected by many interference factors in actual use, resulting in poor user experience. Therefore, how to balance the energy consumption and user experience of the air conditioner control system is a technical problem to be solved. SUMMARY

[0003] The main purpose of the embodiments of the present application is to provide an air conditioner control system control method, system and storage medium, which can balance the energy consumption and user experience.

[0004] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application provides an air conditioner control system control method, the air conditioner control system comprising a passive infrared sensor, a visual sensor and a multi-path detection sensor, the method comprising: receiving first detection data of the passive infrared sensor, second detection data of the visual sensor and third detection data of the multi-path detection sensor, the visual sensor and the multi-path detection sensor being started after the passive infrared sensor detects that there is a moving target object in the target area; determining a temperature confidence of the target object according to the first detection data; determining a posture confidence of the target object according to the second detection data; determining a air supply path interference confidence of the target object according to the third detection data; performing confidence weighting processing according to the temperature confidence, the posture confidence and the air supply path interference confidence to obtain a target object confidence; when the target object confidence is less than or equal to a preset first confidence threshold, controlling the visual sensor and the multi-path detection sensor to enter a dormant state; otherwise, adjusting air conditioner power parameters and / or air supply path.

[0005] To achieve the above-mentioned purpose, the second aspect of the embodiments of the present application provides an air conditioner control system, comprising a passive infrared sensor, a visual sensor, a multi-path detection sensor and an air conditioner controller, the air conditioner controller being in communication connection with the passive infrared sensor, the visual sensor and the multi-path detection sensor, the air conditioner controller executing the air conditioner control system control method of any one of the first aspect.

[0006] To achieve the above object, a third aspect of the embodiments of the present application provides a computer readable storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to implement the control method of the air conditioner control system according to any one of the first aspect.

[0007] The control method, system and storage medium of the air conditioner control system provided by the present application can reduce unnecessary energy consumption by setting the passive infrared sensor to determine the wake-up time of the visual sensor and the multi-path detection sensor, and can obtain the reliability of the detection data of the three types of sensors, i.e., the passive infrared sensor, the visual sensor and the multi-path detection sensor, for identifying whether the target object is the expected target object by processing the first detection data, the second detection data and the second detection data to obtain the temperature confidence, the posture confidence and the air supply path interference confidence, and by performing confidence weighting processing on the temperature confidence, the posture confidence and the air supply path interference confidence, so that the control of the air conditioner is combined with the three types of sensors, and the adjustment time of the air conditioner power parameter and the air supply path of the air conditioner is accurate. Therefore, compared with the related art, the embodiments of the present application can balance energy consumption and user experience. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 is a flowchart of the control method of the air conditioner control system provided by the embodiments of the present application; Figure 2 is an execution flowchart of one embodiment of the control method of the air conditioner control system provided by the embodiments of the present application; Figure 3 is a structural diagram of the air conditioner control system provided by the embodiments of the present application; Figure 4 is a running diagram of one embodiment of the air conditioner control system provided by the embodiments of the present application; Figure 5 is a structural diagram of the hardware structure corresponding to the control method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0009] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0010] It should be noted that although the functional modules are divided in the device schematic diagram, the logical order is shown in the flowchart, but in some cases, the steps shown or described can be performed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the description and claims and the above figures are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0011] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application is for the purpose of describing embodiments of this application only and is not intended to be limiting of this application.

[0012] First, the meanings of several terms involved in this application are explained: PIR sensor, also known as Passive Infrared Sensor, is an electronic device that detects the presence of objects such as humans or animals by detecting their infrared radiation. It is widely used in security, smart home, and automation control fields. The target area of a PIR sensor refers to the spatial range within which it can effectively detect the infrared radiation of a human body or an animal.

[0013] ToF sensor is a depth sensing device based on the Time of Flight principle, which measures the time difference between the emission and reflection of light or sound signals to calculate the distance of an object.

[0014] With the popularization of smart home, air conditioning control systems are designed and installed for air conditioners to achieve targeted air supply and temperature control. However, existing air conditioning control systems have high energy consumption problems, and in actual use, due to many interference factors, the recognition accuracy is poor, resulting in poor user experience. In the prior art, a traditional PIR sensor is usually used to detect moving human bodies for intelligent control, but it cannot identify stationary human bodies and their positions, which can easily lead to invalid operation of the air conditioner, causing energy waste and inaccurate air supply. In some other uses, visual sensors can also be used for control, but visual sensors are greatly affected by light and have high continuous image processing power consumption. Although there are existing PIR sensor and visual sensor fusion solutions in the prior art, they only use simple logic stacking, and when different types of data sources conflict, the recognition accuracy is not enough, which can lead to inaccurate air conditioner temperature control or cooling area control, resulting in poor user experience. Therefore, how to balance energy consumption and user experience of the air conditioning control system is a technical problem to be solved. Based on this, the embodiments of the present application propose an air conditioning control system control method, system and storage medium, which can balance energy consumption and user experience.

[0015] Referring to Figure 1 As shown in the control method of the air conditioner control system provided by the embodiment of the application, the air conditioner control system comprises a passive infrared sensor, a visual sensor and a multi-path detection sensor, and the method comprises the following steps: In step S100, first detection data of the passive infrared sensor, second detection data of the visual sensor and third detection data of the multi-path detection sensor are received, and the visual sensor and the multi-path detection sensor are started after the passive infrared sensor detects that there is a moving target object in the target area; In step S200, the temperature confidence of the target object is determined according to the first detection data; In step S300, the posture confidence of the target object is determined according to the second detection data; In step S400, the air supply path interference confidence of the target object is determined according to the third detection data; In step S500, the target object confidence is obtained by performing confidence weighting processing on the temperature confidence, the posture confidence and the air supply path interference confidence; In step S600, when the target object confidence is less than or equal to a preset first confidence threshold, the visual sensor and the multi-path detection sensor are controlled to enter a dormant state; otherwise, the air conditioner power parameter and / or the air supply path are adjusted.

[0016] Therefore, by setting the passive infrared sensor to determine the wake-up time of the visual sensor and the multi-path detection sensor, unnecessary energy consumption can be reduced, and by processing the first detection data, the second detection data and the second detection data to obtain the temperature confidence, the posture confidence and the air supply path interference confidence, the reliability of the detection data of the three types of sensors, i.e., the passive infrared sensor, the visual sensor and the multi-path detection sensor, for identifying whether the target object is the expected target object can be obtained. At the same time, by performing confidence weighting processing on the temperature confidence, the posture confidence and the air supply path interference confidence, the control of the air conditioner is combined with the three types of sensors. At this time, whether the target object in the target area is moving or stationary, since multiple different dimensional data sources are used for joint evaluation, the adjustment timing of the air conditioner power parameter and the air supply path of the air conditioner is more accurate. Therefore, the embodiment of the application can balance energy consumption and user experience.

[0017] The visual sensor and the multi-path detection sensor in step S100 can be started by giving the output signal of the passive infrared sensor to the control circuit, or can be controlled by software by the above-mentioned method applied to the air conditioner controller. For this, the embodiment of the application does not make any limitation.

[0018] The visual sensor can realize image acquisition of the target object. In some embodiments, the visual sensor includes a monocular RGB camera, and a 3D pose is inversely deduced from a 2D image by combining a common 2D camera with a deep learning algorithm, so that whether the target object is an expected target object can be determined by the pose. In some embodiments, taking a human body as an expected target object, the visual sensor adopts a top-down key point detection method, detects a human body bounding box first, and then identifies single-person key points in the box. When a person is identified to enter the target area, it is judged as a normal pose at this time; if a pet dog enters the target area, it is judged as an abnormal pose.

[0019] The multi-path detection sensor can realize distance measurement of different frequency bands of light paths on the target object. In some embodiments, the multi-path detection sensor can be set as a ToF sensor.

[0020] The deployment positions of the passive infrared sensor, the visual sensor and the multi-path detection sensor are not limited in the embodiments of the present application, and can be selectively set by a person skilled in the art according to the structure of the air conditioner. The models of the passive infrared sensor, the visual sensor and the multi-path detection sensor are also not limited in the embodiments of the present application.

[0021] The first detection data is the data collected by the passive infrared sensor in the current detection period, the second detection data is the data collected by the visual sensor in the current period, and the third detection data is the data collected by the multi-path detection sensor in the current detection period. In the case that the passive infrared sensor, the visual sensor and the multi-path detection sensor are all started, the calculation of the target object confidence can be periodically scheduled or event-triggered scheduled, so that the above steps S200-S600 are executed in the detection period triggered by the scheduling.

[0022] The temperature confidence represents the reliability of the passive infrared sensor identifying the target object as an expected object. The pose confidence represents the reliability of the visual sensor identifying the target object as an expected object. The air supply path interference confidence represents the reliability of the multi-path detection sensor identifying the position as an expected object.

[0023] The target object confidence represents the reliability of the target object identified by the passive infrared sensor, the multi-path detection sensor and the visual sensor as an expected object.

[0024] The air conditioner power parameter represents a parameter affecting the power of the air conditioner, such as air speed, compressor frequency, etc., and the air conditioner power parameter is set to at least one.

[0025] The adjustment of the air supply path is used to realize accurate air supply to the target object, so that the air supply angle can be adjusted following the target object. When it is determined that the target object detected in the target area is the expected target object based on the target object confidence, the spatial polar coordinates of the target object can be drawn by the visual sensor + multi-path detection sensor, wherein the visual sensor outputs 2D plane coordinates and the multi-path detection sensor outputs longitudinal distance. At this time, the air deflector can be adjusted based on the spatial polar coordinates to accurately follow the air blowing of the air conditioning unit to the target object. Compared with the existing air supply path, only up and down and left and right mechanical reciprocating motion is allowed, and the use experience is better.

[0026] Less than or equal to the first confidence threshold value indicates that the identified target object is not the expected target object. In some embodiments, multiple confidence threshold values can also be set, so that the identification result can be classified in multiple levels for further fine control. For example, assuming that two confidence threshold values are set, 0.4 and 0.7 respectively, wherein 0.4 is the first confidence threshold value, 0.4-0.7 indicates that although there is a measurement error of the sensor, the probability of identifying the expected target object is high, and greater than 0.7 indicates that there is no measurement error of the sensor, and the identification result can accurately reflect the true situation. In some embodiments, when the target object confidence P(H) > 0.7, the air conditioning unit maintains the compressor frequency configured by the user + accurate air supply, the visual sensor + multi-path detection sensor locates the human body; when 0.4 < P(H) ≤ 0.7, the air conditioning unit reduces the compressor frequency by 10% + reduces the current air speed, and all sensors remain active; when P(H) ≤ 0.4, the air conditioning unit reduces the compressor frequency by 10% + reduces the air speed and fixes the air supply, the PIR sensor remains active, and the multi-path detection sensor and the visual sensor enter sleep.

[0027] In some embodiments, the method further comprises intermittently waking up the visual sensor, such as starting the visual sensor every 20 minutes, so that it can detect whether there is a stationary target object in the target area, and when a stationary target object is detected, the multi-path detection sensor is woken up. At this time, the passive infrared sensor, the multi-path detection sensor and the visual sensor which are always active jointly participate in the identification and location of the target object. Therefore, through the intermittent waking up of the visual sensor and the active waking up of the visual sensor and the multi-path detection sensor by the passive infrared sensor, more accurate detection can be performed on the moving target object and the stationary target object, so as to further improve the use experience while reducing the increase of energy consumption as much as possible.

[0028] In some embodiments, the visual data collected by the visual sensor can be processed locally at the edge, and the visual sensor only outputs coordinates and quantity metadata; and sensitive data contained in the collected visual data is erased in real time, so that the collected visual data is stored locally without sensitive data, thereby achieving privacy protection.

[0029] It can be understood that, according to the first detection data, the temperature confidence of the target object is determined, comprising: According to the first detection data, the indoor environment temperature and the motion amplitude of the target object in the current detection period are determined; According to the indoor environment temperature, the environmental temperature interference factor in the current detection period is determined; According to the motion amplitude, the motion amplitude measurement accuracy confidence is determined; According to the weighted calculation result of the environmental temperature interference factor and the motion amplitude measurement accuracy confidence in the current detection period, the temperature confidence is determined.

[0030] The environmental temperature interference factor represents the influence degree of the environmental temperature on the detection accuracy of the passive infrared sensor. The motion amplitude measurement accuracy represents the reliability of the data of the motion amplitude of the target object detected by the passive infrared sensor without considering the environmental temperature.

[0031] For example, taking 45 degrees of environmental temperature as the reference temperature affecting the measurement accuracy of the passive infrared sensor, in some embodiments, the environmental temperature interference factor A = abs (45-Te) * 0.06; wherein Te is the indoor environment temperature; 0.06 is a temperature difference conversion factor for quantifying the temperature difference. In actual use, 45 and 0.06 can be selectively set according to actual needs.

[0032] For example, in the case of passive infrared sensor detection through a 24-zone Fresnel lens without considering the influence of ambient temperature, the motion amplitude measurement accuracy confidence B = min(1, Ma / 50), where Ma is the motion amplitude of the target object in the current detection period measured based on the passive infrared sensor, and 50 is a normalization coefficient for normalizing the motion amplitude. The normalization coefficient can be determined based on the number of zones of the Fresnel lens, for example, if the number of zones of the Fresnel lens is even, the normalization coefficient can be determined based on the number of zones, for example, if the number of zones of the Fresnel lens is even, the normalization coefficient 50 = 24*2+2. At this time, the infrared signal emitted by the object is received by different zones of the Fresnel lens, and the size of the object can be estimated according to the number of zones receiving the infrared signal, so that the object can be distinguished as a human body or a small animal. In some embodiments, the Fresnel lens can have a higher precision to collect information about the motion of the object. In some embodiments, the number of zones of the Fresnel lens can be selected according to the motion amplitude of the target object to be detected. In some embodiments, the motion amplitude can be equivalent to the integral of voltage with respect to time.

[0033] In some embodiments, when the weighted calculation result of the ambient temperature interference factor and the motion amplitude measurement accuracy confidence is less than zero, the temperature confidence is set to 0, otherwise the weighted calculation result of the ambient temperature interference factor and the motion amplitude measurement accuracy confidence is directly used as the temperature confidence, i.e. the temperature confidence P(1) = max(0, A*B). Where A is the ambient temperature interference factor, and B is the motion amplitude measurement accuracy confidence.

[0034] It can be understood that according to the second detection data, the posture confidence of the target object is determined, including: According to the second detection data, the light intensity and the posture category in the current detection period are determined; According to the light intensity, the posture interference factor of the target object in the current detection period is determined; According to the posture category, the visual measurement accuracy confidence is determined; The visual measurement accuracy confidence and the posture interference factor in the current detection period are weighted to obtain the posture confidence.

[0035] The second detection data is image data, including at least one of a picture or a video, and the second detection data can be feature extracted through a deep learning method to determine the light intensity and the posture category. The posture category represents whether it is the expected target object. When the posture category is the expected target object, the visual measurement accuracy confidence is set to 1; when the posture category is a non-expected target object, a pre-set visual error confidence is selected as the visual measurement confidence.

[0036] The posture interference factor represents the influence degree of the light intensity on the posture category recognition accuracy. The fitting formula can be obtained by simulating the collected data, so that the posture interference factor can be determined based on the fitting formula. In some embodiments, the fitting formula C = 1 - abs (Lc-600) * 0.001 is constructed. Wherein, C represents the posture interference factor, 600 is the critical value of the light intensity affecting the imaging of the visual sensor, and LC is the light intensity.

[0037] The visual measurement accuracy confidence represents the reliable degree of the recognized posture category as the expected object or the non-expected object without considering the influence of the light intensity. In some embodiments, the visual measurement accuracy confidence can be determined based on the posture category lookup table.

[0038] For example, the posture confidence P (2) = C * D. Wherein C is the posture interference factor; D is the visual measurement accuracy confidence, wherein in some embodiments, when it is determined that the posture category is the expected object, D = 1; otherwise, D = 0.3. In actual use, the value of D under different posture categories can be adjusted according to actual conditions.

[0039] It can be understood that the third detection data includes distance data obtained by measuring the distance of the target object based on multiple different frequency bands. According to the third detection data, the air supply path interference confidence of the target object is determined, including: According to the difference between the distance data of different frequency bands, a multipath interference factor is determined; The distance reliability of each distance data is estimated to determine the path measurement accuracy confidence; The multipath interference factor and the path measurement accuracy confidence are weighted to obtain the air supply path interference confidence.

[0040] The multipath interference factor represents the influence degree of the light intensity on the posture category recognition accuracy. The fitting formula can be obtained by simulating the collected data, so that the posture interference factor can be determined based on the fitting formula. In some embodiments, the fitting formula C = 1 - abs (Lc-600) * 0.001 is constructed. Wherein, C represents the posture interference factor, 600 is the critical value of the light intensity affecting the imaging of the visual sensor, and LC is the light intensity.

[0041] The distance data can be determined according to the output of the selected multi-path detection sensor. For example, if the multi-path detection sensor outputs the distance, the distance data includes the distance under different frequency bands. If the multi-path detection sensor outputs the phase, the distance data includes the phase under different frequency bands.

[0042] The path measurement accuracy confidence degree represents the reliability of the detection result of the multipath detection sensor without considering the interference factors on the light propagation path. In some embodiments, the path measurement accuracy confidence degree E = max(0.5, 1 - X / 20), X is the calculated distance, 20 is a path normalization coefficient, which can be determined based on the detection accuracy threshold of the multipath detection sensor, for example, 10 meters represents the threshold at which the detection accuracy of the multipath detection sensor appears to be erroneous, and here 10 meters is enlarged by 2 times to obtain 20 to normalize the calculated distance, so as to ensure that when the distance exceeds the threshold at which the detection accuracy appears to be erroneous, the expected baseline measurement confidence degree E = 0.5 is maintained, thereby effectively reducing errors. Wherein, 1 - X / 20 represents the actual measurement accuracy confidence degree estimated based on the measured distance. 0.5 is the lowest path measurement accuracy confidence degree without considering the interference factors on the light propagation path, that is, the baseline measurement confidence degree. Therefore, by selecting the maximum value of the baseline measurement confidence degree and the actual measurement accuracy confidence degree, the estimated measurement accuracy without considering the interference factors on the light propagation path can be obtained as the path measurement accuracy confidence degree.

[0043] For example, the air supply path interference confidence degree P(3) = E*F. Wherein E is the path measurement accuracy confidence degree, and F is the multipath interference factor; in some embodiments, the multipath interference factor F = 1 without interference factors; F = 0.2 with interference factors.

[0044] For example, taking the ToF sensor as the multipath detection sensor, the multipath interference factor is 0.2 when there is interference, otherwise it is 1. Wherein, the ToF sensor calculates the distance by measuring the phase difference between the emitted infrared light wave and the received reflected light wave. At this time, the multipath interference factor is determined by the following steps: at least 3 different frequency bands (f1, f2, f3) are used to irradiate the target object in the same frame, and the ToF sensor independently measures the phase difference (φ1, φ2, φ3) between the emitted light wave and the received light wave of each different frequency band. Wherein, φ1 is the phase difference corresponding to f1, φ2 is the phase difference corresponding to f2, and φ3 is the phase difference corresponding to f3. And through the formula Wherein di is the distance, c is the speed of light, is the phase difference, is the frequency. When the calculated di of different frequency bands fi is the same, all equal to the true object distance, it means that there is no multipath interference; the multipath interference factor is 1. The calculated di of different frequency bands fi is not the same, which means that there is multipath interference, and the multipath interference factor is set to 0.2.

[0045] It can be understood that the target object confidence is obtained by performing confidence weighting processing according to the temperature confidence, the attitude confidence and the air supply path interference confidence, including: obtaining a weight parameter group, the weight parameter group including a temperature weight coefficient corresponding to the temperature confidence, an attitude weight coefficient corresponding to the attitude confidence and a path weight coefficient corresponding to the air supply path interference confidence, at least two weight coefficients in the temperature weight coefficient, the attitude weight coefficient and the path weight coefficient being different from each other; performing weighted calculation on the temperature confidence, the attitude confidence and the air supply path interference confidence respectively with the corresponding temperature weight coefficient, the attitude weight coefficient and the path weight coefficient and summing up to obtain the target object confidence.

[0046] The weight parameter group can be pre-configured or dynamically adjusted, and a person skilled in the art can selectively set it according to actual needs. In some embodiments, taking the dynamic adjustment of the weight parameter group as an example, the weight parameter group is determined by the following steps: When the preset weight reset condition is met, the weight parameter group is set to a preset initial weight parameter group; wherein the attitude weight coefficient and the temperature weight coefficient in the initial weight parameter group are greater than the path weight coefficient; When the temperature confidence is greater than the temperature precision confidence threshold and the attitude confidence is less than or equal to the attitude precision confidence threshold, the weight parameter group is set to a temperature weight parameter group; wherein the temperature weight coefficient of the temperature weight parameter group is greater than the attitude weight coefficient and the path weight coefficient; and the temperature weight coefficient in the temperature weight parameter group is greater than the temperature weight coefficient in the initial weight parameter group; When the attitude confidence is greater than the attitude precision confidence threshold and the temperature confidence is less than or equal to the temperature precision confidence threshold, the weight parameter group is set to a visual weight parameter group; wherein the attitude weight coefficient of the visual weight parameter group is greater than the temperature weight coefficient and the path weight coefficient; and the attitude weight coefficient in the visual weight parameter group is greater than the attitude weight coefficient in the initial weight parameter group.

[0047] In the temperature weight parameter group, the temperature weight coefficient is adjusted to the highest value, so that the influence of the passive infrared sensor on the overall estimation can be improved and the influence of the visual sensor and the multi-path detection sensor on the overall estimation can be weakened.

[0048] In the visual weight parameter group, the attitude weight coefficient is adjusted to the highest value, so that the influence of the visual sensor on the overall estimation can be improved and the influence of the passive infrared sensor and the multi-path detection sensor on the overall estimation can be weakened.

[0049] The attitude confidence less than or equal to the attitude precision confidence threshold represents that the light intensity is too low, and the detection accuracy of the visual sensor is reduced.

[0050] The temperature confidence less than or equal to the temperature precision confidence threshold value indicates that the ring temperature is too high, and the passive infrared sensor precision is reduced.

[0051] In some embodiments, only the temperature weight coefficient and the posture weight coefficient in the weight parameter group are adjusted.

[0052] For example, assuming that the initial weight parameter group is (0.4, 0.4, 0.2); the visual weight parameter group is (0.2, 0.6, 0.2); and the temperature weight parameter group is (0.6, 0.2, 0.2); wherein the first parameter in each weight parameter group is the temperature weight coefficient, the second parameter is the posture weight coefficient, and the third parameter is the path weight coefficient. Taking the temperature precision confidence threshold value and the posture precision confidence threshold value as 0.5 for example, as shown in FIG. 1, the target object confidence is calculated as follows: Figure 2 S1.1, based on the first detection data, calculate the temperature confidence, wherein the temperature confidence P(1) = max(0, A*B); wherein A = abs(45-Te)*0.06, Te is the indoor environment temperature; B = min(1, Ma / 50), Ma is the motion area; S1.2, based on the second detection data, calculate the posture confidence, wherein the posture confidence P(2) = C*D. Wherein the posture interference factor C = 1-abs(Lc-600)*0.001, Lc is the light intensity; the visual measurement precision confidence D = (normal 1, abnormal 0.3); S1.3, based on the third detection data, calculate the air supply path interference confidence P(3) = E*F. Wherein the path measurement precision confidence E = max(0.5, 1-X / 20), X is the distance; the multipath interference factor F = (normal 1, interference 0.2); S2, judge P(1)≤0.5? Yes, then jump to S3, otherwise jump to S4; S3: When the temperature confidence P(1)≤0.5, that is, the environment temperature is too high, which will reduce the PIR sensor precision, then judge P(2)≤0.5? Yes, then jump to S4, otherwise jump to S5; S4, when the temperature confidence P(1)≤0.5 and the posture confidence P(2)>0.5, select the visual weight parameter group as the weight parameter group; in some embodiments, the visual sensor is turned on every 5 minutes; (such as the PIR sensor at the ring temperature of 37℃, it may not sense the human body because there is no temperature difference between the environment and the human body. When the motion amplitude is small, it may not be that the human body is moving. Therefore, the selection of the temperature weight parameter group needs to consider the comprehensive factors P(1) of the ring temperature and the motion amplitude. That is, when only P(1)≤0.5, the passive infrared sensor weight is reduced and the visual sensor weight is increased.); ​S5, when the temperature confidence P(1) > 0.5 and P(2) ≤ 0.5, the temperature weight parameter set is selected as the weight parameter set; in this case, it indicates that the light intensity is too low, which will reduce the accuracy of the visual sensor. In some embodiments, the infrared light supplement unit will also be turned on; for example, when the illuminance is lower than 100 lux, it may cause the picture to be blurred. When the posture is abnormal, it may be because there is an obstruction during shooting. Therefore, the selection of the visual weight parameter set needs to consider the comprehensive factors of light intensity and posture P(2). When only P(2) ≤ 0.5, the weight of the visual sensor is reduced, and the weight of the passive infrared sensor is increased; S6, when P(1) ≤ 0.5 and P(2) ≤ 0.5 or when P(1) is greater than 0.5 and P(2) is greater than 0.5, the initial weight parameter set is selected as the weight parameter set; S7, calculating the target object confidence according to the temperature confidence, the posture confidence, the air supply path interference confidence and the weight parameter set, and controlling the air conditioner according to the target object confidence.

[0053] It can be understood that the preset weight reset condition is met, including at least one of the following: The temperature confidence is less than or equal to the temperature accuracy confidence threshold, and the posture confidence is less than or equal to the posture accuracy confidence threshold; The target object confidence is greater than a preset second confidence threshold; the second confidence threshold is greater than the first confidence threshold; The air conditioner control system is in an energy saving mode, wherein the energy saving mode represents a condition that at least one of the following is met: the target object confidence is less than or equal to the first confidence threshold and lasts for a first time length, the passive infrared sensor does not detect a moving target object and lasts for a second time length.

[0054] The target object confidence greater than the preset second confidence threshold indicates that the detection accuracy of the visual sensor and the passive infrared sensor both meet the detection requirements.

[0055] The energy saving mode represents that there is no expected object in the target area, which can be judged by the target object confidence, and can also be judged by the passive infrared sensor. In some other embodiments, it can be judged by both ways.

[0056] For example, when the second confidence threshold is 0.8, the initial weight parameter set is selected when the target object confidence P(H) ≥ 0.8 or when P(1) ≤ 0.5 and P(2) ≤ 0.5. The energy saving mode represents that P(H) ≤ 0.4 or the PIR sensor is inaction for 30 minutes, and then the energy saving mode is entered (at this time, the compressor frequency can be reduced by 20%, and the two-grade wind speed is reduced).

[0057] It can be understood that the method further comprises: When the weight parameter group is set as the visual weight parameter group, the infrared light supplement unit is turned on.

[0058] By adding the infrared light supplement unit, the accuracy of the visual sensor detection can be further improved.

[0059] It can be understood that adjusting the air conditioner power parameter and / or the air supply path includes at least one of the following: When the target object confidence is greater than the first confidence threshold and less than or equal to the third confidence threshold, the current running air conditioner parameter is set to the air conditioner configured power parameter after being adjusted by the first proportion, and the air supply path is determined according to the current position of the target object. When the target object confidence is greater than the third confidence threshold, the air supply path is determined according to the current position of the target object, and the current running air conditioner power parameter is set to the configured air conditioner power parameter; wherein the third confidence threshold is greater than the first confidence threshold.

[0060] It can be understood that the method further includes: When the target object confidence is less than or equal to the first confidence threshold, the current running air conditioner parameter is set to the air conditioner configured power parameter after being adjusted by the first proportion, and the current air supply angle is fixed.

[0061] For example, when the third confidence threshold is 0.7 and the first confidence threshold is 0.4, when the target object confidence P(H) > 0.7, it means that the detection accuracy of each sensor is high, and there are not many interference factors, so the precise air supply is started: the compressor frequency is operated at the initial frequency, the air deflector is adjusted to blow towards the target object, and the visual sensor + multi-path detection sensor locates the target object. When 0.4 < P(H) ≤ 0.7, it means that the detection accuracy of some sensors has decreased, which may be affected by interference factors (such as ambient temperature and illumination), and it is uncertain whether the expected target object (such as a person) has entered the target area, so the compressor frequency is reduced by 10%, the damper is reduced by 1, the air deflector is adjusted to blow towards the approximate target position of the target object, and all sensors remain active. When P(H) ≤ 0.4, it means that the sensor may have misjudged, or the target object has temporarily left the target area, so the compressor frequency is reduced by 10%, the damper is reduced by 1, and the air deflector position remains unchanged. The passive infrared sensor remains active, and the multi-path detection sensor and the visual sensor enter sleep.

[0062] The method further includes: When the air conditioner control system is in the energy-saving mode, the current running air conditioner parameter is set to the air conditioner configured power parameter after being adjusted by the second proportion; wherein the adjustment range of the second proportion is greater than the adjustment range of the first proportion.

[0063] The second ratio represents the step-down of the air conditioner power parameter expected to run in the energy-saving mode relative to the air conditioner configuration power parameter. When there are multiple air conditioner configuration power parameters, the respective air conditioner configuration power parameters can use the same second ratio, or can use respective corresponding ratios. For example, the air conditioner configuration power parameters include the compressor configuration frequency and the configuration wind speed. Correspondingly, the second ratio is set to two, which are 20% and 2 grades, respectively. When in the energy-saving mode, the running compressor frequency is reduced by 20% relative to the compressor configuration frequency, and the running wind speed is reduced by 2 grades relative to the configuration wind speed.

[0064] In summary, the control method of the air conditioner control system provided in the embodiments of the present application combines the passive infrared sensor, the visual sensor, and the multi-path detection sensor. The passive infrared sensor is used to detect the human movement signal in real time, triggering the visual sensor and the multi-path detection sensor to work. The multi-path detection sensor and the visual sensor are combined to construct the indoor heat source distribution map. The visual sensor and the multi-path detection sensor are combined to respond to the signal of the passive infrared sensor and assist in detecting whether the expected target object exists in the target area. When the illumination is too low, the infrared light supplement unit is turned on to perform light supplement work, improving the measurement accuracy of the visual sensor. The combination of the visual sensor and the multi-path detection sensor can be used to draw the spatial polar coordinates of the target object. The visual sensor outputs the plane coordinates, and the multi-path detection sensor outputs the longitudinal distance. At the same time, the target object confidence is calculated in real time by dynamically distributing the weights of the sensors, realizing the hierarchical energy-saving adjustment control: when the expected target object enters the target area, the air supply is accurate; when there is no target object in the indoor area, the standby power consumption is low. Frequent start and stop of the compressor is avoided. In other embodiments, the second detection data collected by the visual sensor is locally edge-processed, and only the coordinate and quantity metadata are output. There is no cloud storage design, and the sensitive data is erased in real time.

[0065] Therefore, by the above method, the target object can be followed to supply air, the air guide can be adjusted in real time based on the coordinates, and the use experience is optimized. Compared with the traditional air conditioner, the standby power consumption is effectively reduced. At the same time, since the air supply can be accurate, the air can dynamically avoid the area without the target object, and the invalid refrigeration capacity is reduced.

[0066] It can be understood that, as shown in Figure 3 , the air conditioner control system provided in the embodiments of the present application comprises: a passive infrared sensor 100; a visual sensor 200; a multi-path detection sensor 300; an air conditioner controller 400, which is in communication connection with the passive infrared sensor 100, the visual sensor 200, and the multi-path detection sensor 300. The air conditioner controller 400 executes the following method: The first detection data of the passive infrared sensor 100, the second detection data of the visual sensor 200, and the third detection data of the multi-path detection sensor 300 are received, and the visual sensor 200 and the multi-path detection sensor 300 are started by the passive infrared sensor 100 detecting that there is a moving target object in the target area; According to the first detection data, the temperature confidence of the target object is determined; According to the second detection data, the posture confidence of the target object is determined; According to the third detection data, the air supply path interference confidence of the target object is determined; According to the temperature confidence, the posture confidence, and the air supply path interference confidence, confidence weighting processing is performed to obtain the target object confidence; When the target object confidence is less than or equal to a preset first confidence threshold, the visual sensor and the multi-path detection sensor are controlled to enter a dormant state; otherwise, the air conditioner power parameter and / or the air supply path are adjusted.

[0067] The passive infrared sensor 100, the visual sensor 200, the multi-path detection sensor 300, and the air conditioner controller 400 are all independent units.

[0068] For example, as shown in the figure, the visual sensor 200, the microcontroller MCU, the PIR sensor 100, and the multi-path detection sensor 300 are all composed of modular PCB boards, so as to improve the installation convenience. Figure 3

[0069] In some embodiments, the starting of the visual sensor 200 and the multi-path detection sensor 300 can be controlled by the air conditioner controller 400, or can be controlled by a circuit, such as the PIR sensor 100, which can use a Fresnel lens to alternately focus infrared radiation onto a pyroelectric element and use a double operational amplifier structure + RC integration circuit to indirectly measure the movement amplitude of the target object. When the expected target object enters the target area, the PIR sensor 100 detects the emitted infrared radiation, uses the pyroelectric effect to generate a weak alternating voltage signal. The first stage of the double operational amplifier structure amplifies the alternating voltage signal by 100 times and outputs it; the second stage of the double operational amplifier structure performs band-pass filtering on the amplified alternating voltage signal to filter out high-frequency noise and DC offset, and retains the 0.1~10Hz effective signal representing the movement of the target object. Then, the energy is accumulated through the RC integration circuit, and the output voltage is calculated. The output voltage threshold is set, and only when it is greater than the threshold 0.02V, the visual sensor 200 and the multi-path detection sensor 300 are woken up.

[0070] ​In some embodiments, the temperature confidence is calculated based on the motion amplitude of the target object, and the motion amplitude can be calculated by the voltage output by the RC integration circuit based on the double operational amplifier structure + RC integration circuit. wherein A is the motion amplitude, t1 to t2 is the time difference, t1 is the detection start time, t2 is the detection end time, V(t) is the voltage corresponding to the time t, and k is a constant coefficient.

[0071] In some embodiments, the visual sensor 200 in the air conditioner control system shown in Figure 3 may be an RGB camera, and the posture recognition can be performed at the same time by the deep learning algorithm to recognize the light intensity. In other embodiments, the visual sensor 200 can be integrated with an ambient light sensor and a monocular RGB camera. The ambient light sensor can sense the intensity of the light; the monocular RGB camera can perform posture recognition. In other embodiments, the visual sensor is also integrated with an infrared light supplement unit 500, which can actively turn on the infrared light supplement when the light intensity is low, and the infrared light supplement will be turned on when P(2)≤0.5. For posture recognition, 2D key point detection can be performed by the monocular RGB camera to directly detect the 2D coordinates of the main key points of the target object on the image. The key point detection method from top to bottom is to first detect the bounding box of the target object, and then identify the key points of the target object in the box. At this time, the 3D posture can be inversely deduced from the 2D image by the ordinary monocular RGB camera relying on the deep learning algorithm. When the expected target object enters the target area, it is a normal posture; if a non-expected target object (such as a small animal or other object) is identified to enter the target area, it is an abnormal posture. In some embodiments, when the visual sensor turns on the infrared light supplement unit 500, the infrared light emitted by the infrared light supplement unit 500 may affect the accuracy of the multi-path detection sensor 300. Therefore, when the visual sensor turns on the infrared light supplement and performs 2D plane sampling, the multi-path detection sensor 300 can reduce the influence by delaying the start. At the same time, the infrared light emitted by the infrared light supplement unit 500 can also avoid the infrared light of three frequency bands emitted by the multi-path detection sensor 300 to reduce the influence between them.

[0072] The multi-path detection sensor 300 determines the air supply path interference confidence by combining the interference factors on the light path to the target object. In some embodiments, the multi-path detection sensor 300 is a ToF sensor, wherein the ToF sensor calculates the distance by measuring the phase difference between the emitted infrared light wave and the received reflected light wave. The method of detecting whether there is multi-path interference is to quickly switch the use of 3 different frequency bands (f1, f2, f3) to irradiate the target within the same frame, and the sensor independently measures the phase difference (φ1, φ2, φ3) between the emitted light wave and the received light wave of each different frequency band. The formula is as follows: wherein di is the distance, and c is the speed of light. For different frequency bands fi, the calculated di is the same, which is equal to the true object distance, indicating that there is no multi-path interference; for different frequency bands fi, the calculated di is different, indicating that there is multi-path interference. At this time, the air supply path interference confidence is determined for the two cases of existing interference factors and non-existing interference factors.

[0073] For example, the air conditioner controller 400 controls the compressor frequency and the air supply gear, the multi-path detection sensor 300 is a ToF sensor, and the expected target object is a human being. The air supply gears include a silent gear, a low wind gear, a medium wind gear, a high wind gear, and a strong gear. Assuming that the air conditioner is configured with a power parameter including a high wind gear and an initial compressor frequency of 60 Hz, referring to FIG. 6, after the air conditioner is turned on, the specific steps are as follows: Figure 4 S1, the PIR sensor detects that the target object moves in the target area, and the PIR sensor wakes up the vision sensor and the ToF sensor.

[0074] S2, the target object confidence is calculated and the current running air conditioner running parameter is adjusted, as follows: Example 1: At noon, the air conditioner is turned on for cooling, and a person starts to move in the room. The PIR sensor detects that a human body enters the target area, wakes up the vision sensor and the ToF sensor, and based on the first detection data, the second detection data, and the third detection data, it can be determined that the indoor temperature Te=30℃, the illumination Lc=600 lux, the motion amplitude Ma=40, the posture is normal, the distance is 5 meters, and the multi-path interference is normal. At this time, P(1)=0.72 and P(2)=1 can be calculated, and both P(1) and P(2) are greater than 0.5, the initial weight is selected, and P(H)=0.838 is calculated.

[0075] Output result: the air conditioner unit maintains the original compressor frequency + precise air supply (the compressor frequency operates at the initial 60 Hz; operates according to the high wind gear set by the user). The vision sensor + ToF sensor locates the human body and starts the precise air supply; the PIR sensor enters sleep. ​

[0076] Example two: people take a lunch break, every 20 minutes to start a visual sensor, based on the first detection data, the second detection data and the third detection data can determine the indoor temperature Te=26℃, illumination Lc=600lux, motion amplitude Ma=6, normal posture, 5 meters, normal multipath interference. At this time, the calculation P(1)=0.1368 and P(2)=1 can be calculated, wherein P(1) is less than 0.5, P(2) is greater than 0.5, the visual weight is selected, and P(H)=0.7774 is calculated.

[0077] Output result: air conditioning unit keeps original compressor frequency+precision air supply (compressor frequency runs at initial 60Hz; runs at high wind stop set by user). Visual sensor+ToF sensor locates human body, and opens precision air supply; PIR sensor enters dormancy.

[0078] Example three: after a nap, people leave the room, and the sensor identifies a moving person. Based on the first detection data, the second detection data and the third detection data, it can be determined that the indoor temperature Te=26℃, the illumination Lc=600lux, the motion amplitude Ma=6, the posture is abnormal 0.3, the distance is 5 meters, and the multipath interference is normal. At this time, P(1)=0.1368 and P(2)=0.3 can be calculated, and P(1) and P(2) are both less than 0.5, the initial weight is selected, and P(H)=0.3247 is calculated.

[0079] Output result: air conditioning unit reduces compressor frequency by 10%+fixed energy-saving wind speed (compressor frequency reduces by 10%: 60-60*10%=54Hz, compressor runs at 54Hz; reduces one stop at high wind stop set by user, runs at medium wind stop). PIR sensor remains active, ToF sensor and visual sensor enter dormancy.

[0080] Example four: after 30 minutes when P(H)0.3247, PIR sensor continuously detects no moving target object, and executes energy-saving mode. The following is executed: Reduce compressor frequency by 20%, reduce two-stop wind speed (compressor frequency reduces by 20%: 60-60*20%=48Hz, compressor runs at 48Hz; reduces two stops at high wind stop set by user, runs at low wind stop); Example five: in the evening, someone starts to move in the room, the PIR sensor detects that a human body enters the target area human body, wakes up the visual sensor and the ToF sensor, based on the first detection data, the second detection data and the third detection data, it can be determined that the indoor temperature Te=26℃, the illumination Lc=90lux, the motion amplitude Ma=40, the posture is normal 1, the distance is 5 meters, and the multi-path interference is normal. Thus, P(1)=0.912 and P(2)=0.49 can be calculated, wherein P(1) is greater than 0.5, P(2) is less than 0.5, the PIR weight is selected and the infrared light supplement unit 500 is started, and P(H)=0.7952 is calculated. The output result is: the air conditioning unit keeps the original compressor frequency + accurate air supply (the compressor frequency is operated according to the initial 60Hz; and the accurate air supply is operated according to the high wind block set by the user). The visual sensor + ToF sensor locates the human body, and the accurate air supply is started; the PIR sensor enters the sleep.

[0081] S3, the target object confidence indicates that there is a person, and the heat source coordinates are located.

[0082] S4, the optimal air supply path is calculated.

[0083] S5, the air direction is adjusted according to the optimal air supply path.

[0084] S6, the target object confidence indicates that there is no person, and the energy-saving mode is entered.

[0085] The steps S1-S6 are repeated until the air conditioner is turned off.

[0086] The air conditioner controller provided by the embodiment of the application includes a memory and a processor, the memory stores a computer program, and the processor implements the control method of the air conditioner control system when executing the computer program. The air conditioner control system can be any intelligent terminal including a tablet computer, a vehicle-mounted computer and the like.

[0087] Please refer to Figure 5 , Figure 5 The hardware structure of the air conditioner controller of another embodiment is illustrated, which includes: The processor 601 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the embodiments of the application; The memory 602 can be a NAND flash, and the related program codes are saved in the memory 602 and called and executed by the processor 601 to implement the control method of the air conditioner control system of the embodiment of the application; The input / output interface 603 is configured to realize information input and output. The communication interface 604 is configured to realize the communication interaction between the device and other devices, and the communication can be realized through a wired mode (for example, a USB, a network cable, or the like) or a wireless mode (for example, a mobile network, WIFI, Bluetooth, or the like). The bus 605 is configured to transmit information between various components (for example, the processor 601, the memory 602, the input / output interface 603, and the communication interface 604) of the device. The processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are connected to each other through the bus 605 to realize the communication connection between the devices.

[0088] The embodiment of the present application further provides a computer readable storage medium, which is a computer readable storage medium, and the storage medium stores a computer program. The computer program is executed by a processor to realize the control method of the air conditioner control system.

[0089] The memory is a non-transitory computer readable storage medium, and can be used to store a non-transitory software program and a non-transitory computer executable program. In addition, the memory can include a high-speed random access memory, and can further include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and the remote memory can be connected to the processor through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0090] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0091] Those skilled in the art can understand that the technical solutions shown in the figure do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than the figure, or combine certain steps, or different steps.

[0092] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to realize the purpose of the embodiments of the present application.

[0093] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the function modules / units in the system and the device can be implemented as software, firmware, hardware or appropriate combination thereof.

[0094] The terms "first", "second", "third", "fourth" and the like in the description of the application and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of these terms herein is to be construed to cover a general order and / or structure unless otherwise indicated by the context thereof. Furthermore, the terms "comprising", "having", "containing", and "including" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, product, or apparatus that comprises, has, contains, or includes an item or list of items who have the item or list does not include only those items regardless of whether other items are present or absent.

[0095] It should be understood that, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0096] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0097] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0098] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0099] If the integrated unit is realized in the form of 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 scheme of the present application or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium, including multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0100] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, but this does not limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A control method of an air conditioning control system, characterized by, The air conditioner control system comprises a passive infrared sensor, a visual sensor and a multi-path detection sensor, and the method comprises: receiving first detection data of the passive infrared sensor, second detection data of the visual sensor and third detection data of the multi-path detection sensor, the visual sensor and the multi-path detection sensor being activated after the passive infrared sensor detects a moving target object in a target area; determining a temperature confidence of the target object according to the first detection data; determining a posture confidence of the target object according to the second detection data; determining a supply air path interference confidence of the target object according to the third detection data; performing confidence weighting processing according to the temperature confidence, the posture confidence and the supply air path interference confidence to obtain a target object confidence; when the target object confidence is less than or equal to a preset first confidence threshold, controlling the visual sensor and the multi-path detection sensor to enter a dormant state; otherwise, adjusting air conditioner power parameters and / or a supply air path.

2. The control method of claim 1, wherein The determination of the temperature confidence of the target object according to the first detection data comprises: determining an indoor environment temperature and a motion amplitude of the target object in a current detection period according to the first detection data; determining an environmental temperature interference factor in the current detection period according to the indoor environment temperature; determining a motion amplitude measurement accuracy confidence according to the motion amplitude; determining the temperature confidence according to a weighted calculation result of the environmental temperature interference factor and the motion amplitude measurement accuracy confidence in the current detection period.

3. The control method of the air conditioning control system according to claim 1, characterized by, The determination of the posture confidence of the target object according to the second detection data comprises: determining an illumination intensity and a posture category in a current detection period according to the second detection data; determining a posture interference factor of the target object in the current detection period according to the illumination intensity; determining a visual measurement accuracy confidence according to the posture category; performing weighted calculation on the visual measurement accuracy confidence and the posture interference factor in the current detection period to obtain the posture confidence.

4. The control method of claim 1, wherein The third detection data comprises distance data obtained by distance measurement of the target object based on multiple different frequency bands, and the determination of the supply air path interference confidence of the target object according to the third detection data comprises: determining a multi-path interference factor according to the difference between the distance data of different frequency bands; determining a path measurement accuracy confidence by distance reliability estimation of the distance data; performing weighted calculation on the multi-path interference factor and the path measurement accuracy confidence to obtain the supply air path interference confidence.

5. The control method of the air conditioning control system according to claim 1, characterized by, The confidence weighting processing according to the temperature confidence, the posture confidence and the supply air path interference confidence to obtain the target object confidence comprises: obtain a weight parameter group, the weight parameter group comprising a temperature weight coefficient corresponding to the temperature confidence, a posture weight coefficient corresponding to the posture confidence, and a path weight coefficient corresponding to the air supply path interference confidence, at least two of the temperature weight coefficient, the posture weight coefficient, and the path weight coefficient being different from each other; weight and sum the temperature confidence, the posture confidence, and the air supply path interference confidence according to the corresponding temperature weight coefficient, posture weight coefficient, and path weight coefficient to obtain the target object confidence; wherein the weight parameter group is determined by the following steps: when a preset weight resetting condition is met, set the weight parameter group as a preset initial weight parameter group; wherein the posture weight coefficient and the temperature weight coefficient in the initial weight parameter group are greater than the path weight coefficient; when the temperature confidence is greater than a temperature precision confidence threshold and the posture confidence is less than or equal to a posture precision confidence threshold, set the weight parameter group as a temperature weight parameter group; wherein the temperature weight coefficient of the temperature weight parameter group is greater than the posture weight coefficient and the path weight coefficient; and the temperature weight coefficient in the temperature weight parameter group is greater than the temperature weight coefficient in the initial weight parameter group; when the posture confidence is greater than a posture precision confidence threshold and the temperature confidence is less than or equal to a temperature precision confidence threshold, set the weight parameter group as a visual weight parameter group; wherein the posture weight coefficient of the visual weight parameter group is greater than the temperature weight coefficient and the path weight coefficient; and the posture weight coefficient in the visual weight parameter group is greater than the posture weight coefficient in the initial weight parameter group.

6. The control method of claim 5, wherein The preset weight resetting condition is met, including at least one of the following: the temperature confidence is less than or equal to a temperature precision confidence threshold and the posture confidence is less than or equal to a posture precision confidence threshold; the target object confidence is greater than a preset second confidence threshold; the second confidence threshold is greater than the first confidence threshold; the air conditioner control system is in an energy saving mode, wherein the energy saving mode represents a condition that at least one of the following is met: the target object confidence is less than or equal to the first confidence threshold and lasts for a first time length, the passive infrared sensor does not detect a moving target object and lasts for a second time length.

7. The control method of claim 5, wherein the control method further comprises: The method further comprises: when the weight parameter group is set as a visual weight parameter group, turn on an infrared light supplement unit.

8. The control method of claim 1, wherein, The adjusting air conditioner power parameters and / or air supply path comprises: when the target object confidence is greater than a first confidence threshold and less than or equal to a third confidence threshold, setting the current running air conditioner parameters to the air conditioner configured power parameters after being adjusted by a first proportion and determining the air supply path according to the current position of the target object; when the target object confidence is greater than the third confidence threshold, determining the air supply path according to the current position of the target object and setting the current running air conditioner power parameters to the configured air conditioner power parameters; wherein the third confidence threshold is greater than the first confidence threshold. The method further comprises at least one of: when the target object confidence is less than or equal to the first confidence threshold, setting the current running air conditioner parameters to the air conditioner configured power parameters after being adjusted by the first proportion and fixing the current air supply angle; when the air conditioner control system is in an energy saving mode, setting the current running air conditioner parameters to the air conditioner configured power parameters after being adjusted by a second proportion; wherein the adjustment range of the second proportion is greater than the adjustment range of the first proportion.

9. An air conditioning control system characterized by comprising: The system comprises: a passive infrared sensor; a visual sensor; a multi-path detection sensor; an air conditioner controller, which is in communication connection with the passive infrared sensor, the visual sensor and the multi-path detection sensor, and executes the control method of the air conditioner control system according to any one of claims 1 to 8.

10. A computer readable storage medium, the storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the control method of the air conditioner control system according to any one of claims 1 to 8. The computer program, when executed by a processor, implements the control method of the air conditioner control system according to any one of claims 1 to 8.

Images