Intelligent air conditioner remote controller

Abstract

The invention discloses an intelligent air conditioner remote controller which is characterized in that a radar sensor assembly and an infrared sensor assembly respectively comprise radar sensors and infrared sensors in multiple directions; the main control MCU continuously executes a detection process, and the detection process comprises the steps of extracting heartbeat and breathing information from reflected signals of the radar sensors in the detection areas at all moments, extracting voltage information from voltage signals of the infrared sensors to obtain corresponding samples, determining sample types based on threshold values of all the information, and determining the sample types based on the threshold values of all the information; determining a personnel actual measurement result according to the sample categories of all the detection areas at the moment; training a deep learning model based on the samples at the multiple moments, obtaining a model prediction result at the next moment, and adjusting a threshold value for a next detection process when the model prediction result is inconsistent with a corresponding personnel actual measurement result; the air conditioner control module controls the working state of the air conditioner according to the personnel actual measurement result; the display screen displays actual measurement results of personnel and air conditioner state information. Whether people exist in the area or not can be accurately detected, and the air conditioner state is automatically controlled.

Description

Technical Field

[0001] The invention belongs to the field of intelligent remote controllers, and in particular relates to an intelligent air-conditioning remote controller. Background Art

[0002] Air conditioning is an indispensable device in people's work and life. When using air conditioning, due to human factors, the air conditioning is still idling when no one is around, which will cause a lot of electricity waste. Therefore, how to accurately detect the presence of human body and intelligently control the opening or closing of air conditioning is a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a smart air conditioner remote controller. The technical problem to be solved by the present invention is achieved through the following technical solutions:

[0004] An intelligent air conditioner remote controller includes: a radar sensor component, an infrared sensor component, a main control MCU, a display screen and an air conditioner control module; wherein,

[0005] The radar sensor assembly includes radar sensors arranged at multiple positions of the intelligent air conditioner remote controller; any radar sensor is used to transmit radio waves to the corresponding detection area, receive the reflected signal at each moment and send it to the main control MCU;

[0006] The infrared sensor assembly includes infrared sensors arranged at multiple positions of the intelligent air conditioner remote controller; any infrared sensor is used to detect infrared radiation information of human body in the corresponding detection area, and output a voltage signal at each moment to the main control MCU;

[0007] The main control MCU is used to continuously execute the detection process, which includes: at each moment, extracting heartbeat information and breathing information from the reflection signal of each detection area, extracting voltage information from the voltage signal, obtaining samples of the corresponding detection area, and determining the sample category based on the threshold corresponding to each extracted information to characterize whether there is someone in the detection area, and determining the actual measurement result of the person in the working area where the smart air conditioner remote control is located according to the sample category of all detection areas at this moment; and training a deep learning model based on all samples accumulated at multiple moments, using the trained deep learning model to obtain a model prediction result of whether there is someone in the working area at the next moment of the multiple moments, and when it is inconsistent with the corresponding actual measurement result of the person, adjusting the threshold corresponding to each information for the next detection process;

[0008] The air conditioning control module is used to control the working state of the air conditioning according to the actual measurement results of the personnel;

[0009] The display screen is used to display the personnel's actual measurement results and air conditioning status information.

[0010] In one embodiment of the present invention, the multiple directions include the front, back, left and right directions of the smart air conditioner remote controller.

[0011] In one embodiment of the present invention, at any time, extracting heartbeat information and breathing information from the reflection signal of each detection area includes:

[0012] At this moment, for the detection area corresponding to each orientation, the reflected signal sent by the radar sensor in the detection area is preprocessed, and the heartbeat information and breathing information are extracted from the preprocessed signal.

[0013] In one embodiment of the present invention, the preprocessing of the reflected signal sent by the radar sensor in the detection area includes:

[0014] The reflected signal sent by the radar sensor in the detection area is processed by mean filtering, linear interpolation and time-frequency conversion in sequence to obtain a preprocessed signal.

[0015] In one embodiment of the present invention, extracting heartbeat information and breathing information from the preprocessed signal includes:

[0016] In the frequency range of the preprocessed signal, the frequency corresponding to the peak point in the preset heartbeat frequency range is determined as the heartbeat information, and the frequency corresponding to the peak point in the preset breathing frequency range is determined as the breathing information.

[0017] In one embodiment of the present invention, at each moment, the sample of any detection area includes the heartbeat information, breathing information and voltage information extracted from the detection area;

[0018] The step of determining the sample category based on the threshold corresponding to each extracted information to indicate whether there is a person in the detection area includes:

[0019] At this moment, for each detection area, determine whether the sample in the detection area meets the following conditions: the corresponding heartbeat information is greater than the heartbeat threshold, the corresponding breathing information is greater than the breathing threshold, and the corresponding voltage information is greater than the voltage threshold; if so, determine that the sample category of the detection area is someone; otherwise, determine that the sample category of the detection area is no one.

[0020] In one embodiment of the present invention, determining the actual measurement results of personnel in the working area where the smart air conditioner remote controller is located according to the sample categories of all detection areas at that moment includes:

[0021] If at this moment there is a sample category of a detection area with a person, then the category result of the working area where the smart air conditioner remote controller is located at this moment is determined to be a person, otherwise, the category result of the working area at this moment is determined to be no person;

[0022] If within the preset time period up to this moment, all category results are that there are people, then the actual measurement result of the personnel in the working area is determined to be that there are people; otherwise, it is determined that there are no people in the working area.

[0023] In one embodiment of the present invention, the deep learning model is trained based on all samples accumulated at multiple moments, and the model prediction result of whether there is someone in the working area at the next moment of the multiple moments is obtained by using the trained deep learning model, including:

[0024] For the samples of all detection areas accumulated at multiple moments, multiple training sets are constructed by random sampling and replacement, and a deep learning model is trained using the multiple training sets and the category label of each sample therein; wherein the deep learning model includes a random forest deep learning model;

[0025] The input data of the next moment of the multiple moments is obtained and sent into a trained deep learning model to obtain a model prediction result, wherein the model prediction result is used to characterize whether there is someone in the working area where the smart air conditioner remote control is located; wherein the input data includes the heartbeat information, breathing information and voltage information extracted from all detection areas at the next moment.

[0026] In one embodiment of the present invention, the air conditioning control module controls the working state of the air conditioning according to the actual measurement result of the personnel, including:

[0027] If the air conditioning control module receives actual measurement results indicating that there are people in the working area within a first preset time period, it generates a first type of binary instruction code, modulates the first type of binary instruction code, and sends it to the air conditioner using the infrared communication module built into the smart air conditioner remote controller to control the air conditioner to turn on;

[0028] If the air conditioning control module receives actual measurement results that there is no one in the working area within the second preset time period, a second type of binary instruction code is generated, and after modulating the second type of binary instruction code, it is sent to the air conditioner using the infrared communication module to control the air conditioner to turn off.

[0029] In one embodiment of the present invention, the air conditioner status information includes: operating parameters including switch status, operating mode, temperature, wind force level, wind speed, wind direction, and power consumption saved by the smart air conditioner remote controller for the air conditioner.

[0030] Beneficial effects of the present invention:

[0031] The present invention provides an intelligent air conditioner remote controller based on deep learning, in which a radar sensor and an infrared sensor are embedded in the remote controller, and the air conditioner is controlled by detecting the presence of a human body. The combination of the radar sensor and the infrared sensor can improve the accuracy of personnel detection, thereby improving the accuracy of the air conditioner working state control. At the same time, the present invention trains a random forest model to predict the presence of a person at the next moment, and dynamically adjusts the threshold used for judgment by comparing it with the actual detection result, which can improve the recognition rate of the presence of a person. Compared with the use of a radar sensor alone, the present invention can reduce misjudgments; by automatically detecting the activities of people in the room, the automatic on / off control of the air conditioner can be achieved, which can avoid energy waste and improve user experience; and the high degree of automation means that users do not need to operate frequently, which can improve energy efficiency and reduce unnecessary power consumption, and it is easy to install and use, and is compatible with existing air conditioning equipment, and has practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the structure of a smart air conditioner remote controller provided by an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of the working process of the intelligent air conditioner remote controller provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention is further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0035] The embodiment of the present invention provides a smart air conditioner remote controller. Figure 1 As shown, it may include:

[0036] Including: radar sensor components, infrared sensor components, main control MCU, display screen and air conditioning control module; among them,

[0037] The radar sensor assembly includes radar sensors arranged at multiple positions of the intelligent air conditioner remote controller; any radar sensor is used to transmit radio waves to the corresponding detection area, receive the reflected signal at each moment and send it to the main control MCU;

[0038] The infrared sensor assembly includes infrared sensors arranged at multiple positions of the intelligent air conditioner remote controller; any infrared sensor is used to detect infrared radiation information of human body in the corresponding detection area, and output a voltage signal at each moment to the main control MCU;

[0039] The main control MCU is used to continuously execute the detection process, which includes: at each moment, extracting heartbeat information and breathing information from the reflection signal of each detection area, extracting voltage information from the voltage signal, obtaining samples of the corresponding detection area, and determining the sample category based on the threshold corresponding to each extracted information to characterize whether there is someone in the detection area, and determining the actual measurement result of the person in the working area where the smart air conditioner remote control is located according to the sample category of all detection areas at this moment; and training a deep learning model based on all samples accumulated at multiple moments, using the trained deep learning model to obtain a model prediction result of whether there is someone in the working area at the next moment of the multiple moments, and when it is inconsistent with the corresponding actual measurement result of the person, adjusting the threshold corresponding to each information for the next detection process;

[0040] The air conditioning control module is used to control the working state of the air conditioning according to the actual measurement results of the personnel;

[0041] The display screen is used to display the personnel's actual measurement results and air conditioning status information.

[0042] The smart air conditioner remote control of the embodiment of the present invention can be adapted to any existing air conditioner and can be another smart remote control independent of the original remote control of the air conditioner, used to detect in real time whether there is someone in the working area of ​​the air conditioner, thereby controlling the working status of the air conditioner, for example, controlling the air conditioner to be turned on or off.

[0043] Furthermore, the intelligent air conditioner remote control of the embodiment of the present invention can also be improved on the basis of the original remote control of the air conditioner, such as by integrating additional modules and performing corresponding configurations, so that the original remote control of the air conditioner becomes the intelligent air conditioner remote control. In this case, the original functions of the original remote control of the air conditioner remain unchanged, wherein the radar sensor component and the infrared sensor component are additional integrated modules, and the main control MCU, the display screen and the air conditioning control module can be implemented by programming and writing configurations on the corresponding components of the original remote control of the air conditioner to achieve functional upgrades, and the specific process will not be repeated here. Of course, the main control MCU and the air conditioning control module can also be additional integrated modules, which is reasonable. For the original functions of the original remote control of the air conditioner, please refer to the relevant technical understanding, which will not be explained below.

[0044] To facilitate understanding of the solution, various parts of the intelligent air conditioner remote controller in the embodiment of the present invention are described below.

[0045] Radar sensor components:

[0046] In the embodiment of the present invention, a radar sensor is respectively arranged at multiple positions of the intelligent air conditioner remote controller, which together constitute a radar sensor assembly. Each position corresponds to a detection area.

[0047] The number of multiple positions can be set according to the requirements of detection accuracy. For example, in an optional implementation, the multiple positions include the front, rear, left, and right positions of the smart air conditioner remote controller. Then, the radar sensor located in the front position can be located at the midpoint of the front side of the smart air conditioner remote controller, the radar sensor located in the rear position can be located at the midpoint of the rear side of the smart air conditioner remote controller, the radar sensor located in the left position can be located at the midpoint of the left side of the smart air conditioner remote controller, and the radar sensor located in the right position can be located at the midpoint of the right side of the smart air conditioner remote controller.

[0048] Each radar sensor is used to detect the situation of people in the corresponding detection area. Specifically, the radar sensor can adopt a 24GHz radar sensor. Each radar sensor can cover a certain range of detection area. The radar sensor continuously transmits radio waves to the corresponding detection area, receives the reflected signal at each moment and sends it to the main control MCU.

[0049] Among them, the radar sensor transmission frequency is f t When the radio wave encounters a moving target (such as the chest or heart of a human body), the frequency of the reflected wave changes due to the movement of the target. This frequency change Δf (Doppler frequency shift) is related to the speed v of the target and can be expressed as:

[0050]

[0051] Among them, f t is the frequency of the radar sensor transmitting signals; v is the relative speed of the target, that is, the speed of the chest cavity caused by breathing and heartbeat; c is the speed of light.

[0052] The reflected signal received by the radar sensor at each moment can be expressed as a time domain signal, which is a continuous signal over a period of time, expressed as:

[0053] s(t)=Acos(2*π*(f t +Δf)t+φ);

[0054] Where A is the amplitude and φ is the initial phase.

[0055] Infrared sensor assembly:

[0056] In the embodiment of the present invention, an infrared sensor is respectively arranged at multiple positions corresponding to the radar sensor, and together they constitute an infrared sensor assembly. Each position corresponds to a detection area.

[0057] In the embodiment of the present invention, for each orientation, the positions of the radar sensor and the infrared sensor can be reasonably set to ensure that both can achieve good detection of the same detection area.

[0058] Infrared sensors can use pyroelectric infrared sensors to detect the presence of a human body by detecting infrared radiation emitted by the human body. The surface temperature of the human body is usually around 37°C, and it emits infrared radiation with a peak wavelength of around 10 microns. When someone enters the detection area of ​​the infrared sensor, the infrared radiation from the human body causes the temperature of the pyroelectric material in the infrared sensor to change, thereby generating an electric charge. The pyroelectric formula is as follows:

[0059] Q = p*S*ΔT;

[0060] Among them, Q is the generated charge; p is the pyroelectric coefficient (related to the material); S is the effective area of ​​the infrared sensor; ΔT is the temperature change. The charge is then converted into a voltage signal through the circuit and transmitted to the main control MCU for processing.

[0061] Main control MCU:

[0062] The main control MCU continuously executes the detection process, and any detection process is described below.

[0063] Among them, at any moment, the heartbeat information and breathing information are extracted from the reflection signal of each detection area, including:

[0064] At this moment, for the detection area corresponding to each orientation, the reflected signal sent by the radar sensor in the detection area is preprocessed, and the heartbeat information and breathing information are extracted from the preprocessed signal.

[0065] In an optional implementation manner, the preprocessing of the reflected signal sent by the radar sensor in the detection area includes:

[0066] The reflected signal sent by the radar sensor in the detection area is processed by mean filtering, linear interpolation and time-frequency conversion in sequence to obtain a preprocessed signal.

[0067] Specifically, the mean filter denoising process smoothes the data by calculating the average value of all points in the neighborhood through mean filtering, thereby reducing the impact of noise.

[0068] The reflected signal sent by the radar sensor is s(t), and the data after mean filtering and denoising is y(t). The window size is 2*k+1, then:

[0069]

[0070] Wherein, s(t) represents the reflected signal received at time t. For the mean filtering denoising process, please refer to the relevant technical understanding and will not be described in detail here.

[0071] Then, the linear interpolation method is used to insert a data point between two adjacent points. The formula is as follows:

[0072]

[0073] Among them, y'(t) is the value corresponding to the interpolation point, t is the independent variable value of the interpolation point, and t1 and t2 are the independent variable values ​​of two adjacent points.

[0074] Then the interpolated point set is merged with the original data set into a data set z(t). Interpolation can expand the amount of data, thereby increasing the size of the training set for subsequent model training, which is conducive to improving training accuracy.

[0075] For z(t), the time-frequency conversion process is to perform Fourier transform, so that the time domain signal z(t) is converted into the frequency domain signal Z(f), which is expressed as:

[0076] Z(f)=F{z(t)};

[0077] Wherein, F{} represents Fourier transform.

[0078] In an optional implementation manner, extracting heartbeat information and breathing information from the preprocessed signal includes:

[0079] In the frequency range of the preprocessed signal, the frequency corresponding to the peak point in the preset heartbeat frequency range is determined as the heartbeat information, and the frequency corresponding to the peak point in the preset breathing frequency range is determined as the breathing information.

[0080] Specifically, Z(f) is the frequency domain representation of z(t) at each moment. The heart rate is usually between 1 and 2 Hz, which is the preset heart rate range. The breathing rate is usually between 0.1 and 0.5 Hz, which is the preset breathing rate range.

[0081] In the frequency range of the preprocessed signal, a peak value can be found in a preset heartbeat frequency range to obtain heartbeat information, and a peak value can be found in a preset breathing frequency range to obtain breathing information.

[0082] For infrared signals, the voltage change transmitted by the infrared sensor is mainly considered. The relationship between voltage and temperature change is as follows:

[0083] V(t) = δ*ΔT(t);

[0084] Among them, V(t) is the voltage information extracted from the voltage signal at time t, δ is the sensitivity coefficient of the infrared sensor, and ΔT(t) is the temperature change at time t. When the human body is present, the temperature change ΔT(t) will produce significant voltage fluctuations.

[0085] In the embodiment of the present invention, at each moment, the sample of any detection area includes the heartbeat information, breathing information and voltage information extracted from the detection area. Therefore, it can be understood that for the four directions in the above example, at each moment, each direction obtains a sample, for a total of four samples.

[0086] For the main control MCU, the threshold corresponding to each extracted information is used to determine the sample category to indicate whether there is a person in the detection area, including:

[0087] At this moment, for each detection area, determine whether the sample in the detection area meets the following conditions: the corresponding heartbeat information is greater than the heartbeat threshold, the corresponding breathing information is greater than the breathing threshold, and the corresponding voltage information is greater than the voltage threshold; if so, determine that the sample category of the detection area is someone; otherwise, determine that the sample category of the detection area is no one.

[0088] The heart rate threshold, breathing threshold, and voltage threshold are determined in advance based on a large amount of data. th Indicates that the breathing threshold can be used th Indicates that the voltage threshold can be used V th Only when the heartbeat information, breathing information, and voltage information corresponding to the detection area are all greater than the corresponding thresholds, it is determined that there is a person in the detection area, and then the sample category of the detection area is determined to be a person.

[0089] For each sample, once its sample category is determined, the category of each information in the sample is the sample category.

[0090] As described above, at each moment, each detection area can obtain a sample and determine the sample category. Then, for this moment, the actual measurement results of the personnel in the working area where the smart air conditioner remote control is located can be determined according to the sample categories of all detection areas at this moment. The process includes:

[0091] If at this moment there is a sample category of a detection area with a person, then the category result of the working area where the smart air conditioner remote controller is located at this moment is determined to be a person, otherwise, the category result of the working area at this moment is determined to be no person;

[0092] If within the preset time period up to this moment, all category results are that there are people, then the actual measurement result of the personnel in the working area is determined to be that there are people; otherwise, it is determined that there are no people in the working area.

[0093] Therefore, through the above judgment, the actual measurement results of personnel in the working area can be obtained at every moment, and the main control MCU will send it to the air conditioning control module and the display screen.

[0094] Because the main control MCU will obtain samples and sample categories of each detection area at each moment, after accumulating multiple moments, the main control MCU can train a deep learning model based on all samples at the accumulated multiple moments, and use the trained deep learning model to obtain the model prediction result of whether there is someone in the working area at the next moment of the multiple moments.

[0095] Specifically, the process may include the following steps:

[0096] 1) constructing multiple training sets by random sampling and replacement for the samples of all detection areas accumulated at multiple moments, and training the deep learning model using the multiple training sets and the category labels of the samples therein;

[0097] Among them, the deep learning model includes a random forest deep learning model, which is described in detail below.

[0098] First, the samples of all detection areas accumulated at multiple moments can constitute an original data set, where each sample is the heartbeat information, breathing information and voltage information extracted from a detection area at a moment, and carries the corresponding category, namely the sample category.

[0099] The sample information extracted from radar signals and infrared signals is grouped into a data set of I samples, that is, all three types of information are grouped, and J training sets are generated by random sampling with replacement. The size of each training set is also I. Then the probability of each sample being selected in one sampling is 1 / I, and the probability of not being selected is (I-1) / I. After I sampling, the probability of a sample not being selected is:

[0100]

[0101] At each splitting node of each tree in the random forest deep learning model, instead of considering all features (there are three types of features, including breathing information, heartbeat information, and voltage information), a part of the features is randomly selected, and the randomly selected features are used to extract a subset from the data set (the information of each feature carries the corresponding category) for training. For example, the two features "heartbeat information" and "voltage information" may be randomly selected to consider splitting. Then let each tree grow as much as possible until there are no more features to split. When all the trees are built, they can be used to predict the result of the next moment (whether there is someone in the work area), and the prediction results of all the trees are integrated. For example, if 60 trees predict "yes" and 40 trees predict "no", the final prediction result is "yes".

[0102] In an embodiment of the present invention, the random forest deep learning model makes predictions by constructing multiple decision trees. Each tree is trained using a subset of the data and a subset of the features. The number of trees, maximum depth, minimum number of samples and other parameters are adjusted through cross-validation and grid search methods to find the optimal combination of parameters, which can improve the accuracy of judgment.

[0103] In an embodiment of the present invention, the training process of the random forest deep learning model can be understood in combination with the existing random forest deep learning model training process.

[0104] 2) obtaining input data at the next moment of the multiple moments and feeding it into the trained deep learning model to obtain a model prediction result, wherein the model prediction result is used to characterize whether there is someone in the working area where the smart air conditioner remote controller is located;

[0105] The input data includes the heartbeat information, breathing information and voltage information extracted from all detection areas at the next moment.

[0106] The model prediction result at the next moment is used to compare with the actual measurement result of the person at the next moment. When the two are inconsistent, the thresholds corresponding to the heartbeat information, breathing information and voltage information are adjusted so that in the next detection process, the adjusted thresholds are used to determine whether there is a person in the detection area. At the same time, the actual measurement result of the person at the next moment will also be added to the original data set and continue to be used for prediction.

[0107] Air conditioning control module:

[0108] The air conditioning control module controls the working state of the air conditioning according to the actual measurement results of the personnel, and the process may include:

[0109] If the air conditioning control module receives actual measurement results indicating that there are people in the working area within a first preset time period, it generates a first type of binary instruction code, modulates the first type of binary instruction code, and sends it to the air conditioner using the infrared communication module built into the smart air conditioner remote controller to control the air conditioner to turn on;

[0110] If the air conditioning control module receives actual measurement results that there is no one in the working area within the second preset time period, a second type of binary instruction code is generated, and after modulating the second type of binary instruction code, it is sent to the air conditioner using the infrared communication module to control the air conditioner to turn off.

[0111] Specifically, in order to avoid false detection and reduce power consumption caused by frequent switching of the air conditioner, the embodiment of the present invention sets a first preset time for turning on the air conditioner and a second preset time for turning off the air conditioner. The air conditioner is turned on only when the actual measurement results of personnel within the first preset time indicate that there are people in the working area, and the air conditioner is turned on only when the actual measurement results of personnel within the second preset time indicate that there are no people in the working area. It can be set specifically according to needs, for example, the first preset time can be 10 minutes, and the second preset time can be 30 minutes.

[0112] The binary instruction code is composed of binary data. Modulating the second type of binary instruction code can be to perform pulse width modulation on the carrier signal and the binary instruction code to obtain a modulated signal. This process can be understood by referring to the relevant technology and will not be explained here.

[0113] In the embodiment of the present invention, the infrared communication module built into the intelligent air conditioner remote controller is designed to be compatible with air conditioner controls of various manufacturers, so that the purpose of communicating with all air conditioners on the market to control the working status can be achieved.

[0114] Specifically, the infrared communication module may be an infrared light emitting diode, which transmits a modulated signal toward the air conditioner, so that the air conditioner can be turned on or off after being received by an infrared receiver of the air conditioner.

[0115] Display screen:

[0116] The display screen may be a liquid crystal screen, on which the measured results and air conditioner status information may be displayed. The air conditioner status information may include: operating parameters including switch status, working mode, temperature, wind force level, wind speed, wind direction, and the amount of electricity saved by the smart air conditioner remote controller for the air conditioner.

[0117] Among them, the working parameters can be various parameters usually displayed on the display screen of the original remote control of the air conditioner. If the intelligent air conditioner remote control is independent of the original remote control of the air conditioner, it can communicate with the air conditioner through the infrared communication module to obtain the above working parameters. If the intelligent air conditioner remote control is integrated and improved on the basis of the original remote control of the air conditioner, its display screen can also obtain the above working parameters. For the specific process, please refer to the relevant technical understanding and will not be explained here.

[0118] Compared with the parameters displayed on the traditional display screen, the embodiment of the present invention can display the power consumption saved by the smart air conditioner remote controller for the air conditioner. This part of data can be obtained by multiplying the unit power consumption when the air conditioner is turned on and the off time of the air conditioner under the control of the smart air conditioner remote controller.

[0119] The working process of the intelligent air conditioner remote controller according to the embodiment of the present invention can be referred to Figure 2Understand that, among them, labeling data refers to determining the sample category, parameter optimization refers to adjusting the threshold, and the rest will not be explained one by one.

[0120] The present invention provides an intelligent air conditioner remote controller based on deep learning, in which a radar sensor and an infrared sensor are embedded in the remote controller, and the air conditioner is controlled by detecting the presence of a human body. The combination of the radar sensor and the infrared sensor can improve the accuracy of personnel detection, thereby improving the accuracy of the air conditioner working state control. At the same time, the present invention trains a random forest model to predict the presence of a person at the next moment, and dynamically adjusts the threshold used for judgment by comparing it with the actual detection result, which can improve the recognition rate of the presence of a person. Compared with the use of a radar sensor alone, the present invention can reduce misjudgments; by automatically detecting the activities of people in the room, the automatic on / off control of the air conditioner can be achieved, which can avoid energy waste and improve user experience; and the high degree of automation means that users do not need to operate frequently, which can improve energy efficiency and reduce unnecessary power consumption, and it is easy to install and use, and is compatible with existing air conditioning equipment, and has practical value.

[0121] It should be noted that, in the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0122] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0123] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A smart air conditioner remote controller, characterized in that: include: Radar sensor components, infrared sensor components, main control MCU, display screen and air conditioning control module; among them, The radar sensor assembly includes radar sensors arranged at multiple positions of the intelligent air conditioner remote controller; any radar sensor is used to transmit radio waves to the corresponding detection area, receive the reflected signal at each moment and send it to the main control MCU; The infrared sensor assembly includes infrared sensors arranged at multiple positions of the intelligent air conditioner remote controller; any infrared sensor is used to detect infrared radiation information of human body in the corresponding detection area, and output a voltage signal at each moment to the main control MCU; The main control MCU is used to continuously execute the detection process, which includes: at each moment, extracting heartbeat information and breathing information from the reflection signal of each detection area, extracting voltage information from the voltage signal, obtaining samples of the corresponding detection area, and determining the sample category based on the threshold corresponding to each extracted information to characterize whether there is someone in the detection area, and determining the actual measurement result of the person in the working area where the smart air conditioner remote control is located according to the sample category of all detection areas at this moment; and training a deep learning model based on all samples accumulated at multiple moments, using the trained deep learning model to obtain a model prediction result of whether there is someone in the working area at the next moment of the multiple moments, and when it is inconsistent with the corresponding actual measurement result of the person, adjusting the threshold corresponding to each information for the next detection process; The air conditioning control module is used to control the working state of the air conditioning according to the actual measurement results of the personnel; The display screen is used to display the personnel's actual measurement results and air conditioning status information.

2. The intelligent air conditioner remote controller according to claim 1, characterized in that: The multiple directions include the front, back, left and right directions of the smart air conditioner remote control.

3. The intelligent air conditioner remote controller according to claim 1 or 2, characterized in that: At any moment, the heartbeat information and breathing information are extracted from the reflection signals of each detection area, including: At this moment, for the detection area corresponding to each orientation, the reflected signal sent by the radar sensor in the detection area is preprocessed, and the heartbeat information and breathing information are extracted from the preprocessed signal.

4. The intelligent air conditioner remote controller according to claim 3, characterized in that: The preprocessing of the reflected signal sent by the radar sensor in the detection area includes: The reflected signal sent by the radar sensor in the detection area is processed by mean filtering, linear interpolation and time-frequency conversion in sequence to obtain a preprocessed signal.

5. The intelligent air conditioner remote controller according to claim 4, characterized in that: The step of extracting heartbeat information and breathing information from the pre-processed signal includes: In the frequency range of the preprocessed signal, the frequency corresponding to the peak point in the preset heartbeat frequency range is determined as the heartbeat information, and the frequency corresponding to the peak point in the preset breathing frequency range is determined as the breathing information.

6. The intelligent air conditioner remote controller according to claim 1, characterized in that: At each moment, the sample of any detection area includes the heartbeat information, breathing information and voltage information extracted from the detection area; The step of determining the sample category based on the threshold corresponding to each extracted information to indicate whether there is a person in the detection area includes: At this moment, for each detection area, determine whether the sample in the detection area meets the following conditions: the corresponding heartbeat information is greater than the heartbeat threshold, the corresponding breathing information is greater than the breathing threshold, and the corresponding voltage information is greater than the voltage threshold; if so, determine that the sample category of the detection area is someone; otherwise, determine that the sample category of the detection area is no one.

7. The intelligent air conditioner remote controller according to claim 6, characterized in that: The determining of the actual measurement results of personnel in the working area where the smart air conditioner remote controller is located according to the sample categories of all detection areas at that moment includes: If at this moment there is a sample category of a detection area with a person, then the category result of the working area where the smart air conditioner remote controller is located at this moment is determined to be a person, otherwise, the category result of the working area at this moment is determined to be no person; If within the preset time period up to this moment, all category results are that there are people, then the actual measurement result of the personnel in the working area is determined to be that there are people; otherwise, it is determined that there are no people in the working area.

8. The intelligent air conditioner remote controller according to claim 7, characterized in that: The deep learning model is trained based on all samples accumulated at multiple moments, and the model prediction result of whether there is someone in the working area at the next moment of the multiple moments is obtained by using the trained deep learning model, including: For the samples of all detection areas accumulated at multiple moments, multiple training sets are constructed by random sampling and replacement, and a deep learning model is trained using the multiple training sets and the category label of each sample therein; wherein the deep learning model includes a random forest deep learning model; The input data of the next moment of the multiple moments is obtained and sent into a trained deep learning model to obtain a model prediction result, wherein the model prediction result is used to characterize whether there is someone in the working area where the smart air conditioner remote control is located; wherein the input data includes the heartbeat information, breathing information and voltage information extracted from all detection areas at the next moment.

9. The intelligent air conditioner remote controller according to claim 1, characterized in that: The air conditioning control module controls the working state of the air conditioning according to the actual measurement result of the personnel, including: If the air conditioning control module receives actual measurement results indicating that there are people in the working area within a first preset time period, it generates a first type of binary instruction code, modulates the first type of binary instruction code, and sends it to the air conditioner using the infrared communication module built into the smart air conditioner remote controller to control the air conditioner to turn on; If the air conditioning control module receives actual measurement results that there is no one in the working area within the second preset time period, a second type of binary instruction code is generated, and after modulating the second type of binary instruction code, it is sent to the air conditioner using the infrared communication module to control the air conditioner to turn off.

10. The intelligent air conditioner remote controller according to claim 1 or 9, characterized in that: The air conditioner status information includes: operating parameters including switch status, working mode, temperature, wind force level, wind speed, wind direction, and the amount of electricity saved by the smart air conditioner remote controller for the air conditioner.

Images