Millimeter-wave radar-based air conditioning control system, method, and air conditioning

Abstract

The present invention discloses a millimeter-wave radar-based air conditioning control system, method, and air conditioner. The system includes a millimeter-wave radar for emitting electromagnetic waves and collecting radar data within a preset area; a data processing module for performing intra-frame and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information, acquiring gesture features based on the intra-frame information and inter-frame information, and obtaining instructions for controlling the air conditioner based on gesture feature recognition. The present invention uses millimeter-wave radar to collect user gesture features, obtains air conditioner control instructions based on the recognized gesture features, and achieves free, convenient, and highly private air conditioning control. The present invention can be widely applied to the field of energy-saving homes.

Description

Technical Field

[0001] The present invention relates to the field of energy-efficient home furnishings, and in particular to an air-conditioning control system, method, and air-conditioning based on millimeter-wave radar. Background Art

[0002] Currently, home air conditioners are primarily controlled via remote controls. These devices are technologically mature, offering convenient and precise control, and are widely favored by users. Meanwhile, with the application of deep learning and various sensors, the smart home sector is gradually exploring new interactive control methods. Most of these control technologies rely on the user's macro-position within the air conditioner's operating area to adjust the air conditioner's preset control modes, providing users with more intelligent services.

[0003] Most remote-control devices are small and easily lost. Most air conditioners lack backup temperature control options, creating inconvenience for users who lose their remotes. Furthermore, remote controls operate on radio waves in specific frequency bands, making replacements time-consuming and labor-intensive. Furthermore, remote controls only allow for macro-level control of the air conditioner's modes, limiting flexibility and failing to fully tap the potential of smart homes in terms of interaction. Summary of the Invention

[0004] In order to solve at least one of the technical problems existing in the prior art to a certain extent, the object of the present invention is to provide an air-conditioning control system, method and air-conditioning based on millimeter-wave radar.

[0005] The technical solution adopted in the present invention is:

[0006] An air conditioning control system based on millimeter wave radar, comprising:

[0007] Millimeter-wave radar, used to transmit electromagnetic waves and collect radar data within a preset area;

[0008] The data processing module is used to perform intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information, obtain gesture features based on the intra-frame information and the inter-frame information, and obtain instructions for controlling the air conditioner based on gesture feature recognition.

[0009] Furthermore, the millimeter-wave radar is arranged on the air conditioner.

[0010] Furthermore, the data processing module is deployed on a local processor of the air conditioner.

[0011] Another technical solution adopted in the present invention is:

[0012] An air conditioning control method based on millimeter wave radar comprises the following steps:

[0013] Collect radar data within a preset area through millimeter-wave radar;

[0014] Performing intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information;

[0015] The gesture feature is acquired according to the intra-frame information and the inter-frame information, the instruction information is recognized according to the gesture feature, and the air conditioner is controlled according to the recognized instruction information.

[0016] Furthermore, the intra-frame data processing of the collected radar data includes:

[0017] Perform two-dimensional fast Fourier transform on radar data to obtain multi-channel range Doppler map data;

[0018] Perform CFAR detection and peak search on the range Doppler map data to obtain the detection points and the range and velocity information corresponding to the detection points;

[0019] According to the distance and speed information, the multi-channel phase solution is used to obtain the angle information of the target relative to the radar;

[0020] According to the distance, speed and angle information, all the detected points in a frame are weighted and averaged to obtain the target center of gravity.

[0021] The target center of gravity reflects the pose information of the target in the frame, and the pose information includes distance, speed, pitch angle and azimuth angle. The target refers to the hand.

[0022] Furthermore, the expression of the posture information is:

[0023]

[0024] Among them, x represents the detection results within a frame, including speed v, distance r, pitch angle angle ele Or angle azi ; m represents the number of detection points in a frame, A i Indicates the amplitude of each over-detection point on the RDM diagram, x i Indicates the detection result of each over-detection point in a frame.

[0025] Furthermore, the inter-frame data processing of the collected radar data includes:

[0026] Acquire multiple frames of radar data, remove the radar data based on the posture information, and obtain multiple valid frames;

[0027] Calculate statistical values ​​as gesture features based on multiple valid frames;

[0028] Among them, the statistical values ​​include: the larger proportion of positive / negative speed frames to all frames, the mean speed of all valid frames, the distance variance of all valid frames, the speed variance of all valid frames, the pitch angle variance of all valid frames, the mean pitch angle of all valid frames, the mean azimuth of all valid frames, the azimuth variance of all valid frames, the larger proportion of positive / negative azimuth valid frames to all valid frames, and the larger proportion of positive / negative pitch angle valid frames to all valid frames.

[0029] Furthermore, the formula for calculating the larger value of the ratio of positive / negative speed frames to all frames is:

[0030]

[0031] Where N pos_vel Represents the total number of frames with positive speed of all target hand detection results, N neg_vel represents the total number of frames with negative speed of all target hand detection results, and N represents the total number of all valid frames;

[0032] The formula for calculating the mean of all valid frame rates is:

[0033]

[0034] Where, v i Indicates the speed of the target hand in each valid frame;

[0035] The calculation formula for the distance variance of all valid frames is:

[0036]

[0037] Where r i Indicates the detection distance result of the target hand in each valid frame. Represents the mean distance of all valid frames;

[0038] The formula for calculating the variance of all valid frame rates is:

[0039]

[0040] The calculation formula for the mean pitch angle of all valid frames is:

[0041]

[0042] Where, angle ele_i Indicates the detection pitch angle result of the target hand in each valid frame;

[0043] The calculation formula for the pitch angle variance of all valid frames is:

[0044]

[0045] The calculation formula for the mean azimuth angle of all valid frames is:

[0046]

[0047] Where, angle ele_i Indicates the detection azimuth angle result of the target hand in each valid frame;

[0048] The calculation formula for the azimuth angle variance of all valid frames is:

[0049]

[0050] The formula for calculating the larger value of the ratio of positive / negative azimuth valid frames to all valid frames is:

[0051]

[0052] Where N pos_azi Indicates the total number of valid frames with positive azimuth angles for all target hand detection results, N neg_azi Indicates the total number of valid frames with negative azimuth angles in all target hand detection results;

[0053] The formula for calculating the larger value of the ratio of positive / negative pitch angle valid frames to all valid frames is:

[0054]

[0055] Where N pos_ele Indicates the total number of valid frames with positive pitch angles in all target hand detection results, N neg_ele Indicates the total number of valid frames in which the pitch angle of all target hand detection results is negative.

[0056] Furthermore, the identifying instruction information according to the gesture feature includes:

[0057] The obtained gesture features are input into the trained machine learning model and the corresponding instruction information is output.

[0058] Another technical solution adopted in the present invention is:

[0059] An air conditioner is provided with a millimeter-wave radar and a data processing module, wherein the data processing module is used to execute the air conditioner control method based on the millimeter-wave radar as described above.

[0060] The beneficial effects of the present invention are as follows: the present invention collects the user's gesture features through millimeter wave radar, obtains instructions for controlling the air conditioner based on the recognized gesture features, and realizes free, convenient and highly private air conditioner control. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present invention or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0062] Figure 1 is a schematic diagram of a gesture instruction set in an embodiment of the present invention;

[0063] Figure 2 is a schematic diagram of an air-conditioning control system based on millimeter-wave radar in an embodiment of the present invention;

[0064] Figure 3 is a flow chart of intra-frame data processing in an embodiment of the present invention;

[0065] Figure 4 is a flow chart of inter-frame data processing in an embodiment of the present invention;

[0066] Figure 5 This is a flowchart of the steps of an air conditioning control method based on millimeter wave radar in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0068] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They 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 orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention.

[0069] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0070] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0071] See also Figure 2 This embodiment provides an air conditioning control system based on millimeter wave radar, including:

[0072] Millimeter-wave radar, used to transmit electromagnetic waves and collect radar data within a preset area;

[0073] The data processing module is used to perform intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information, obtain gesture features based on the intra-frame information and the inter-frame information, and obtain instructions for controlling the air conditioner based on gesture feature recognition.

[0074] like Figure 2 As shown, the millimeter-wave radar sensor emits electromagnetic waves into a designated area and collects radar data from that area in real time. To control the air conditioner, the user simply enters the preset area and performs the corresponding gesture. The millimeter-wave radar collects the corresponding radar data, analyzes and processes it, and then generates the corresponding control instructions for the air conditioner.

[0075] See also Figure 1 As an optional implementation method, the gesture instruction set needs to be designed and determined in advance. Specifically, Figure 1 As shown in (a), the clockwise circle gesture corresponds to the command to turn on the air conditioner; Figure 1 As shown in (b), the counterclockwise circle gesture corresponds to the instruction to turn off the air conditioner; Figure 1 As shown in (c), the leftward swipe gesture corresponds to the instruction to lower the temperature; Figure 1 As shown in (d), the rightward swipe gesture corresponds to the instruction to increase the temperature; Figure 1 As shown in (e), the upward swipe gesture corresponds to the instruction to reduce the wind speed; Figure 1 As shown in (f), the downward swipe gesture corresponds to the instruction to increase the wind speed; Figure 1 As shown in (g), the forward and backward push and pull gestures correspond to the instructions for switching the air conditioning mode; Figure 1As shown in (h), other gestures are invalid instructions.

[0076] See also Figure 1 The millimeter-wave radar is installed on the air conditioner. This millimeter-wave radar can be installed on the air conditioner or outside of it, such as on the sofa, allowing users to control the air conditioner directly from the sofa. Installing it on the air conditioner allows it to be powered directly by the air conditioner's power supply, eliminating the need for a separate power supply for the millimeter-wave radar. Furthermore, the millimeter-wave radar chip is relatively small, measuring approximately 5cm x 5cm including the peripheral circuitry and antenna, making it easily mountable on the air conditioner's indoor unit.

[0077] like Figure 5 As shown, this embodiment also provides an air conditioning control method based on millimeter wave radar, comprising the following steps:

[0078] S1. Collect radar data within a preset area through millimeter-wave radar.

[0079] S2. Perform intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information.

[0080] Among them, see Figure 3 , performing intra-frame data processing on the collected radar data, including steps A1-A4:

[0081] A1. Perform a two-dimensional fast Fourier transform on the radar data to obtain multi-channel range Doppler map data;

[0082] A2. Perform CFAR detection and peak search on the range-Doppler map data to obtain the detection points and the range and velocity information corresponding to the detection points;

[0083] A3. Based on the range and velocity information, perform multi-channel phase analysis to determine the target's angle relative to the radar.

[0084] A4. Based on the distance, speed, and angle information, a weighted average is calculated for all detected points within a frame, which is used as the target center of gravity.

[0085] The target center of gravity reflects the pose information of the target in the frame, and the pose information includes distance, speed, pitch angle and azimuth angle. The target refers to the hand.

[0086] A 2D Fast Fourier Transform (FFT) is performed on the ADC (Analogue-to-Digital Conversion) data from each antenna channel, converting the time-domain signal into a frequency-domain spectrum. This yields a multi-channel Range Doppler Map (RDM) with dimensions (range, velocity, elevation, and azimuth). Because angular resolution is positively correlated with the number of antennas, MIMO (Multiple-Input Multiple-Output) technology is employed to increase the number of virtual antennas. The number of angular dimensions in elevation and azimuth corresponds to the number of virtual antennas in the corresponding directions. An RDM for one antenna channel is selected, and points that pass constant virtual warning detection and exhibit maximum values ​​in both the range and velocity dimensions are designated as over-detection points. By calculating the target's angle information based on the phases of the over-detection points at the same corresponding locations on the RDMs of different antenna channels, the target's elevation and azimuth angles relative to the radar are determined. The specific solution formula depends on the spatial arrangement of the antennas. For all the detected point information obtained in a frame, the information of each point is weighted and averaged with respect to the amplitude to obtain the information of a single target point. This point is considered to be the center of gravity of the target, reflecting the position information (distance, speed, pitch angle and azimuth) of the target in this frame (i.e., the current moment).

[0087] See also Figure 4 , performing inter-frame data processing on the collected radar data, including steps B1-B2:

[0088] B1. Acquire multiple frames of radar data, remove the radar data based on the position information, and obtain multiple valid frames;

[0089] B2. Calculate statistical values ​​based on multiple valid frames as gesture features;

[0090] Among them, the statistical values ​​include: the larger proportion of positive / negative speed frames to all frames, the mean speed of all valid frames, the distance variance of all valid frames, the speed variance of all valid frames, the pitch angle variance of all valid frames, the mean pitch angle of all valid frames, the mean azimuth of all valid frames, the azimuth variance of all valid frames, the larger proportion of positive / negative azimuth valid frames to all valid frames, and the larger proportion of positive / negative pitch angle valid frames to all valid frames.

[0091] Inter-frame data processing: cache multiple frames of information for a gesture, eliminate frames with a speed of 0 (considered invalid frames), and only calculate the statistical values ​​of valid frames (frames with a target speed not equal to 0) as feature statistics, including: a) the larger proportion of positive / negative speed frames to all frames; b) the mean speed of all valid frames; c) the distance variance of all valid frames; d) the speed variance of all valid frames; e) the pitch angle variance of all valid frames; f) the mean pitch angle of all valid frames; g) the mean azimuth angle of all valid frames; h) the azimuth angle variance of all valid frames; i) the larger proportion of positive / negative azimuth angle frames to the total number of frames; g) the larger proportion of positive / negative pitch angle frames to the total number of frames.

[0092] S3. Acquire gesture features according to the intra-frame information and the inter-frame information, identify instruction information according to the gesture features, and control the air conditioner according to the identified instruction information.

[0093] The statistical values ​​are input as features into a machine learning model (such as a random forest model) for gesture recognition. The machine learning model needs to be trained in advance.

[0094] The above method is explained in detail below with reference to the accompanying drawings and specific embodiments.

[0095] Step 1: Define the gesture command set. Figure 1 , defines a complete and low-cost gesture command set, including: a) clockwise circle - turn on the air conditioner, b) counterclockwise circle - turn off the air conditioner, c) right swipe - increase the temperature, d) left swipe - decrease the temperature; e) upward swipe - decrease the wind speed; f) downward swipe - increase the wind speed; g) push and pull forward and backward - switch modes; h) other gestures - invalid commands. Schematic diagram of the 8 gestures can be seen in Figure 1 .

[0096] Step 2: Build a hardware platform to collect data. Build a radar sensor hardware platform, collect radar raw data of different target gestures, and annotate them accordingly. Figure 2 The radar is placed vertically and fixed on a rack. Its detection range is a fan. People make different gestures within the detection range to control the air conditioner. In actual installation, the radar is installed on the air conditioner.

[0097] Step 3: Data processing and training recognition model. Perform intra-frame processing on each frame of raw data, see Figure 3 After radar data preprocessing algorithms such as 2D-FFT, CFAR, peak search, and angle calculation, the pose information (range, velocity, and angle) of each detection point in each frame is obtained. All detection results are relative to the radar, where velocity and distance are radial values ​​relative to the radar. The pose information of the target hand in each frame is calculated based on the weighted average of the amplitude values ​​of each point:

[0098]

[0099] Where x represents the detection result within a frame, which can be speed v, distance r, pitch angle angle ele , or angle azi , m represents the number of detected points in a frame, and its value in different frames may be different, A i Indicates the amplitude of each over-detection point on the RDM diagram, x i Represents the detection result of each over-detection point (corresponding to x) in a frame.

[0100] Based on the hand posture information frame sequence, inter-frame processing is performed, see Figure 4 ,Use the sliding window to cache the fixed length of gesture sequence data, extract the dynamic gesture features, define the frames with the target hand velocity of 0 as invalid frames, otherwise as valid frames, and calculate the statistical values ​​of the gesture sequence data as features, including:

[0101] a) The ratio of positive / negative speed frames to all valid frames is large N pos_vel Represents the total number of frames with positive speed of all target hand detection results, N neg_vel It represents the total number of frames with negative speed of all target hand detection results, and N represents the total number of valid frames, the same below. Obviously, N pos_vel +N pos_vel =N;

[0102] b) Average of all valid frame rates v i Indicates the speed of the target hand in each valid frame, the same below;

[0103] c) Distance variance of all valid frames r i Indicates the detection distance result of the target hand in each valid frame. Represents the mean distance of all valid frames, the same below;

[0104] d) All valid frame rate variances

[0105] e) Average pitch angle of all valid frames angle ele_i Indicates the detection pitch angle result of the target hand in each valid frame, the same below;

[0106] f) Variance of pitch angles of all valid frames

[0107] g) Average azimuth angle of all valid frames angle ele_i Indicates the detection azimuth angle result of the target hand in each valid frame, the same below;

[0108] h) Azimuth angle variance of all valid frames

[0109] i) The ratio of positive / negative azimuth valid frames to all valid frames is large N pos_azi Indicates the total number of valid frames with positive azimuth angles for all target hand detection results, N neg_azi Indicates the total number of valid frames with negative azimuth angles in all target hand detection results;

[0110] g) The ratio of positive / negative pitch angle valid frames to all valid frames is large N pos_ele Indicates the total number of valid frames with positive pitch angles in all target hand detection results, N neg_ele Indicates the total number of valid frames in which the pitch angle of all target hand detection results is negative.

[0111] Create a data set and input it into the machine learning model for training.

[0112] Step 4: Deploy the algorithm. Deploy the raw data extraction algorithm, feature extraction algorithm, and machine learning model to the air conditioner's local processor for corresponding control.

[0113] This embodiment also provides an air conditioner, which is equipped with a millimeter wave radar and a data processing module, the data processing module is used to perform the following Figure 5 An air conditioning control method based on millimeter wave radar is shown.

[0114] The air conditioner of this embodiment can perform Figure 5 The method shown therefore has functions and beneficial effects corresponding to the air conditioning control method based on millimeter wave radar.

[0115] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" 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 representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0116] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0117] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. An air conditioning control method based on millimeter wave radar, characterized in that: The following steps are involved: Collect radar data within a preset area through millimeter-wave radar; Performing intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information; acquiring gesture features according to the intra-frame information and the inter-frame information, identifying instruction information according to the gesture features, and controlling the air conditioner according to the identified instruction information; The inter-frame data processing of the collected radar data includes: Acquire multiple frames of radar data, remove the radar data based on the posture information, and obtain multiple valid frames; Calculate statistical values ​​as gesture features based on multiple valid frames; The statistical values ​​include: the maximum value of the proportion of positive / negative speed frames to all frames, the mean speed of all valid frames, the distance variance of all valid frames, the speed variance of all valid frames, the pitch angle variance of all valid frames, the pitch angle mean of all valid frames, the azimuth mean of all valid frames, the azimuth variance of all valid frames, the maximum value of the proportion of positive / negative azimuth angle valid frames to all valid frames, and the maximum value of the proportion of positive / negative pitch angle valid frames to all valid frames. The calculation formula for the larger value of the ratio of positive / negative speed frames to all frames is: Where N pos_vel Represents the total number of frames with positive speed of all target hand detection results, N neg_vel represents the total number of frames with negative speed of all target hand detection results, and N represents the total number of all valid frames; The formula for calculating the mean of all valid frame rates is: Where, v i Indicates the speed of the target hand in each valid frame; The calculation formula for the distance variance of all valid frames is: Where r i Indicates the detection distance result of the target hand in each valid frame. Represents the mean distance of all valid frames; The formula for calculating the variance of all valid frame rates is: The calculation formula for the mean pitch angle of all valid frames is: Where, angle ele_i Indicates the detection pitch angle result of the target hand in each valid frame; The calculation formula for the pitch angle variance of all valid frames is: The calculation formula for the mean azimuth angle of all valid frames is: Where, angle ele_i Indicates the detection azimuth angle result of the target hand in each valid frame; The calculation formula for the azimuth angle variance of all valid frames is: The formula for calculating the larger value of the ratio of positive / negative azimuth valid frames to all valid frames is: Where N pos_azi Indicates the total number of valid frames with positive azimuth angles for all target hand detection results, N neg_azi Indicates the total number of valid frames with negative azimuth angles in all target hand detection results; The formula for calculating the larger value of the ratio of positive / negative pitch angle valid frames to all valid frames is: Where N pos_ele Indicates the total number of valid frames with positive pitch angles in all target hand detection results, N neg_ele Indicates the total number of valid frames in which the pitch angle of all target hand detection results is negative.

2. The air conditioning control method based on millimeter wave radar according to claim 1, characterized in that: The intra-frame data processing of the collected radar data includes: Perform two-dimensional fast Fourier transform on radar data to obtain multi-channel range Doppler map data; Perform CFAR detection and peak search on the range Doppler map data to obtain the detection points and the range and velocity information corresponding to the detection points; According to the distance and speed information, the multi-channel phase solution is used to obtain the angle information of the target relative to the radar; Based on the distance, speed, and angle information, a weighted average is taken for all detected points in a frame to serve as the target center of gravity. The target center of gravity reflects the position information of the target in the frame, which includes distance, speed, pitch angle, and azimuth angle. The target refers to the hand.

3. The air conditioning control method based on millimeter wave radar according to claim 2, characterized in that: The expression of the posture information is: Among them, x represents the detection results within a frame, including speed v, distance r, pitch angle angle ele Or angle azi ; m represents the number of detection points in a frame, A i Indicates the amplitude of each over-detection point on the RDM diagram, x i Indicates the detection result of each over-detection point in a frame.

4. The air conditioning control method based on millimeter wave radar according to claim 1, characterized in that: The step of identifying instruction information based on gesture features includes: The obtained gesture features are input into the trained machine learning model and the corresponding instruction information is output.

5. An air conditioning control system based on millimeter wave radar, applied to the air conditioning control method according to any one of claims 1 to 4, It is characterized by: include: Millimeter-wave radar, used to transmit electromagnetic waves and collect radar data within a preset area; The data processing module is used to perform intra-frame data processing and inter-frame data processing on the collected radar data to obtain intra-frame information and inter-frame information, obtain gesture features based on the intra-frame information and the inter-frame information, and obtain instructions for controlling the air conditioner based on gesture feature recognition.

6. The air conditioning control system based on millimeter wave radar according to claim 5, characterized in that: The millimeter wave radar is arranged on the air conditioner.

7. The air conditioning control system based on millimeter wave radar according to claim 5, characterized in that: The data processing module is deployed on the processor of the air conditioner.

8. An air conditioner, characterized in that: The air conditioner is provided with a millimeter-wave radar and a data processing module, and the data processing module is used to execute the air conditioner control method based on millimeter-wave radar as described in any one of claims 1-4.

Images