Intelligent range hood control methods and intelligent range hoods

Abstract

This application relates to a control method for an intelligent range hood and an intelligent range hood itself. The intelligent range hood includes three sensors arranged on the same plane. The method includes: assigning a first coordinate to each sensor; calculating a second coordinate of a target object based on the time-of-flight difference of the ultrasonic waves emitted by each sensor and the corresponding first coordinate in a continuous time series; recording the second coordinate of the target object in the continuous time series to generate a coordinate sequence; calculating the velocity component of the target object relative to each sensor; obtaining the trajectory of the target object based on the coordinate sequence and velocity components; and matching corresponding control commands based on the trajectory to control the intelligent range hood. This solves the technical problem of poor accuracy in existing gesture control methods for intelligent range hoods, leading to a high failure rate in gesture control.

Description

Technical Field

[0001] This application relates to the field of intelligent range hood control, and in particular to an intelligent range hood control method and an intelligent range hood. Background Technology

[0002] Range hoods are essential appliances for daily cooking. With the development of smart appliances, the non-contact gesture control function of existing smart range hoods provides users with a convenient and hygienic interactive experience. The reliability of this function highly depends on the accuracy of gesture recognition and environmental robustness.

[0003] Currently, existing gesture control methods rely on optical sensing principles. For example, infrared or radar sensor arrays are placed at specific locations on the panel of a smart range hood. By detecting hand movements within a two-dimensional sensing area, preset simple trajectories are identified, and these trajectories are mapped to basic commands to achieve gesture control of the smart range hood. However, light signals are often attenuated and distorted due to grease buildup, leading to inaccurate gesture feature extraction. Furthermore, in-plane trajectory recognition algorithms struggle to distinguish between unconscious user movements and valid commands, exhibiting poor anti-interference capabilities. Therefore, existing gesture control methods suffer from poor accuracy in practical applications, easily resulting in gesture control failures.

[0004] There is currently no effective solution to the core technical problem of how to improve the accuracy of gesture recognition in order to effectively reduce the control failure rate. Summary of the Invention

[0005] This embodiment provides a smart range hood control method and a smart range hood to solve the technical problem that the gesture control method of existing smart range hoods has poor accuracy, resulting in a high failure rate of gesture control.

[0006] Firstly, this embodiment provides a method for controlling an intelligent range hood, wherein the intelligent range hood includes three sensors arranged on the same plane; the method includes the following steps:

[0007] Assign a first coordinate to each of the sensors;

[0008] In a continuous time series, the second coordinates of the target are calculated based on the time difference of flight of the ultrasonic waves emitted by each sensor and the corresponding first coordinates;

[0009] Record the second coordinates of the target object in the continuous time series to generate a coordinate sequence; calculate the velocity component of the target object relative to each of the sensors; and obtain the trajectory of the target object based on the coordinate sequence and the velocity components.

[0010] The control command is matched based on the running trajectory to control the smart range hood.

[0011] In some embodiments, the step of calculating the second coordinates of the target object based on the time-of-flight difference of the ultrasonic waves emitted by each of the sensors and the corresponding first coordinates, in a continuous time series, includes:

[0012] All sensors emit ultrasonic waves synchronously;

[0013] Record the first timestamp of the ultrasonic wave emitted by each sensor, and the second timestamp of the corresponding ultrasonic wave reflected back to each sensor after passing through the target object, in order to calculate the time difference of flight of the corresponding ultrasonic wave.

[0014] The distance between the target and each of the sensors is measured based on the time difference of flight;

[0015] The second coordinates of the target object are calculated using a triangulation algorithm based on the distance between the target object and all sensors and the first coordinates corresponding to each sensor.

[0016] In some embodiments, recording the second coordinates of the target object in the continuous time series and generating a coordinate sequence includes:

[0017] The continuous time series is constructed based on discrete timestamps;

[0018] Record the second coordinates of the target object corresponding to the discrete timestamp;

[0019] Based on the distribution order of the discrete timestamps, the distribution order of the second coordinates of the target object is set accordingly to obtain the coordinate sequence under the continuous time series.

[0020] In some further embodiments, calculating the velocity component of the target object relative to each of the sensors includes:

[0021] The velocity component of the target object relative to all sensors is determined based on the coordinates of the target object corresponding to two adjacent discrete timestamps and the first coordinate corresponding to each sensor.

[0022] In some embodiments, the control of the smart range hood based on the control command corresponding to the running trajectory includes:

[0023] Construct a control strategy matrix;

[0024] The control strategy matrix defines the mapping relationship between the value range of the characteristic parameters and the control commands;

[0025] One or more feature parameters are extracted from the running trajectory, and the extracted feature parameters are matched with the value range of feature parameters defined in the control strategy matrix to determine the corresponding control command;

[0026] The intelligent range hood is controlled based on the defined control commands.

[0027] In some further embodiments, the characteristic parameters include: the second coordinates of the target object, displacement, velocity component, trajectory angle, trajectory enclosing area, peak velocity, and action duration.

[0028] In some of these embodiments, each of the sensors receives an ultrasonic wave reflected from the target object and detects a change in the signal intensity of the corresponding reflected ultrasonic wave.

[0029] All sensors perform oil concentration detection on the intelligent range hood based on the corresponding signal strength change values;

[0030] Based on the results of the oil concentration detection, adaptive calibration is performed on the measurement benchmarks of all sensors.

[0031] In some of these embodiments, all sensors emit ultrasonic waves at different frequencies.

[0032] In some embodiments, several auxiliary sensors are added around each of the sensors to form three sensor arrays.

[0033] Secondly, this embodiment provides an intelligent range hood, including:

[0034] Three sensors are arranged on the same plane;

[0035] An intelligent control module is used to implement the steps of the method described in any of the foregoing embodiments.

[0036] Compared with related technologies, the embodiments of this application have the following beneficial effects:

[0037] Firstly, unlike existing control methods that rely on optical sensing signals that are susceptible to oil contamination, this application uses ultrasonic waves as the sensing medium. By utilizing the physical characteristics of ultrasonic waves that are not easily affected by oil contamination, the reliability and stability of gesture feature detection are ensured from the signal source, effectively avoiding recognition failures caused by signal attenuation and distortion.

[0038] Secondly, unlike existing control methods that only detect hand movement trajectories in a two-dimensional plane, this application embodiment uses sensors to perform triangulation, calculates the coordinates of the target object in three-dimensional space, and generates its trajectory, thereby expanding the gesture recognition dimension from a plane to a three-dimensional space, greatly enriching the feature information of gestures, providing a data foundation for accurately distinguishing between command gestures and unconscious environmental actions, and significantly improving the anti-interference ability of recognition.

[0039] Third, based on the spatial trajectory, the embodiments of this application further calculate the velocity components of the target object, which together constitute the running trajectory used for identification and judgment. Kinematic features are introduced, making the feature description of the gesture more comprehensive and unique, thereby supporting more complex and accurate recognition logic, and ultimately achieving a high accuracy judgment of the gesture intention, fundamentally reducing the control failure rate.

[0040] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0041] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0042] Figure 1 This is a flowchart of an embodiment of the intelligent range hood control method provided in this application;

[0043] Figure 2 This is a schematic diagram of the second coordinate solution provided in an embodiment of this application;

[0044] Figure 3 This is a schematic diagram of an instruction matching process provided in an embodiment of this application;

[0045] Figure 4 This is a front view schematic diagram of an embodiment of the intelligent range hood provided in this application;

[0046] Figure 5 This is a side view schematic diagram of an embodiment of the intelligent range hood provided in this application;

[0047] Figure 6 This is a block diagram of an intelligent range hood provided in one embodiment of this application.

[0048] In the diagram: 410, frame; 420, panel assembly; 421, first sensor; 422, second sensor; 423, third sensor. Detailed Implementation

[0049] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0050] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects.

[0051] This embodiment provides a smart range hood control method. Figure 1 This is a flowchart of the intelligent range hood control method of this embodiment, as shown below. Figure 1 As shown, the process includes the following steps:

[0052] Step S101 involves deploying the three sensors on the same plane and assigning a first coordinate to each sensor. In this step, by assigning coordinates to all sensors, a reference system for spatial measurement is established, providing a fundamental reference for the precise positioning of the target object. In this step, "the same plane" means that the detection reference points of all sensors are located within a common two-dimensional reference plane. This deployment method is the mathematical prerequisite for subsequent application of triangulation algorithms to calculate three-dimensional spatial coordinates, establishing a stable and accurate spatial measurement reference for the entire system.

[0053] Step S102: Under continuous time series conditions, the second coordinates of the target object are calculated based on the time-of-flight difference of the ultrasonic waves emitted by each sensor and the corresponding first coordinates. In this step, ultrasonic waves are used as the sensing medium, ensuring increased detection stability from the signal source. Furthermore, triangulation expands the gesture recognition dimension from a two-dimensional plane to three-dimensional space, significantly enriching the feature information of the gestures and helping to improve measurement accuracy. In this step, "continuous time series" refers to the system continuously performing multiple measurements at a fixed high sampling frequency (e.g., 10ms), thereby connecting discrete spatial location points into trajectory data describing the movement process of the target object.

[0054] Step S103: Record the second coordinates of the target object in the continuous time series, generating a coordinate sequence. In this step, using the continuous time series as a reference, the spatial location points traversed by the target object are organized in chronological order to form a coordinate sequence, providing technical data for subsequently obtaining the target object's trajectory. It can be understood that the target object's movement here can be mapped to hand gestures in practical applications.

[0055] Step S104: Calculate the velocity component of the target object relative to each sensor. In this step, kinematic features are introduced, and the motion state of the target object is described by the velocity component, i.e., the rate of change of the target object's coordinates.

[0056] Step S105: The trajectory of the target object is obtained based on the coordinate sequence and velocity components. In this step, spatial path and dynamic velocity information are fused to form a complete description of the gesture.

[0057] Step S106 involves matching the corresponding control command based on the running trajectory to control the smart range hood. In this step, the trajectory mapping, which integrates spatial and dynamic features, is used as the command to achieve a high degree of accuracy in judging gesture intentions, thereby realizing accurate control of the smart range hood and fundamentally reducing the control failure rate.

[0058] It should be noted that the principle of three-axis spatial gesture recognition in this embodiment is as follows: three sensors form a plane. When a target object moves above the sensor plane, it reflects ultrasonic waves. The continuous movement of the target object generates the Doppler effect and changes in the phase of the sound waves, thus enabling the capture of its trajectory in three-axis space, thereby performing three-axis spatial gesture recognition. Here, the target object corresponds to the hand, and the movement of the target object corresponds to the movement of the hand.

[0059] Through the above steps, compared with related technologies, this application embodiment uses ultrasound as the sensing medium. Utilizing its physical characteristic of being less susceptible to oil interference, it ensures the reliability and stability of gesture feature detection from the signal source, effectively avoiding recognition failures caused by signal attenuation and distortion. This application embodiment uses triangulation by deploying sensors to calculate the coordinates of the target object in three-dimensional space and generate its trajectory, thereby expanding the gesture recognition dimension from a plane to three-dimensional space. This greatly enriches the feature information of the gesture, providing a data foundation for accurately distinguishing between command gestures and unconscious environmental movements, and significantly improving the anti-interference capability of recognition. Based on the spatial trajectory, this application embodiment further calculates the velocity component of the target object, jointly constructing the trajectory used for recognition and judgment. This introduces kinematic features, making the feature description of the gesture more comprehensive and unique, thus supporting more complex and precise recognition logic, ultimately achieving a high-accuracy judgment of gesture intent and fundamentally reducing the control failure rate.

[0060] The aforementioned technical means and the achieved technical effects enable this embodiment to effectively solve the technical problem that the gesture control method of existing smart range hoods has poor accuracy, resulting in a high failure rate of gesture control.

[0061] In some embodiments, the process of calculating the second coordinates of the target object based on the time-of-flight difference of the ultrasonic waves emitted by each sensor and the corresponding first coordinates in a continuous time series includes the following steps:

[0062] All sensors emit ultrasonic waves synchronously. This step, through precise timing control, ensures the consistency of the signals emitted by each sensor, thus avoiding excessive measurement errors caused by differences in the timing of ultrasonic wave emission.

[0063] The system records the first timestamp of the ultrasonic wave emitted by each sensor, and the second timestamp of the corresponding ultrasonic wave reflected back to each sensor after passing through the target object, in order to calculate the time difference of flight of the corresponding ultrasonic wave. This step, through high-precision timestamp recording, enables accurate measurement of the ultrasonic wave propagation time, providing a reliable time basis for subsequent distance calculations.

[0064] The distance between the target object and each sensor is measured based on the time difference of flight. This step utilizes the propagation characteristics of ultrasound to convert time measurements into spatial distance information, achieving a conversion from the time domain to the spatial domain and providing distance parameters for subsequent spatial positioning.

[0065] A triangulation algorithm is employed to calculate the target's second coordinates based on the distances between the target and all sensors, as well as the first coordinates corresponding to each sensor. This step fuses multiple distance measurements, achieving a precise conversion from one-dimensional distance to three-dimensional spatial coordinates, significantly improving the accuracy of position perception.

[0066] This embodiment solves the technical problem of achieving high-precision and high-reliability gesture spatial positioning in complex cooking environments through the above-mentioned technical solution, providing accurate spatial position data support for subsequent gesture trajectory recognition and control command generation.

[0067] In some further embodiments, when measuring the distance between the target and the corresponding sensor, the speed of sound is assumed to be C, and its propagation speed in air is approximately 340 m / s.

[0068] Then the distance from the target object to the corresponding sensor can be obtained as: ;in, This refers to the time difference in flight time.

[0069] In some further embodiments, please refer to Figure 2 Using the plane where the three sensors are located as the XY plane and the direction towards the target object as the Z-axis, the calculation of the second coordinates of the target object includes the following process:

[0070] The distance between the hand and the three sensors can be obtained by measuring the time difference of flight of the three sensors. The velocity components in three directions are then used. A triangulation algorithm is then used to calculate the hand position. :

[0071] Let the coordinates of the three sensors be respectively , and The location of the target object is Based on triangulation, the following relationship is established:

[0072] ;

[0073] ;

[0074] ;

[0075] Based on the above relationship, the real-time target position can be directly obtained. .

[0076] In some embodiments, the process of generating a coordinate sequence by recording the second coordinates of the target object in a continuous time series specifically includes the following steps:

[0077] Constructing continuous time series based on discrete timestamps. This step transforms continuous hand gestures, i.e., object movements, into collectable signal sequences through discretized time sampling, establishing a structured data foundation in the time dimension for subsequent trajectory analysis.

[0078] Record the second coordinates of the target object corresponding to the discrete timestamp. This step, by precisely mapping spatial coordinates to timestamps, achieves complete acquisition of spatial position information during the gesture movement process, ensuring the spatiotemporal consistency of trajectory data.

[0079] Based on the distribution order of discrete timestamps, the distribution order of the second coordinates of the target object is set accordingly to obtain a coordinate sequence under continuous time series. This step constructs a complete trajectory sequence reflecting the gesture movement path by organizing spatial coordinate points in time sequence, providing accurate data support for subsequent velocity calculation and trajectory feature extraction.

[0080] This embodiment addresses the technical problem of accurately recording and reconstructing gesture motion trajectories through the aforementioned technical solution. By establishing a spatiotemporal coordinate sequence acquisition method, it ensures the integrity and temporal accuracy of the gesture motion process, providing reliable data support for subsequent trajectory recognition.

[0081] In some further embodiments, the process of calculating the velocity component of the target object relative to each sensor includes the following steps: determining the velocity component of the target object relative to all sensors based on the coordinates of the target object corresponding to two adjacent discrete timestamps and the first coordinate corresponding to each sensor. This step transforms continuous static position information into instantaneous velocity information through differential operations, realizing the transition from spatial positioning to motion state analysis and introducing a key dynamic feature dimension for gesture recognition.

[0082] In a further embodiment, the direction of motion of the target object can be determined based on the coordinates of the target object corresponding to two adjacent timestamps, and the distance between the target object and each sensor can be measured, thereby calculating the velocity component of the target object relative to all sensors.

[0083] In a further embodiment, a velocity component sequence can be formed based on the velocity component and the timestamp, and the trajectory of the target object can be determined by combining the velocity component sequence with the coordinate sequence. This embodiment presents a more intuitive technical implementation for obtaining velocity components.

[0084] In some of these embodiments, the process of controlling the smart range hood by matching corresponding control commands based on the operating trajectory specifically includes the following steps:

[0085] Constructing a control strategy matrix. This step decomposes the complex feature matching problem into multiple levels of simple threshold judgments by establishing a tree-like judgment structure, providing a systematic logical framework for achieving efficient and reliable gesture command mapping.

[0086] The control strategy matrix defines the mapping relationship between the value ranges of characteristic parameters and control commands. This step establishes a fault-tolerance mechanism by setting reasonable threshold ranges for different characteristic parameters, enabling the system to adapt to natural fluctuations in user operations. At the same time, through the combined mapping of multi-dimensional characteristic parameters, the uniqueness and anti-interference capability of the commands are greatly enhanced.

[0087] One or more feature parameters are extracted from the trajectory and matched with the value ranges of feature parameters defined in the control strategy matrix to determine the corresponding control commands. This step transforms the collected trajectory data into standardized feature parameters and achieves intelligent and accurate classification from continuous gestures to discrete control commands through step-by-step comparison in the decision tree.

[0088] The smart range hood is controlled based on control commands. This step completes the closed-loop control from gesture perception to device execution, achieving precise, contactless human-machine interaction.

[0089] This embodiment solves the technical problem of how to reliably map complex gesture trajectories into specific control commands through the above-described technical solution. By using a decision tree model to perform structured judgment on multi-dimensional features, it effectively avoids false triggering and missed triggering, supports rich and customizable interactive commands, and thus greatly improves the user experience.

[0090] In some further embodiments, the feature parameters include at least the trajectory angle, peak velocity, and trajectory enclosing area. That is, the feature parameters are defined as:

[0091] ;

[0092] based on Calculate the peak speed, where The sampling period.

[0093] based on Calculate the trajectory angle, where This represents the coordinate difference between adjacent frames.

[0094] The area of ​​the polygon enclosed by multiple sampling points is calculated using the shoelace-theorem formula. Calculate the area enclosed by the trajectory.

[0095] It should be understood that the calculation method provided in this embodiment is a method that can be adopted in actual application, rather than a strict limitation. Those skilled in the art can refer to the above method to obtain the necessary parameters in the execution process of this method.

[0096] In a further embodiment, in addition to trajectory angle, peak velocity and trajectory enclosing area, the feature parameters also include: the second coordinates of the target object, displacement, velocity component and action duration.

[0097] In some further embodiments, the control strategy matrix is ​​shown in Table 1.

[0098] Table 1 Control Strategy Matrix Mapping Table

[0099]

[0100] Table 1 is interpreted as follows:

[0101] The mapping logic for the right-waving hand trajectory is based on mapping conditions: the determination of this gesture is based on a combination of three key parameters in spatial and dynamic characteristics. First, the hand must produce an effective displacement of more than 100 mm in the positive X-axis direction of the horizontal plane to ensure the significance of the movement. Second, the instantaneous velocity in this direction of movement must be higher than 0.8 m / s to ensure the decisiveness and clarity of intent of the movement. Finally, the angle between the entire waving trajectory and the horizontal reference plane (XZ plane) must be less than 20 degrees to strictly limit it to an approximately horizontal lateral movement. This multi-dimensional constraint mechanism can effectively eliminate slow, random lateral movements during cooking, ensuring that the power-on or gear-up command is triggered only when the user makes a quick, decisive, and directional gesture.

[0102] The mapping logic for the leftward hand-waving trajectory is based on mapping conditions: This gesture is a mirror image of the rightward hand-waving operation, and its recognition criteria are symmetrical but in the opposite direction. It requires the hand to have a displacement exceeding 100 mm in the negative X-axis direction, a movement speed below -0.8 m / s, and the trajectory's angle with the horizontal plane to be less than 20 degrees. This strict symmetry design constitutes an effective anti-accidental touch mechanism. Through clear reverse motion characteristics, it reliably distinguishes between reciprocal operation commands such as power on / off and gear shifting, avoiding control confusion caused by directional ambiguity.

[0103] The mapping logic for the upward hand-waving trajectory is based on mapping conditions: the recognition of this gesture focuses on the vertical motion characteristics. The judgment conditions include: the displacement in the positive Z-axis direction must be greater than 150 mm to ensure sufficient amplitude; the entire action must be completed within 0.4 seconds to ensure speed; and the angle between the trajectory and the horizontal plane is limited to between 70 and 110 degrees to ensure an approximately vertical upward path. This composite condition design conforms to ergonomic principles, allowing users to control the rise of the fume hood with a natural hand-raising motion, while the strict requirements for verticality and speed effectively prevent accidental triggering due to normal arm movements during daily stove operation.

[0104] The mapping logic for the downward hand-waving trajectory is based on mapping conditions: as the corresponding operation for an upward hand-waving gesture, this gesture requires the hand to displace more than 150 mm in the negative Z-axis direction, with a completion time of less than 0.4 seconds, and the trajectory angle is also kept within a near-vertical range of 70 to 110 degrees. This design specifically considers child safety factors. Since the downward hand-waving requires the hand to start from a high position in front of the sensor, this starting position requirement significantly reduces the possibility of children accidentally triggering the device while playing near the stove, thereby enhancing the product's safety.

[0105] The mapping logic for the circular motion trajectory is based on mapping conditions: the recognition of this complex gesture relies on the precise analysis of the geometric characteristics of the hand's motion trajectory. First, the projected area of ​​the gesture on the plane must be greater than 100 square millimeters to ensure the significant scale of the movement. More importantly, the ratio of area to the square of the feature height is introduced as a roundness criterion, and this ratio must be within a specific range of 0.9 to 1.1. This original algorithm can effectively identify motion trajectories that approach a circle, while excluding invalid movements that are excessively elongated in the X or Y direction (such as waving back and forth). By utilizing the unique geometric characteristics of circular gestures, the system can reliably trigger special functions such as the "stir-fry" mode, and is not easily triggered by routine operations.

[0106] The logic for mapping hovering trajectories based on mapping conditions is as follows: Gesture recognition relies on precise detection of the hand's stationary state. The judgment conditions include: the hand's movement speed must consistently be below 0.1 m / s to ensure a near-static state; the vertical distance fluctuation between the hand and the sensor must be less than 20 mm to ensure positional stability; and this state must be maintained for 3 seconds. This strict spatiotemporal constraint mechanism clearly distinguishes between intentional hovering commands and normal brief pauses during cooking, effectively avoiding false triggers and ensuring that auxiliary functions such as self-cleaning or brightness adjustment are only triggered when the user has a clear and stable hovering intention.

[0107] This embodiment constructs an intelligent judgment system based on a combination of multi-dimensional feature parameters, incorporating various physical quantities such as spatial displacement, motion speed, trajectory angle, duration, and geometric shape into a unified evaluation framework, thus establishing a highly reliable and interference-resistant gesture recognition system. This solution can accurately distinguish between conscious control commands and unconscious random actions, fundamentally solving the technical pain points of high misjudgment rate and poor reliability in traditional gesture recognition technology, ultimately achieving a significant reduction in gesture control failure rate.

[0108] In a preferred embodiment, please refer to Figure 3When acquiring the continuous coordinate sequence of the target object, for example, in actual operation, acquiring the second coordinates corresponding to 20 consecutive frames, i.e., 20 timestamps, and calculating its trajectory characteristics, the control command is matched through the following decision logic: If the trajectory characteristics meet the preset "left and right waving" characteristic conditions, the power-on, power-off, or gear adjustment command is triggered; if the trajectory characteristics meet the preset "up and down waving" characteristic conditions, the raising and lowering control command of the smoke hood or smoke baffle is triggered; if the trajectory characteristics meet the preset "circling" characteristic conditions, the stir-fry mode command is triggered; if the trajectory characteristics meet the preset "hovering" characteristic conditions, the self-cleaning start or panel brightness adjustment command is triggered.

[0109] This embodiment, through the aforementioned technical solution, efficiently and reliably classifies continuous trajectory signals into discrete, highly discriminative gesture types using a decision tree model, and maps them to rich device functions. This structured judgment process effectively reduces the false recognition rate, supports multiple types of complex gestures, and thus constructs an intuitive, smooth, and highly intelligent contactless human-computer interaction system.

[0110] In some further embodiments, by capturing the spatial position of the power-on gesture, the user's height characteristics are automatically calculated, and the target height of the relevant structures of the smart range hood, such as the smoke collection hood or the smoke baffle glass, is adjusted to provide the user with the best operating line of sight and sense of space.

[0111] The mathematical model is established as follows: ,in: Represents the target height, obtained through calculation; This represents the base height, which is set by the factory, such as 700mm from the surface of the fume hood. The ergonomic coefficient, such as 0.85, can be determined experimentally, and can be given separately for different machine configurations. Represents the waving height, obtained through location measurement; This represents the baseline wave height, calibrated by the laboratory.

[0112] This embodiment addresses the common technical problem of obstructed vision or insufficient operating space in smart kitchen appliances caused by differences in user height. By extracting height features based on gesture recognition and adaptive height adjustment, it achieves personalized device adaptation, significantly improving the operating comfort and user experience for users of different heights.

[0113] In some embodiments, the intelligent range hood control method further includes the following steps:

[0114] Each sensor receives the ultrasonic wave reflected from the target object and detects the change in the signal intensity of the reflected ultrasonic wave. This step reuses existing gesture detection hardware and provides a cost-free data acquisition method for detecting oil contamination by monitoring the energy attenuation characteristics of ultrasonic waves in the propagation medium.

[0115] All sensors detect the oil concentration of the smart range hood based on corresponding signal strength changes. This step, by integrating monitoring data from multiple sensors, provides a comprehensive assessment of the oil concentration in the environment, improving the accuracy and reliability of the detection results and providing a quantitative basis for equipment maintenance and user reminders.

[0116] Based on the oil concentration detection results, adaptive calibration is performed on the measurement benchmarks of all sensors. This step compensates in real time for sensor performance degradation caused by oil adhesion, enabling the system to maintain its initial measurement accuracy during long-term use and ensuring the consistency and stability of the gesture recognition function.

[0117] This embodiment addresses the technical problem of decreased measurement accuracy caused by oil accumulation in sensors during long-term use in harsh kitchen environments. It achieves self-diagnosis and continuous performance optimization of the system, significantly improving the product's durability and reliability.

[0118] In some embodiments, all sensors emit ultrasonic waves at different frequencies. For example, it is recommended that three groups of sensors use different frequencies to reduce interference (each group includes one transmitter and one receiver), such as group A using 22 kHz, group B using 40 kHz, and group C using 80 kHz. This step, by assigning an independent operating frequency to each sensor channel, distinguishes the signal sources at the hardware level, fundamentally avoiding the problem of crosstalk between multiple ultrasonic signals operating at the same frequency.

[0119] In some embodiments, several auxiliary sensors are added around each sensor to form three sensor arrays. This step, by constructing sensor arrays and utilizing the synthesis and processing of multi-unit signals, enhances the intensity and signal-to-noise ratio of the echo signal, thereby improving the robustness and detection range of a single measurement channel in complex environments.

[0120] In some embodiments, the three sensors are arranged in an isosceles triangle. Similarly, the three sensor arrays can also be arranged in an isosceles triangle. This step, by employing a symmetrical isosceles triangle layout, establishes an optimal geometric measurement baseline within the mounting plane, ensuring that the spatial positioning algorithm achieves uniform and high-precision calculation results in both the left and right operating areas in front of the range hood, thus optimizing the gesture recognition performance across the entire area. Considering that users may operate from the left or right cooking position, an isosceles triangle layout is recommended, with the center of symmetry at the left and right center lines of the range hood. The distance between groups A and B is set to 'a', and group C is located at the vertex of the isosceles triangle. The distance can be adjusted according to the panel height and is defined as 'b'. The sensors form an XY plane, with the Z-axis pointing outwards towards the user. A user's hand gesture may cause movement in the XYZ directions.

[0121] This embodiment addresses the technical problem of how to optimize hardware deployment to improve overall system perception performance and user experience through the above-mentioned technical solution. By enhancing signal quality through arraying and eliminating recognition blind spots and performance unevenness through symmetrical layout, it ensures that users can obtain accurate and smooth gesture interaction experience in any typical operation position.

[0122] This embodiment also provides a smart range hood, please refer to... Figure 6 The smart range hood includes:

[0123] Three sensors are arranged on the same plane;

[0124] The intelligent control module is used to implement the aforementioned method embodiments and preferred embodiments, and will not be repeated hereafter.

[0125] The terms “module,” “unit,” “subunit,” etc., used below can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0126] In some further embodiments, please refer to Figure 4 and Figure 5 The intelligent range hood includes a frame 410 and a smoke inlet located below the frame 410. A smoke baffle is provided outside the smoke inlet, and a panel assembly 420 is located outside the smoke inlet. Sensors, including a first sensor 421, a second sensor 422, and a third sensor 423, are all integrated within the panel assembly 420, facing the user's daily cooking area. This embodiment optimizes the sensing path and shortens the signal transmission distance by directly integrating the sensors and their signal processing units into the panel assembly 420 facing the user's operating area. This effectively improves the real-time performance and signal-to-noise ratio of gesture detection, while also providing a hardware foundation for a compact and modular design of the entire machine.

[0127] In some further embodiments, a panel assembly is installed outside the smoke baffle or smoke inlet, and sensors are mounted on the panel assembly. The panel assembly integrates a bandpass filter module and a signal acquisition and processing motherboard, and is externally fitted with a tempered glass panel. Furthermore, a gesture detection area is pre-set between the panel assembly and the area in front of the user, facilitating gesture detection by the sensors and the recognition of corresponding commands by the intelligent control module to control the intelligent range hood.

[0128] In some further embodiments, please refer to... Figure 6 The intelligent range hood in this embodiment also includes the following structure:

[0129] The switch module interacts with the intelligent control module to control the smart range hood's on and off functions.

[0130] The fan drive module interacts with the intelligent control module to adjust the air volume, wind speed and other functions of the intelligent range hood;

[0131] Communication module;

[0132] An optional lifting drive module interacts with the intelligent control module to control the lifting of the smoke hood or smoke inlet based on the user's height, thus facilitating the user's gesture control.

[0133] The lighting module interacts with the intelligent control module to control the on / off state of relevant indicator lights;

[0134] Storage module.

[0135] This embodiment constructs a fully functional modular system architecture, realizing a complete control loop from gesture recognition and intelligent decision-making to multi-dimensional execution of airflow, height, lighting, and communication, providing solid hardware support and execution capabilities for rich intelligent interactive functions.

[0136] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0137] This embodiment also provides a computer device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0138] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0139] Furthermore, in conjunction with the intelligent range hood control method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any one of the intelligent range hood control methods in the above embodiments.

[0140] It should be noted that all information and data involved in this application are authorized by the user or fully authorized by all parties and will be used legally.

[0141] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0142] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0143] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0144] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application.

Claims

1. A method for controlling an intelligent range hood, characterized in that, The intelligent range hood includes three sensors arranged on the same plane; the method includes: Assign a first coordinate to each of the sensors; In a continuous time series, the second coordinates of the target are calculated based on the time difference of flight of the ultrasonic waves emitted by each sensor and the corresponding first coordinates; Record the second coordinates of the target object in the continuous time series to generate a coordinate sequence; calculate the velocity component of the target object relative to each of the sensors; and obtain the trajectory of the target object based on the coordinate sequence and the velocity components. The control command is matched based on the running trajectory to control the smart range hood.

2. The method according to claim 1, characterized in that, In the continuous time series, the step of calculating the second coordinates of the target object based on the time-of-flight difference of the ultrasonic waves emitted by each sensor and the corresponding first coordinates includes: All sensors emit ultrasonic waves synchronously; Record the first timestamp of the ultrasonic wave emitted by each sensor, and the second timestamp of the corresponding ultrasonic wave reflected back to each sensor after passing through the target object, in order to calculate the time difference of flight of the corresponding ultrasonic wave. The distance between the target and each of the sensors is measured based on the time difference of flight; The second coordinates of the target object are calculated using a triangulation algorithm based on the distance between the target object and all sensors and the first coordinates corresponding to each sensor.

3. The method according to claim 1, characterized in that, The process of recording the second coordinates of the target object in the continuous time series and generating a coordinate sequence includes: The continuous time series is constructed based on discrete timestamps; Record the second coordinates of the target object corresponding to the discrete timestamp; Based on the distribution order of the discrete timestamps, the distribution order of the second coordinates of the target object is set accordingly to obtain the coordinate sequence under the continuous time series.

4. The method according to claim 3, characterized in that, The calculation of the velocity component of the target object relative to each of the sensors includes: The velocity component of the target object relative to all sensors is determined based on the coordinates of the target object corresponding to two adjacent discrete timestamps and the first coordinate corresponding to each sensor.

5. The method according to claim 1, characterized in that, The control command based on the running trajectory to control the smart range hood includes: Construct a control strategy matrix; The control strategy matrix defines the mapping relationship between the value range of the characteristic parameters and the control commands; One or more feature parameters are extracted from the running trajectory, and the extracted feature parameters are matched with the value range of feature parameters defined in the control strategy matrix to determine the corresponding control command; The intelligent range hood is controlled based on the defined control commands.

6. The method according to claim 5, characterized in that, The characteristic parameters include: the second coordinates of the target object, displacement, velocity component, trajectory angle, trajectory enclosed area, peak velocity, and action duration.

7. The method according to claim 1, characterized in that, Also includes: Each of the sensors receives the ultrasonic wave reflected by the target object and detects the change in signal intensity of the corresponding reflected ultrasonic wave. All sensors perform oil concentration detection on the intelligent range hood based on the corresponding signal strength change values; Based on the results of the oil concentration detection, adaptive calibration is performed on the measurement benchmarks of all sensors.

8. The method according to claim 1, characterized in that, All sensors emit ultrasonic waves at different frequencies.

9. The method according to claim 1, characterized in that, Several auxiliary sensors are added around each of the aforementioned sensors to form three sensor arrays.

10. A smart range hood, characterized in that, include: Three sensors are arranged on the same plane; An intelligent control module is used to implement the steps of the method according to any one of claims 1 to 6.

Images