Cooking action recognition method, intelligent extractor hood, device and computer equipment

Abstract

This application relates to a cooking action recognition method, a smart range hood, a device, and a computer equipment. The method includes: acquiring sound signals generated by the collision of a cookware during use; determining a corresponding decay time constant value based on the sound signal; determining a preset value range to which the decay time constant value belongs; associating the preset value range with different cooking actions; and determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs. This application solves the problem of ineffective cooking action recognition in related technologies, achieving effective recognition of cooking actions during the cooking process.

Description

Technical Field

[0001] This application relates to the field of smart kitchen appliance technology, and in particular to cooking action recognition methods, smart range hoods, devices, and computer equipment. Background Technology

[0002] With the rapid development of smart technology, range hoods are constantly generating new intelligent functionalities, such as remote control via Wi-Fi, contactless gesture control for power on / off, and integrated air quality sensors for kitchen environment monitoring. However, in actual cooking, how to recognize changes in the user's cooking actions still lacks in-depth research and effective technological applications.

[0003] There is currently no effective solution to the problem that related technologies cannot effectively recognize cooking actions. Summary of the Invention

[0004] This embodiment provides a cooking action recognition method, a smart range hood, a device, and a computer equipment to solve the problem that cooking actions cannot be effectively recognized in related technologies.

[0005] Firstly, this embodiment provides a cooking action recognition method, including:

[0006] Collect sound signals generated by the collision of cookware during use;

[0007] Based on the sound signal, determine the corresponding decay time constant value;

[0008] Determine the preset value range to which the decay time constant value belongs; the preset value range is associated with different cooking actions;

[0009] The cooking action corresponding to the cookware is determined based on the preset value range to which the constant value of the decay time belongs.

[0010] In some embodiments, determining the corresponding decay time constant value based on the sound signal includes:

[0011] Extract the envelope of the sound signal;

[0012] Logarithmically linearize the envelope to obtain a linear sequence;

[0013] Perform linear regression fitting on the linear sequence to obtain the fitting slope;

[0014] Based on the fitted slope, the corresponding constant value of the decay time is determined.

[0015] In some embodiments, the preset numerical range includes a first numerical range and a second numerical range; determining the cooking action corresponding to the cookware based on the preset numerical range to which the decay time constant value belongs includes:

[0016] If the constant value of the decay time belongs to the first value range, the cooking action is determined to be a stir-fry action;

[0017] If the constant value of the decay time belongs to the second value range, the cooking action is determined to be a steaming or boiling action.

[0018] In some embodiments, after determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs, the method further includes:

[0019] When the cooking action is steaming or boiling, the range hood's fan speed mode is switched to the first mode that matches the steaming or boiling action.

[0020] In some embodiments, after determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs, the method further includes:

[0021] When the cooking action is a stir-frying action, the frequency of the stir-frying action within a preset time period is determined;

[0022] The occurrence frequency is compared with a preset frequency threshold.

[0023] If the occurrence frequency is greater than or equal to the preset frequency threshold, the range hood's fan mode will be switched to a second mode that matches the stir-frying action.

[0024] If the occurrence frequency is less than the preset frequency threshold, the current wind mode is maintained.

[0025] In some embodiments, after switching the wind mode to a second mode that matches the stir-frying action, the method further includes:

[0026] Stop detecting the sound signal within a preset time window; the preset time window is a preset period of time during which the second mode continues to run after it is started.

[0027] In some embodiments, after collecting the sound signal generated by the collision of the cookware during use, the method further includes:

[0028] The sound signal within a preset frequency range is extracted using a bandpass filter;

[0029] When the amplitude of the sound signal within the preset frequency range exceeds a preset amplitude threshold, the analysis of the sound signal is triggered.

[0030] Secondly, this embodiment provides an intelligent range hood, which includes a controller; the controller executes the cooking action recognition method described in any of the first aspects above.

[0031] Thirdly, this embodiment provides a cooking action recognition device, including: a data acquisition module, an analysis module, and a matching module;

[0032] The acquisition module is used to acquire sound signals generated by the collision of cookware during use;

[0033] The analysis module is used to determine the corresponding decay time constant value based on the sound signal;

[0034] The matching module determines a preset value range to which the decay time constant value belongs; the preset value range is associated with different cooking actions; and determines the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs.

[0035] Fourthly, this embodiment provides a computer device including a memory and a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cooking action recognition method described in the first aspect above.

[0036] Compared with related technologies, the cooking action recognition method, intelligent range hood, device, and computer equipment provided in this embodiment collect sound signals generated by the collision of cookware during use; determine the corresponding decay time constant value based on the sound signal; determine the preset value range to which the decay time constant value belongs; associate the preset value range with different cooking actions; and determine the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs. By analyzing the physical characteristics of sound wave damping oscillation, the sound signal is quantified into a decay time constant value with clear physical meaning, and the cooking action is accurately distinguished based on the decay time constant value, solving the problem of ineffective recognition of cooking actions in related technologies and realizing effective recognition of cooking actions during the cooking process.

[0037] 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

[0038] 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:

[0039] Figure 1 This is a hardware structure block diagram of a terminal device for a cooking action recognition method provided in an embodiment of this application;

[0040] Figure 2 This is a flowchart of a cooking action recognition method provided in an embodiment of this application;

[0041] Figure 3 This is a flowchart of determining the value of the decay time constant provided in one embodiment of this application;

[0042] Figure 4 This is a schematic diagram showing the relative positions of the installed smart range hood and the cookware according to an embodiment of this application;

[0043] Figure 5 This is a schematic flowchart of a cooking action recognition method provided in an embodiment of this application;

[0044] Figure 6 This is a system block diagram of an intelligent range hood provided in one embodiment of this application;

[0045] Figure 7 This is a structural block diagram of a cooking action recognition device provided in an embodiment of this application.

[0046] In the diagram: 102, processor; 104, memory; 106, transmission device; 108, input / output device; 201, range hood fan frame; 202, smoke baffle; 203, piezoelectric sensor; 210, acquisition module; 220, analysis module; 230, matching module. Detailed Implementation

[0047] 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.

[0048] 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 these processes, methods, products, or devices. Words such as “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. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. Normally, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," "third," etc., used in this application are merely to distinguish similar objects and do not represent a specific order of objects.

[0049] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the cooking action recognition method in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0050] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the cooking action recognition method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0051] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0052] This embodiment provides a cooking action recognition method. Figure 2 This is a flowchart of the cooking action recognition method in this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0053] Step S210: Collect the sound signal generated by the collision of the cookware during use.

[0054] Specifically, the sound signals generated by the collision of cookware during use can be directly picked up by a piezoelectric acoustic wave sensor integrated into the inner wall of the smoke collection chamber of the smart range hood; alternatively, they can be collected by a microphone array built into the range hood and matched with preset metal collision spectrum characteristics using voiceprint recognition technology to filter valid signals; alternatively, vibration sensors installed on the stove bracket or cookware handle can be used to collect mechanical vibration signals transmitted through the structure. This application does not limit the method of sound signal acquisition. Meanwhile, to improve the signal-to-noise ratio, the collected raw signals are filtered to retain the main frequency band components that best reflect the structural characteristics of the cookware for subsequent analysis.

[0055] Step S220: Determine the corresponding decay time constant value based on the sound signal.

[0056] Specifically, based on the physical law that the sound signal generated by the collision of cookware during use conforms to damped simple harmonic oscillation, the corresponding decay time constant value is determined. First, the envelope of the acquired time-domain voltage signal is extracted to characterize the exponential decay trend of the amplitude over time. Second, the envelope is logarithmically linearized to transform the complex exponential decay relationship into an intuitive linear relationship. Finally, linear regression is used to accurately calculate the fitting slope directly related to the decay time constant value, and the decay time constant value is determined based on the mathematical relationship. The calculation method for the decay time constant value can also be the spectral analysis method or the step response method for system identification; therefore, the method for calculating the decay time constant value is not limited here.

[0057] Step S230: Determine the preset value range to which the decay time constant value belongs; the preset value range is associated with different cooking actions; determine the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs.

[0058] Specifically, based on the correspondence between the preset value range of the decay time constant and the cooking action, the system automatically determines the current cooking action type. Cooking actions include, but are not limited to, stir-frying, steaming, boiling, or deep-frying; there are no restrictions on the type of cooking action. During the determination, the system also performs secondary confirmation by considering the effective event density per unit time to improve the accuracy of cooking action recognition.

[0059] The above steps resolve the issue of ineffective recognition of cooking actions in related technologies. High-precision, interference-resistant recognition of cooking actions based on the attenuation characteristics of sound waves from pot collisions has been achieved, providing crucial support for adjusting the range hood's fan speed mode according to the cooking actions.

[0060] The above steps are explained in detail below:

[0061] In some of these embodiments, such as Figure 3 As shown, step S220, determining the corresponding decay time constant value based on the sound signal, includes the following steps:

[0062] Step S221: Extract the envelope of the sound signal;

[0063] Step S222: Perform logarithmic linearization on the envelope to obtain a linear sequence;

[0064] Step S223: Perform linear regression fitting on the linear sequence to obtain the fitting slope;

[0065] Step S224: Determine the corresponding constant value of decay time based on the fitted slope.

[0066] Specifically, sound signals are picked up by a piezoelectric sensor, which is preferably made of lead zirconate titanate piezoelectric ceramic (PZT-5H) material. Figure 4 As shown, the piezoelectric sensor 203 is fixedly mounted on the inner wall of the smoke collection chamber of the range hood fan frame 201, and the smoke baffle 202 is used to prevent the spread of oil fumes. The installation position of the sensor is optimized to avoid the direct airflow of oil fumes, and its installation method can be embedded or fixed with a bracket. There is no restriction on the installation method of the sensor.

[0067] The output voltage of a piezoelectric sensor can be expressed as a damped oscillation model, and the formula for the damped oscillation model is:

[0068] ;

[0069] Where V(t) is the time-domain voltage signal detected by the sensor, V0 is the amplitude of the signal, t is the time, τ is the constant value of the decay time, and f0 is the dominant vibration frequency.

[0070] First, the envelope is obtained by taking the absolute value of the oscillation signal to eliminate sinusoidal fluctuations and retain the decaying trend of the amplitude. The expression for calculating the absolute value of the oscillation signal is as follows:

[0071] ;

[0072] Secondly, logarithmic linearization transforms exponential decay into an intuitive linear relationship. The expression for calculating the natural logarithm of the envelope is as follows:

[0073] ;

[0074] make We can obtain a linear equation:

[0075] ;

[0076] For discrete sampling points over a period of time, perform least squares fitting to solve for k:

[0077] ;

[0078] Where n is the number of sampling points, x i Let y be the time coordinate. i This is the logarithmic envelope value.

[0079] Finally, by inversely calculating the value of τ using the slope k, the expression is:

[0080] ;

[0081] Here, τ represents the time required for the amplitude to decay to 36.8% of its initial value.

[0082] This embodiment constructs a complete and highly interference-resistant signal processing flow. By extracting the envelope and performing logarithmic linearization, the exponential decay model, which was originally difficult to fit directly, is transformed into a linear model that is easy to process. Then, the least squares method is used for fitting, thereby achieving high-precision calculation of the decay time constant. This provides a reliable technical guarantee for subsequently determining the preset value range to which the decay time constant belongs and the corresponding cooking action.

[0083] In some embodiments, step S230, which determines the cooking action corresponding to the cookware based on a preset value range to which the decay time constant value belongs, includes the following steps:

[0084] If the constant value of the decay time belongs to the first value range, the cooking action is determined to be a stir-fry action.

[0085] If the constant value of the decay time belongs to the second value range, the cooking action is determined to be steaming or boiling.

[0086] Specifically, the first numerical range corresponds to a decay time constant of less than or equal to 50ms, physically characterized by rapid decay of sound wave amplitude, typically generated by intense, high-frequency collisions between the spatula and the pot, consistent with the typical characteristics of stir-frying. The second numerical range corresponds to a decay time constant of greater than or equal to 200ms and less than or equal to 300ms, physically characterized by slow decay of sound wave amplitude, often caused by the closing of the lid, steam escape, or liquid boiling, corresponding to steaming or boiling cooking actions. When the decay time constant is greater than 50ms and less than 200ms, it is considered an atypical action. When the decay time constant is greater than 300ms, the corresponding sound signal is identified as the sound of boiling water, and this sound signal is excluded as interference.

[0087] It is understood that the specific ranges of the first and second numerical ranges mentioned above can be configured and adjusted according to the actual cooking environment, equipment characteristics, etc., and are not limited to the fixed values ​​listed.

[0088] This embodiment achieves the quantitative differentiation and automatic recognition of typical cooking actions, providing a clear basis for the precise control of devices such as smart range hoods. This embodiment transforms abstract sound wave signals into constant decay time values ​​with clear physical meaning, and establishes a stable mapping relationship between these values ​​and cooking actions through interval division. This allows the device to respond based on objective acoustic characteristics rather than subjective preset patterns, thereby improving the anti-interference capability and overall intelligence level of cooking process recognition.

[0089] In some embodiments, after determining the cooking action corresponding to the cookware based on a preset value range to which the decay time constant value belongs, the following steps are also included:

[0090] When the cooking action is steaming or boiling, switch the range hood's fan speed mode to the first mode that matches the steaming or boiling action.

[0091] Specifically, when the system determines that the current cooking action is steaming or boiling based on a constant decay time value, it will automatically generate a control command to switch the range hood's fan speed mode to the first mode that matches the steaming or boiling action. The first mode corresponds to a lower fan speed and noise level to accommodate the characteristics of less smoke emission and slower smoke generation during steaming or boiling.

[0092] This embodiment achieves precise identification and response to steaming and cooking actions. The system determines when cooking has entered the steaming or cooking stage based on acoustic characteristics, automatically reducing the intensity of smoke extraction, decreasing energy consumption, and significantly lowering operating noise, thus improving user comfort during prolonged cooking processes such as steaming, cooking, and slow cooking.

[0093] In some embodiments, after determining the cooking action corresponding to the cookware based on a preset value range to which the decay time constant value belongs, the following steps are also included:

[0094] When the cooking action is stir-frying, determine the frequency of stir-frying within a preset time.

[0095] Compare the occurrence frequency with a preset frequency threshold;

[0096] If the frequency of occurrence is greater than or equal to the preset frequency threshold, the range hood's fan speed mode will be switched to the second mode that matches the stir-frying action.

[0097] If the frequency is less than the preset frequency threshold, the current wind mode will be maintained.

[0098] Specifically, after identifying a single cooking action as a stir-fry, the system does not immediately switch the fan speed mode but enters a continuous monitoring phase. During this phase, the system times and counts the number of stir-fry actions detected within a preset duration (e.g., 10 seconds), which is taken as the frequency. If the frequency reaches or exceeds a preset frequency threshold (e.g., 5 times / 10 seconds), it is determined that the user is in a high-intensity, continuous stir-fry state, and the range hood is automatically switched to a second mode, which corresponds to a stronger fan speed, to adapt to the characteristics of large instantaneous amounts of oil fumes and rapid generation during continuous stir-frying. If the frequency is lower than the preset frequency threshold, it is considered that the current situation is only occasional stir-frying or non-continuous stir-frying, and the system will maintain the original fan speed mode. The frequency threshold can be calculated based on the frequency of the user's stir-fry actions or can be customized according to the user's cooking habits; there are no restrictions on how the frequency threshold is set.

[0099] This embodiment achieves reliable identification and response control of continuous stir-frying actions. By introducing a frequency judgment mechanism, it effectively distinguishes between accidental actions and continuous cooking states, avoiding erroneous switching caused by occasional collisions, thereby improving the stability of system control while ensuring timely exhaust of oil fumes.

[0100] In some embodiments, after switching the wind mode to a second mode that matches the stir-frying action, the following steps are also included:

[0101] Stop detecting sound signals within the preset time window; the preset time window is the preset period of time during which the second mode continues to run after it is started.

[0102] Specifically, when the system determines that the current cooking action is a stir-fry based on the constant decay time value and triggers the corresponding second mode of the range hood, a preset time window (e.g., 120 seconds) will be activated. During this window duration, the system will stop or suspend the acquisition and analysis of sound signals to avoid repeated triggering of control commands and frequent mode switching due to the continuous collision sounds of pots and pans during the same cooking process. The duration of the preset time window is set according to the duration of the cooking stage, and there is no limitation on the duration of the preset time window here.

[0103] This embodiment achieves stable system operation within a preset time window after the range hood has entered the corresponding working mode based on the recognition result. It prevents excessive response and repeated decision-making within a short period, ensuring the continuity of range hood mode switching and a smooth user experience.

[0104] In some embodiments, after collecting the sound signal generated by the collision of the cookware during use, the following steps are also included:

[0105] The sound signal within a preset frequency range is extracted using a bandpass filter;

[0106] When the amplitude of a sound signal within a preset frequency range exceeds a preset amplitude threshold, the analysis of the sound signal is triggered.

[0107] Specifically, the system is set to a preset frequency range of 3kHz to 5kHz, which is the main resonant frequency band of the sound produced by the collision of metal cookware. First, the original sound signal passes through a digital bandpass filter to filter out irrelevant components such as low-frequency noise, ambient human voices, and high-frequency noise outside this range. Second, the system determines whether the maximum amplitude of the filtered signal exceeds a preset amplitude threshold (e.g., 0.5V).

[0108] The system only recognizes a signal as a valid cookware collision event and initiates the subsequent decay time constant calculation process when both conditions are met simultaneously: "frequency within the preset range" and "amplitude exceeding the threshold". The preset amplitude threshold can be adjusted according to different kitchen environments and sensor sensitivity; therefore, no specific value is imposed on the preset amplitude threshold here.

[0109] This embodiment enables the screening of valid collision events, thereby effectively suppressing environmental interference and false triggering signals in the initial stage of signal processing, significantly improving the signal-to-noise ratio and reliability of the entire recognition system.

[0110] The present embodiment will now be described and illustrated through preferred embodiments.

[0111] like Figure 5 As shown, firstly, the system continuously monitors the sound signal. When a sound signal is detected, it determines whether the frequency of the signal is within the 3-5kHz frequency range. If it is within the range, it calculates the constant value of the decay time. If it is not, it continues to monitor the sound signal.

[0112] Secondly, determine if the decay time constant is less than or equal to 50ms. If it is, increment the stir-fry event count by one, then check if the count is greater than or equal to 5 within 10 seconds. If the event count is greater than or equal to 5, it is determined to be in a stir-fry state, and the wind mode is switched to the second mode, maintaining strong wind for 120 seconds. Sound signal detection stops during this time, but resumes after the duration expires. If the event count is not greater than or equal to 5, sound signal monitoring continues.

[0113] Furthermore, if the decay time constant value does not meet the condition of being less than or equal to 50ms, it is further determined whether the decay time constant value meets the condition of being greater than or equal to 200ms and less than or equal to 300ms. If this condition is met, it is determined to be in steaming / cooking mode, and the system switches to the first mode, after which the sound signal is monitored again. If none of the above conditions for the decay time constant value are met, the sound signal is monitored again.

[0114] This embodiment also provides a smart range hood. Figure 6 This is a system block diagram of the intelligent range hood in this embodiment, as shown below. Figure 6As shown, the intelligent range hood includes a main controller, a light module, a piezoelectric sound sensor, a memory, a switch module, a fan drive module, a communication module, and an optional lifting drive module. The main controller is configured to execute any of the cooking action recognition methods described in the above embodiments. The light module provides supplementary lighting for the operating area in low-light cooking environments. The piezoelectric sound sensor picks up sound signals. The memory stores the system control program and user data. The switch module includes physical buttons and touch controls, enabling users to input basic operation commands such as turning the range hood on and off, selecting modes, and controlling the lights. The fan drive module drives the fan motor to operate at different speeds. The communication module supports wireless connection protocols such as Wi-Fi and Bluetooth for remote control. The optional lifting drive module drives the smoke hood or air inlet to move vertically.

[0115] This embodiment provides a cooking action recognition device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that implement a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0116] Figure 7 This is a structural block diagram of the cooking action recognition device in this embodiment, as shown below. Figure 7 As shown, the device includes:

[0117] Acquisition module 210 is used to acquire sound signals generated by the collision of cookware during use;

[0118] Analysis module 220 is used to determine the corresponding decay time constant value based on the sound signal;

[0119] The matching module 230 is used to determine the preset value range to which the decay time constant value belongs; the preset value range is associated with different cooking actions; and the cooking action corresponding to the cookware is determined according to the preset value range to which the decay time constant value belongs.

[0120] The device provided in this embodiment automates the entire process of collecting and analyzing pot collision sound signals to matching cooking actions. It solves the problem in related technologies of ineffective cooking action recognition, achieving qualitative action recognition based on decay time constant values, thereby significantly improving the response accuracy of the range hood in complex cooking scenarios.

[0121] In some embodiments, the analysis module 220 is also used to extract the envelope of the sound signal;

[0122] Logarithmic linearization of the envelope yields a linear sequence;

[0123] Perform linear regression on the linear sequence to obtain the fitted slope;

[0124] Based on the fitted slope, determine the corresponding constant value of the decay time.

[0125] In some of these embodiments, the matching module 230 is further configured to determine the cooking action as a stir-frying action if the value of the decay time constant belongs to a first value range.

[0126] If the constant value of the decay time belongs to the second value range, the cooking action is determined to be steaming or boiling.

[0127] In some embodiments, the matching module 230 is also used to switch the range hood's fan mode to a first mode that matches the steaming action when the cooking action is a steaming action.

[0128] In some embodiments, the matching module 230 is also used to determine the frequency of occurrence of the stir-frying action within a preset time when the cooking action is a stir-frying action;

[0129] Compare the occurrence frequency with a preset frequency threshold;

[0130] If the frequency of occurrence is greater than or equal to the preset frequency threshold, the range hood's fan speed mode will be switched to the second mode that matches the stir-frying action.

[0131] If the frequency is less than the preset frequency threshold, the current wind mode will be maintained.

[0132] In some embodiments, the matching module 230 is also used to stop the detection of sound signals within a preset time window; the preset time window is a preset period of time during which the second mode continues to run after it is started.

[0133] In some embodiments, the acquisition module 210 is also used to extract sound signals within a preset frequency range through a bandpass filter;

[0134] When the amplitude of a sound signal within a preset frequency range exceeds a preset amplitude threshold, the analysis of the sound signal is triggered.

[0135] 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.

[0136] 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.

[0137] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0138] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0139] S1 collects the sound signals generated by the collision of cookware during use.

[0140] S2, determine the corresponding decay time constant value based on the sound signal.

[0141] S3, determine the preset value range to which the decay time constant value belongs; the preset value range is associated with different cooking actions; determine the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs.

[0142] 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.

[0143] Furthermore, in conjunction with the cooking action recognition method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the cooking action recognition methods described in the above embodiments.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, 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. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for recognizing cooking actions, characterized in that, include: Collect sound signals generated by the collision of cookware during use; Based on the sound signal, determine the corresponding decay time constant value; Determine the preset value range to which the decay time constant value belongs; The preset numerical range is associated with different cooking actions; The cooking action corresponding to the cookware is determined based on the preset value range to which the constant value of the decay time belongs.

2. The cooking action recognition method according to claim 1, characterized in that, The step of determining the corresponding decay time constant value based on the sound signal includes: Extract the envelope of the sound signal; Logarithmically linearize the envelope to obtain a linear sequence; Perform linear regression fitting on the linear sequence to obtain the fitting slope; Based on the fitted slope, the corresponding constant value of the decay time is determined.

3. The cooking action recognition method according to claim 1, characterized in that, The preset value range includes a first value range and a second value range; determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs includes: If the constant value of the decay time belongs to the first value range, the cooking action is determined to be a stir-fry action; If the constant value of the decay time belongs to the second value range, the cooking action is determined to be a steaming or boiling action.

4. The cooking action recognition method according to claim 1 or 3, characterized in that, After determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs, the method further includes: When the cooking action is steaming or boiling, the range hood's fan speed mode is switched to the first mode that matches the steaming or boiling action.

5. The cooking action recognition method according to claim 1 or 3, characterized in that, After determining the cooking action corresponding to the cookware based on the preset value range to which the decay time constant value belongs, the method further includes: When the cooking action is a stir-frying action, the frequency of the stir-frying action within a preset time period is determined; The occurrence frequency is compared with a preset frequency threshold. If the occurrence frequency is greater than or equal to the preset frequency threshold, the range hood's fan mode will be switched to a second mode that matches the stir-frying action. If the occurrence frequency is less than the preset frequency threshold, the current wind mode is maintained.

6. The cooking action recognition method according to claim 5, characterized in that, After switching the wind mode to the second mode that matches the stir-frying action, the method further includes: Stop detecting the sound signal within a preset time window; the preset time window is a preset period of time during which the second mode continues to run after it is started.

7. The cooking action recognition method according to claim 1, characterized in that, After collecting the sound signal generated by the collision of the cookware during use, the method further includes: The sound signal within a preset frequency range is extracted using a bandpass filter; When the amplitude of the sound signal within the preset frequency range exceeds a preset amplitude threshold, the analysis of the sound signal is triggered.

8. A smart range hood, characterized in that, The intelligent range hood includes a controller; the controller performs the cooking action recognition method as described in any one of claims 1 to 7.

9. A cooking action recognition device, characterized in that, include: The module consists of a data acquisition module, an analysis module, and a matching module. The acquisition module is used to acquire sound signals generated by the collision of cookware during use; The analysis module is used to determine the corresponding decay time constant value based on the sound signal; The matching module determines the preset value range to which the decay time constant value belongs; The preset value range is associated with different cooking actions; the cooking action corresponding to the cookware is determined according to the preset value range to which the decay time constant value belongs.

10. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the steps of the cooking action recognition method according to any one of claims 1 to 7.

Images